{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"[1. Introduction](#1)\n\n[2. Brief Introduction About Natural Language Processing](#2)\n\n[3. Bag of Word](#3)\n\n[4. Importing Libraries and Data Set](#4)\n\n[5. Text Analysis](#5)\n\n[6. Heat Map](#6)\n\n[7. Analysis and Visualisation of Target](#7)\n\n[8. Analysis and Visualisation of Features](#8)\n\n[9. Text Preprocessing](#9)\n\n* [9.1 Removing Punctuations and StopWords](#9.1)\n\n* [9.2 Removing StopWords](#9.2)\n\n* [9.3 Removing Noise](#9.3)\n\n* [9.4 Lowercasing](#9.4)\n\n* [9.5 Tokenization](#9.6)\n\n[10. Model creation Using LSTM](#10)\n\n* [10.1 Splitting Text data](#10.1)\n\n* [10.2 Embedding Layer](#10.2)\n\n* [10.3 Long Short Term Memory – LSTM](#10.3)\n\n[11. Evaluation](#11)\n\n[12. Submission](#12)\n\n[13. Reference](#13)\n\n\n","metadata":{}},{"cell_type":"markdown","source":"<a id=\"1\"></a> <br>\n# 1. Introduction","metadata":{}},{"cell_type":"markdown","source":"Twitter has become an important communication channel in times of emergency. The ubiquitousness of smartphones enables people to announce an emergency they’re observing in real-time. A machine learning model is built, that would predict which Tweets are about real disasters and which ones aren’t.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"2\"></a> <br>\n# 2. Brief Introduction About Natural Language Processing","metadata":{}},{"cell_type":"markdown","source":"Natural Language Processing refers to the branch of artificial intelligence that gives machines the ability to read, understand and derive meaning from human languages. Robots such as Sophia or home assistants uses Natural Language Processing (NLP) to sound like human and 'understand' what you're saying. NLP can be represented by using the Venn diagram as below.","metadata":{}},{"cell_type":"markdown","source":"![image.png](attachment:d46f46cd-3dea-4932-aab8-b7e806d5ed3b.png)","metadata":{},"attachments":{"d46f46cd-3dea-4932-aab8-b7e806d5ed3b.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"Natural language processing focuses on feature engineering and for this, we should have excellent domain knowledge of data. All the data are in the form of text or string. While modeling it with the machine learning classifier algorithm, it will require a numerical feature vector and for this \"Bag of Word\" can be used.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"3\"></a> <br>\n# 3. Bag of Words","metadata":{}},{"cell_type":"markdown","source":"The bag-of-words model is used to extract features from the text by disregarding the grammar and order of words by keeping their multiple occurrences. It is represented as a bag of its words and here the occurrence of each word is used as a feature for the training classifier. It is mainly used in document classification and also used in computer vision.\n\nFor document classification, the word counts can be represented as a vector. We can use cosine similarity metrics is used to determine the similarity between these vectors by measuring cosine angle.\n\nThe cosine of two non-zero vectors can be derived by using the Euclidean dot product formula:","metadata":{}},{"cell_type":"markdown","source":"![image.png](attachment:ef1055b9-0a05-4c18-b7a7-09f58b4bf4bc.png)","metadata":{},"attachments":{"ef1055b9-0a05-4c18-b7a7-09f58b4bf4bc.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"(1 - similarity) gives cosine distance between two vectors.\n\nWhen the angle between two points is zero, cos(0) = 1, and cosine distance will be equal to (1–1) then is zero. It indicates the two are very the same.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"4\"></a> <br>\n# 4. Importing Libraries and Data Set","metadata":{}},{"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the read-only \"../input/\" directory\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2022-05-08T16:15:11.251208Z","iopub.execute_input":"2022-05-08T16:15:11.251980Z","iopub.status.idle":"2022-05-08T16:15:11.275476Z","shell.execute_reply.started":"2022-05-08T16:15:11.251879Z","shell.execute_reply":"2022-05-08T16:15:11.274876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#Libraries for visualisation\nimport seaborn as sns\nimport matplotlib.pyplot as plt\n\n#Libraries for formattting and handling text \nimport string \nimport re\n\n#Library for nltk\nimport nltk\nfrom nltk.corpus import stopwords\nfrom nltk.tokenize import sent_tokenize, word_tokenize\nfrom wordcloud import WordCloud, STOPWORDS\n\n\n#Library for Splitting Dataset\nfrom sklearn.model_selection import train_test_split\n\n\n#Libraries for NN\nimport tensorflow as tf\n\nfrom tensorflow import keras\nfrom tensorflow.keras.preprocessing.text import Tokenizer\nfrom nltk.stem import PorterStemmer, WordNetLemmatizer\nfrom tensorflow.keras.preprocessing.sequence import pad_sequences\n\nfrom tensorflow.keras import optimizers\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Embedding, LSTM, Dropout\n\nfrom tensorflow.keras.utils import plot_model\n\n#Library for evaluation\nfrom sklearn import metrics\nfrom functools import reduce\nfrom sklearn.metrics import confusion_matrix\nfrom sklearn.metrics import classification_report\n\nimport warnings\nwarnings.filterwarnings(\"ignore\")","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:11.276619Z","iopub.execute_input":"2022-05-08T16:15:11.276920Z","iopub.status.idle":"2022-05-08T16:15:17.973200Z","shell.execute_reply.started":"2022-05-08T16:15:11.276896Z","shell.execute_reply":"2022-05-08T16:15:17.972370Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data = pd.read_csv('/kaggle/input/nlp-getting-started/train.csv')","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:17.974230Z","iopub.execute_input":"2022-05-08T16:15:17.975044Z","iopub.status.idle":"2022-05-08T16:15:18.019732Z","shell.execute_reply.started":"2022-05-08T16:15:17.975008Z","shell.execute_reply":"2022-05-08T16:15:18.019129Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"5\"></a> <br>\n# 5. Text Analysis","metadata":{}},{"cell_type":"code","source":"train_data.head().style.background_gradient(cmap='coolwarm')","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.021062Z","iopub.execute_input":"2022-05-08T16:15:18.021379Z","iopub.status.idle":"2022-05-08T16:15:18.093657Z","shell.execute_reply.started":"2022-05-08T16:15:18.021354Z","shell.execute_reply":"2022-05-08T16:15:18.093095Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print(\"Number of rows is = \", train_data.shape[0], \" \\nNumber of columns is = \" , train_data.shape[1]) ","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.094569Z","iopub.execute_input":"2022-05-08T16:15:18.094861Z","iopub.status.idle":"2022-05-08T16:15:18.099434Z","shell.execute_reply.started":"2022-05-08T16:15:18.094837Z","shell.execute_reply":"2022-05-08T16:15:18.098606Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.100571Z","iopub.execute_input":"2022-05-08T16:15:18.103406Z","iopub.status.idle":"2022-05-08T16:15:18.118824Z","shell.execute_reply.started":"2022-05-08T16:15:18.103365Z","shell.execute_reply":"2022-05-08T16:15:18.118298Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"6\"></a> <br>\n# 6. Heat Map","metadata":{}},{"cell_type":"code","source":"sns.set(rc={'figure.figsize':(11,8)})\nsns.heatmap(train_data.isnull(),yticklabels=False,cbar=False,cmap=\"coolwarm\")","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.119634Z","iopub.execute_input":"2022-05-08T16:15:18.120138Z","iopub.status.idle":"2022-05-08T16:15:18.374113Z","shell.execute_reply.started":"2022-05-08T16:15:18.120105Z","shell.execute_reply":"2022-05-08T16:15:18.373188Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Here each red line indicates there is missing value and as per heat map of keyword and location have missing value. As for NLP model building we will be using only text and target, so there is no need to handle missing value.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"7\"></a> <br>\n# 7. Analysis and Visualisation of Target","metadata":{}},{"cell_type":"code","source":"train_data['target'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.375704Z","iopub.execute_input":"2022-05-08T16:15:18.376000Z","iopub.status.idle":"2022-05-08T16:15:18.382773Z","shell.execute_reply.started":"2022-05-08T16:15:18.375963Z","shell.execute_reply":"2022-05-08T16:15:18.382248Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(5,3))\ncolors = [\"blue\", \"red\"]\n\nsns.countplot(x = 'target', data=train_data, palette=colors)\nplt.title('Target Distributions \\n (0: Non Disaster || 1: Disaster)', fontsize=14)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.384738Z","iopub.execute_input":"2022-05-08T16:15:18.385460Z","iopub.status.idle":"2022-05-08T16:15:18.582173Z","shell.execute_reply.started":"2022-05-08T16:15:18.385422Z","shell.execute_reply":"2022-05-08T16:15:18.581448Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"8\"></a> <br>\n# 8. Analysis and Visualisation of Features","metadata":{}},{"cell_type":"markdown","source":"<div style=\"color:white;\n           display:fill;\n           border-radius:5px;\n           background-color:#5642C5;\n           font-size:110%;\n           font-family:Verdana;\n           letter-spacing:0.5px\">\n\n<p style=\"padding: 10px;\n              color:white;\n          text-align:center;\">Keyword</p>\n\n             \n\n</div>","metadata":{}},{"cell_type":"code","source":"train_data[\"keyword\"].nunique()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.583174Z","iopub.execute_input":"2022-05-08T16:15:18.583365Z","iopub.status.idle":"2022-05-08T16:15:18.589895Z","shell.execute_reply.started":"2022-05-08T16:15:18.583343Z","shell.execute_reply":"2022-05-08T16:15:18.589006Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting top 20 keywords","metadata":{}},{"cell_type":"code","source":"chains=train_data['keyword'].value_counts()[:20]\nsns.barplot(x=chains,y=chains.index,palette='deep')\nplt.title(\"Top 20 Keywords\")\nplt.xlabel(\"Count of Keywords\")","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.591063Z","iopub.execute_input":"2022-05-08T16:15:18.591348Z","iopub.status.idle":"2022-05-08T16:15:18.982841Z","shell.execute_reply.started":"2022-05-08T16:15:18.591321Z","shell.execute_reply":"2022-05-08T16:15:18.982111Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting top 20 disaster and non disaster keywords","metadata":{}},{"cell_type":"code","source":"disaster_keywords = train_data.loc[train_data[\"target\"] == 1][\"keyword\"].value_counts()\nnondisaster_keywords = train_data.loc[train_data[\"target\"] == 0][\"keyword\"].value_counts()\n\nfig, ax = plt.subplots(1,2, figsize=(20,8))\nsns.barplot(y=disaster_keywords[0:20].index, x=disaster_keywords[0:20], orient='h', ax=ax[0], palette=\"Reds_d\")\nax[0].set_title(\"Top 20 Keywords - Disaster Tweets\")\nax[0].set_xlabel(\"Keyword Frequency\")\n\nsns.barplot(y=nondisaster_keywords[0:20].index, x=nondisaster_keywords[0:20], orient='h', ax=ax[1], palette=\"Blues_d\")\nax[1].set_title(\"Top 20 Keywords - Non-Disaster Tweets\")\nax[1].set_xlabel(\"Keyword Frequency\")\n\n\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:18.984270Z","iopub.execute_input":"2022-05-08T16:15:18.984489Z","iopub.status.idle":"2022-05-08T16:15:19.870348Z","shell.execute_reply.started":"2022-05-08T16:15:18.984464Z","shell.execute_reply":"2022-05-08T16:15:19.869582Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting highest usage disaster keyword and lowest usage disaster keyword","metadata":{}},{"cell_type":"code","source":"top_disaster_keyword = train_data.groupby('keyword').mean()['target'].sort_values(ascending = False).head(20)\ntop_nondisaster_keyword = train_data.groupby('keyword').mean()['target'].sort_values().head(20)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:19.871379Z","iopub.execute_input":"2022-05-08T16:15:19.872000Z","iopub.status.idle":"2022-05-08T16:15:19.884097Z","shell.execute_reply.started":"2022-05-08T16:15:19.871967Z","shell.execute_reply":"2022-05-08T16:15:19.883404Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"fig, ax = plt.subplots(1,2, figsize=(20,8))\n\nsns.barplot(y=top_disaster_keyword[0:20].index, x=disaster_keywords[0:20], orient='h', ax=ax[0], palette=\"Reds_d\")\nax[0].set_title(\"Top 20 Keywords - Highest used Disaster Keyword\")\nax[0].set_xlabel(\"Keyword Frequency\")\n\n\nsns.barplot(y=top_nondisaster_keyword[0:20].index, x=top_nondisaster_keyword[0:20], orient='h', ax=ax[1], palette=\"Blues_d\")\nax[1].set_title(\"Top 20 Keywords - Least used Non-Disaster Tweets\")\nax[1].set_xlabel(\"Keyword Frequency\")\n\n\nplt.tight_layout()\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:19.885163Z","iopub.execute_input":"2022-05-08T16:15:19.885548Z","iopub.status.idle":"2022-05-08T16:15:20.859348Z","shell.execute_reply.started":"2022-05-08T16:15:19.885523Z","shell.execute_reply":"2022-05-08T16:15:20.858415Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"color:white;\n           display:fill;\n           border-radius:5px;\n           background-color:#5642C5;\n           font-size:110%;\n           font-family:Verdana;\n           letter-spacing:0.5px\">\n\n<p style=\"padding: 10px;\n              color:white;\n          text-align:center;\">Location</p>\n\n             \n\n</div>","metadata":{}},{"cell_type":"code","source":"locations = train_data[\"location\"].value_counts()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:20.860800Z","iopub.execute_input":"2022-05-08T16:15:20.861300Z","iopub.status.idle":"2022-05-08T16:15:20.869278Z","shell.execute_reply.started":"2022-05-08T16:15:20.861262Z","shell.execute_reply":"2022-05-08T16:15:20.868551Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting top 20 locations of tweets","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(10,7))\n\n\nsns.barplot(y=locations[0:20].index, x=locations[0:20], orient='h')\n\nplt.title(\"Top 20 Locations\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:20.870263Z","iopub.execute_input":"2022-05-08T16:15:20.870655Z","iopub.status.idle":"2022-05-08T16:15:21.222597Z","shell.execute_reply.started":"2022-05-08T16:15:20.870606Z","shell.execute_reply":"2022-05-08T16:15:21.221793Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"color:white;\n           display:fill;\n           border-radius:5px;\n           background-color:#5642C5;\n           font-size:110%;\n           font-family:Verdana;\n           letter-spacing:0.5px\">\n\n<p style=\"padding: 10px;\n              color:white;\n          text-align:center;\">Text</p>\n\n             \n\n</div>","metadata":{}},{"cell_type":"code","source":"print(len(train_data['text']))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:21.223583Z","iopub.execute_input":"2022-05-08T16:15:21.223787Z","iopub.status.idle":"2022-05-08T16:15:21.227901Z","shell.execute_reply.started":"2022-05-08T16:15:21.223765Z","shell.execute_reply":"2022-05-08T16:15:21.227361Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can create a column length in train_data, which will have length of each text.","metadata":{}},{"cell_type":"code","source":"train_data[\"length\"]  = train_data[\"text\"].apply(len)\ntrain_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:21.228858Z","iopub.execute_input":"2022-05-08T16:15:21.229203Z","iopub.status.idle":"2022-05-08T16:15:21.248273Z","shell.execute_reply.started":"2022-05-08T16:15:21.229174Z","shell.execute_reply":"2022-05-08T16:15:21.247477Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data['length'].describe()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:21.249500Z","iopub.execute_input":"2022-05-08T16:15:21.250116Z","iopub.status.idle":"2022-05-08T16:15:21.263184Z","shell.execute_reply.started":"2022-05-08T16:15:21.250065Z","shell.execute_reply":"2022-05-08T16:15:21.262589Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data[train_data['length']==157]['text'].iloc[0]","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:21.264223Z","iopub.execute_input":"2022-05-08T16:15:21.264652Z","iopub.status.idle":"2022-05-08T16:15:21.271518Z","shell.execute_reply.started":"2022-05-08T16:15:21.264627Z","shell.execute_reply":"2022-05-08T16:15:21.270722Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Here the maximum length word is having repeated punctuations. So the important information delivered is very less.","metadata":{}},{"cell_type":"markdown","source":"## Plotting tweets length ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize=(5,3))\nsns.histplot(train_data[\"length\"], kde=True,color='purple',bins=30)\nplt.title(\"Length of tweets\")\nplt.xlabel(\"Number of Characters\")\nplt.ylabel(\"Density\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:21.272851Z","iopub.execute_input":"2022-05-08T16:15:21.273506Z","iopub.status.idle":"2022-05-08T16:15:21.611723Z","shell.execute_reply.started":"2022-05-08T16:15:21.273470Z","shell.execute_reply":"2022-05-08T16:15:21.611033Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting tweets length wrt target","metadata":{}},{"cell_type":"code","source":"train_data.hist(column='length', by = 'target',bins =60, figsize= (10,3))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:21.612683Z","iopub.execute_input":"2022-05-08T16:15:21.612877Z","iopub.status.idle":"2022-05-08T16:15:22.208887Z","shell.execute_reply.started":"2022-05-08T16:15:21.612854Z","shell.execute_reply":"2022-05-08T16:15:22.208285Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting number of words in tweets","metadata":{}},{"cell_type":"markdown","source":"Column \"num_word\" is to be created, which will have number of words in each tweet.","metadata":{}},{"cell_type":"code","source":"def count_words(x):\n    return len(x.split())\n\ntrain_data[\"num_words\"] = train_data[\"text\"].apply(count_words)\n\nplt.figure(figsize=(5,3))\nsns.histplot(train_data[\"num_words\"],kde=True,color='purple',bins=30)\nplt.title(\"Histogram of Number of Words per Tweet\")\nplt.xlabel(\"Number of Words\")\nplt.ylabel(\"Density\")\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:22.210149Z","iopub.execute_input":"2022-05-08T16:15:22.210922Z","iopub.status.idle":"2022-05-08T16:15:22.499919Z","shell.execute_reply.started":"2022-05-08T16:15:22.210880Z","shell.execute_reply":"2022-05-08T16:15:22.499339Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Plotting number of words in tweets wrt target","metadata":{}},{"cell_type":"code","source":"train_data.hist(column='num_words', by = 'target',bins =60, figsize= (10,3))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:22.504473Z","iopub.execute_input":"2022-05-08T16:15:22.504826Z","iopub.status.idle":"2022-05-08T16:15:23.303004Z","shell.execute_reply.started":"2022-05-08T16:15:22.504787Z","shell.execute_reply":"2022-05-08T16:15:23.302187Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"9\"></a> <br>\n# 9. Text Preprocessing","metadata":{}},{"cell_type":"markdown","source":"<a id=\"9.1\"></a> <br>\n* 9.1 Removing Punctuations","metadata":{}},{"cell_type":"markdown","source":"string.punctuation will give the punctuations.","metadata":{}},{"cell_type":"code","source":"string.punctuation","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.303985Z","iopub.execute_input":"2022-05-08T16:15:23.304299Z","iopub.status.idle":"2022-05-08T16:15:23.309639Z","shell.execute_reply.started":"2022-05-08T16:15:23.304264Z","shell.execute_reply":"2022-05-08T16:15:23.308921Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We can create a function 'toclean_text' to remove punctuations, and then it can used to clean text column of training data.","metadata":{}},{"cell_type":"code","source":"def toclean_text(text):\n\n    \n    clean_text = [char for char in text if char not in string.punctuation]\n   \n    clean_text = ''.join(clean_text)\n    \n        \n    return clean_text","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.310897Z","iopub.execute_input":"2022-05-08T16:15:23.311115Z","iopub.status.idle":"2022-05-08T16:15:23.318591Z","shell.execute_reply.started":"2022-05-08T16:15:23.311092Z","shell.execute_reply":"2022-05-08T16:15:23.317794Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Function 'toclean_text', will remove punctuations in a text. Now we apply it to training data and create a column clean_text for the training data, which will have text without puntuations.","metadata":{}},{"cell_type":"code","source":"train_data['clean_text'] = train_data['text'].apply(toclean_text)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.319656Z","iopub.execute_input":"2022-05-08T16:15:23.319846Z","iopub.status.idle":"2022-05-08T16:15:23.406660Z","shell.execute_reply.started":"2022-05-08T16:15:23.319825Z","shell.execute_reply":"2022-05-08T16:15:23.405800Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.407836Z","iopub.execute_input":"2022-05-08T16:15:23.408540Z","iopub.status.idle":"2022-05-08T16:15:23.420133Z","shell.execute_reply.started":"2022-05-08T16:15:23.408507Z","shell.execute_reply":"2022-05-08T16:15:23.419490Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"9.2\"></a> <br>\n* 9.2 Removing Noise","metadata":{}},{"cell_type":"markdown","source":"Noise in a text can be considered as anything which does belong to normal human language interaction.\n\nNoise in the text can generally be considered as URL, abbreviations, emojis, message inside HTML tag, etc. Punctuations can also be considered as noise. But here we have already removed punctuations. \n\nThe main reason why abbreviations are included as noise is that some people write thx for thankyou. If abbreviations are not replaced with the original word, 'thx' and 'thankyou' will be considered as two different words. ","metadata":{}},{"cell_type":"code","source":"abbreviations = {\n    \"$\" : \" dollar \",\n    \"€\" : \" euro \",\n    \"4ao\" : \"for adults only\",\n    \"a.m\" : \"before midday\",\n    \"a3\" : \"anytime anywhere anyplace\",\n    \"aamof\" : \"as a matter of fact\",\n    \"acct\" : \"account\",\n    \"adih\" : \"another day in hell\",\n    \"afaic\" : \"as far as i am concerned\",\n    \"afaict\" : \"as far as i can tell\",\n    \"afaik\" : \"as far as i know\",\n    \"afair\" : \"as far as i remember\",\n    \"afk\" : \"away from keyboard\",\n    \"app\" : \"application\",\n    \"approx\" : \"approximately\",\n    \"apps\" : \"applications\",\n    \"asap\" : \"as soon as possible\",\n    \"asl\" : \"age, sex, location\",\n    \"atk\" : \"at the keyboard\",\n    \"ave.\" : \"avenue\",\n    \"aymm\" : \"are you my mother\",\n    \"ayor\" : \"at your own risk\", \n    \"b&b\" : \"bed and breakfast\",\n    \"b+b\" : \"bed and breakfast\",\n    \"b.c\" : \"before christ\",\n    \"b2b\" : \"business to business\",\n    \"b2c\" : \"business to customer\",\n    \"b4\" : \"before\",\n    \"b4n\" : \"bye for now\",\n    \"b@u\" : \"back at you\",\n    \"bae\" : \"before anyone else\",\n    \"bak\" : \"back at keyboard\",\n    \"bbbg\" : \"bye bye be good\",\n    \"bbc\" : \"british broadcasting corporation\",\n    \"bbias\" : \"be back in a second\",\n    \"bbl\" : \"be back later\",\n    \"bbs\" : \"be back soon\",\n    \"be4\" : \"before\",\n    \"bfn\" : \"bye for now\",\n    \"blvd\" : \"boulevard\",\n    \"bout\" : \"about\",\n    \"brb\" : \"be right back\",\n    \"bros\" : \"brothers\",\n    \"brt\" : \"be right there\",\n    \"bsaaw\" : \"big smile and a wink\",\n    \"btw\" : \"by the way\",\n    \"bwl\" : \"bursting with laughter\",\n    \"c/o\" : \"care of\",\n    \"cet\" : \"central european time\",\n    \"cf\" : \"compare\",\n    \"cia\" : \"central intelligence agency\",\n    \"csl\" : \"can not stop laughing\",\n    \"cu\" : \"see you\",\n    \"cul8r\" : \"see you later\",\n    \"cv\" : \"curriculum vitae\",\n    \"cwot\" : \"complete waste of time\",\n    \"cya\" : \"see you\",\n    \"cyt\" : \"see you tomorrow\",\n    \"dae\" : \"does anyone else\",\n    \"dbmib\" : \"do not bother me i am busy\",\n    \"diy\" : \"do it yourself\",\n    \"dm\" : \"direct message\",\n    \"dwh\" : \"during work hours\",\n    \"e123\" : \"easy as one two three\",\n    \"eet\" : \"eastern european time\",\n    \"eg\" : \"example\",\n    \"embm\" : \"early morning business meeting\",\n    \"encl\" : \"enclosed\",\n    \"encl.\" : \"enclosed\",\n    \"etc\" : \"and so on\",\n    \"faq\" : \"frequently asked questions\",\n    \"fawc\" : \"for anyone who cares\",\n    \"fb\" : \"facebook\",\n    \"fc\" : \"fingers crossed\",\n    \"fig\" : \"figure\",\n    \"fimh\" : \"forever in my heart\", \n    \"ft.\" : \"feet\",\n    \"ft\" : \"featuring\",\n    \"ftl\" : \"for the loss\",\n    \"ftw\" : \"for the win\",\n    \"fwiw\" : \"for what it is worth\",\n    \"fyi\" : \"for your information\",\n    \"g9\" : \"genius\",\n    \"gahoy\" : \"get a hold of yourself\",\n    \"gal\" : \"get a life\",\n    \"gcse\" : \"general certificate of secondary education\",\n    \"gfn\" : \"gone for now\",\n    \"gg\" : \"good game\",\n    \"gl\" : \"good luck\",\n    \"glhf\" : \"good luck have fun\",\n    \"gmt\" : \"greenwich mean time\",\n    \"gmta\" : \"great minds think alike\",\n    \"gn\" : \"good night\",\n    \"g.o.a.t\" : \"greatest of all time\",\n    \"goat\" : \"greatest of all time\",\n    \"goi\" : \"get over it\",\n    \"gps\" : \"global positioning system\",\n    \"gr8\" : \"great\",\n    \"gratz\" : \"congratulations\",\n    \"gyal\" : \"girl\",\n    \"h&c\" : \"hot and cold\",\n    \"hp\" : \"horsepower\",\n    \"hr\" : \"hour\",\n    \"hrh\" : \"his royal highness\",\n    \"ht\" : \"height\",\n    \"ibrb\" : \"i will be right back\",\n    \"ic\" : \"i see\",\n    \"icq\" : \"i seek you\",\n    \"icymi\" : \"in case you missed it\",\n    \"idc\" : \"i do not care\",\n    \"idgadf\" : \"i do not give a damn fuck\",\n    \"idgaf\" : \"i do not give a fuck\",\n    \"idk\" : \"i do not know\",\n    \"ie\" : \"that is\",\n    \"i.e\" : \"that is\",\n    \"ifyp\" : \"i feel your pain\",\n    \"IG\" : \"instagram\",\n    \"iirc\" : \"if i remember correctly\",\n    \"ilu\" : \"i love you\",\n    \"ily\" : \"i love you\",\n    \"imho\" : \"in my humble opinion\",\n    \"imo\" : \"in my opinion\",\n    \"imu\" : \"i miss you\",\n    \"iow\" : \"in other words\",\n    \"irl\" : \"in real life\",\n    \"j4f\" : \"just for fun\",\n    \"jic\" : \"just in case\",\n    \"jk\" : \"just kidding\",\n    \"jsyk\" : \"just so you know\",\n    \"l8r\" : \"later\",\n    \"lb\" : \"pound\",\n    \"lbs\" : \"pounds\",\n    \"ldr\" : \"long distance relationship\",\n    \"lmao\" : \"laugh my ass off\",\n    \"lmfao\" : \"laugh my fucking ass off\",\n    \"lol\" : \"laughing out loud\",\n    \"ltd\" : \"limited\",\n    \"ltns\" : \"long time no see\",\n    \"m8\" : \"mate\",\n    \"mf\" : \"motherfucker\",\n    \"mfs\" : \"motherfuckers\",\n    \"mfw\" : \"my face when\",\n    \"mofo\" : \"motherfucker\",\n    \"mph\" : \"miles per hour\",\n    \"mr\" : \"mister\",\n    \"mrw\" : \"my reaction when\",\n    \"ms\" : \"miss\",\n    \"mte\" : \"my thoughts exactly\",\n    \"nagi\" : \"not a good idea\",\n    \"nbc\" : \"national broadcasting company\",\n    \"nbd\" : \"not big deal\",\n    \"nfs\" : \"not for sale\",\n    \"ngl\" : \"not going to lie\",\n    \"nhs\" : \"national health service\",\n    \"nrn\" : \"no reply necessary\",\n    \"nsfl\" : \"not safe for life\",\n    \"nsfw\" : \"not safe for work\",\n    \"nth\" : \"nice to have\",\n    \"nvr\" : \"never\",\n    \"nyc\" : \"new york city\",\n    \"oc\" : \"original content\",\n    \"og\" : \"original\",\n    \"ohp\" : \"overhead projector\",\n    \"oic\" : \"oh i see\",\n    \"omdb\" : \"over my dead body\",\n    \"omg\" : \"oh my god\",\n    \"omw\" : \"on my way\",\n    \"p.a\" : \"per annum\",\n    \"p.m\" : \"after midday\",\n    \"pm\" : \"prime minister\",\n    \"poc\" : \"people of color\",\n    \"pov\" : \"point of view\",\n    \"pp\" : \"pages\",\n    \"ppl\" : \"people\",\n    \"prw\" : \"parents are watching\",\n    \"ps\" : \"postscript\",\n    \"pt\" : \"point\",\n    \"ptb\" : \"please text back\",\n    \"pto\" : \"please turn over\",\n    \"qpsa\" : \"what happens\",\n    \"ratchet\" : \"rude\",\n    \"rbtl\" : \"read between the lines\",\n    \"rlrt\" : \"real life retweet\", \n    \"rofl\" : \"rolling on the floor laughing\",\n    \"roflol\" : \"rolling on the floor laughing out loud\",\n    \"rotflmao\" : \"rolling on the floor laughing my ass off\",\n    \"rt\" : \"retweet\",\n    \"ruok\" : \"are you ok\",\n    \"sfw\" : \"safe for work\",\n    \"sk8\" : \"skate\",\n    \"smh\" : \"shake my head\",\n    \"sq\" : \"square\",\n    \"srsly\" : \"seriously\", \n    \"ssdd\" : \"same stuff different day\",\n    \"tbh\" : \"to be honest\",\n    \"tbs\" : \"tablespooful\",\n    \"tbsp\" : \"tablespooful\",\n    \"tfw\" : \"that feeling when\",\n    \"thks\" : \"thank you\",\n    \"tho\" : \"though\",\n    \"thx\" : \"thank you\",\n    \"tia\" : \"thanks in advance\",\n    \"til\" : \"today i learned\",\n    \"tl;dr\" : \"too long i did not read\",\n    \"tldr\" : \"too long i did not read\",\n    \"tmb\" : \"tweet me back\",\n    \"tntl\" : \"trying not to laugh\",\n    \"ttyl\" : \"talk to you later\",\n    \"u\" : \"you\",\n    \"u2\" : \"you too\",\n    \"u4e\" : \"yours for ever\",\n    \"utc\" : \"coordinated universal time\",\n    \"w/\" : \"with\",\n    \"w/o\" : \"without\",\n    \"w8\" : \"wait\",\n    \"wassup\" : \"what is up\",\n    \"wb\" : \"welcome back\",\n    \"wtf\" : \"what the fuck\",\n    \"wtg\" : \"way to go\",\n    \"wtpa\" : \"where the party at\",\n    \"wuf\" : \"where are you from\",\n    \"wuzup\" : \"what is up\",\n    \"wywh\" : \"wish you were here\",\n    \"yd\" : \"yard\",\n    \"ygtr\" : \"you got that right\",\n    \"ynk\" : \"you never know\",\n    \"zzz\" : \"sleeping bored and tired\"\n}","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.421531Z","iopub.execute_input":"2022-05-08T16:15:23.421953Z","iopub.status.idle":"2022-05-08T16:15:23.440548Z","shell.execute_reply.started":"2022-05-08T16:15:23.421925Z","shell.execute_reply":"2022-05-08T16:15:23.440066Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Remove all URLs, replace by URL\ndef remove_URL(text):\n    url = re.compile(r'https?://\\S+|www\\.\\S+')\n    return url.sub(r'URL',text)\n\n# Remove HTML beacon\ndef remove_HTML(text):\n    html=re.compile(r'<.*?>')\n    return html.sub(r'',text)\n\n# Remove non printable characters\ndef remove_not_ASCII(text):\n    text = ''.join([word for word in text if word in string.printable])\n    return text\n\n# Change an abbreviation by its true meaning\ndef word_abbrev(word):\n    return abbreviations[word.lower()] if word.lower() in abbreviations.keys() else word\n\n# Replace all abbreviations\ndef replace_abbrev(text):\n    string = \"\"\n    for word in text.split():\n        string += word_abbrev(word) + \" \"        \n    return string\n\n# Remove @ and mention, replace by USER\ndef remove_mention(text):\n    at=re.compile(r'@\\S+')\n    return at.sub(r'USER',text)\n\n# Remove numbers, replace it by NUMBER\ndef remove_number(text):\n    num = re.compile(r'[-+]?[.\\d]*[\\d]+[:,.\\d]*')\n    return num.sub(r'NUMBER', text)\n\n# Remove all emojis, replace by EMOJI\ndef remove_emoji(text):\n    emoji_pattern = re.compile(\"[\"\n                           u\"\\U0001F600-\\U0001F64F\"  # emoticons\n                           u\"\\U0001F300-\\U0001F5FF\"  # symbols & pictographs\n                           u\"\\U0001F680-\\U0001F6FF\"  # transport & map symbols\n                           u\"\\U0001F1E0-\\U0001F1FF\"  # flags (iOS)\n                           u\"\\U00002702-\\U000027B0\"\n                           u\"\\U000024C2-\\U0001F251\"\n                           \"]+\", flags=re.UNICODE)\n    return emoji_pattern.sub(r'EMOJI', text)\n\n# Replace some others smileys with SADFACE\ndef transcription_sad(text):\n    eyes = \"[8:=;]\"\n    nose = \"['`\\-]\"\n    smiley = re.compile(r'[8:=;][\\'\\-]?[(\\\\/]')\n    return smiley.sub(r'SADFACE', text)\n\n# Replace some smileys with SMILE\ndef transcription_smile(text):\n    eyes = \"[8:=;]\"\n    nose = \"['`\\-]\"\n    smiley = re.compile(r'[8:=;][\\'\\-]?[)dDp]')\n    #smiley = re.compile(r'#{eyes}#{nose}[)d]+|[)d]+#{nose}#{eyes}/i')\n    return smiley.sub(r'SMILE', text)\n\n# Replace <3 with HEART\ndef transcription_heart(text):\n    heart = re.compile(r'<3')\n    return heart.sub(r'HEART', text)\n\n","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.441532Z","iopub.execute_input":"2022-05-08T16:15:23.442117Z","iopub.status.idle":"2022-05-08T16:15:23.454415Z","shell.execute_reply.started":"2022-05-08T16:15:23.442038Z","shell.execute_reply":"2022-05-08T16:15:23.453905Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def clean_tweet(text):\n    \n    # Remove non text\n    text = remove_URL(text)\n    text = remove_HTML(text)\n    text = remove_not_ASCII(text)\n    \n    # replace abbreviations, @ and number\n    text = replace_abbrev(text)  \n    text = remove_mention(text)\n    text = remove_number(text)\n    \n    # Remove emojis / smileys\n    text = remove_emoji(text)\n    text = transcription_sad(text)\n    text = transcription_smile(text)\n    text = transcription_heart(text)\n  \n    return text","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.455358Z","iopub.execute_input":"2022-05-08T16:15:23.455715Z","iopub.status.idle":"2022-05-08T16:15:23.465992Z","shell.execute_reply.started":"2022-05-08T16:15:23.455682Z","shell.execute_reply":"2022-05-08T16:15:23.465482Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Function clean_tweet() will remove all the noise in the text.","metadata":{}},{"cell_type":"code","source":"train_data[\"clean_text\"] = train_data[\"clean_text\"].apply(clean_tweet)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.466836Z","iopub.execute_input":"2022-05-08T16:15:23.467212Z","iopub.status.idle":"2022-05-08T16:15:23.759031Z","shell.execute_reply.started":"2022-05-08T16:15:23.467181Z","shell.execute_reply":"2022-05-08T16:15:23.758258Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.760492Z","iopub.execute_input":"2022-05-08T16:15:23.760712Z","iopub.status.idle":"2022-05-08T16:15:23.771891Z","shell.execute_reply.started":"2022-05-08T16:15:23.760684Z","shell.execute_reply":"2022-05-08T16:15:23.771119Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"9.3\"></a> <br>\n* 9.3 Removing Stopwords","metadata":{}},{"cell_type":"markdown","source":"Stopwords are commonly used words, which do not have any distinguishing features, like \"a\", \"an\", \"the\", so on… and search engine is programmed to ignore them while indexing entries and while retrieving the results of a search query. It  saves space in the database and decreases processing speed. \n\nNatural Language Toolkit(nlkt) in python has a list of stopwords stored in 16 different languages. It is a leading platform for building a python program to work with human language data.","metadata":{}},{"cell_type":"code","source":"print(stopwords.words('english'))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.772870Z","iopub.execute_input":"2022-05-08T16:15:23.773144Z","iopub.status.idle":"2022-05-08T16:15:23.787621Z","shell.execute_reply.started":"2022-05-08T16:15:23.773121Z","shell.execute_reply":"2022-05-08T16:15:23.786826Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def toremove_stopword(text):\n    remove_stopword = [word for word in text.split() if word.lower() not in stopwords.words('english')]\n\n    return remove_stopword","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.788650Z","iopub.execute_input":"2022-05-08T16:15:23.789347Z","iopub.status.idle":"2022-05-08T16:15:23.794580Z","shell.execute_reply.started":"2022-05-08T16:15:23.789308Z","shell.execute_reply":"2022-05-08T16:15:23.793738Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data['clean_text'] = train_data['clean_text'].apply(toremove_stopword)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:23.795845Z","iopub.execute_input":"2022-05-08T16:15:23.797855Z","iopub.status.idle":"2022-05-08T16:15:36.381412Z","shell.execute_reply.started":"2022-05-08T16:15:23.797825Z","shell.execute_reply":"2022-05-08T16:15:36.380522Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train_data.head()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.382562Z","iopub.execute_input":"2022-05-08T16:15:36.382881Z","iopub.status.idle":"2022-05-08T16:15:36.395325Z","shell.execute_reply.started":"2022-05-08T16:15:36.382845Z","shell.execute_reply":"2022-05-08T16:15:36.394790Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"9.4\"></a> <br>\n* 9.4 Lowercasing","metadata":{}},{"cell_type":"markdown","source":"Lowercasing is a preprocessing method in which the text is converted into the lower case. In tokenization, Keras tokenizer is used, which will be converting texts to lowercase.\n\nSo here there is no need for lowercasing the texts as it will be a duplicate work.\n","metadata":{}},{"cell_type":"markdown","source":"<a id=\"9.5\"></a> <br>\n* 9.5 Tokenization","metadata":{}},{"cell_type":"markdown","source":"Tokenization generally decomposes text documents into small tokens and constructs a document word matrix. A document can be considered as a bag of words. Collection of document is called Corpus.\n\nIn document word matrix :\n* Each Row represents a document (bag of words)\n* Each column distinct token\n* Each cell represents the frequency of occurrence of the token\n\n\nHere Keras Tokenizer() is used which is supported by Tensorflow as a high-level API that encodes the token to a numerical value. The main reason to use this is in LSTM input is provided by embedding layer, which requires input data to be integer encoded.\n\nParameter 'num_words' can be used to restrict the number of the token to considered by the model.\n\n\nTokenizer() uses fit_on_texts() and texts_to_sequences() to encode the texts to numerical values.\n\n1.\tFit_on_texts() Updates internal vocabulary based on a list of texts. It will create a dictionary with word mapping with an index (unique numerical value). Here all the words will be in lower case and the least value of index will be the more frequent word.\n\n2.\ttexts_to_sequences() Transforms each text in texts to a sequence of numerical value. It will give assign the index of each to the word. So the output will be series of numerical values.","metadata":{}},{"cell_type":"code","source":"max_features=3000\ntokenizer=Tokenizer(num_words=max_features,split=' ')\ntokenizer.fit_on_texts(train_data['clean_text'].values)\nX = tokenizer.texts_to_sequences(train_data['clean_text'].values)\nX = pad_sequences(X)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.396175Z","iopub.execute_input":"2022-05-08T16:15:36.396466Z","iopub.status.idle":"2022-05-08T16:15:36.561955Z","shell.execute_reply.started":"2022-05-08T16:15:36.396443Z","shell.execute_reply":"2022-05-08T16:15:36.561109Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"We are not be having the same length for all the sentences and while providing input to neural networks, we should have the same dimension for all inputs. So pad_sequence() is used to pad the input so that all the inputs have the same dimension. It will add zeros to the input, in the beginning, to make sure all the inputs have the same dimension.","metadata":{}},{"cell_type":"code","source":"X.shape","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.563047Z","iopub.execute_input":"2022-05-08T16:15:36.563297Z","iopub.status.idle":"2022-05-08T16:15:36.567883Z","shell.execute_reply.started":"2022-05-08T16:15:36.563270Z","shell.execute_reply":"2022-05-08T16:15:36.567430Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Here size of tokenized vector is 20, it is the maximum length of clean_text considering excluding those tokens which does not belong to top 3000 tokens. That is if the maximum length of clean_text is 35, then the 15 token will not be qualified to come under top 3000 tokens.\n\nWe can restrict on enhance dimension of tokenized vector by providing a parameter maxlen to pad_sequence().","metadata":{}},{"cell_type":"code","source":"X[0]","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.568665Z","iopub.execute_input":"2022-05-08T16:15:36.569250Z","iopub.status.idle":"2022-05-08T16:15:36.580311Z","shell.execute_reply.started":"2022-05-08T16:15:36.569221Z","shell.execute_reply":"2022-05-08T16:15:36.579462Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"In X[0] out 7 cleaned word only 5 belong to top 3000 words. ","metadata":{}},{"cell_type":"code","source":"tokenizer.sequences_to_texts([[ 713,  154,   56, 1434,   14]])","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.581250Z","iopub.execute_input":"2022-05-08T16:15:36.581791Z","iopub.status.idle":"2022-05-08T16:15:36.587129Z","shell.execute_reply.started":"2022-05-08T16:15:36.581759Z","shell.execute_reply":"2022-05-08T16:15:36.586498Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Other words in the first column does not belong to top 3000 tokens.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"10\"></a> <br>\n# 10. Model creation Using LSTM","metadata":{}},{"cell_type":"markdown","source":"<a id=\"10.1\"></a> <br>\n* 10.1 Splitting Text data","metadata":{}},{"cell_type":"code","source":"y = train_data['target']","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.588164Z","iopub.execute_input":"2022-05-08T16:15:36.588379Z","iopub.status.idle":"2022-05-08T16:15:36.596038Z","shell.execute_reply.started":"2022-05-08T16:15:36.588356Z","shell.execute_reply":"2022-05-08T16:15:36.595396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(X,y, test_size = 0.2, random_state =41)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.597147Z","iopub.execute_input":"2022-05-08T16:15:36.597348Z","iopub.status.idle":"2022-05-08T16:15:36.607944Z","shell.execute_reply.started":"2022-05-08T16:15:36.597326Z","shell.execute_reply":"2022-05-08T16:15:36.607454Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"10.2\"></a> <br>\n* 10.2 Embedding Layer","metadata":{}},{"cell_type":"markdown","source":"Embedding layer is the first layer of neural network and it has 3 parameters:\n\n* input_dim: Number of distinct token vector, here it will be 3000 (max_features)\n* output_dim: Dimension of embedding vector, we can take 32 dimension\n* input_length: Size of input layer \n\nHere embedding layer of size will be (3000, 32).\n","metadata":{}},{"cell_type":"markdown","source":"<a id=\"10.3\"></a> <br>\n* 10.3 Long Short Term Memory - LSTM","metadata":{}},{"cell_type":"markdown","source":"LSTM is an artificial recurrent neural network specially designed to avoid for long term dependency problem. LSTM have 4 neural network layer.","metadata":{}},{"cell_type":"markdown","source":"Each LSTM has 4 layers ","metadata":{}},{"cell_type":"markdown","source":"![image.png](attachment:75a90b02-0552-48f9-935d-b788f9ab28ef.png)","metadata":{},"attachments":{"75a90b02-0552-48f9-935d-b788f9ab28ef.png":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAm0AAAGVCAYAAACsIsZXAAAgAElEQVR4Aey9B3xVVbq/P3Nn7lXv7/7vnaIz41hHZywzjqOOo4hiG+zYQAVBugKiYAHEgop0kN4hoRfTE6p0CJCEhPSE9N57Pzn9PP/P2vucFAQEISEneQ+fxd7nnH32XutZb9b6rne1nyEvISAEhIAQEAJCQAgIgQ5P4GcdPoYSQSEgBISAEBACQkAICAFEtIkRCAEhIASEgBAQAkLADQiIaHODTJIoCgEhIASEgBAQAkJARJvYgBAQAkJACAgBISAE3ICAiDY3yCSJohAQAkJACAgBISAERLSJDQgBISAEhIAQEAJCwA0IiGhzg0ySKAoBISAEhIAQEAJCQESb2IAQEAJCQAgIASEgBNyAgIg2N8gkiaIQEAJCQAgIASEgBES0iQ0IASEgBISAEBACQsANCIhoc4NMkigKASEgBISAEBACQkBEm9iAEBACQkAICAEhIATcgICINjfIJImiEBACQkAICAEhIAREtIkNCAEhIASEgBAQAkLADQiIaHODTJIoCgEhIASEgBAQAkJARJvYgBAQAkJACAgBISAE3ICAiDY3yCSJohAQAkJACAgBISAERLSJDQgBISAEhIAQEAJCwA0IiGhzg0ySKAoBISAEhIAQEAJCQESb2IAQEAJCQAgIASEgBNyAgIg2N8gkiaIQEAJCQAgIASEgBES0iQ0IASEgBISAEBACQsANCIhoc4NMkigKASEgBISAEBACQkBEm9iAEBACQkAICAEhIATcgICINjfIJImiEBACQkAICAEhIAREtIkNCAEhIASEgBAQAkLADQiIaHODTJIoCgEhIASEgBAQAkJARJvYgBAQAkJACAgBISAE3ICAiDY3yCSJohAQAkJACAgBISAERLSJDQgBISAEhIAQEAJCwA0IiGhzg0ySKAoBISAEhIAQEAJCQESb2IAQEALtQsABqNB2L3V3uzOc/UmueJzpijN91nbxlTsLASEgBC6MgIi2C+MlVwsBIYCjSRrpMM4sg1yfuoCp90pS2VoE9V57uS5WH7jOnddbnde7fqveq3NXcGg/UHe1OIM6Vzdpfa/WHznA4QzOy1z3038o/wsBISAEOh4BEW0dL08kRkKgAxNQEsmOFRtW7Np5s4RzCiVn7F3ay3V0ySpzC3mlCTKXdnKpJruup+wOsDjA5AAjoH6njirYHLr4UzLN6oyRAzMOTFrMbNpndlA3cUZA02jNck57iMOhSz67w4H6TesUdOBskKgJASHQJQmIaOuS2S6JFgI/hYCSNEqoWbHZTNisjdhtjdgcSja18G65bq1frgkhJaeMDjsmmxWLxYrFasNis2G22TDa7FgduvTT9JUSZFYHVosdi8WO2WLHYLVTb9WPZosNm9mGTd3Dbsds13+vxcvRiNluotFuweSwabFVEVCCTQlEFVwONpdGVPexWszYrCan/04XbyLgXBkpRyEgBDoKARFtHSUnJB5CwB0IOOxKUWHLzqb+RAgVCVGYjQ3Y1eenv5rEkh273YKjsRZHQT72A8EYN3rTsGErjTt2YktLwW6o17xqWp9njQV7TDr2QydwHAzBejgUc3Ao5qMhmI8cxXI4GGvwUexHj2MNDaEsLoGG6lpoNODISMEYeoT62Cgay8qxKTFod2gONyXJTMoD5xKTSsHVOzBHRVMbvJ+q2HCwGlFeN5UaEW2nZ6i8FwJC4HITENF2uXNAni8E3ISAJmKU4rHZMfntJOL5V9g+eDDG0hJs9jOINqdfzm63QkkpVv+dlA98h8QnehL9UA9iH3qExB6Pk/baa2QvWUR9SgqYrJBVRPrIsST0fJaEp54m9qmnSXiiJ9k9Hiezew9inuxJZM+nSXj6GeKee5b1bw0i71QalJfDgvkU/PsJTjz7LBlb/FDdn8qLp/SZBdWBatdFm+pfbTBDch6lffsT0+0B9r0zBIw1mgA9c2rcJKMkmkJACHRaAiLaOm3WSsKEwKUl0CTarA7MyzYSe8PtbLrnXzRk52CzqxFhp7+Uq80KRgPWnQcoffJVYq+9mdjnXiR15EiKxnxAad9BJN91H0fu/BuJX07CXlmBIzeP0ukzyRw4gIyhA8gcMoCyZ5+l9A83E3PFr0h87mVS3hpM5oAhpA8ewvZxE8g/lQKF+TBhHIZf/4qk//lfQgaPAovqJrVr4+H07lG75kXTBsWVlOFYvJyGP/yRtCuuYsfD3cBQhUN5DX+YmNMTJ++FgBAQAu1OQERbuyOXBwoB9ySg6Rg1IMzmwLF8Pck33sbGu++lISdbE20/SJUSbJZ6KCiitu9gon9/MzljJmJNzwJDA5gaoKICfIIofOBBDt91J7XHDmJvqIcGA9TWQV0N1FbBgf2UP/oE/v91JeWHDuGoq4Paeqirw2EwgMUK+bkwYSyWX/8fBf/xc/b/427suTk0Wq00OCcyqI5PLR02O47EBEz3/QPzlVeR8Z9Xsvfhh8Bc5xRtSnCKv+0HeSofCAEhcFkJiGi7rPjl4ULAzQho3aMOWLGG5JtuZf0995xdtKku0/o6OHyU4nsf4Og992CMPInBYKBBTUpwjo+jqobiiZ/gf/NNHP3yCxoryjHaHRjtdgx2OzabBUKOU/JkTzZe9d8UhoZQa7NS7/ze7LDjsFggLwc+/RDDTX/EcPutJN5yI7FzZlFfVanNONUkmNPrZm80Ydqxi/grrsBw222k3HgTgY883Fq0naXL181yTKIrBIRAJyIgoq0TZaYkRQi0OYEm0eZJ8k23sO6ef5xVtDnUtfUmOH6C0n91I+yO2zHs/x5jQ4M2k1QbY6YEl91GfchR0pcsJmf395jr6rE6V+vQ5qSqMXGhIZpo23Tlf1McFoYSaqq7Uwkx1eHpsJohNxfHZ5+QevvN1PZ/jZzu3fHr9iDVSae0WatqTqj6Z7VZsRcUUf7p12z4xS+oGzSA2Lv/jo8SbcY63cOmdZGKp63N7UkeIASEwAURENF2QbjkYiHQxQmcJtrO5WnTltYw26GwhPq3BpF6/XVkvf469UeOYy4sxFpXjdlowK68aVYLdpMJzBZttqfWM+nQRZmarUqIS7T9P4rDQrG4xtBpS3nYsNvMkJeP47Mv2PuXmyn5ciJlo99jyxVXUODng8Vo0NZh0xb1sJqxHj1G6uNPs+ymm6idPZ2I+/6hi7ZG1T1qc3aRimjr4tYuyRcCHY6AiLYOlyUSISHQgQk0iTYPzdO2/h7XmLYfChx9RTeHvkba9zuoeKQb6VdcRfxf/0XemAk0+AfiyMzGajJhdDi0JT+U0NMGnTmP2l1tNggJdXra/kf3tNnVGmz6tUbUWm1qTFshjs8m4X/rzWQtnEOD1xb2/OIXxLw3mrr8XBqwU6c8c1YLdfMWEn7DXwj/6GOMyxcT+dfb2eb0tJkdNm2Wqb7wRwfOC4maEBACXY6AiLYul+WSYCFwEQSaRNtqp2i7j4YcNXu0tWhTmsu1A4L6xlFTie14MIbxE8jq9hBJN/2J+BtuJe3hJyj8cDy1x47hqKvVI+YSbq610mz21qIt9IQm0vR5oHZtKQ81e5W8AhyfTiLg5puIXzAHa3QkRXffxfZ/3kfBoQPaGDqTzYYjJYWc1/uy7c67MB4Pw+6xmqg/38J2JdpM9VgddmzKL6d53FRk5CUEhIAQ6BgERLR1jHyQWAgB9yDQJNpWkXzTn1h/zz/PKdr0jaUcWnemvbERe34+lv37qJk1h9KBgyns9jBJf/ozsY8+Qd7KlTjU8iBa12eLHRbUmmohYZQ8+W82Xfk/FGuizYKSVmqPA+XRcyhhp0TbxC8IvOEGoubNxlFcgPWbL9h54/XETJ+G1WjEobpfN24h5O5/sKt3b6ipgzVriLrlT2zv8QiYG7SuUV2wObtJ3SNnJJZCQAh0AQIi2rpAJksShcAlI6CJNjusWOkUbfefVbQpMWVTXY1Wkzb432qza8ujWax2bA0N2LOzsO3YQc2QYaTfdAtH7vsn9VERNCpvl7Z3gRJlTpddk2j7/ygODcdsV8vk6kvm6qLNAXmFOCZ+zrbrriNizkwwVOOIDOHEP/7O0V4v0ZCSBnX11Ix6n/133knkvG+xqfFyG9YT/aebddFmadAmIqi12prGtl0yeHIjISAEhMDFERDRdnH85NdCoGsRaBJtuqdt7T26aLPalXRqNRxN27IdmwlKCqG4CEddg7bIba0D6hz6XqRq/1FHSQkNo4YTed21RE78lJqKYhqcG79rcK0uT1tPNl35vz8i2r7QRFv4nFlgtUB9DaV93+To7XeSuGSJNoYu7N5/8n2PRygPD6POZMC+aQPRf3J62kS0dS17ltQKATcjIKLNzTJMoisELisBbXFdG6xYRdJNt7Dmnvupz8nF7NC3jFe+MVfQZnga6qmZPY/gJ3sSNWsWStzVO9DWTTNqW386sDbUUj/9a6Ku/SMHB75NTXEJanKBLgNVD6gDjqvu0Z5svup00WbVZoU6VBeq1j36OTuuu56Tc2bhUJMTTBasyzyJvPMuTvbqhWPlWrar7tMvxmOprcFmNOPYsFFE22U1Knm4EBAC50tARNv5kpLrhIAQ0NcwU4vdLltN9g1/Zud93WjMysFhseKw2vSj2aIt3WGzmnHUVWFauYZTt91FePeHaQwLw1RXg8lm1nZRsJktmver+u13CPnjTZyYOJXaimqtc1StqaYEoDZe7fgxSp98jK1X/j9KQsOx2F1j2mxYlU9PzTDNzcPxyUS+v/56or6drW+tpcRc1ClKn3mJ5Kt/S8ODDxN479/J2hWg/6bRDBvWOLtHHwarwTmmTbpHxdyFgBDoeAREtHW8PJEYCYGOS0DbxcCEbelqiq+9haS/3EVt0E7qj4ZSfyyU+qMh1B85Sm3wcapiorFVlOBIOEVVv8Ek3nQrmc+/RI3PdzTGRmCKj8V0LAzD1Hmk3Xk3e+97gKJ9xzEYjNqMULXZuybarFY4dpiSJ7qz4YorKAo9gcWuJiCoPULV7FE7NrtFX1x3/AR2X3stUbNmYnf+nmoj5i+nUn7VVST88pcEDx9MVU6W5vXD0AgbPDj5p5sI7NEs2tR9ZUxbxzVDiZkQ6KoERLR11ZyXdAuBn0LAKdoalqwg7VfXkPKfV3D0N1ez7+rfsdcVfnsNO6++hnWPPEJ1Yjx21Q15Ipryt98n4bfXcvTXv+bkTTcSe8stxP/hOsKu+B8O/P3vJC1ZhMNi0yYraAttaIu2oW36zvEjZDzRg9lXXUVemBJtap02dZVdG/2mJiaQk4d9wiTW/+Zqjk+ZisM5zk7rXt2xm7zb7sTjl78gw3sjVrMBi1qmpKEBNq1n1y1/YlX37mBu1D1t2LC7Ftn9KZzkN0JACAiBNiAgoq0NoMothUCnJaB0ktWBOSqRktkLKZ38DYVTplAwZRr5U6aTN3UGeVOmkzN1BkkenpirKjBZzFjrGrDm5WM6dIiyWbPIGj2GrHfeJfvDjyhavJD6qDAaq0qxORzaPu1qGJvavcCsukfVGmwF2VRuWkfYvPnU5Bdos1L15XVtmLBicFix19Xj2HuQ6HkLyD56TLuXtnqc+q+olKrN3oTO/Zb6/Bxt9qnVYQOTEeLjSVu8lKh1G1G7LyjPnRmr9s+ubc3QaXNTEiYEhICbERDR5mYZJtEVApeTgObbsoOt3oilvApTaSnm0hLMZaWYtFCmHY1lpZhranDYbNpitWrHA7PyfJlNWMtLMWdnYcpIx5yXg7W6Apu5ETMWbdU11eupnGBKsFmce4vazAastdUYq6uwWyyaN0xfp00tg2tF7WKgZqJaG+oxVldjMRq1rlU12UEJQJvZirnOgKG6Bpv6vfbPBmosnKEBc3UNxlq1X4JDi4OSbGq5EtVFKy8hIASEQEchIKKto+SExEMIuAEBJWGUkLI4l+yow6FtD6W2iKrXgo16bKidPtU1+suhCTclwvSZpTaMyjumrnFu4K53ZSoZpsaS6WuHqKM6VY4ytUivJrWUmlPiz+FAecG0raYcVm2mqLqmARsm1XVq1zehanR660xq73qHHnd9X1O1vZYaE6eu0++t0qVeDnU/LahrXGlwfikHISAEhMBlJCCi7TLCl0cLAXckoESUvjGCWjxXCTL9qM5bBjURwCW79MVqlX9LF2GuZUG0iQYKguvS04E4P9cEnDpXL+ebJkGliS+bfm+nkNM9aa5LdWGmrlD/NLGnumGVKHTGWcXVFVyiTY+U85lyEAJCQAh0AAIi2jpAJkgUhIA7ElCC51yhteg5myr7kZS7fnauoybXlPzTZ5PqslBJS6erThN7zTfQpdu54q578n4kZvK1EBACQqDdCYhoa3fk8kAhIATOm0Cz1mr2xp3+me5jc/rwND+g81xTa2d91LkEp/pOXkJACAiBjkZARFtHyxGJjxAQAs0EThdoZ3ovoq2Zl5wJASHQqQmIaOvU2SuJEwJuTuCMIu30NKmLWnrYnF2jmpg7/drm9+Jpa2YhZ0JACLgHARFt7pFPEkshIATOSeB0dXfOi+VLISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkJACAgBISAEuhoBEW1dLcclvUJACAgBISAEhIBbEhDR5pbZJpEWAkLAXQk4HA53jbrEWwgIgctMQETbZc4AeXzHIyCVasfLE4mREBACQkAIgIg2sYIuQUD3baj/HdgddixWCyazCaOxEaPJiNlixmqzYrfbEdHWJUyi3ROp7EoLOLR/yg6tNptuhyYjJpMJi8XSZIeIR67d86irPlDZpd1uw2Ixa+VhY6MBk8molZNamYh4hzuKbYho6yg5IfFoOwKq8nM4sJpN1NfWUFJSREpaCiciwgg+eoSjx44QHRNFWkYqRSVF1NXXY7Vapc5suxzpcnfWmwuaGWI2maitraWgsIC09DTCwsMIPhZM6IlQ4hPiychMp6KslMb6Ohx2e5djJQluewIuCWa32TEYDJSWlZCTm018QhxHjwVz6MhBQsKOk3gqgdy8XKqqqzAajajr5XV5CYhou7z85eltSMDhsIPDBnYzdpOJjIRUlsxYxIgBI3jxyZd58K6HueOGv3P79XfxwF3deeHxFxk9eDQr5q8gOz0Ps8mqeeWUd+70f20Ybbl1ZyDgUmlaWlSjwQ42Ow6zhZPHw5k+aRpDXh/MM488xf133sedN97G32/9Kw/f043ez7/KJ++NJ2CTN6baOuxWmzJBXfF1BjaShstLQHl87XbsNhuVZRV4bfRh1JD3ebFnH7rf+zh33Xofd9x4N3fedDfd7+tB7xd688kH4/k+aCc1ZZWnNSRchu46Xt6kdYWni2jrCrncRdOoXP5Wk5GqokK812xldL8xvNy9L+P7f86CcctZ8fl6PCd74/mNNysmbWL+uOV81O8Tej/Sl+F9R7N1ozdFxQVYrWZNvNlp/tdFkUqyz5dAqzrMgclgIi0mlbmfz2bgswN568lBTHlnGksmLGPN5I2sn7KFdVO2sPrLDUx7bx6j+nxI32feZNy7Yzm8bz9VFeUi2s6XvVx3dgIOtEZARWkFQV5BfPTOOPo88SYjXv6Qqe8uZOlnG/D4+jvWTPFm1VebWfyZB1+OnMaAZ4fw0mMvM/H98RzYvY+qSqd407rwlffNpg09OfuD5ZtLRUBE26UiKffpMAT0sUPQ2GAkIymTxdMW0bfnQEa/OpHVk3wJXhNNrHcGp/zzSfYvIsm/iAS/fKK9MjjiGYnHl14Mf2UMrzzbm7lzZpOWlkyj0dBCskkXQYfJ7I4aESXa7Oo/MDaYiQs9xaRRU+j70GC+HDAN/5m7OLkxiXivXFICSkkNLCc1sILkgHJObs1h98oTzBm3jNd79mPoG4Pw3+pFZVm5jLfsqPntBvFS+spitpKWlIXH/PX0e3IwI14Yw+KPPdm7NJSoLRmc8s0nJaCI1MBikv0LSfArIGxzGkGLgpkyei5vPDOAN199i03rNlNSVILFbNa9yKgyUbd3N0Dh1lEU0ebW2SeRbybQ7Nqw2x1YzA4yMwqZ+uV87r/5IaaMWsB+z1hifEs45VNCim8paT5lpHmXk+ZVTqqPHpJ9yonzKeLQhkg+HzWZf/39fmZO+4a83CxsNrO0KJuBy9m5CCjBZrFjtzpIOpnFhwM+540HhhMw+zgxWzNI8y0g07eKLF8TWX4NZPrVk+VXrx3TAxtI3VZNXEAB+9aGM/ylUfTq8Txe6zajBoirCQzyEgLnR0AvF5Vgs9nslBRXMPmLb3nkjheY+OpMQjwSSPEpItO3nGzfKnJ8a8jxqW4KWb71ZPgZSfGrJdovl8CVB3n79Q949F9Ps2bVRsrLKrFZLE7hdn4xkqsujoCItovjJ7/uMATUqDObNgNKNfgqKxtZtGQr9/3jGcb0/pAtUwOJ2JxJil8VGX6VZPpVktUUqsjyqybTr4ZMvzoy/WpJ9C/l0MYYZk9cwL/+dhceS5ZQVVamd1FJg7LD5HqHjYgawmayU1Nm5OMhX/Pmw+/gN2M/oRvTOLjyOAEzdnJ8ZQJpvkYyA2rJCqgiK6CarIAaMgKrSFOet6AKkoLK2bsyjI/7fsKrPV8m+OhhGhrqnV4N8W502PzvMBHTZyyrhmxDg4l5c1fzaLfejHx1Msc9s0n0LSdNlYNOwZbrW0fLkOOrysN60v1qSPIrIdY3i12rghk7bBL/uOtRdm07QH1tw2nj3DpM4jtlRES0dcps7YqJUkt52LTlEmxW2Ls9hP6vvM+7b37OkCeG8eFzn3B0eSxZ/tVk+SvBVk6Wf4V+HlBBVkAl2f7V5PjXke1fT6p/NfH+xQRvimT8kLH0e743h/fs12dPiWjrigZ2YWm226kuq2bN4u9488l3WTspiKjvsokNzGfhx0t5+cFXWDl+E8n+taQHVpERWEmWOgZUkB5YTnpgqS7cAmtI8C1i56KjjOozltdfeY301FQcaoKN1iUlwu3CMqbrXa0EW3V1Hbt27efhbs9w+43dGPHSV0RvKiPFv5Y0vxoyfFWjtZpM35oWQX1WRYZ/Jen+FaT5l5HiW0iCbw671oYx5LWPGPDaMIIPBWuz7W1quaSuh7fdUyyird2RywPbioDqNlJrr5UVV/HJyMmMeP5DvGcF0b/HQN7qNpT980PJUC1L3xJSvYtI9yklw6+cDP9yMv3LyfavItu/hqyAWjIDqkkPqCDRL4d9aw7Q/7l+TJ74JRWlZdpablI6tVUudoL7OhzYLGbiwmN45O6nmTRsEUfXpnAqsIy4bUVMHjGNbnc8yNz3F5PoV0ZqYBlpAaWkB5ST5l9OWkAl6a4QWENKQCVx3kWs/8afe/90H35bvTHU1eldUlpXqXSXdgKraZMkaJOxbDaysnIZNuRd/v3Ii9x72yP0f/x9YjaWkOpXQ6pfNam+VZrHLc2vgjTfyubgV0m6Cv4VpPuXk+6nbLWcWN8CfBfv4+nuL/DNV1MoKSvFYrNJsdgmudj6piLaWvOQd25MQIm2+oZ6Du8L4/kH3mDee8sJ3RDBm08M4M3uAwmYsYdQj1PsXxhB8PIYotZnkOJVQrpvORl+FVp3qfK2ZSnhpo4ByvNRQpx/MtPGzuCVp15mz87dmM1m6Q5wYztp66irirKxwUDAJn9uv+Y+vpt9gDjfEs1jlrAtl69Hfs2/7rifGaNnEbImkRCPaI6tjCR8bTJJPmVaRZrmX02a8nBojYcaUgOqOLY+jn49BzD+vY/ITE0DtYZbk8etrVMl93dHAjZli0YTB/cHc+sNd/LpmK/p9Wgf3njsbcI2ZRGxJYvwzRlEbM4izquAU77FpPiVk9oUKjTRluGvPG7qXHncKrUJM3HbcvjgrQm8/sobhJwIRfO0abNJ3ZGU+8RZRJv75JXE9EcIqMqyqrKGud8sZ/TLE/l+QTCRm+Po8+/Xealbbz598xv6PzCSF/7aj973DGbGkKWcXJ+qTUjI8FXj3KrI9FehWvO0KW9bZoCa0ZeL94Ig+r86mDlz5lFfr8ZwSEfAj2RHl/66NL+U6eNn0+fhYexfEUOyfxlJfoUkbsvk65GTuO8v/2BUr1EM6f4eb/y9P73ueIURT3/MoVWJnPKuIk11WwWoowrV2nmkVwarp2/grT4D2bt7vz5ZT9mhVJRd2tbOlXglpIqLy1kydxXPPvgKy6es5aUer/Fi935smLmNMb0n0f/RUbz30qf4ztpL9NY8Uvx10ZYWoASa8rApwdY6pKuZzkFFbJ27jbd6D2XhwoVYbRaZ3XyuzLhE34lou0Qg5TaXn4ASbWUlFbz31gSmvbOIiHWJRG6M541/9+WBm7rTv/twZg5bypz3V9Gn21Be+Ec/1kz0JdmriBy/KrL9qsnQBFuNLtqUt02N6ZD+XMsAACAASURBVPAtZd/aUN4fPp6Px0+kvKIKm01Vlpc/zRKDjkdA2WFMSBwjX/2A9VO3Eb0lR/NSpAWUEL8tly9HfM2d19/B43/+N5Ne+5al763ho96f8tCt/+bdFz4n1COd9IAazcvWUrTF+uWyzXM/Pe5/gtUr1+r2J3bY8QygA8VIzRhNT8vi8w8n884L7/Pd3ABeeLg399z8EIN6jqbfo8Po030Qj975HC/eO5Dt34aQ5FOiT4bRxrGprtGqVsIt3b+SDNWVH1hG8OZY3h3wIR+P/Riz2agPHelA6e+MURHR1hlztYumSTkcSgrLGPzqaBZ85Ens1nQiNsTx5pNv8cDNjzBn+FIi1iYT6ZXJis838cK9b/DesxOJ3ZJNtl8FOao1qXnXqskIqCIzoFKbqJATUMVxrxg+GvUpffsOoKiwBKtF7VHaRUFLss9KQAk2FbZ77eCNRwcS/l2qNgYoO6CSjMAK4oOK+GLENO68/m8Memwkx1enEbM1mx1LDzHsxff4668eYNe3IXpFGaB72DThFlBFnH8eezYd496/3s+cWfN00Wa1N60Hd9ZIyRddloDNZuNUQgqj3vqAsX0+wXfBDl585DVuv+YeJr01C795e/Cbv4evhs3mzl89yLKxW4jbmqvZbKpzfKXqDlXjLHWvm+uoxmKWEu6XxIdDJ/DuOyNpbGwQ0dYOliairR0gyyPah4Dd4aCoqJT+L73DwnFriPFOJ2xjHL179OeFe18jcMY+0v1KSA4sYvvS/drnz9/1Bie3pJHonUeSd6E2e09VriqoweGJXnmc8ingmHc0H42cyHPPvkBBfiFWi01EW/tkq1s9Rdtc2+EgaGsgfbr3JcY7l0z/SpTwzwyqJCGomM9GzuSft3dnzqiVpPoZSAusJMIvmcnvz+X6K+/Ef9ohUnzLSVVdU2r5D1VhBlQQG5DLni3HuP/uB5k2daYm2hxqiyvpqncrG2m/yDpQoi0+Jomhr7/H2Nc/w2/Rbno/NoBn7unNwRWRxPsWEuObgd/87Tz2p55MH7SYE2uTtQWfU/zLNNtMCaggJaCcVBX8y0lWZaga+xZUQnhAAuNGTmTk229jMNRpz2u/9HXNJ4lo65r53ilTrQbd5inR9uoI5n/sQbR3GiGbYnntiYG8/tBgvp93lEz/UtICitmxYh+vPtaXp//2Cie2JhM05zDbZh4hzV/N4isjNaCEE2uTWDPBj3WfBbJ7XTAfjfyEV196lcKCQmxWJdrE1dYpDekiEuXytG3zCuS1h/sSvSWXbL8q3YsbWEFiUDETR83kn3c8wrx3PbWFS9OCqojwT2Xy2Pn88Yo78J16kKgNOeyZe5K4LfnaoHCXaPt+6zHuvet+pk2bqcdSbPAicquz/9ShlVNJ8emMGjCO9/t8it/CPfR7fCh9HxrCyY3pJPuWkxiQx87le3ju772Y3H8uR1fHEu+TT5J/Caf8S0gKKCU5oFQTcok+RRxZEc+R5XGcCiwg1C+GMUM/YPjQIRgM9djsaikaebUlARFtbUlX7t2uBKwOB/nF5QzrO5Y5Y1ZwcmsKoVviefXR/vTtPpTdmmgrIz2giJ0r9vLqY6/z1N9eJmRTAvNGrmFKv0WEeZwixa+IVP9i4r2y2TnvGMs+3Ir3kp2MfedjRo18l4ryCq1FKaKtXbPXbR6mlnk+vOcQQ194h31LokneWqLNTFaDt5Vo+2TUTO6/4xHmj/Ig089IelAV4QGpfP3BfK694g78ph1k//wo5g5Zy/4FUZzyKm7ytO3YdIT77+nGt98u0HmIaHMbu2j/iCpPm520pEzGjfiCUa98hP/CXQx4bDBvPTyc6I2ZWjd8UmABOzTR9gJf9p3JznlH2fr19wTMPErklhzifAqI88nnlH8Rsd/lsvHznWyd9L0m9o55R/D+4PcY9fZwjEbpHm2PPBbR1h6U5RntQkCtElRaWcPXE+bwcd+v2bsshOMbY3m1R3/6PTyUvQuOk+mvRFsxu1bupffjr/P0317i+KYEZg9fxddvLODw0mi2zwzm0JIoorakc2hFFMs+2MzKqRsZ+uY7zJg+k/q6ehm70S456q4PcZCdns34t7/ks35LiFibpXVxpgRVkBBUxCejZuii7V1PMv1MpAVWEa552hZw7RV3ap62A/OimTt4LYcWxTSJtkjfLNYvCuD5p17GxydAh6NEmzh83dVQ2jjeDm0x8PzsAmZ+/i19H3+LLbN9ePPR/gzoPkQTbWrsbkpQITtXKE/b80x6YyYBMw/y7XBPFr27meOeyYSuTWXX/BPEeuUS553HtllH2fz5buL9cghcvpvhfYczc9pULBYTDtlirY3zFES0tTlieUB7EVBLjNYbjOz0O8jzD77Owg88Obw2gtceHcjAR97hwIIQsjXRVsT3K/fxxhP9eO6uVwjdfIrF729kwaj1hHgmMf65qcwd7snBFVEEe8SwYvxmJo2eyUvP9GFbYJC2Tlt7pUme454EqitrWTF3E91u7Muu+VEk+6slEiqJCyxi4uhZ/Ouvj7Jg9BpdtAVUc9Ivg2ljl3DjVXfjO+UQx5cls/aDIOI25ZLiq7rrywnZksLE92YwYthoYmPidbEmnjb3NJB2irVamqiuooagTYHcf9ODzBwzjzce7segh4cRsyFdG7ubHFTAruV76XX3i3zZdw475x5n1Yc++E05RNjaVLwmH2DG4NUEr0ok1iuPfQsj8Jq8l5PeqXw2/Btee+519n2/B7vdKpvGt0O+imhrB8jyiLYnoJwNSrSZrXYKsyt455UPGPPSRHYuPcSIXh/w/nMTObwokiw/5Wkr4ODqMEb1+pi3eowkdEsCa7/wY8bQ5WyfF0LI+jSivfII9kxg3gfrGd77Ux69vxcfjB5PSVGxvr9p2ydJnuDGBKwWK8cOhXPH7x5k2fjviNtaQGpAJfGBRcwat1pb/HnluI2o9QHV7NBYvxxWfraJHjc8z7bpxwlbmc6q0X5sm3qM6A1ZnPItwH/Rbv71twdYuXgVtVW1usGLaHNjK2mHqDsc2C1WMhMzeOu5QQx+ZiTP3v0qwx4dTcKmTLKDKrWJWd8vO84b9w9j9tAV7F90Eo+P/Fn9UQCHlsWx9es9zBjqweFVp4jYmMV3k79n4Xse+M7bwXMPvMSE9yZQWJCPTURbO2SoeNraBbI8pO0JuESbWrbKYrSzYZE3bzw6hMWfeOI9/3t2Lw4ndmMBmb7VpAaUEumVxfdLwwmYe4ST32VwdE0C+5ZGEbI2jYSAclRXVpRXDt/NP8CQfhN4+MHn2LrZD6tFLSApLcq2z1H3foKayayWn5kyYRbDnv4Q/xmHSfIt1ezq8No4ti88wgnPBHJ91TZBVSQFFBO+MRG/afuIXJtN4uYiwlalEOaRTJxXNsGeUXw29Aue6t6DuKgYrCar09Pm3pwk9u1AwGanrqoO79W+PPbXZxn67FhWjdtMxtYCcgOqSPUtIWJDJhs+3cH388KI3JDJ8VVJ7JkfRZhnOiGeqexdGEuCVwXxW4u1cb4rPlnDe73H8Gy35/Hf6o/JZHKKtnZITxd/hHjaurgBdJbkK9HWFGyQcSqXb8bN5rUnBrF+5nYivfJJURsiq83gA6pICiznlLaqdxVJassWtddjYA0ZQTWkBlaQsq2Mk94ZrJ8dxFOPvcrnn04lNTXT+RQ1Q0o9TV5C4MwE1CQVY6OJU1FpvP3yB4x5+Qv2Lz9JelA5aUHlZG+rIte/mjzvWjL8a0gPqtQ+Twss19YIzAqqICOomNQd+QRvjGDGBwvo9ciLeCxaSmVpOajWiewVf2b48mlrAg6HJvLL8sr5ZMRX9HvybdZ+6kX6ljyyfEvJ1PYbrSDJq4Rkn1J9Cyv/cpK8S0jyLiXZp4Jk3ypS/WtJ9i/nkOdJZn80n57/7MnCGYvIzczTxrKpCTjyansCItranrE8oZ0IqCJD2zpb1WcWB1HhcQx98116dRuIz+xDJPgUkxmkNuCuIDmwgtSgajKDGsgMbCAroJ6cwDptLa1TgflEB6SzeW4QL/Z4g+GDRhAXG4/FamkhDdspUfIYNyVgx2G3YWm04b9uO889+Apjen/CiQ0JJPsUkhdUR2FQI7mByv5qSQ+qJm2bEm/VpAeWkbGtkORtGYT7RfHNB9N44O5uvD/ifQw19Thcgk3aDm5qG5ch2mqbWpOD+BPJjO4/jhfu7sO2GbuJ2pBMim+xtk2VvjG8viagWmJGrcmmL7BbTmpgOUmBxYRsTWTh56t48oGnGf32aLIzcrTJDtqildJV3y4ZK6KtXTDLQ9qDQJNoU+LNAbUNjUSExzFm0Ke8/M9BzBq2klDPRG0MR1pgqba1UJZfNVm+1doWVmqf0US1gKnHMcYNnUTPR3rx7oixJMQlYGw04NA255bWZHvkpfs/Q9mJQ9ujtq60jl3f7WHg88Po8+AA1k/0I8oziwwf3bOrFnJW21alBTSQHlRPZlA5Sb6Z7Ji/i2HPv83Tjz7FzNnTycnJ0mctq5aJK4g5ur+ptEcKlL3YwFRvJv5EEpPHTOfxW//N+Ncmse3bQyR6F5K1rVZbAkTtgKC2qlJBbVWVFFDIya2p+M7fy5AX36Vn92f56ouvSE9P17pFm7o42iMd8gyZPSo20LkIuOowdVSL7RoajJyKTGbupAW82XMgQ54bro0N2jzLn4Oe4RxbH0PIhlgOeZxg6+wAJg7/ktef6c/zT77IjGmzSUpKxmwyY3fYsKMWFVGln+spnYudpKZtCDgsDqrLqjmw8xCjB4+hzxNvMuLlsUx5by4BK/dwcMNxDm+M4MjGaPZ4hrD8izWMf2si/Z56kzdeeIP1a9eRW5DdvHCpMj8xw7bJrM56V2UzTrsxNpjITs5h6azlvPrka7z2xAA+7v8Fq77czPalRzjgGcGRtdEcXhfF9mUHmP/JEka9/j4vP9GHN18ZgOcqD1LTUrBa1fhelyG6HtBZAXacdImnrePkhcSkLQioZaxsdorz8gny9eP9EaN4+ekX6P/yYN7pN5bRAz7mvbfGM+LN9+n/ykB69+rDB6PHst1/G0UFhU3rsSmx5vqnC7e2iKzcs1MSUDZoV2PcGklKSmLF8hUMHTKUXs/3YkDft3j7rXcYOWgUIweOYmi/4ZoNvvbK60z+6huOHztGVVVls2DrlIAkUe1KwIG2U0JdTR17d+7lq0+/os+Lr/Pa8/0Y3GcEI/qNZVS/D3m3/8cMfHUYvZ9/hTdfe51pX08mJDiYqsoK7DY1GcvpvlMuPGlFtFsWimhrN9TyoMtCwNUAtDuwmS001taTk56N56p1jPtgIkPeGsGwQaMY/9FnbFq3hYLsfIz1jdo4DSX2VGWr/rkEmzqKaLssOdlJHurQPBQ1NdVERkUyc+ZMRr83mqHDh/L2O8OZMHE8O3ZtJ78gn7r6uqZGg0q87MDRSUzgciejqUwEh9WBpdFCWVE5u4J2M3XyTEaPGMvwIaMYPfIDpk2ezoE9+6koLdOEnl1517StqlyCTYk3l4BTN5ZXWxMQ0dbWhOX+l5eAq4DSjmqFcBsWs4W62jpyc/P4fs9+Dh0+SmFhMQ31Daj1tbSB3i3KH122Nf8v3aOXN0vd/elKfKmN5c1mMzU1NZSUFXMs4iieWzzIr8ijxlCDwWzAbDO3Emoi2tw95ztI/FXZpjSXs2dTNUxVuafKv6qqauIT49i9Zwdp6SlUVJTT2GDApspFu2rEqhkNKtiU4sPhUF2k+jJIYp/tk78i2tqHszzlchFoJdqah6OpgkrNCB00aCgTJnxKdnauPgtKxbOFYHNFu1myneFL10VyFAI/gUB1XTXLVi/l6V5PcTIuggZjPTY1htJh10Sbqgxd4SfcXn4iBFoTcJWJTtHmmkigbMxgaGDdOg+ee/4ptgX5UVdbrVy8zvFwalq+HZSnTQVNtCnhpoJNtrBqTbnN3oloazO0cuMOQcBVQLm0lvNYW1PL0kXLuO6P1/PnW27Dx8uXhroGrTv0bPF2CbezfS+fC4ELIeASYkeCj9DjsR789urfMvGzT8jLz9O7RVVd2UKwqXN5CYFLQqBluegUb3abncT4eF7r3Zvf/ObXvPVmP9JTU7GaLbpwU1PytdDsbdPFmhJsItouSb6cx01EtJ0HJLnEzQm4CiiVDGdFGBMVw/PPvcDPf/ZzLQweOIS0FGcB1Sq5UlG2wiFvLgkBJcCsVqvWRTp27Fj+7//+j1/84hf86le/Yvv27TQ2NmrPEdF2SXDLTc5EwFUuas4zu9Y9OuWbb7jxhhv55S9+wTVXX82m9Ruoqapyett00dZsk8oT7BJsItrOhLgtPhPR1hZU5Z4dloBqTaoK8bPPPuOaa67hZz/7mRb+eO0fmT17FiajsdXg7w6bEImYWxNQFZ/BYCA4OJh77rlHE2z/8R//gQrDhg0jOTm5aTxbcyUpDQi3zvQOHHmj0UjkyZM8/PDDXHHFFfz85z/XbLLXCy8QGhp6RltsaZeu8w6cxE4TNRFtnSYrJSHnQ0AJtgMHDnDvvffyX//1X02i7Ze//CU9n+pJeMQJLBbz+dxKrhECP5mAzWYjJSWFV155hf/93//VKklVUSrRdvPNN7NixQrq6+ubKsuf/CD5oRD4EQJqUkx+fj5jxozht7/9rWaLrsasej9jxgwqKyu1u7jE2dmOP/Io+foSEBDRdgkgyi3cg4DqjsrOzmbQoEH8+te/blU4qULq97//HeMnfEx5eRmqUpWXEGgrAmrWqKenp+bVUN2iSqwpG3R5OB5//HGOHTsmdthWGSD3bSJQV1dHYGAgN954o9aQVTboCso2lS0qj7ASd2cTa67Pm24qJ21GQERbm6GVG3c0ArW1tfj4+GiejP/+7//mP//zP7XCSVWY6vyqq67kttv+zIkTofr2LB0tARKfTkFAVXCJiYn06dOHq666SqsoVeWoKkplh8oD/Pvf/55x48ahuq3kJQTakoDqih84cCBXXnmlZnvK/pQdqt4Hda6Gkbz77rtad/6PCbe2jKfcWycgok0soUsQUBVlQ0OD1mJcsGABc+fO5Z133uHqq6/mhhtuYPTo0dqYtqVLlxIVFSWirUtYRfsn0lXpqa5RDw8PZs+ezfjx47njjju0btIhQ4YwZcoU5s2bp3k/TCaTdJG2fzZ1qScWFhbi5eXFnDlzmDx5Mj169NAmxvTq1YuvvvoKVV76+flp5afqgRCv2uU1DxFtl5e/PL0dCVgsFlRXQHl5uRZUl8Ctt96qjW/bu3cvJSUlVFRUUK8W2bWqVb7lJQQuLQFXhafGVio7LC4u5sSJE/Ts2VPzrm3cuJGsrCzKysq0hXeVHarfyEsItBUB1TBQ3fXKHtUm8KoB+4c//IFJkyaRlpZGaWkp1dXVWle9q9EhNtlWufHj9xXR9uOM5IpOQkAVNKrQUa1FFdSEBOXhePDBB7UZUkrUuVqSnSTJkowOSsBlh+qYmprKSy+9xB//+EdtuQ9VgUrl2EEzrpNGyyXC1IQD1S1//fXXM336dK0hqxoOrnJRXee6tpOi6PDJEtHW4bNIIngpCbgKHHU8ePAgd955J926dSMsLEy8a5cStNzrvAkob8bLL7/Mddddx86dOzVvsMtOz/smcqEQuAQEqqqqNNGmbFHNGlUeX2WLYo+XAO4luoWItksEUm7jXgRUIXTo0KEzijZXIeU6ulfKJLbuREB51ES0uVOOde64imjr+Pkroq3j55HEsA0IiGhrA6hyywsmIKLtgpHJD9qQgIi2NoR7iW4tou0SgZTbuBeBs4k2l3et5dG9UiaxdScCItrcKbc6f1xFtHX8PBbR1vHzSGLYBgREtLUBVLnlBRNQdnh696haT1B9Li8h0N4ERLS1N/ELf56ItgtnJr/oBATOR7R1gmRKEjo4ARFtHTyDulj0RLR1/AwX0dbx80hi2AYEVGWpZo+qJT9azh5Vn7tCGzxWbikEWhE4U/eoeNpaIZI37UhARFs7wv6JjxLR9hPByc/cm4BLtN1+++0dSLSpLrGzBwf6P/cmL7FvSUBEW0sacn5ZCTigqqqa8ePGc/111zNj+gzKy8qlEXtZM+WHDxfR9kMm8kkXINDxRJsSa3ZAbVSvjs3Bgb3FP5sm3bpAFnWJJCrRplahb7lOm9t72s7e7jhXm0S+6wDcqiurmTBuAjdcdwOzps8S0dYBSyERbR0wUyRKbU9AiTa1I8Jtt912Rk8bl2UgeLNQO7toU9eo0l1enYGAiLZzOpdFyLWzkBPR1vFLFRFtHT+PJIZtQMBhP5toQ5+51+6iTZXO5yfaVCepvDoHARFtItrOMSKi3UVrdWVNk6dtpnjaOmQhI6KtRbacT6OmxeVy6sYEdNF2kNtuU2PaHmraxkppNbuajNAibS67aPFRG5yqp/xQtKmu0dbdo6qrVI+fK15ybPe67bzr2R/maOtctp2he7Suts69l/wQg+y4BvkjeaOLtk+4/robmHEm0aZ+3/Ry3azpAzlpBwIi2pyQlfmpAtY1okgdTw92h/LCtAxqpqFdgrsxUDLIbufAgf3cdttf6PaQ2ns0FIvVgs3hwOpwaEdlDy67cJ23UnNt8QeqFYp6YaikmZJoNu2fVfvf9c6mfa7eSeioDKzYOVuwuL6zW0lLS20xpm03akybsk/Xq5XTt8k+1PfN17iubfNj6wKwZWF42vml9qC1KnhPe5Z8d1rFdF58Ts9K1RjUNowfP17fMH7GDErLyrHbVXmp6rrm2+olo6u2dNmiZpxtboJd/QEi2pwWoAzW4rBhxqYVtAargfK6ckqqSyh1hrLqEsqqXKGY0qoiSqsKKKnKk+AuDKrzKK3Oo6wmH78dW/nT7ddx1723s/vANkqqCiivKaGmsRqL3ax5tJQgUBWv7t1ShZKrgGqDokPXapqXRZ96YMXmMFNrrKSitoiy6kJnKKCsOl9CB2VQWp2PCiXVeWcMxdV5qKB9X5lLeFQITz/7FH+49lo2bdlCdl4GFdUl1NRXYrFb9Nl7TnNTMr7ZBlueqxrVKZQuyjR1L27znZUlWlTpiN1uosFQQWVVIWUVeVoor8hDC5X5lFcWUF6ZT1llHmVVlzho9y2grFLCxTPIp7Qqj+LKHEoqc/VQlUtJVS4ZeYmMGT+S62/5A5NnfkZq9inKakqoqKvAaDNitauGbcsSUU2MsoIWlIgT4XZRf37n8WMRbZqZKbMzU2eqJK88g9jUE+wP286moFV4eC3Sg/ciPLwXsbpVWMhqnwVa8PBdgAT3YeDpt5BJcz/kvn/fzkPP/p2v543H02sR63yXE7j/O07EB5NVkkq1sQKjoxELSsSpwqmtCiaX19aK1W6ioq6ElNx4QmMOsuOgF1uDVuO1zROv7Z58t92D73asltCBGWzdsZrN21ex6Rxh845VbApaySKPOdz74N385prf8MWUT9nsuwqfbWvYtmczxyL2kZadSFVdKSZLA3bMmoBqriSd8kpzg1x8neny7qpq2aKs3tFIZV0xGfmJhMUcxH/3erYErGCT3zI2+y/TztX7rYEqrNTClqAVbA5afomDuudKCZeIwaag5WwIXMpGVwhaxsagZXh4z+ejr96m95Cn+WzmGFZ7LWCD/0q8d61nX+h24jPDKarKosFc5+yZ0j39emPikrQazkO2dO1Luq5oU2OXVNeSw4LRVk9xdRahCXvYvGMJ89Z+zvTlHzJj5YfMXP0RMzw+1sJ0z4+Z5vkxU7XjOKZ5jmP6Gj3MWDseFaZL6PAMZqybwLQ145i0dDQfzBrEhHnD+Xr5WKauHMfkJR8yddl4ZqycyGrfeew54U9aUTw1pnJMdgMOVMvy0r/Ufc22emoaiknJjmZ3sA9r/RexZNN0tuxciu++lfgf8CDwkCcBhzzwP7S6dTjsgb+EDsEgwJkPvkdW43PO4IHPQQ9WbF3Ivd3/wW9+9yu+mfspvt+vImD/Crx2LWLVlulsCVrG7sPexCSHUFFXqNmJA7PTu2F39lk5BdtFGqf6uRVVJtZR1VhMcn4UOw5vZdV33zLHYxKzPT9nmdc01m6bx6bdS9iyZ6kzLGPrnmVs2buMzXuXsnnvEjbvu5RhGZv3LZdwKRjsXcamvUvYtGdx67BXf+8RNIflftNZs30um/YsYf2OBSz5bgpz1n7OSu/p+O/3JOJUCGU15RisJiwOJdzEx3bpa4Uz37HrijbNZ2LFaKsipzyOjUELmbz4fWas/pAt+75lf9x6QjN9icgLIrJgO5GFO5xhJ5GFrrCLyMLdRBZ+T2ThHgluxOBk4feE5e4gON2foxkBhOXsICx7J4eTfNketo4Fmycxce4IPpo+jNlrJ3Hs1D7KjSWYsDSNe7zI+rHpL1Ldx4aF8tpsDoT6Mnflp6z0msreyC1E5x8gq+4kBcYYcutPklN/kuy6cHINJ8lpCCer/gSZdWHkGCLIM0aS13hSQgdgkNt4khzjSbLOEbKNKg+jCY4/zOMv/Js/3PA7vHZ7klZ2nLz6UAobQ0kuPsCRGB/W+s1l9vJJbDvgrXXvWx2Nmi9MqyqVAbUMTZZ1YSd2Z+VrpoGyhjT2hfswc8XHfDl/JMu8p7ArcgvhefuJKz9GUs0JUusjSDdEkdZwUjtPrT9JWkMkaYYIMkyRZFtjyLJcqhBLliWOLIs6SrgoBuYY0htPkt4QQVpDOGn1ztAQTmpdGKeqjxFfEUxs2WFSakNJU59VBGvl466T61jhPYXZK77ku+0byCnJotFm0voglM/3UpWJF2a5XevqriXanBalXLlq5FqdsZqolMMs2/wVy7ZOZueJDUTn7SOl8qhWGeaZIslpjCDbEK4Fda4qxxxDuPMYSY4hihxDjAQ3ZJBRc5LE0mMklYWQVh1BZn2kFjJqI4ktCmZfrB/rdi3mqyUfMmPVJHYE+1NYXYDJoUY+6mN/mmvLCys4lCnqHVt2LA4r2UVpBO1dx+qtgc3dcAAAIABJREFU09kXvoX4AiXWIsg1xpFnjKPAFEeBMZZ8LcSQb4zWQp4xirzGKPKc712fy1Hnc7k4qPzINUWTc46gvs81xBGSEMa/ez3L76+/ho3bVpFRHkaRMYpCUySFxiiyqiNIKQ4lOGYb6/wX471zrdZdacWkjbXULO+niramMhFsDtV0sFFQmcHOoxuZvWoCnn7TOBi9hcTiI2TURZJtjDtryDHFkWOKRz/GkmOKJccYS/YlCTFkGyVcKgYqX3IUT5VHLUJWYzQpNeEkVhwnqSqULEM0ucZYco0x5DTGkFEXQULxYQ7H+rPefxFrvZcSeeoEtea6FmVic1noNK/mD+Tsogl0HdHWVKgpyWbFYK0hPjOC9YGL8PCfwbHkQNKrT1BgitVCvjkGFfJUMEWfIajPY7UKVVWqEjowA1MceS2DMZ58UwJZ9TGcKgslsTSEzLpochrjyDXGk2eM147qs7jiYLwPr2Layk+YvvxLdofspMpUhdmhBmc3D9e+kDamMkX1SyX8jPZGimoy2HZoHWv8ZnEkzpfM6nDyDFGaQGsZ73xTHK6QZ1S2J6GjM9ArPFXp/TCouOc3xBMaH0rPF57hd9ddzdqAZaRXhFFoiqbQGE2xKZYiUxyFjbHk1EQQkhTIWv/Z+O5ZR35ZDla7miJzES9nuajs0WS3UN5YzO4Qb+at+5w1QbOJzNxFTm04hY0xWsMhzxSPCqoxcfbww7SeKf0X9lmMJhyUeJBwsQzOkD8m9Vkc2YZYUqrCSSg9TnLlCbINqp5T5Wdsc9ljita8+ycyduLhN5d1AcuJzYik0dbYJNxc1a2yq4uyz4sw7c760y4n2tRK+Fa7kdyyFDZvX8maoAVEZO8l2xBFgSWeArOqGGM1I1WFg1YpON9rIq3VuSq4zvAHIJ91LC5NeeYSbyp/48msjyaxLIT4kmNk1EXpoq1RF2x5xgRn5RRDcmUIfsEeTF/9BTNXTyMhLx6Dpc45a0qXX7oMO7/iSV2lfmXBSo25gv3hPqzymcL+6C2aveU2xtAUtEoqllxVqJritKAKUd3uzlVxyndnFxXtw+bcDTmn17QhgbD4EJ56/mlNtK3xX0JaRWhT47HQFEuhEm2mGApNURSYThKc4MUa//nsOhJEnbFBW1dQVVCuivL8rNBZpTl/pJa6qTXXczR+Hws3TWbN9m+JyN6jNR504RireXo7ukiW+F1MQ84p2irDSSg5TkplONkNSiCqBrnzvlo5pDzIkeSaowjL3M36HUvZutOT4ppCjDa1NJE+XUuVca5wQTbZWdXWJUpX1xJtasyu3YrBXMWeY/6sCVjE4VPbyWqMJVeJNUus7l0z6YaqGWtLD83ZzkWkdSyRdlp+tPRWNZ8nNIu24mbRpnnbnMJN5X++OY5Ca7wm3NRA6AlzxuCzfwuVtSXgULNJL1y0qb9d5R8x2RspqE5j6eZp7AhZT0ZNBLnKo9Kod0Vo3Reqa6lF94U6l4ZC52CgdXU3xP9AtKVWhGl2p2xP9/y7jrEUmmO1cY07jm9m6fpvySvNw2yz6mtoOe3qQitIrSHrsFFQlc+8tVNYvPUbjqfvoNB2ilzVmDVEUdgY3STaxP46h/39MB+bRZtqyGqeNk20NQtB1XjMNkVrIbMxUutiDT61jVXeczgadYhaYwNWbbpWa+F2oTZ5ifRNp7xN1xJtDjsWSwN5xSms8VrAjmObSK0KJ0e5+pU3xtUV6vJuOCv/plaGq7XR4vhDw++sf9Dum67T80/lWZOnrTREa1WqrlDVNapEmysoAaV7V5WHLobQjB18u/Fz5q77mtTMU1itag2tlm3J8yua1FVq5nKdqYyQ+J2s8Z9FRMZucuqjNA+bEm16F5A+3kQJtZZBbM59bbFl3p1btMVqXn/ladPGM5riKTDFU6iOxjhicg6xwX8Zx8MPU99Qr6/lps2Iv9DuKLXUjBWjpYH4zJN8s+QjvA8t41T5cfLN8ZqnraAxioJGNUZQr7xbpkHOO4ct6vl4HqJNjYUzqbFwSrhFaeM2E0sOE3h4FZv8PSmuLNMWJ3ctjtSydOyUCuoyJKoLiTa1+KSNRlM1UUnBrNw6i7CU3eQ0KCOM01oMamCwPn6tM/0hSlrOVLH8QLTV/1C05Ti9Xur3ykN3qvwom/fNZ9KC0YRGBmMyNeJwXPhkd1202Sivy2f30Y34HVhKYuEh8tSgX6eXzRXnloOEXeeu7+To3rZ9dtEWSr5ZiTbVNeoSbcrbpkRbIoWmBNIrIth+aDN+27dQXlmmL8jsFG2qojy/lyoT7dgdFqoNpew7sY2pyz7gYLwXOY3R+jhdTawpL1uMPmzkNC+22KB722Dr/Dtf0dbsbVN1Znp1CIfjvmOhxwwy8rMx2dQ0v2ZPmyrvzq85e35W29Wv6mKizUpNfQn7TwSyYcdiYvOPkKcNPlfelWhytBlfrgkGnemPUdLSunA6g6ftjKJN2YXqrtQ9bmk1J9h9ciNfzhvN3iNB1NZXYbfbmgcTnWdpogowtTVVUUU2fns82HNiI+kVIeSrbnoVWlaM2hiS5hle2ti2lt/LeWtebsTjp4u2RHLrYglP3Mfq9QvJL8zRPL5qz1zVhLgw0ebA7jBTWpOHz561zFn7CSdzdzd7mNWsZJMKesNFG17gRoxb/S1JvH/kb+UMos2gl0eqt6IlS9WAdDk5surDCUvdxrxVU4hOjqfebMLawusrgu08K4bzvKxLiTaHVjjl4HtwPQFH15FcFkaBGnCuKmY1pVmbni+ireUfZ2c9Pz9PmxJtepepGt+W1RBFSMpOpiz8iO37vqOiplhf+MPVlDzP0kldpobr5pdl471zDftP+mgzRlU32OmF4+ldu673nTVfulK6fopoK9A8bYkUGBKJSQ9m0YoZZOUka12cap01JdjO0wybqgi190F+WRqbti9jzroJROXv0cbUKYGWa1S9D2oWvd5wOd0+u1J+df60thZtSRVh2mxSVfa50u4qf5qOqqvUEEV0zn6WbpjDifiT1BrVGoLyaisCXUq02R1W8isyWbdjOf7H1pNcdoICY6LTuyGizfWH2RWOalkPNXtUTW1XM6XU+elj2lxj27TJCWoZkMY4YgsOM23JOPx3b6a0svCnizaHjbzSbL7bsYaDkT5k157UZglKpdi6Rd+ZbfHsok1NRDhz96gu2k5R2JhEfFYIcxZNJiU9FpvNpNniTxFtahO//PJ01gYtYva6cUTlf++cCBGvz1o2x5Aroq1JuHRem/xx0XZ62nVhH0NicTCePks4Gnmc6ob6Fo2HC21CtJXU6Tz37UKiDZRoU3uLrtm2BP/jrUVbe3jamlonLSYytPdnp//Rnel9e8eprZ53prS5PlOiTS3zoQRbQsmx8xNtxnjiCo8wdck4/HZtoqSyQPdrqHLJFc6jbFCXKk9bbkkWW7d56KKtRok2tUZc1xEtrrzQj82t+dafd14eLUVbzxZLfqRWnH1MW7NoSyY+O4TZC78iOTUG60WINrVuZW5ZGmsDF/5QtJnVzHoRbV3DJn+KaFOTU2JIKjvOhqCVHAo7TGVdrYi286gHfuolXUy02cgvz2RtK9HWuns0V3UFqPEbrSpP17pOegXyU0SGVkA3rWjvWtn+8hx/LP4dKa4XG5fW+dhSALQUbefpaXOJtsUf47dr40WLtpySTLZsW8WBkz5kOUVbvnNxXyUqzxz0RYxd1ynvoNZ94Rz7pr13LoCqfq93bbjs13VsyeHynKs1zPS4K29OAk3r4mnCVX13aeL1Y7Z+dvu4NM8/Vzry1ZIyap22hObFddcELCWtMkybOarWjDx9IoI+GSGBwsZTxGcfd4q22IsSbWofhEsl2ly8z5Vu+a7tbeunMXaJthPa2pWqezTHoOrCs/89qrpSzXRXok3t5nEwVBdtF9CG/anapcv+rouJNjv55VlO0baWpPJQbUybZuBqbTaXYNPGFrkqOHVUlYqqRF0VZhyqwC1oPEsw6gtRqm2HXOFixcfF/l5NuFBBqyjUsVHFTW2NpJYQiCdf+0z//GzP0pceUPf4EbHZYuV+bQV/VTn92G+avnfGUfvNj53/SDyc9zy9ANMr6jgy66NIKD3m9LRFaQLHNfHg9KNL/MQVHmbK4o9+VLSpta/sdrsWTi9ddE+blZySNDYHreDASV+yq6MoNCZqoaAxkbOHBAoaXeEU+YYkLeQZkshuSCSvLoESQxIlpmTyVde/MaFZHDl3enCl5czH0ysU3f71+6h7XWhQwtH1G3UvfQ3EHGMCOVr8ksg1JpHTmESWIYEsda05QZv8oS25cobdRs4c75Z/r/q59vfqErDaUV/ZXRtM3/LzMzzD9bfelkclvPMNCUSkHOfFvr34/Q3XsH77SjKqoig0J1JgVrNF9VmjSqzpf3/OxXYbE52i7WuSU2OxWo2cbUybzWY7ox0qu1S2qOb65ZalszZQdY+Od45piyffrPIiTusaVcczTUJwiTTXUf2dqzHCTaEV29Nt60Le/zB/z9cOznadlreqXFSixDkJSJuYpsY4G9QC16p8cX5/iRoRp5dF5/f+QtJ+IUx/eK3aASGl8gQJJUdJqQxzTsJSz//hteozTbQ1xnCq9Bgbt63kYOghzdPWLNqaz1R5eC5b/P/Z+w7ouKqra0yHBHCv2MY2mE5ICNWYgE3oIRCSPyGBQMoHbjSDOyV03HvFvVvuvdvqXZrRaGbUu2ZUrT4qxrD/tc99d2Ykj2TJFsQEaa2z7ps3b55euffcfU/Zp6GebPvs+wn8BEFbBpbvnIetwcthKwoRvi5FpUALG9PaqZwUK77bElBjFUtATjXBjQW5Rpvj4krZjJxKM7IrTeBnAXI+QIpWav+dlkpJSTav3bjurEoTMipikcFqAJUmZDFTiArXh/tWD1pf39XbpwmISVZMRW8oexngPs5b77eiIBuzMDXcT2Xq+1q99+vr9tVmuGKRUh6J5DLWklU19tzEtprgth4FhwlxjmP4dK4B2oobd4+WlpYiOzsbVVVV+OYbkp9Seak/bn2DOmTlJ2Ldzvk4GrUFGSUmOKttIg6XFadJtVWsKw4X45nUcXmuBBS6UnDClQlrWgQCIvchNGI3MrIjkFdpRW6tHTm1dum7nr7sC8Tp/t5QOWu+OO5vzGrX1IRCRa/PwZb1OAmOud+KnOoE5FYmINERCf/oXTgQ4ofI9KNIcZmRTo6w2ngZb3rcsWX/zWoobjCq70O18nueo9YqZctkASHl6WKFRFuXqZPsyB+4dmtujaLR4MIprSQGmw4uxfvT3kFk2nFkVBCoxbtBmi6tl1trQm4dAR1LXJlhyTiGKbMmKdB2iqDtlJdbyuhr332H1NRU5Obmevog++J3qnYuY+DEVV+YiuXb52KyJCIcFMCWU2dFVp3FAG6+QVu9xZiANROyXWZkVplEsqoI4FoD+Og+WP8de/p1y/fLQpy6UPpVHLJdceD1UhdSL/IeuE9dvwYt3v1Zb6vvqHd86ZmW7PPWXZ5tPr/6+q/x+z7Xa1D1RRNLQpFaESX3o6/D133UB20LcTT0CE5UlBr9kJqOPexb6XsEbOyHDocDJ0+S49KjE7VubGvP/ATaQJsUOFaEgeyACrQ1nNisyK5WE4gANg7kSjMyy2ORURaN9FJKFDLLYxR4kxVafSuQ7vgqcLN5A4u/8TVQWr7PQxibScVEpVQWg7TSKKSURIqweHp6RQwyqmIFwAgFCmlQ3KIVFNvGr0tZMTxgTX9u6jee75qrmPl+eGzj13Gm7zzPVlUf0Mc3F7Rt3rMK+cW57rLx3kONyigzMxOffPIJJk+ejOjoaJSVlbmtHZwuT6EO2QWJWL9rPo5FG6DN5QXaBKQRqNUHcE6XHSJVdjhKbUjLjEZQwE5sXr8I86Z9iMXTPsCWDXNw4PhaWB2hyKomaKPYkOWWhv2bEx73ee/Xz5dglkDLECHUVKSavmvyaq5DtjHIrov2CD/XEqxY4KyKR2Z+LA4cWovNfgswd8YkTP/qPaxZPw2bjy5FlMMfqZWxssBQE6cHsKmMXmb1KtETmHKxsvyYEgFrdVYQfNBqxEWEqikcg5y6aBFeH7dZHuqHF/5fRVqbVBwOizMQ6RWxYvVWblCCN9b8NJISCNbqouGoi4Gz1oT4zCOYMnsCEpLjJBGBoI3ToJ4KtbV35syZGD16NHbt2oX8/HzU1NRIX9THkn4mqxHQlt1M0JZNQmhXLDIqo5FWHg3qk9TSKKSVRSOjkjrFoze0TmjY6jHo3XqOaTko0/3CVysgiGCNutwAawRqvO6UUqUT5doN8Mbrb0w3eJNhe1/72Wy754l6C1IN2owwAvdY9R6v+vmcvU5U16vuM60yWrJCuc+jK08/N+dMzhG2/ECs2jEfR8MOu0Gb0okqNYZ9sa6uDps2bcK7776LzZs3C3irra1tA2/ek0cztn+ioI2JCMrSllMPtOl4Nj0A9Ko+HlkGaKMbkVY1gjQKQZsWgre00khkVESL+9F7FeoejO66kRwA3kDo9G33b9zgxOsYN2u+Rxk2pSQkE9JlRkalSRQprz2N11umRCur1PIoGay0QmmhFcpbYXmu+/RBrK/h9Gtv/Fj9G9U2F7id+fl5rtPrubmfuWGl03VJ3c/Y93UqxWWCxXkcn80bDTdoE6uFVyICLRjffQe73Y7nnnsOP/vZz/DCCy9g/fr1SE1JhcvlEhfBqe8UaNuwewGOx2xDekmsWNdI5ZDrim8gBnirtsJZbUeeKxF5FYlISAmF39r5WD1nMvy3rIN53w6Y92zBnlVzsXD2B9i0cxESCk3IdCUiuyYZObWUJLG+EdAocKMBG7OobQLyCPTUNicFvg/P8xP6B6keolwj5O+qL0ZR+zqjJFwdrVpa6JK3oKjajhxnNI7sXY2FX0zE4XVLELvXD7ZD2xC1dz0WL/gAc1f+B6HJ+8XiIW59w8omljZtWXOXG1NFzMWyRnBG65qAtHhk13mLRVFXeFvbTtJ6RYltXWHBdwLUps7L7wWUMXYtHk5ec00cHHXcViS6tLjxsxJ+Z4KzzgxnjQXWLH9Mm/sBklLjcOpbTn6qeLyAMaMf0so7YsQIdOzYEbfddpssJIKDg1F84gS+OaVAnnKP0tI2x2NpM4Av690K+biue9tgnGgdR8CWWhYhklamwBp1C4GbSHmUUOZwjItu0BZ53TY4r9YJbtAm/dBLL+s+0Fh7Jmus7k8GYEsvjxHAJvqwPBr8LOCTC9vSSCgQU18PeutEAW6ik5X+cF+3vr9zan3fd0Prm/psULNovdbStt57OEPtbeNYgjarBm2hh3CiosS9cNBLCOpEArTZs2ejf//+uPHGGzFp0iRIXywuPs0b0Qzs8pM95CcI2jIbuEeVRYHZo57JycsyxbJGLguyq+KQ67KIOzSlOBzpJR7LGkEcJasiVgLKU06ES0kirj61UqunqLTiak6rB12DY72Vmt5uqmVAaVqlCanlCqTR0pbJ6y2PcbsCuJ1cGiEuQ3KSZXiLK8YAc2w9gM6zrb/Xlrrmgcn619xcwKaUGN3YzREFPBoqPv4vH2K4kbU72d3y2Goz4p0B+Gzee9h2YB2KSwsEoFEhNRSbzYbf//73uOiii0Tat2+P5597HkcOH0FlZSXqvq1BRh4tbYvgH7sdORUWFJ9KRvG3SSg6lXiaFH5jRx4n8hob8qqS4SxOxKG9G7Hg8w+RExoMR0go8sJCURwZDkfwMST578WaJVOwbvcKpJclIf9kDgpP5aLwVAYKv01FwbeJyD9lQ/4pK/K+sSP/m0Tkn0xB3slUQ9K8tvW+VDjrUpFXp1pnbQo8kgpHrbfwu2Q4a5PgEEmEozYR+dWJqK7NxtHda/D15++j0hyLalMM8oP8kXvoAE7FxaDEEoxNa6Zi3sqP4KyzIL/OgoKTFuQbknfSAorTh8h338Qj7xt1jIPB/CLxcNTa4ai1SeusS0L+N8nIP5WCQso3ySg8mYyCJoTfF51MQqEhBScToSQJBScpns+eY/R3jbeFJxNR+A1Fn4PXkYKCk2koOJmB/No0OGtS4KhJlPfvqElAQV0aEnNiMGPuZ0hKseDbb5W7qWE/JGgbNWoUrrrqKlx88cW45JJLcP3112Pq1KkC3Bhn9M13TERIxbJtczB5OXnaDhruOMYdmpHB0kVek7kbrLhM0Ba29Apa7cPAluEWKuwiViyHaeUxAnwYhkB9Ib8nLyZ1LoGOsQD1BXQ839M967GiNrXty7J2Gn0P3Y1GmAtdogRoBJvaNUqvA92jbutbeaQxP/he1HnrMV/30dx93ufxbDdfLzaMxW3ss4rh84TNaD2n6I0MvdiYLvTeX8P50QxrXhBWbp+Po2GHUFpZdpo+ZL+kpY2grXfv3rjwwgulP950002gJZihJLQA04XKY9v+Gn8CP0HQli6UH1uClkuGTHpVLNKqYpBaFYW0Kq4Go5BeGSNB6mkVMaCI25DgRlyhUUgriRSQxs+pJyJEtHuULtKUknAkU4GVRyKdK8zySKSWRwoYYgwVhZ+bIynlCkR5/0afgy0VYXMkpSwSyaWRSC6JEKAmyqk8FsknIkShSgwHrXDl0UguDUdSaRhYAaDxc/M7HqcksSQMWvS+s2sjkFQa2XIpUb9LpnvDS/hZ7pv37iXqf/A3EfX2ex9Tb7ssUurURqYfxKSpIzHsnX/gnTFvYfyECZgwbiImjBuvZPx4jB8/Hq+//rpMjhdccAEoBG/XXHMN7rjjDowYOQIHj+xFjC0M81ZMxsyln2LNrsXYeGAFNh1cebocWCnfbdi/Ahv2r8LW/euw5OvpmPLROFgPHkRhSCTWfzkFy7/8AhumfIXAZUtQFBqAwK1rMfGTMZi/Zi6WbV6CFdsoC7Fi2wIs3zYfy7fOxbItc7B08xws85uHZX4LsNRvocjXfovw9aZFWLJxERZr2bAIizcswII1czBv1UzMpaxW7ZyVMzB75QzMWjEds7Usn4bZy6di5vKpmLFsMqYv/QozF3+BmVM/xOSJo3F09QrUxFlQGWuC//IV2Dl5Ck5GRaPOEgur/x58+vk7GP3xcHw49R18NG00Ppw2Gh9MfUfk/alvY9KUtzFx8luY8NUbGP/lKIyjfDFSyecjMebTYRj98Wt4h/Kf1/H2f4bj7f+MwNsfjcTbH43C2x+OwlsfjFTy/gi8NUnLcLw5qb68NWk43p44Am9PHIW3Jr5RT96cOAJvThyJNyeOwqjxo9T2hOF4c/xwjPIhb4wfjjcmKHmTx00YpmTiMLw5kftH4I0JI/HGBJ5vJEaOHYHhY4Zh2Huv4fUx/4fXx7yG10e/hn8MfwWPPDoYrw/7JyZOHIuJkyZg/KRJmDBxEiZMmIgJEyZIX7zrrrsErLVr1w6Uyy+7DNdeey2ee/55LFuxCpk5mcgsSMGybbPxxdLRiMjYC+rF9CoTUkU3RiO1KhrplUpodUqrUJJeQVdohOi8NAKbSlrXIpBCvVISKUBIrFZlURLYnkJrXHkkeGw9/VcRiVRfIsdFgR6AlPLopoVjXcb76WO+oU7h2Kae0JZA6j0BmpWM8Y0VPUgwR2HICK+betGXPmyo5+Q4HtsC8T6H1qOeljq2gU4sUfqItbMpid5yIkKSCVjw3VuYYKCP079rlbY0ArHZx7B4wwxM+HQcxr4/HuMmTsT4CeMxYcI4TJigdOJ7772HoUOHiveBOpF98YorrhAQ9/jjj2PhwoXIyMiQeLfGIUvbNz8x0KYoP8jTtsl/KaKyjsJeFCYJCdbiIKktaSsKgq0wRMRaECxZMfaCINgLgmHPD0ZiQYi4RZmAQOsaQRv3saWlTVvb1G+CYCsIFH+/tSAQ8a0klvwAaInL80dzJD6P1xGEpBPhbqVEhZVQGCrATWLayglQo5FQHAJLvr8h6n/F5wfUv359DY38f0ueP1ouAbDkBTZTghCXFyhCglxuW/KZCarIcr1bSz7PyXP7EN6XSKBkTDFryqcU8Bz+CE7ciXc/+Sfuf+QuXDfgOjH1D+g/AAP69/fIgAHo2bMnrr76alFMXFVSqKRo6eh7XV+88c4I7D26A2P+8yZuv+9m3HbfTbj9gdtxxwO/aFJ+8cCduGvQnbhpYB8M+8ufUGmxozrWhv1LluNff3geb//5j0jctQPVsTFI8T+Kf7z2Mm696xbcfNeNuOlXA+vJjb+8ATfeeQNuvON63HgH24FuGXjHQAy8fSAG3jYQN3jLrTdgwE0D0P/G/uh/Yz9PO7Af+olch34Dr0O/Gzxy3Q190ff6vug7oA/69u+N3r2646VnnkD8/n1IOXAIEX5bMPe9cfjslX8iZvU6pO3ei9TjRzFh7Fvo1L0Duvfpih59uqJ7ny6SYcksy66Uazuji0gndOnVCZ17dfRIz47o1KMDOvRoj4492kurtjugY4+O6NhdSYfuHdChmyFdddseHbpSOijp1gEdu1I6omPXTujYtTM6dtPSRY65pnN7XNWxA67u1AmdunVG5x6d0bl7Z3Tq3smHGN/36IwuWnp2RpeevCfeaw/07NsTPfv2Qo++PZX06YnufXqgm7TGdq+u6NDpavTu0xP9B1yHfv37oV///ujXf4D0S7qh+vXrJ/2Qiwa9gGBf5Gdaf4cM/S32HNiL9LwkLNk8A58sehOBidtgLw4V3WgtCoa1OBjSFgbV1wEFWr8FIOlEqMSzZVfGiLchsSAUSYWhstClTswoj0ZCIfUp9VCAiNU99qhbmhBjTOrx3rClztD7fOkP/Z13y+Pi84JEJ1IH0i2aWanAGvWiuEQZ+sJrF9AWaVwj9YxH/+rt5ujgsz8mwH1/3vcg285AxDkDYXYGeMQRALPDHyaHv2efM0CO47H8ndKFZ6OjvX/D61KfI9P2Y/6ayXj2L89g4C03ot8A1QcHDOgPiu6LdNNfeuml7r5Incj+KH1xyBDs3btXLG5t0KwYAyfIAAAgAElEQVTxJ/ATA21k/k4Vyg+/gOWIzj4Oe3E4bMWhsBUHw14chISiYCQUhsBeGApbQYiANioagjaCMyoiWtVyjQxMWt0S8r1AG4P8DQXlAW5BsBYEwVrY+tIcIGgtVNfP+0o+ES6WQ66CGfxMhUUgpy1wXHHai0PA33ifu+G12woJbpU09Z0+pnltsBswa+DcaFsUCmthiCgggjZbUSjIK0QQXl9CYSvieT3XW2+7KAh2efd8/yFNCgF9WMoeTJg8DP9+4xWMeHMExo4ba1jZxmLi+LGYMJ4rywliaRswYIAANbqlKFdeeSX69bsOw4a9hkPH9iMsNhBjPnoT9w6+C/c/cjcGPXovBg1pTO5R3w29D4MffQB3//oOjHjxL3BZE1FjtuPgitV47U9/wht/egFphw7CZTIh0f8o3hw9AoMffRAPPnI/Bj18Lx58+B5D7saDDxvyyN148BG9X7c89j48+Mh9GPzI/Rg85H7VPnK/nIvnU6KOeZDfaxnqdfyQB+odP+g39+OB++/G8L/+GbE7dyJw5SrMfOddDHvyGbwy6GHMGjYKO6fOhPXgIXz8/jjced8deOixQfjNEw/iN48PwuDHHsDgxwfhQcpjhnD/4w/K/oeeeBBKBuOhJwbjoScH4zdPPoTfPDVY5OGnH8LDT/mQJwfjEcpTD2HIU4MxRFpua/kNhjxFeRhDn34Yjz4zBL/93VA89uyjckzv6/vgksuvxA233YLf/m4InvnjY3jmT4/jd43Is//vCVB+/+cn8eyfn5T2uRefxgsv/Q5/+9ef8MrrL+Lvr78o7SvDXsTfh/0VLw//G14a/hJeGvEy/j7ib3jxHy/goaH34rVhf8f4Ce/h3THv4t0xY/DumLF4b8wY0LJBufvuu2Wi5ARJYZxl9+7d8dTTT2PFqtVISk1GqiMBSzbPFNAWlLTdbamxnwiFTSREjSMZS17jlMAtPxAkBM6sjEEOE5lorS8MQ1KBAm1c3NIDkVgUDNGJhUFIKAyCvbEx6WO/tTAY1oIQcCF9ulBfeYkcx2ObFnthiNJ/xWEqYYKJCKVRohcTi8JkMUswx4UsLW3UD9QlPvUdF/teeqbhMef2mf/T6/4abNs4Vxn6kM+Gi1eCOAJTt140dCM/i07ltco187rPTexFQYjOPIglG6dj4mfj8d7EsXhv7DiMHTsW48aNxbjxbNVnWtToqteWtssuu0z64qOPPopp06YhMTFR3KiNQ5a2b35CoI2FkVnGSoG2HWFrYC0Mk3i1jGoz0iVLMkYyoLKZ6UT6C5rHGbfhYhabWTLZZNVYFi2xbQRvyUVh4i6lpU2yRysY6B+pVp1GTBvjPiT2owGNhDs2pAX7GefgHeRf7xyMFzlNGIiuUte5aiRYE3cv49kqYtxgje5SCkEb3a468FbHrHmySL0zSj2BuTouxROHcebYj9OPbX7sBuNWUstZ0YCAOESqG6i4DJ08omPYVCyaOzZGx9AYcTSnX0Pj181nYco5io9nvwO/3RuQk5cjCoaxGnV1tYZwuw4WiwXPPvusWznRDfDUU09i06aNKCk5gdpvqpHpTMYKv3k4HrMTGSfMBs2HBQ5XXCNikUSEgup0HPXfgRmfTIAjPAxZAUGYOWYMZo4bi68/eB97589DbkQoQg/swOS5n8KUHonsskTklFuRW2FWUhmL3MoYJVWxcFSZ4HDxGvT/tsBRxcxVGxxVifXEWZ0EpysJTu6vTICjipIIp0tJHr+XY5LhdKXAWZUMR1UycqtSkF2agsS0WKxZPBOBm9agKi4GpbFROLBwAVZ9+BFcdJfabYgPOow58z/Dsei9yCm1I68qBY7yRORSKpNPEwe/9xKnKxXO6jTkGSKfuc+H5LlS5fz8H5R8kVTku1KRX6UkryoVea5kxYHnsiK/2oaCGhsKa+1IzjPjHyP+jo6dO+CT6ZOQkBuGfB7TDCmotiHfZUMeaV4qLXBWWOR3eVVWOCmVRltlQ67LjmxXgpJKK2JTjmDavA+RkGxGXV2NV19UfZD9sLq62h3TRusarRr333cf5s2bh/SMdNSePIlT355CVoFKRFC1Rw8anIUWiWdLrzEho14MmqrJS+oVJolkVsWIzmMoSBZDS0pUyAgXtNoDkVmhwkYI7KhfW64TyZ3G+CkVQ8U4Ko9wjCuKGB3r5iuureE+Xjv1vFjTmCWqqT6YaGbE+mr3qLiGq1RGpdaJjbWN60pv3dl0Nmo9vc5n3ITwvnRSAp8JXcRcyCYUh6vaoTopg0kbst24TtT/16e+9NadepuxjuRpMxIRDoccQGFpkc++yJg19ru+ffu6PRC33norPv/8cyQkJMhvGGPZ9tf0E/hJgzZbUZjQHKjsKGbKqMQBRZqr+NgUAa1Z+NeczCCtMoulzUP3ESUuUca3acoPxnQw9Z3KyZtc1xtsndO2ZCIZ4ELAhxo4esA1bIV7zciS0tlRdAVI7IbhFtAKi6tKDdganqepz+5B7hWw3BJApI7VoE3TTzTVWiTeUIM2xh7qYFrdakV22rOW5A7F88bkE+8gYV7HacdzH7Poqk0w5R7FJ3NGY9v+Tcg/ke81uuoHz3LFyKxRWjWeeOIJzJkzB7GxsSgvL1cEkziJ7LwUrNg8C4FxW5BdEYm8GjOctWbk1Zp8SKyxj8AtEUmZkdi5YTF2LpiF5COHEL5hPdIO7kf2gf2I2bwJ1mP7sW7lbIlfSymzwHHSDqcE6Mch7xuKGXmnzO7W+Y0ZzpMqaD9X6l4yo5JUExbkMsPyZKwhJk9gvzurUWc3WoUU1pPtaEPeyQRD7HDWJSK3NgU5lSnYs2sV1kz7GPlBh1ERE46w1cuxb9Z0AXFOczh2b1mGJWunIqmY9BYJyD+ZhLzaRNkmaTApeOoLuRQ9wuzY3FobcuvsZxAmJiTAKefm+RPl//B/5dV5bdcmIK/Ohrw6C/Lq4pBXZ0a+IckFNvxj1P+hQ5f2+GDaWFidQXDWxsFZa2mWMMGCvGu51TxnPBzMIDWIudmqbQtyDKoH3ie3zZlHMG3++0hJt+G70xjaSMX2nfS1N954A926dcOdd96J999/H0GBgSgqLJTYoVPfsrzfd8g2QNvUleMQm3sIGvxQN2aQ1kGY7/XY4NhR9BOKrJsB+4wP48JVZdVnlsUgqzxW6cqyGGkZ+0adyOQs6kW2Pseaz/3UDb71Aa/Fzd1XQxoYDe6abrMMDjYBZsJXqYBbVqUCctSJ8h3dpkKB4VmkNqULm/Od6EsvXdn0c/A8b/Xc9YLU02pdx+fA2D8N2lRigec4D3BV+k//X9F7hl6kTuQ9qH2Kn68xvagossziidKUH2VV5V56UW2yL5Kbbf78+RLrSy/E22+/jf3798PpdEpm6Wk/atvh8wn8hEHbatgKFWhjWnsWO6yANp3xSSVJUWz+BHIOEuu64pDBdHBSfjDbyOBmUy4Axm4wcypaLHQ6c1QrJ3b8sxEOLO9BU08pSDZW08pEQJteVRpxG8zooqWNLWlAyKXEz0zC4Aqy3v9okSXwbLJG9XPRoK2+ktEKqWGraofS5RwiAE4Uks5sqkcFoM9fv81wxaig6MpouV8Cs8bej+YjImj7dM472LpvA/KL8wyNdPrY0jxtdBEEBQXhxIkTMoHqXPhvWTooLwkrNs+Av2kDMsqC4aiOhaPaZLTc9iWc3OPhrLDBajmGdQumYMfXc5Fw7ACcEcFwhgUiyf8ANi2dgU1+C2DKDBI+s5yTcQb4MiP35OmiOMwUIbLaJmUHJQ45J6ORczISOSejjG1SeBjfGSTKp//eglwCkFpSVyj6CrY5dQkC3KyJAdi1di42zfoU9iO7kHBoF2z7dyAj7Ci2rJyNRUs+w9Ho7WIJz6nmeQiubEI668ny9s74brhtjJkzUi0QPJCD0YpcAUMEREpIT8Ix7xbRBzxeAw+S3MYgMT8B/xg5DB06t8fEKe/BkuOPXBctl9QZJG9tXEhEm1QYjlU75mLOms9hcQYgsyoWWVUxyK6ONUQR1nIxornpCFjNGUcwdf4kJKdZ8d13p4R3Rug+jO6oQdv06dMxfPhw4cbiBEkLHP947LffKdDmtrQJaDsstCkEbr5Am87G5njU+lFTfqRxwcqgfmMRS28EhVRIzCxlpQRvvdjYeDt9v2/doK1MHjBCa1LTlilttfKANnoZyDGnJIvEwAbZOFvxTJyDTmxMl55+j/X1k+d73/feUB/qzyllGrSFybPQ+71b9Q59/z8CVHpbOBfwGvT847keY2wReBsGBLq9V+9YIDxtpVVlpylEDdq2bNkiLvulS5ciJSVFLMG6n572o7YdPp/ATxa0bQ9dLe5RWaG5QVsssmsotLrVX4mw4xK4sfwTV4sZ5UoRMU2cpvR0xj5I4GqMm0hSr2Ia6/QNB0Fjn+X32hzdAgCllYVO71YrUFJ/xAr1B92LBD7Mokqju5RK6wwkkvqcTbVuq5u+5haBVSqo+sL791b0nCj4fmhdo6WNMRpiaasH1LyBn2/lxOw1JiEkMojaqIjQ6DswSCSVpY2gbR0KvEGbl6GNSogWNWZCsXVXRPCaUb9lRYS8BKzYMh3HTRuRXhpmWGVZWkxZIny3/J6VNyzILIlDjO045s7/DEu/no61q+dj3cq58Nu0EOs2zUa4ZR9yXKwGQLJjVvugkrXIZ2+Q5W1p9L1Na6QmzVWVQwhifR9rMOdLKTOWYaLFi0Lgxf/NElx25FfYkZwWgmVLv8T6tbOxYc0c+K2dh3VrZ2P2wo9wPHoHMio4ARuk1sZ5eP3qf58jH5VcvzqHWpzx/xhCEGcANEe1GVpoCavfD01w1MQiMd+Kf4z8twJtk0cjPvsYnFUmcXmK21PKkulSeKqqCln4hai7Kh7htkA89vwQDPxlf+yL3CgLKenzLGElpeZ0OTePC5C/N2ccxtR5E5GUGi+hH7S2KSpTj66nu4mcgaRUoKXDF6UC+ytB27LtczClWaCN40mNUV6n1k8cQ2kV5GiLBMGbZJGWhEsGPemDGLqhj9dtY+PN9/6GeoHgTFVxER2n9Yz3vmZsM3yEyQYiTKQQ9oBo4ZWTRSzj9M5C757pN77v0beu0s9btwRgqo82aKstSC2LhjU/GAlFoSAwZV8R8foNf6/PpVr1OcNlRmJJuMQNMsNWnq9+rg1avkPqEc6XLGO1ipQfod7kul4Kj+XSvCoiuAmeveiSPL22baupJ/CTBW3bQlchviBUVq7a0pZVyzI7ZIA/3VqklYxutQlZDXimhVN5KN4bxY1z+jlaNkg9g5f/k0DoTEqg8e/JWu1ZfXJgMp1fC0Echfv1tTd+rpZfh6/n2ZJnkSMlf8ikr4WWDg3aVFC0L9CmV5aN/S+uJpn9lOAF2uRZN1BO/L23pe2TOW9j6761p4O2BsCNE6bPSVKcWQRtNqzcOg3HTZskDkgWBD5dQw3cSARQsrCgKy0JaSesiEoJQXhCIEITAhCXE4LU0mhVa1ZAjrZCcdLThLle/cttjWrwf9wLFwWS1UJGbzc89vTPBDgadLjDDGpoSYyD0xUPZ6UNzooEWNJDEJ0UgMikAESk8H3EIK0qDul06Rs1fxXYVICzsffpvV+P0+a1+p5Uq61H7He0duYaFk+CNrHG0lVogFaCUHuBGa+MekVA2/jJ7yAu+ygcrljku+KRzzqxdCXWxiNLiLyN+CNOpJxEq6wIiw/D0KcfxQ239sOesA3i3hJeNL6Xev1BPw9VK5igbdoZQBuVf2P9UCYGqWjlAW2TV9E9elhAduOWNk/f0c9cAXjqD+oH6hIPzyM/6+Nas+WzaT09RWCmrjud9CZuiWnF/1Ffd579s2C/UP2HwF/AvwZm1RZJqrARtBWGSrUHN2gzjuXxCrQ1dDdbZA4gTQiz70kzotyr7Hc+3rkv0BZ2CMUVJbJ40CWsNMEu+xsXCOyPlLa/s3sCP13QFkLQFlIPtCkrm2/QVr/TegAZLVMEPAwA9ZjofXfy+uc4fRA09j2VU2uCNg5EAjS3kItIAJtaubaeIlRK6txBm2HhYGIHkzqMYs60EjIJgQqGcRwamPJeBEAbljeZ+IxJ1vsZkwMvLu/49wLamhqOLGP1LWoN0DYV/qaNSCsJV0W2fShH72uWVTHLQbFWZrUFThfrdybBkhUJv0NrsD9yGxJORCKDE6XbGuYN2vQK29P/vIFB/f/lOeZs9vO8DS1TCoDTemVBXpUNhZVJcFYk4mjUbuwO2YLUchvSq63IYNF41gDWlrUGdWzP5nqa+xvPNRNgmgS0OavNyKu2IL/GLskBWSUmpBdGIT0/CqaEALz8rz+jQ8dr8N6kEQiP24uU3CCkO0OQWxKN3EqzvCs1UXLCVMBZrIYuK0LjQzHkyaG4/pZ+2G2ANiG0Pc1dr0EbLYJxMGccahZoa6ov0kfqbWk7W9Amz9aIeyP4Yd1KWrKlH+rJ3XClcQHU3HfR1HHsX62tq2gtTHfFiJXtXMJEmnNdTd1b098pomEuBqgDdBkulThnlgxYgjZmwMo+4ZtTyWhSXcQrcUH3ST13UXcygYEeDCY0UI/yOfu6Hhnf9Sxt84Rcl6BNOesJzBrafpvsjW1fNuMJtIE2WscauEfPDDIUaOPApAmZVBMEEAQNahCc/6BNAzdtbdOA57yxtIliN9jSCSh13B3jCcuikcLU/JJI2JnqXhAs74HAjS5fficxe7QeMj5FXJ+qRBmVj1ZCP07QRisPLW0atCUirzIVu4754dm/PYHRH49EvCNU1bDkalwmyqZBmy+F3Br7RKnXA260kNJaqkBbgcuOwookxKcF4533X8fLI/4fLNnhSKskWItHli5BVa/yReuOLV/3yetWLmi6cikW5LgsSCuIhCn2ACJDdyPwyGbs3LwY65dPx6pFUzB62Kv4w2+H4oN3RmLlwq+wfsVUrFnxJQ7uX4GAYD+EmXfDlH4M6VV0cVrF4kkrXXYVQVsIHnlySD3Q5m1p81yjN2ije/Q8A23G5E7ARnoM8j0SALHygduV3ggA8Nyjb4Dg63u+p+aAo5YcI6Ct6jwHbeLyVZmvOuaOOlETBZPKyV4QIqCNfHN6v2TEGnF7ohc59zUIKdGgjbQh1KdcJNLC3tjzr+8ebQNtzcBc53zITxi0rTQsbWcD2qhYTBKsScAQ5wxAQnGYuBvVIPDdyX11/ObsE5DRiu5RAWiGi1Rco8ycOo8sbXK/opCNAtSikMi8rkRiCIW1nMkUKguWLYEalVcyqQaEIDNKKE1UUK1KNvB+3j9e0KYsbVxpO6uSkJoXj5HvvoaOXa/BgJv7YufhdcgojIXTZTNccyoz2jt2xfs5fF/bfI8eqxW3CdpURjUzsQurE1FYkYK5Sz7DgIE90W/AtVi4cjKS8sPE/c1i5TqL0dPSUtj8if1sjuUkxWebW2ODw5WM1OJYhCcdxo4DKzF90ttYPe0zBG1Zh6i92xC5czOidm2Bae9uxO3dD/PevYjZsxNhO/2wb81i+C2egfVfz8CsyRPw9crJOGbZC7MjBOksi1dn+58BbXrMMnYtsSRUiKgZL8qxRyDE98Bj9HFn814a/obnagkga86x5zto4z0wYUJYAEQfMqZa1UqlXpTFqk4yM4Cc6EtDNyr9GIGkExESx0wKFQ3caHBoCNo02G747PX7bANt54zBWnyCNtDWQkubDsCmuzLxRBi4IiHLNNvk0igjcPP8B20cnLSyKdDGjFEqQF43XaT1Yy/O9fOZLZfekzAzGOOl7h+rNEiiB5VPSaRk6uZUxSHbKC9DtwDdA1xtUrSbgGTBBHh6P8+TxNJiZRFq5V+rLE8/RtBGQJFTE42cmhgFyMoSsGHnStxw0wC0u7AdrvzZFXhjzD8Ql+yPvCq7JCKolbK3tc37eX9/25xUTwdttLSZpOB5flUikrOj8dCjv8Yll12Ey664BHfcOwDHYrYgh7xxTFowMkaZyEChS9HXBNKa+/i8WNPWWZeAE6407Ni8DPO++hBbls3G0RVfI/3YYVTFW1BpiUOpKRZV1jiUW8woM8ejMt6OE7Em5EdGImDtWrz5wvOIP7gfztgIxB3bA79VszB30QcIse9DVp0dWS67uEd/zJY2DcY4wXOMkUhWsf8fF8JZZiO25vvR5/o+QBtrLnvL9+ki1ffR3JZ6mIkeUh6sNAqsH83kN9aQpk6kUOd5885p96hwdHJ+MmhMmHRG71ASvRKVtNxbkFNnFR48uke1pa0NtLUYU33vP2gDbS0EbXqAMV5DKSejfIjDX9inORDqZTK1glWAyqk1Y9oYp0DzuHaNpnOgG6CNE9a5grSGv28uaJPJ0jDXc8VIa5mY9Gk9K1QkxqRY0TVghV6Fx9GyRtJgQ4HRPZBcHC7EnullMW5FJvVXK8KRUcNUdlpKf1wxbQoE0QoUjdyaGGRXWWDJiMDv//QMrrr657jgwgtw4UUXoveAHliybjoyTjAGkNxlBOMatH1/IE2PDd2q6z0duBG05dVYkeSIxFczP0CX7h3R7sKLceHFF+HKqy/Hf2aOFtoMgnBau0jF4ahRWah0KSqL4fd7H3QrZ5bGINB/CzbPn424XbuR6X8Myz94H+s/+wyxmzcjYc8ebJ46FQcWLYR9/z5Ebt6CtV98iVWffooIv83Yu3Ahnr79DiyaMBHHV62EIzQQ+RHHsXXVDCxdNxmR6UfgqE5EuMS0/fjdowQ4dIuy3JvZeVyE2wRy2tpGPab7x7m2PwRoI4BrqM9a63NL75/XIpm5ZVFCLUXi4pTiCKFUoU4kDRUtaULdVBEDLlZ1eUKpKc3KN6yVLceo0BEJJyFFSxVd2PFtoO17h1zn/g/aQFsLQJuApxoG7cdKvEZcnqrxJnXecv3FTcqCvPxeH9vSgenreDnXOVm/lBXNE7dmJCIYCQjMfNWgjYCztZSSPk9LQRuvhS5OKiFWoCBQY/kwMqxzW3ifDLb1tBJVlSKlOBxpJyKRXhKFJJagKQxFanGEgDnyLnHFySLXCWWhSK/hyr8haDsDJ1E9yo8zZ482NTTPNhGB/UBZrsgPFofkghgs3bAQ3Xt1F7B2wUWqOD3b3/15KI7H7kZOtc1IyjhfQBvjxSzILIvD7mOb8Kt7b8Nll1+GC9q1wwUXtsOFF1+IXw6+BVuOrUBaOa1tCXDU2uGstUubU2sTK5ivcdJq+2pVTFtKbgiWzvsMwZs2oCzahMLQcKnasGPGTJi3bkPkho3YOXs23n/pZfhNnYoNkyfj09dew1cjRmLm6NHYPns2Hr/pZiyeNAnT33oT9r274DJHwhqwCzPnjMf6vfORV5WIiPgwDPmxx7RVmyT5gKXvCNhMjmMKuDmOCZATa5uhw1rrPXE8aB3TGi31treVTW9zf2ucv+E5WvIc+FuhUymPRBa9Cqxec0JVnNBceCknImSxKsCtPEYAmoC00kjxWCQVhyGlJEKEwE0W7pUmSTigsYEJMtS9bZa2prT3f/+7NtDWUtBWbQLr0DFew+z0l8K8BG1mKdIbIJxh3qSErQHezh200d3pofzQMW2eMjBGSRgBbK2rCKlsWgLaaAWkuV5iLgzQRmZ1lgujcmIlCgI1gjOCMrYEbNr6RmDHz+klkchgXBvLixkuAU4cSeVhSK9RwdFuyo/iEAW0T8vW81hzWkr50dTQPmfQRr5Alw37Q7bjkacfwWWXX44L2l2ogA/BT7sLcO11PfDprAnIKLcIb6CiXfh+qBcam3w8IFODTWZRku3fhtj0IIwa+5qUVeL1ilzUDhdc3g4XX30hXnn7RUSm+SO3xgBtdaolaJOsy0aCoxu7lpbsp0uIiQgpjhAsnf+5gLbSqFgUhUVi18zZsO7cjbTDR7B37jyErt+AN599FvPGjMGaLz53W9qmvvEGNk2bhj/ecw/816zBookTELpuNapiw5EUul9A26ods+CosCHC8uMHbYxlI3UO3aLKyqZAG8Ebi6onloTJGCMAasm7aOrYVgVtLsb1GlQlpCsxhNQf5xVoKyNoixXQll4arXRiGUuHRcq2LF5L6DqNRkapqtKjQR0tc9mMAaaljdn2LsXZySxRTZnUBtqa0tznx3dtoK0FoI0KRAJtT4TCku+v4jacAWJhYzICgVtcXiCSy8hv07pugHN3jxrlXXi/htBtRjeQxAoxDVz2E7Q1lHOLcWsJaJPs2+o4MeEzdoMKhtY1bUkTUFYULp8FnJVGiRtU3Kal0aK8FGiLEqWlQVtmhUkoCFJdkcgwuPh+rKCNhLW2vAh8OG08rvz5lbjo4ovQjqDtokvQ7tJLJLbt4ksuwqBH74Z//E6pJ5vharxuYkv7KidLb2lsYj0dtMUJ2W5mhQWLNs7AgFv7yrWyiLkGbozLa3dRO/S78TrMXDVZVSqotiHXEJZwUoHTHkDd2P8/6/2ag60iDrExB7FpzixYduxDcWQMglatxqYvvsCB+fMx6803sWv2HIx46iksGDcO6778EhunTMa6r77AlDdGwm/qFPztwUEIXr8OSyZNQOj6lTgRHYKNS6dgxcZpsBeFI7fK1kL3qFE+Ssh1z4/sUfYfZowyXES7RTVwI6UOt+MLApBaESlhHmf9XhqEmrQOaFP8bKpms5GtXh2NrOpoIZTOklCKWHXdrVhDusVjrlbNPSml4coDUU7wFSO6j4vY1BNqsZpUGCb7BLAxNMQIJ6Eepe7MYfwvvRVSCYdkyIpgnVY3jqs20HZ+ALOmrqINtNEC1QLKD4K2pNJwYdFPOBEGa2GoJCKwlJK9OFRWm4ydau0V5bmANlURweopFuyKQ3qZCfb8CMTlBCMuJ1DqJdKsnu2yIMsV7y6Xoyx0GsSdPXhrXiyLymTKpPuM5cKYESrlwlQiAleK4ho1SuMwhk3cpxWx4jJgUepMZlJJlQpVZiyVxavLo8B3wjhEZXFS1r8fArRpTvD67Xc4hTpk5tmwguS65o1IKz0zT5sCQbiEzzAAACAASURBVATa8bAXRmDZtrkY+8nbGP/xGDz8+EP4WfsrcU23a/B/b7+K0R8Ox6ezxyLQtkuY3rOk0ody23sDLr3d4onUIJglF5z+rT6XbhVJrWbzZ0tS2HhkVsZhu/8ajP/iHbwxbgSee/H36HXdteh+bXf8c9TfMXz8a3j387ex6egqZDMmz6vOqFQw+V6sbCoJR1Mc8FpJ95FTbEFw0A6sWjoV65ZMQ8TWrfCbNgVHVixF4No12LtgAXbMno3IzZth3rkD8bt3wLZ/N8L8NiBu3y5snzcTlgO7sOfrOdiyZBrmz/kIqzfPRljKIWTI87AhrMUxbZpc9yCmzZuApFQLvv3uJNirWsyK5cXTtrxFFRE8753vX6zYpeGi/6yFwWDoiCWPWfXUiWFiaaO7UWUb1v+t7j/Nadm3eJyAnnMKGaEu43kIyGKQ44pFrise6SVx2HF8Leas+gLz107Gkk0zEGjZI6W5clg31RAWvBeddg7XoHX6me5bxpNBgcTa0Kl0d7IsGC1kpPSQbHmGgkQIMNOAjbpR60cmKzAGmC31JmPdWAlHquFU8hkovUK92+YebQoy/fe/+0mDNms+yXVbBtpoNSJwI6kuVyWJJVEwO4OQyBTqSlX6RJvTzzQYm/u9KKpzUg5xyHbZBZCx9h8DvAMsezD+y3fw59dewF9eew6vj/0r9oSsB60gWS4bMqutyOQEy+xMt2v17EEblaxaXfq2QCplzHdhQYZkCCrSSAbV6oBa3TKoVqexS11AKiLWTS2PRlo54zciweLUXJUml4SpOnpVvig/jIoI36N7lGBNU0x6Wk6vJ5GZb8eKbdNwPG6TXC8nAj0p+e4bigeQ1sj0ChOST0QjqTAKWSds+PCrd9Gp11Xoe1N3BJr3w+YIQ1Ihn4VOjFFA1fd5WzaJsni4t8ikYljfdCFwFXtHoKZLQnnK7bD/pZTEwJYXDUtWFFZvW4E77/klfnHXbdgfshWxWYFCi2EvikJ2rYrJ8/TBll1r8+5XLRa8qQ8EtJFSpdqOjJIYhNp2Y8OOudj09TzsWL4Iu1Yuwf41K3Bsw3oEbvFD1K6dMO3ehdg92xCzZ6tQfgTt2IA9axZhz9qF2ETQt3YGNh5chuicQCQzLumkKnrffJ42de983qROMWccwLR545GUGodvv6vDd/gG34LO9xb8GaBNF4zXZaw0xYrv2qOnvwOObeq9dIYglEZI9iGLlktpPOFKNKyzXiC/ee+m/v+S8XEOulDrIdUywYt8h9HIr41DXqUNMYnB+Pdbr+IX99+Kuwbfgbt/8yt8OnMibI4g5AqwU8BNxqoB3Oqf8+x05JmehYwxPjveexX1XTTSyphUQD2ndB31HoGcuEa1lc0oscgFuehPeiYMOiSWLhQLGwGbUNy0JSK0YOT81w79yYK27SErQdCWwUxKZorRJWJYI5py56nBoygBGLiZXBYDkyPQKPnhG5CcaUCe6ftzVVRcRWW7bMh2kUHbjKwqC+atnYZb77sVl7W/Epdeczm69e+CCV+9A3s+i90TtBGwtT5oo4KT+/Hh6hC6ES/QxomTLtvMKgJlE5jlypUhSXWZ8MFyK7aiUNiLwpB4gqv8MNiLgkVoDWXgLlf3fJ++Utd/KEubB6wpAHdKbCIKtK3c3nzQJtm1JJoVRnMWNbfBUZOAslO5+GzmRHTtcw363dYDsWmByHGRZ4yZo3SntW72qDdg4zb7L98pgVp90KYsa1JGh1Ylt7Af0uWZDEd1GrYe3oR7H7oPv7rnDkQkHpOao9k1CciqZvwa3aHa0mtYWBr0nTONnzN9L8/VYIkncBP6A+NaHSTXZRZrlQVZxSbE2wJht4Vh04YlGP/eMIx763WMe3sYRv7jb/i/F1/ApLf/jU8njML40f/C2NH/xPsTh+HokQ2wJwUgxREBR3UCsmvtyCSx7kn2b0sLyHW9n7U3aDP/10GbfsYc3ynlUSBgo/eBYFsBQHLusR/WB2Et/XyuurA+wNKgLQp5rlg4y6xYs2Uxfj34TlzV5Qp06HkVftb5Mvzp1WcQHL/TDdpyXSb80KDN13PivVC/UY8xZpA1lBOLw5BYFColrCSLnskJWpgkR6BmkI7zvZDmg5Z7WVxxgd6WiPBfA2PN/cdtoK2FoM0zeBgbZkFyaQxMuec7aKN1jZYrC7IqLUgqisNfhv0V194yAJ369kKH3l1xRbcr8dwrzyI04TiyqmzIFBfpDwfa1HNVljYpXySuIzXRS5ybZu424vGoXMjYzYmBEwRXjcoN7HFbeN6V74nixwbaFNUFecoILAjIrBKoX/xNFj6fPRHdrmuP/rf1RHTqcWRVKg479exaF7RlML7Gy9qmn7MGbh5uNsMl6gZrFkVay+LvpPKoThTQtvngetzz0L341b13ICrpuAHa7GLt1aBN/4/WbtUCwreljROZAm0WOFzxcFTZkFthR25FArJKrEgvsiCj0ApzYjhe/fdf0bVbJ4z/YATCYg8gzRmDzBNxyCpjqTE7HNV25PCdEYRSWO3hZNz/BGjjMxQxatgyHIGl5VhijuNUWTDPHbB5Ay5a9bRHw3t/c7Y9fYiWaxMcNdHIY2m8oli8OfZf6HdzL3S+9hp079cZHXtejdvvvx6zV36InKoYELCdL6DNcx8e6x4XtlzUsgwVF7KZ5LQkga60KhFISl+5S/zpRaBq20Bbc6HTf++4NtB2zqAtutVBm1sJamXI1ek5uQTMEhdEzq6UYhO2Hd+COx+6Gx36dEXHPp3RpV8XXN3z57jjwZsxb+1UZFbSTE63qLdrtPX429REWR9IqX313aNULp7ixhqsqFayTAnaCkKkjBXdMJq/y9f5PQrO839/3KCNFjRymCWi+JtMfEbQ1leBtqiU48is5DtXilg9l9Zzj/JZSpklw2qi+6tY2qrjkOsWFRemSkGpklDaDaMSC5KQU50Kv4PrcHcD0JZTY0dWtVUsAc19n77ecXP2eVvavK1stAyyRioL3KuW92AVKyFj7ZjB63AlwZ4bi1eG/w0dO1+Djya/A2tmMHLKrcitssJRZ4OzjgkYCsASwNDlSMlm3cbq+B+9pU2/f1rSGLPW2qBNv38NyDRgaz3QFos8VxxiEo7iN4/fg259O6BL72vQa0AXdOnTCb1u7Izh4/6MxLwgZFfGIsfFseVZHOrrOpe2Of20qWP0O6Blk9mgXMjSE0E6J4YjaNHW7noLYb0gbktE+O8hsRb85zbQ9j2ANj2AtLJparA197uzVQjK+kQLB1f7CYjPjcB7n45Gn1v7ofN1nTDgjj74xf03oXv/9ugxsAP+/uYLSC6OlFgUrroyqpW0Zk3Sxp9LHCQJwYhp86VgqGxEquMkrs1GN0x+sMS0iRvYC+g2/n8UcPsxg7YscXvSPZqIopOZ+GzWDwvadL/lM1aWNVWeylFthsNlWKaqrXC4hQCOVBoKiHN/XnUSCqpS4bdrBe4d9Ev86p7bEG45gLRyMzJqrMhgnI24b2gR8YBt/b9bo1XXX98iKNco10mwZkiN3vZYJgjg8llGzGHG/w1/CR07X40JnwyHNSMIzkobcivj4RRrHQvPxyKX8aQkryboFdBG63dLao+qZ6Cu+fxxj/J6RL4n0KbfM3WgXrxq4HY2elGfj62ytJmRVhiJTbuWot8tPdH52qtw8y/748nnh6DX9b3QuU97PPzML3EsegvSS6KRQxAk9T+Vu/5srqHhb7yv6Wy2+fz5Ow3aWNHADdoYs0Y3tcSu+fBe+ABttNTRk+ErrERfn/TDtoLxLYBbrXNoG2j7PkAblZchUvaqhRNOwwHdnM9aiXmvPjm4OEnQuuEk35UrEUHxhzDoqXvRsW979LmlB15+/QVxCVx3U1d07nMFHnzqDhwzb0Uqg1pdJqQzwNiQ5lxHc47RCkYPfk9LF4rik3ODMy+FotwsKs6NJVuYBZVQGApbfrCUdmHsWxbjTYxJxHNe3xN+G2jz/VzO9Nz09/o5q1g2gja6jszILDMhpShKCHRzquLhcBG8EfSwULxZgbeqeOSdsCArLQJrv56CIfffjkcfugs7di5BTIY/EipNSCXIk9JVjIs6d/eavm7dyqQjoLMBaGOB+CqzUCeQ1JkxbayVqq1uCqQqd6mjwIJEazDeGfkqbh7YF/8e9hwCw3cgPS8a2aVxcLjsUgPW4SI/HWuvKgDKMlm5dYyXsyKs2QXjf9qgTfc3Ddyao2t8HaPfP1ueM9dlQXTiMbz25svofUM39OzfCX/465NY5bcEd9x9Ozr0vAYD7uiBqYveR1JBFLLEC6F5L1sHuHlfU+PbOpnL97jlvdKyRvcoa2IzC5Q1meke5QKYixFfC2GtV9mmGzFtbaCtdQDW93GWNtD2IwJtVFZaGiqjpkAbi1/nME6t1Aq/A6sw4M4+6NrvGvxy0I1YsPwr+O1civseuh3d+12FG37VHXNWfyzBrARr6TVKuN3wf57tZw1ktRJmqxUVs3KF7NFIQ5dgWZm44yWgmdY0KZjsRfvBbClmRCWT3qMsAuRc0udrqm0DbZ7n3tRz8v5O3lk1wYcZuVyYsDXAGIFZbkUcopOPYtH6KdgTuAHZZVbkVlrhdFngNCxtGdUWpBVF4ejhtZj2/ihsXzINAZuX47jfMmz8ejJmzZ2IHf6rpJZvTh1rIrY+aNN9T10/AaV2hRKwWZBcGI4V26bjiwVjYEo/itxKWg8JPplEwWPikZQdjg1r52D1vMnYu/ZrHN+5HlvWzMHX8z/G0mVfINS0F5klcRILp0Cfel607hCE5jK2rw20NWus6j4ouuIcdZE+FxeIEjNZacPOoxvxy/tvR6de14iV7dNpE2BOCsPzf3kOvQb0QK/rO+Dx5x9AVDJDD8hnFidJbK3lgeA16T7ZsKXOZ1au1E5mYhXnAUNnyvOghc0VqxbaJM41hBQf3Ga2fYZRm9kXaNML5DbQ9n1ArNY/Zxto+xGBNoIk7wHLgav3cdBq4KbBlGRN1tAlxRV9AmJSAjDpq3fQtX97dLnuKjz310dxLGQbbKkheOX/XgCtbX1u7oS/vP47hCUfQborDmk1JpGMmtYr5VIvO1ffkyhiVcSeGaFMMGCGKOujuleCdIlWmZAiHEXRyGRaOyktmBHlTflReTq9h1Zy3m0baGs5aJP+xzJtRgZdTrWyrtEaRVBDkLbl4Coh9h009Nf4ePp4hNuPIKs0DnkuO3JJoVEZj8DQrVg//3NYdvsh5eAuFIT6Iy/kGGz7tyF87zqsXvYFjkb6IZsB+61oZeOCQfcBPTkyRkkyRGmRoFTGIcERhnGfDEfvAV3x8mt/wIadS5CcG428igQ4KxOQnBWB3duWYcuS2Yjesx3pwYHIi41Egv9+JAftx36/xVi9ZhpSCmKkKDyTEFSsn3LJ8TpoRcx1KZ625hWMV9fO665P+fHfzR7Vz5Hv6fuIadPvi62AlAagzdu7oHWfbkUnCkWTqiHq0T2MjWUyTyLseSZ8MuMj9OzfA116d8TDT9yHHQdXIbPAgunzvsJNv7geXfr8HLfc3Rfr9y5BUnGU6CQJ5dCcgQ2uSf//ZrdcaBqZ9bKoNZI6pO9LRm6kEBSztisr8uh75m/4PwjqUksjhKeSVQ+yK0xS/YC6UYBbmSoWr12kBGpuvWps8340uW6bpa31wVZrnbENtP1oQJvB3C1kkDqo3DCXc+A2AG0yuVZTuRO0WZFdacPWI6vw8LP34uqel+PaGzvjgy/eQbrThKLyFHwxfRLuuOcG9Li+I24fdDN2BPohqTQWadVmpNXESpF1KgetJJqtjBooMyrNer/VWWCs7+difb0Y4XgyO0nOGQR7cZhY3nRRe9bISzHKWbGElS7fIqvLCq4oo4VEl0rNreS9LHneE0AbaPMAGO/nop4b3XgeUf2JEwsBchTSKyKRXk5CzzD1DkpikHEiDin5cZi7ajp6978Wl152Cbpd2wUvD/szNh9YifisEAF1yblR2LZ2DkI2rkBZVDgOzJuDyDWrELlqBY7Om42C8OMI2rkCa7bMQFJ5VL2kh4bXeebP2q1Kt7ln3MjkzXupjEI6yUqFmJTkpBFIL46AJTUQI0b/CxdccAGuan+F1Ej9ctoHCI7cJ2MmLHQ31s+fiuwAf0Tv2ondi5fAtGs3Nk/9Cgn7tiM99DD81s7CwbDNsJ0g7QxBG615BB6xENBWZzlvQFtWQSq8yXVbwtP23wRtAsq8dJ/3Z60TCWhIjcHP6lrZr+ORU5uInJpUHIjYgz+8/Ae079YZXa7thHfffw1xKUeRV2bF8bB9ePL5oQLaeg1sj7Gfj0RMZgBy6+zK8k9wZeiXenqtgd5r7nceUOkZm/wtrWyWPFWFx1oYKPQepDRiuS2W2kotj0A6ycNLo5BREomsshhpWf1AKiCIxS3GHdfmDdo0N6Y3aGNMnMS0UQc0smjifSuyZBNsBUFYtX0ejoYdQnFFCU4B+M7NUNki5sDWwjb/s+dpA23nGWjjQOAg9S7cTkVEpSNCBVQZ7SHyrSLY8bKy6RUbmbs1aWK1Dekl8Zj29Se47vbuuKrHpbj74VuxfsdiFFamoLQ6A7sPbcDQpwehY6+r0blvJ0yc8h6iM/0lESFdQJuytLUUtHmDNEVIHCvXTsBERdRQaF1jSbA4JwlWPaXBNHgjaCPXEIsms/YeS1axLilZwWltyyRvUZkiOua1aoXqa3JvA22eiaHh81GxkEYMDOlfKs3igib3kzU3EMdNW7HxwHws3zoNK7fOxMqtc7By6wIs91uEV0b8DZ27d8IFFxoF7C++ALfffSP+M/U9RMYfhtVyFHtWzkFO4GGUmmOwdsqX+OjVlzD5n68gctVylESHIObwZsxcMBGBKXvFqtDw+s78mWCN1oR4acUFxMQalkQrYWHtCMRkHMG+0DVYs3O2uodtM7By20ys3DIdC1ZMxu/++JSANrmPCy/A1e1/jt//8bdY67cIm9cvws5Fc1AXFw/7kaNY8PHHGPfSS/jk1VeQtHcXis0ROLhjBYaPfwnhGccVaJNsVC9LmwHaQt0VEa7D7rCNMllKdq4XIPC+X5ks65Hrnqul7VtkFaRg+bY5OBtyXV6PyA9taWugFxW5OQGaFpKgK8Jf6swsV6yRNEM+wXg4apKQU5WKhevm4VeDf41O1/YQV+iyDdORV25BQaUdGfnxGP/xO+g9sAs697kKj/3xIewL2wxHjV1cq4xN1DqmucDM+zgNMqnbWQrMoxfr60da2HRJMJYFYz1Xlg2j/pTflIYjszIG2axHWhyBFOrEonABbCwuT90oFW+MZIR6oI0WtlqLJIFpS5sGbXQhUxd49z+9Lf2wLRHhBweHbaDtPANtMiAMLjISyqZVxiCpJEIsTiyTZS8KVYSyxWFC6EsQQ7qL9CqyWzPolKspXZaFK3u7JCBEJgXgr8NewDW9L8fPu1+K37/0KI5H7UJeeQKKqpJhT4/Eu5OGo2f/jri8/SV44k8P42DUFilvIokIrAThJd6Kp7Ftsc5IvAVrE7KgdBjiC4IElJmdLCxNCagnJgdXkwRs/m7Qpo+hIiH3EDmHJIOr0iSALbEgVDJJsyQRIVZAmypZ1QbalHKm0tVWJt9ATRSwOxNUJQswfstRbUNaiRmmjFAs37oYw8b8G8+++CTufOA2dOrZAde0v8qQq3FNeyWXX3k5LrqUtVAvUMCt3QW45NKL0anbNXjs6fuwbeNCHFm7GHlhgSi2mBG8ayv++dRv8ebTj6EyKgw11hgkBu/DtLnjsd+8BWluOheCMN8TiJ5IVMuJhpOpIvHNqU5CbnUq0ktsOBK5G/+ZMRZ/ff15PPb8bzDg9t5C1eG5D3U/V139c1x++WUe0NbuAlx4YTtcdvml6N2vO/74zFDsmD0T38bZUGwyYd2MaXj81lux9sOPUBQcjIp4Ew7vWIOHf/9rBCXsE2oPiS2V6zJ7WdqsCLGEgO7RATf3xd6wTUhhvV1ab34A0PadVERQoG2ZVxmr89HSJsBQx29VRAmhLIvUk1DbVhQEWyEt8yFSSiu5LFxAkFSvoZWNsWDkWTPiL53V5M9LhD3XjDcnvoHu/XugY+/2eOb/DcHR0O0oqExBfnky8kpTsHjNLNx27w1o3/NnuO62nli8YQYyywn8LJJw1hLQxnGoLVfU7VykckHq0YusX+0l4nEIhCUvUOlN0YvUjf7ymftthSESz5vJuLUKE9JORCAxP1gSaQjYqC+lJCDLFLpBm69xFGe4R8PE25FcGiXGA31/9ceYAura0mbPD8LqNkvbDwLg2kDbeQjaOOEwdZvmacZ3EaxQuM00bg50Dih+zwmNcV4EeCxvokEbS64wuJpZo/m1qVi9YwnuHnInft7jMnTq9zN8MW8i4jOCJUan0JWCrGI75i6dgl7Xd8ZVXS7FHfffgPlrv5QAVk4g3oCNyQn83BhY895PpZlYEo74ghB1H3mBinizMETi1qhwtDCOjfepQZpY2pwBIJATdymfQWGIlGNRlrYoAW1uSxsn96pYJLMaQjPi2tosbR4Adzpoo+uOtRhNCIzbh+Hv/Qs333kzevTujl8PuhMPPnq/yKBH7seDIg/gwSGDMOiRQejeuycuvvxSN2BjMfgLL7oQnbu3x2NPDcbalbOwa/lcpAceRb4pGsumfI6v3hiGWaNex/EFc1AU5o/4ozuwaMVnCEo9WD+usdmgTVddSBDAllgQj3W7V+A3Tz2IPjdciwE398EDj/wag4feh4eGPoDBQ+53y4ND7sc9g36NXn17KtDWTlkMWcz+oksuwvU39sNzTw3FtrmzcDI2DuZt2zB/3DjMGPkG5gwfheQdu1AYHYl9O9Zi2PiXEZ1x1KiyQG49BTw5cefWxckz1qCt/019sTfc29KmJkafk2UrWdoI2r797hQy85OxbNvs89zSpkplkf2fVqb4/AA3UJNqACUMpVCWJ10NhfqHFiixQlXFuDOY86gbK+04HnUQQ599FB2v7Yhu/Tvi85njYMsIQmFVIvLLbSisTMKx8F34499/h2t6/Bydel+DYe+9gsikw3AYoE2/H2+9d6bttIpoJBSHSQgIdR5jyHQVCepBG7PiDd1ILkqCs3oLWYfSi8LHxhCSkkgQtLGIPL0PzHpmS9codWXLQFu46GEmhNHj0wbafhAs1ux/0gbazkPQJlk8lSZ34V6CNdY2TWU2EMs5EaTR1WOI8KmRaoGWpiptaWOAOCcFGxxVyRjz6VvofUsPtO99JX4x+AbsDliPzBNxyK9MBEFbQVUG9vlvwyNPP4hOPa9C937tMWL8KzDl+AunlLDgG5mkzQVtNP0TGIlCylcp6FQEtLoJ2CTg9BLGszFd3Ru40U3Kz7QwEqxSdCKCFI8viZQi8qkljLNSypmgTWJY6GZuJJ6N+/83QFtCq/C0nQ7a4pFTaUVyoQkTv3oXfa+/Fn0H9sLLr/0Z81dNw5aDa7AnwA97/P2wJ2Az9gZsw17/Hdh9fCeeffF5XHHVlRCQc/FF6NC5PX55z60YOfqf2H1oHeLij2PL6jkI2bEemWEBWDvtC0RuXo+oDaux6bOPkHZsP0L3bsCmXQulRqcuhaTcnb4sBB7wqd63EbNUbUduDa1saTgcsx9P/eUxXH7NpXjwsXvw3ocjsHbHYmw/vA57/f2wL8BPWm7vOrYJa7YtxdDfPSygrd1F7XDlz69Az+u647fPDMHkOZ9jk98yrJs/HY7QQBxf+jWOL1mC5H37sWPqNMRs2ISEgGNYv2ER9oRuRFJxmOFiovVPXb9v0NYHe8I2uN2jqrRew3szLBytBdq+Pf9BmwYNBEKpFQzIDxShlU2HQujQEcZ4qdrQRtiIT9BmQh7fQ0kcpi38Arffczs6XtsJA27vi+0HV0plhMJKG5ylccgvtyMpOwYfT/1AWeN6dcLgx+/D9qOrJUaR1E5ax5wJqMn34tKNRiK9DkbVCC7EqRe5CBfdWMEQEiXUj9T7tMbJYtbB0BEV70vAJgv4sigkl0aK658hI6msg80i8iciVJF4hpJw7ij3jmnzXLe+flqxvd2jbaCt2TjqBz2wDbSdh6CNk1RSqQI7XG0xCF/KwZAg0bDC8RgtpMHg9wzk16Atl7QMVXFiKQlPOIIhvx+Mq3v+DN2v74RX3/wTwm0HkXUiDrml8cgttSOvPA22jFh8PvMTdO7VER16XI1Hnx+MXcEbJB5HglUNi5uAtmYE2jK2JKE4BIzB4KpS2LlZc1GIYT0kpcqVZZGyYFRc4h5lXJuY/qmYo5HJUizkEaqMlUQEiWEri5ZVJDm1uMqUIsosGC8BukYM3v80aLNK7dEiVkQQct0OUsbqbCoinA7amEVpQ3x2LO4c9At0u64zJnzxBpxVichlOSey/Vfb4BRJgLM6Gc7qNGSVp+Kf77yKDl074GdXX4F+A/vgHyP/il3HNiK3zIbC6mSccCUjIGAj1i/6AtbD25EVegSFpjAUm8KREnAQgXs2YuHCz7AvZBMyqlVMmgJsLXGP0tJml7ilrMokzFgxBdfe3BO3D74JhyJ3Ia8mBfm1ScirS0JebQLyau1w1thEsiri4R+3F3949WlcfMlFaN/5atz9yK/w2byPEJsWhtyqNCQ7TNi1cwV2rV4A2/4dKI4IRakpFnlR4UgPDsD2dUsxb/kUpJaQVJeJByZFqGv0R1+grd+NfbA7lKAtxiDg9W3lUO+qdch1v/sRgDYBFUadTRXb5S8uUC4KCYS0678haGJ4Rn1LG70PzHI2w1FlhjUrBI89/wh6DOiBzn264Na7b8Le434wJwXCkhKM+NQQxKeEwZQYgUWrFmHgL25F1769cNNdN+Kj6WORVhpjuEcVAGr4/xt+lutxsVZohFgKuRglMNJ6XLcsjyhiEIkLkDoRLqCNgI0cbHoRT53K79PKY5DGJAQCs0rqfrPKqi+LVmCOFjeGlZCuRs7bFjj7tQAAIABJREFUBtp+UKTViv+sDbSdp6CNqy+upBjPpi1rHNQEaO5BbQxuGexidSO481jaHFUWJDojMHfVV7ju9l64qudV6NK3E14f8zLmr/kKyzfPxAq/WVi+aQ6Wb1yIxWsW4K3xb6Fb3x7o3Lsrbr//Fkxf9hmyq6yGYmmeS1QrK7oobUV0eQbKKpLX3RhgU24ji9QQFfdAUag7a1QAG+/VSE0nYWRKSaQUQiY/G1eQbBlgzgwqTwLC/6qljUXUVTF4R60NRd9k4LPZ76Nb344KtKUek5qDqowVQQ8VtJ7cTrfccFI8HbSZkFEaB3+TPwbeNhBP/b+hOBa9E3k1rBdqUzGFLOcjwsLwLO+UgMyKBIx4/9+4+f4b8Pc3/oLdgX6IywpDRindrVZkl5uRX2NHblEMQo6ux5z3R2Hv8lk4tGkZ9m9cjvVLZmDq9PexJ9APqWWcvHivnnffnJg2SaJgoXda2lwJSCo04+XhL6JT144Y9f5rsORECJjjs3NXPxDyUWZax8lCICB+J/4y4hlc/+ue+Hj2OPhb9iGhkLxXVmSx2kGVHWm5EdixcR42zf0KARtWIWjzBhz2W4Xls77C4iVTEJl8HPwfDnm+BG0eEFYPtBnkugRtu0LWI4VUNozd8jreYw3R7+rHAtrUYqs57837HhtuU6fQMs4MSrpFaWGTcS7UGKpPa73j3YrVzYhpy66KlWodTibWlMRix9E1uOXugejSt6vItQN74JEnH8ATzz6CJ54d4pbHf/co7n94EHr2vw6de/dEh14d8eSfhyIq/ZgQ7Uo9WfdiummyXQJNuneZSMCFLBfk0r+1bvfq63oxq0Eb5wOGxbDOMvfJfKCPd6kKMfQ+aBFrGy1ukqQVqwAbQZvo4TbQ1oo46gc9VRto+wFAW0MFdKbPtJoxpkEGqbEScw9SA7QpAKcmMwFtvA/JIo1GFhMRyJ9VZUV0sj9eGfUXdO7XEVf3vBqdr+uCPrf0xcBf3YCbf30Dbr5rAG6+qz9uvut63PTLG9Dvln7o3KsbOvXqil4De+DZlx5DbMZxZe2rpqLwlqZBHF0ZjD2xFbGgO7nTqFypLBoTrhrpAomW49VKmpNUg+N5DUzSKIuGvTAECYXkLooS0l1SUnBCVM/4fw206edHINYAtM36EN36djZA22GJb2TQsXbHnQ1os+aG4uOZH6Njl44Y/u6rSC6IQR4z7lwWqTzBrGUltPLS2huPjCor9oT7YeOR5QhJPIzUErOA/hyS0nKFz4oIzKLkOQpjEBq+A0uXfokX/jAUv392KDb4LUaY5TCSi3ntCXKfKgOU96ytbvr9+gagQnMjSRRMwkmAJTsCz/3tafS5vhfmr5+OxKIYKVgvVgcJzCbprSK+zWEfrTIhLjcAm48tw+ZjK2DKDkZ6OSc7O7JdNkjdUZbnqoxHSm4YQkL34O2R/8KQwfdi9Lv/hN/eJTBnBCL9/7P3HeBVVena/51779y5Y6OoKEqzgCCiCILSVFTUGWdso446dkSsFAuigyBdepdOQu+9Q0gP6ck5J7333pOThPr+z/utvc7ZCScQENsleZ7v2Tv77L3P3uus9a53fbVMJdAlaWNeNfZJ/h5CKtkGOk+bEYjwf4u0+SCqwE9p/x3j1/XvdSE85OckYgwuotaeAQfJlcyVZh7fDWCRYCLdSVgthUmUo5FTFYO47GBMnf8dbrnjRrRo3Qwt6dPWviVa33YDbrmtFW7pcBNad7hJbdvfjFbtWuP6tq3Rsu1NaNamBe7t3xWrdixCWoUNWbXsE1xgcEGtntVMHM37mrTRxBtfwtqgRs1kA1frYyP7ikqFRNMpo2KpXdQ4oHBR9SkWhqfFIVxIGivFxOb7S442JiPnPXTf09tz273JPPqLsq9L/LIm0vYbJW1UgZO00VzIlZiaFAkIdc2i8plxzEzaODmmlVmx32cb7u3bBS3bN0fzts3R7NYWaHZzCzS7qTma3dQMzW66Fs1uvkbJTdei+U3N0LJ1S9zQppWUb7nnoTux45ibaLUUKGltH5+jAaA0jtMpmKtimjQYcp/GHHN1gPZcEOc9uYKm6PtrnxYNMvyfwEMfONYdjcrzRRLbiSRFVt58RnW9vsbVVvm00XTrL4TXSfbOfS7m1eLzR2R5YPy84di2fy3yi3LVsGMaIi31BiIPn6knp3EWp3ESaXkxcNsxA56WTVLJgUWo67+rq+cmYVOkjRN/FApPpWDinHFo1a6VQdoOIa0qRIpaO+/HCc48ydV9R56nyjOpLc3r4SleGPrVB7j6uqvx1fefIb1E1QsV0sbAF7sWkjZF3FKrLEinJkO2NMVESRk1EjX1LBFIlwS3NmTVxCKjMhYb9i1Hjz53476eXeETfghZlfGiCctg0XjjXZ1bTdzqPr+5nVRuQlW6Lac6Dj6Wg3jsb/1xe+f2WLtviTJZSmSp0jqoLPGauKni2qkVEUii+YtaRdEiRkkEKCd+0fxKWSp+RxTicq14e+hbkhLk/ZGvwy9pH5Lt4YoYigZPtSn7rHxXNUsK2ZBTGyVlro5b/THw6YFwkjYVPfr71LRZhVzZ8lVKCpJ6829zqfvEAo5XcbUo9jd8VpV5VOOEy61d+/+qfpldHYes8lh4Bu/Fi/96Gje1b4FW7Vqi/V23oluvzujasyPuFumEu3t2wt097kKXHp3RuWcXdLq/C9p0bo8bbrsRt959Cz759gNE54RIXWcuSliUXZG2hombmbTR95b/s030s7tsHxMW8jyX5xiYyL7PxWx0vr/gIhe3TgxoeMyoezaRtnrw/Zv8t4m0/VykzSi9w8m+oUHW4PHqSPFbcJA2w2eN2jatcVOatro+blJ2qppAxoz1FsTlhGL20qkSFdXs1mvRoVt7PPXSIDz7r7/g2defxnOvP4XnXn/SJE/huVefwl9efAxtO94q2cHvuOdWfDv1E9iyvA2TmJrUeH8NNK63ygxgyVX+JyqaU4Fs40GEbXcuSKnrLeK0yzYiwaUDL1epQtrq+bE19H1cudPc8vslbao2Z+GpZEyc8z1atbvJIG0HkVYVrJK4OtriUknbUFzd4mqMnjQCGWXRyK6MRVaVDRkkZfSb0WJXK32SGu07k3PChhzmImOCZ6nFy98zXMx+1Jpl18Qixx6PrQfd0HtAN9zfqxv8Iw4jrYT3j0ZmbUOkrRGathobcmvjpCj9tiOr0aPfPbijS3tsOLBMfJEk/YZhKlKkTRE483Hus2oBibESagvpF0RtIU2pkciusSAhPwqDP35XUp989OWbCEg+IO/ouJep5mN90pZjj4GTtLXBLr91yoeTi4TfpXnUTNp8RBPbIM45+uaFMZIYwzQeJG00LzrMnvUIjSssSq0mbmrSFo/UAhuWrpmFth2vR6t2zdC5++14/9N/Ye6SKZi9ZDJmLZ2EmUsnyXbWUv4/BdMXT8Hk+RPw8rsv4dbOt6J5++bo+Xh3HArerczl1Hwb2ja1sHYuOs3PxEAJRrpS08b3aRRpc9FOrjCNx9i/6CoSlesrpI04zcVC436DJtL2m2Rp9R6qibRVM7GgxQBIZsy+sDZIDQCuqqxIKA1FeJaPBA5wcDZucFwApC6CtNXVtEVKwd80mYxiERTriyEj3kPzW69FszbX4vk3n4FX2D4k5AchqSAYyQUhSM6nhCI5Pwwp+WFIyglGZLwXXnvvBdxyxw24sf21ePiZ++ERvkXCxhmhKUBwkaRNa9rYRq4A5+LbzTVpU/dp3O8gpM3QBBI8f3+aNpIhKxRpo6btwqStobZXgO/UtlHTFpbsifc/H4yrW1yFbyaPVKStKkZIm+TJ44RAoYaTov9nKSjRJlmQzdQWBsGRigS1irQxD1gOSZU9AdsOuaN3/27o0eteBNk8kVJsRaadyUvPT9oaehdqG7JroiTdTWZFNDYeWIHufe/GnXffhi1HViKljFowo4aoJm7cklyZ/zc0YlJuiqZMkjh5F+c7ZdkjkZBnw+CP38N1za/Bx6PeQkCKibTVJ2zGd/Be1LSZSVv7Tm2w02+d+C2lUvviYsHC/q1+q9+qT9vPT9oYNdp40hYpNUI1acuyxyEi0Rcjv/0A1996FZq3vgp/eeFR7DrkjvTCMMHExMIQJBaHIqkkDEklEUguikRKkQWJ+RYs3/Qj7u3XDc3aNsfNd7XCoo2zEZ0XJNrYDJr8HZYQ16RNB2cp0uYsR6WJ3cXjYN25RJM2W46PEDeOSY6Hxt23ibTV40e/yX+veNJGgpNGHyhZ1ZJQNG7CF98DIW1hiMjyrUPaGppMXA0cnqtFf07zCzVIFDGPGpo2ZYJymkjFXOlwgFUDTvsWMaHo8s0/4v7+96N5m+vR6s4b8PWU4YjPD0HeCQtyayKQWx2BvOpI5NltyLNblVRZkVMehTnLJqFLz9txfbur0KZLc6zaOQdJJaF1JmkNNK634YgvOQ7RtBX5G3nTnJo2eWdDk3Ax7aXbiO1P7RrbiJo2mkqVP0hdEHOef+5xkjaCJ823v23SplbL2hcloyYaIrVWZJ2wGaTte7Rqq0hbaNIhpFeFIJPlkmSVTtBWfZv9Wwn7nSIqZiJCgKcwCWlYihcGf/4+rmp5Fb6d8rmQtpyqWAkoEGdmOjTTJ0z7hdUjPHIfB2ljcW4mjDWiKElYTsQjryYJ2w67o/eAe9GjN0nbMaSXMUAgziBt0UivUaLem+ZWZWp1vpualFSfUiZIBgDk1MQhqyJGzK/3PtgZne65Hds9VyO1PMJE2hiwQK0fEwlz36pSORjtIEROTJwkbCR1StOmtG2RyKGmjaTto3eFtH0y6m0cTzkoeCLE8AKkLdukaRPS5rtWkTZGPjaARXzPy1V79KdEj0p7m/CLix6mwKAZk24RLLdkNo/WP/98Y9N8Ls8jxlAzFZF9TEWOSj3RRphHqWUziFQ6/SrtsVIb97G/PYSWba7C9W2vxdCRbyI8zgO5VVYwfxv7QKZEuFOzyvJjUchhJHJlLDxDD+Dx5wbiqpuuxvV3tMAbw16Gp3UvMuxqEXBh0sb0Hf6CO4wiJfnUrhx8x/O1SWM+M5M2Ejf6uZnTkpz/HhdP2jKMighNyXV/OX53hZK2Bdju7yYTvqiyjclET2YuOzY1ROJrFakSDtIZtNoiAMsksMyTQ38GTlQCOIZvlStzHe+vznESNgdIiZO9Mo+K2U+yWNPxm+p9w9lU9pVvGVXy2seGpI7nUUMRnReKEeM+RbNbWuDq1tfj7j4d4bZrEbLsMcg9QZMPTTvKvMMkkTTzMBw+t8aGgtp47PZcj8efG4Dr2zfHn2/8H4yc8AGCk44KOGnNiiuypgEo3R6hSBvTfRT6KZ82XWJLwIkApeVcQuXyN6hjJrgcpC0EzETOShN0VGZJmoa+99fyaVNETZErtjtNj2mVVnGATq+wIrMyBgU16Rg/cyxatb0RHe5ujZD4o5Jkk0k10yotkmqFDs/MCp/BUj7VdMRn1QP6VEUjxx4lQSs0SaZTKmNFQhL98d7IIbi6+dX4dvJI8WnLKo9HVkWspANJr2LgAX2GGLEcYfR9RTCF7Nht4DOmV9pE5LkrWRIrCpmVscipSkBuZRK2HViD3v27o/sD3eAr5lErMquikF7F4vKxSK2Mk21aJX3gopFRoSo2qMSf/M0sRgkejhErMqpsyK7i/eORVRaH9btWoFvvu9Gpa0fs9NyM5BL1jmkVjASNQlalFdmVFhFO2hwHbB+aQp1E2SDOBg7I+1Yr0hafa8V7H72LZi2uxRdjhyI4/YiQNkUu6xNu3T5KS8r2p3mUFRHadzRp2n5l0pbJ1Dy1NkeORm2qdeCUxjDTluSAnzOyMyrPR+pRkrSd7xpX483V+bxPYmkgIknauMgyyI74gQoun+sL68QnhdUZ1TbwNx8z4wvc0f1WtGx/Ne647xYsWj0NKYXhyOGCVbDQGG+yOFD72RwrVdGIyQ7F4JHvotWdN+Hadteg64COcN+7CKkVSrt8IdLG544p4oLcW8gt30uIrX6HOhh38bjIhRhrM9tyfWHLVaTtfBaEuu1/8aTNXBGhqfboL0PcrkDSloyVu0ja3A3SRsdoJRosdEfm/yQW1MKwEDlFZ9fmNrUyTMqHcEXDFBScUKmO5mQicl4HUwUyGSQLFE0K6dxdFYGYPH9EsxQJi6PL5MsJ2Cn6u+T7tF+R8f1ZNTE4HLYLz/zraVx107X4Y8ur8c+Pnscxy25kn0hAVm0sMkV7QYd27dit8qaJ2aYmBpY0f3z41Xto3rYl/nzT1XhgUDesO7hUkTYxiTmdZ6V9jPqnJAa6jRKKj8NK0lbgh1RGj1aqUjKsWkCgMl+n27zx259K2iyStJKaOiaupK/gb420sf9pTQ/JOftYWPIRhCceQWTCEVgSjsKW4IPYhGD8e/xwtG7fEp263YJjPpsREXsIEYmH5dzQxMMISTiA8OQDSC4+jszKIMkMT9NcbkUsknNDYUn0giXJG5GJFH9EJBzHUf/9eOejNyVP2eixQ2CNPYrohADEJPgjOsEP1kQvhCYeQlj6QSSVBToiJOU3tEcisSAYoXEeiIz3FgmP80RknBcscZ6IivNCdJw3ouJ8sHr9XDzw4N3o3rMLdh1yQ2j0HkTEH0B4/GGExHsgON4TIYaExXvAkuwh9RXF9CPpC5i/LwLRuQEIS/RAZOIx2BK9EJPoi5gEXyxzn4Fu93dC5653YPXWZQiO8kZEog/CEo4iIuEoLGzLuMOITfdGIX3hqiOQXcM6lVpT6Zw89TjlmGWENjVtcTkWvPfhO5JEeOz0zxGe5Ym02ogLaji4EMiuiUaAkfKDpI0+bUzroEvHuRoPql/8DObRbXPxg/sohGcdEV+++qTNHKjCduA4FuFiTAtr/5YGIpoa7HxfGfMOjNNYJ/kkeQ21vs625bsK0TJSdAiWGPvE3sSSQFiyjiGu0B8pFSHqO6UKjPEcxsJEiJDJ140LSQZmsb9E5QTitY/+gRa3XYMb77wWD//9ARwM2Ixs5h20c/FKkqYW07rt+YxZJPI0f5ZHYcnmhbi7f1dc0+5q3NSlJcYv/BrxRSFiWlekzYmNGud08l/mkGT0KzWRSaVBjnlF5hZqDx0axEsN4LBIqiTmgGOeS4VrP795tKlg/C9D2PgtTaSN4OMgbVwpqpW7HrAkFlT3c3VHsIjTW+4XBki2c6adiCs6Xkfod0GJK1FbKVhsAig65tN8GFfEewSo+/Le3C88jph8f0lnwQLd/J9bp7BsCXOShUp6AhI4p1AbY8PUpWNw530d8Kfr/4Q/XfMnjJnzOSw5vioar5p512xIrbYipdoiwn2aipWmwoqUUgvmuP2A9ve2xZ+a/Q9a39EK4+aNQnIZgxwihWQSYAlGutAxzY1JZcFIKg0UYVsRuClxhX5KivzV+0r7+Ev70EzgKuBA/waut1cKaeMK3gZGM249uhivDB6AocMfx7CRAzFixECMHPEERg5/Gm+83gvP/KUjnv37XRj26aPy2bARj+KzkY/hkxGPY8inA/HZqL9jv+8ypJf5OUhbZpEVS1ePx5CPH8VnIx7BsBGPYdjwJzFs+NP46KMn8do/H8Izf70T/3r9Xgz77FEM++wxfPrp4yIffTYQQ4Y/hqGjnsEu36XIMNKtcGWfWh6C9bum4+XXemDwkIfx/pBHMOSDR/DBkAH4YEhffPR+H3zyQT98OvRhDH7rQTz3TBf87a+d8e67ffDhh30w9KOH8MGHD2HIh33w/od9MfjDvnjvwwF458PH8PqQgTgavEEmUZqvqAUJTzqICTOG4LORT+OzYYMwfNgTGD78cWmfwYP74vlnu+CF5+7B0KFPyLt98tmj+GRYf3w64hF8NPxJ/ONfD2HwZ39H8Ylo5IoGmqQt7BxS4SBt1CyaSNu7H76DFtc3w9jpXyA82xOpjSBt1MozBcXvibSJhpbkinUzZUz7iyad2nSO9/hiE54VMh2P6Tg/M4TnJ5QcF5KmxzfxhKRGSlIJvhIziBcKM7gIJJbwnvo+eptQHAB+TiEmObVsRhS5PRzJZSGSwuXZd57GfQPvRs8n7sFXkz9CUPxhZFXRLErTOokk/S7DkSr+lyRPisDzs0x7FDwi9mHwV2+h++Nd0f3xzvj37OEO/zEu1tV3q0L1fB/OH4ykjy8NFKF5lMJnd7aZMbcY8wbnBhVtX5fU6rZqeNtE2n45+vTrfFMTaWuAtHF1RSFpiy9VNe2Sy4MleWtKeYhojqg9Sq2gxo2auHCHoz5zkjGPEIWEhoOVQOIYaASnylBVI7M8WN3L0ORxxcVVZEpFsLENgfN71fcnl6sksqkVwUirCpV6o6w5ytUu649SI7Pd2w2TF3+Lb2eMxNjZX8LDssNIi0FQUUJfD03auBXSRs1FlTJP+cccwswVE/Dv6Z/j+3nfYJvnGjEDOEibUZKF78j34TsqbaTSqjnepZzvwzZjIlxD5BoCWpCUpiHQOdrHRG4bPvZ/n7Tx3TmBiDa1NBwbd0/HV9/+Bce8xiEw4HuEBExEiP8UhPjPQJDvTAT5zESgz3SEBExDsN9khByfjJDA7xEUOAlePtOwefcEbN4/E6mlmrRFIb0wGEvdRmHT5uE47jcOwX4TEew3FcF+0xHsNwMBXlMR6PsDgvynIMh/PEL8v0ew7xSE+E5EkP9k+PvPxeJlX2DHsR9V1LL4h1okhYmH/wJsXj0U/h4TEeg9FYHeUxBwbAKOe05AiM9EBHtPRJDneAR58fNJCPCeAH/vcQjyHwefY9/C49BX8PMcg0DfCQj0nQh/38k45j0Po8a+gaNBGySamb5HTNYbErUL02a9hdDQ2Qjme4tMQsjxScaz/4Agv2kI9p+BEP8fVNsdH4fgoLEIDJ6DBYtH4I3Bg5DP4vLiz0Yt27l98ryk7YZm+H7ml4jIYek3Z2HwhvqwIm1RvxvSRjykFortQ9JG0iXjWfDKGOPEMcFFA8f02DfhGz9PLguWRSu1YLp9iAHEkqSyIIUXci+FG+Z7cl/hifFd+t4VIYq0GXWHHcTNMEFykcs6sNRmbjq6Ats83REYfxhJxWFqAUBtnMwHirSRuFE4Bql1VWJBXFEwjkbsxIbDy7DxyFIcCd+ExJIAZFQz7ZDJiiBaszBxHyA2cuHOLbGSZM78DhofNckj0bv4hSwJXhNp+3Wo1C/3rU2k7QKkjeptasuSykPEJ0ibAVQSznBJZiiFeg3ixsSckr/KSL3BQSoOp0Y+HgEog7QlGupx+hk5TKQEmEoSNgKXU+hYnm4PEQdzpnNIraQEST6udDuJm0HeCBQVoUgqDUVKOf1AqP0KkmfS/mYazBgKr0mbw1lXfIIYvUe/qUiJokoujURCMfNWWRokbULYHCYSw1xCcwXNyAaIS4ktfQ7NF1z9CrFVVQw0eDdue2WQtvRaBn9EIKM4FDv3zsDMmS8iJ2cxKstWoKpsNSqLN6Awey2SYxbDEjITEYHTEHp8MlLiF6CieBXslT+iqmIFCko2wT9yGTYcnImkUn8JNMim/2NxANw3fAV///EoL1oJe/Fq2IvXw168GfkZ7rCGzkJ44CwhgtawqcjLWITKQjdUlyyDvcwdleX7sHPXNOz3cwf7k/hw1tL0HIhgy2JEh4xDRcFq1JRuQE7KYvh7fI2izBWoKFiDioK1KMlxR2XRelQWr0dZ4WqUFKyEvWI9UhLmIiJoHErzVqGqeC2qSzfAXr4ZRSUHMWXWR/AK3axIW60VeTWxCIzchnmL3oS9ej2qKlehstwdVeVrUF7qhuSEOYgMnYLwoMkI8huHhKgZKMlbjuqylaiuXAp71U7s3fcD3v/4b8iuTlLa9lrX5qkLkbYJs0chMtdbkbYLLD5+j6RNadoUaaN5z2wiJY5xjHOxZiZWPEdhnNoSQ3lOfPFxlZPRaCfikix2afrkNTRryj0NHHGQM0XaFJ6YXUu4YA0UckTCo3BOlffjYpZYpBacOtKZgQlRyDRS2HCckXSl17AiRRhSjS3/px+oCMmbPJdKwkxXFi6c06qCkFHNAuskaeFqAWs3afy0OwjJm0Hc2EZ8Jj2nSLsIJqpFf+NwsL4mzknaaCKlz/Yv4dPWZB5tIm2XvwXOnsWZs6eQWXQ+nzaneVRr2qiiZl6g5HLlQ8EBK4OWpsFylk4KRHyxEmq4pGh5Ff21wpTfFklbmQrtdgxCXksfDYO0cbAqgFK1Q7lqSyimScAPsYW+iC/2r0POmDg1rZIVAOhHpwmbJm3Kv4OZscVnRBzEqfLXIFZ3y9QCJGwO0qZTNxhRgZK9/gQTjNqQXmUVrY9Z05ZcxUzdIeKLQRJGIeASlEkWpX0MEzA1hnxX7TOiQZqVE8Tv5AKTnKP95LwrgbTRdO8kbdt3/YAZs55FXv5iVFWtgr1qHcpLN8HH83tMnfgU/j16AD4cci9ef6UDNq57Fzk581FSNhel5T8it2QdAqJXYO2h2Ugo9Rcfn+zqSGSXBWDtpi8RGDhRCE5VmRsqStYgN2Ml9uwYgVFf9MfoL5/CW6/di08/7A0/7zEoKViC6vKlsJe7oaRsJ7bt+QF7fd2Mkj5WmSSSygIQaFkIS+i/UVKwAmVF7ti/+xMMfqs9An3HwRY+Db6e/4a/91ikJS9HfMxCBB2fBB+vMYi2zUVI4BTs2vYpgv0nIiRgAgpy3FBZsRlFpfsxdfZQeIVtRKbhh5hTEwv/iC2Yt/hN1Jxcjyr7clRUrEJZ2TpkZ6/A3Ll/xbff9MYXI+/H3/96A6ZOGojk+JmwV7ihpnoZTlTvxIH90/Deh88g056g/DzpMuGiP56PtLW8oTkmz/sGljyf/5OkTWnZnJo2+q6ZSRtJFMc8TZTajYSmTB7TxE0TFCFtJa5Im9JCSdAMF9RiPQgTa4M2wcYW0ETqK75z5vvyGtH+ERMdeFeXtGnslsV1JYkXCaiqXawwkxGpirClkLhVk3gxwlMF93XQAAAgAElEQVSVB5SUUPxfLz6l0gI/ZzJrlUCcfmnEdx0sQWwT/122T3mwzCexRQGILfSXd6CWjfcjaSR+CqmrCJFSZq764PmPOUmbrYm0XX4e8Ru4Y5Om7UKaNgdpU4RDkysSNvokkJQQlOjfQb8KARtTYAH/5+cctI7B5iBtgWr1ZwQhcNDyvgQ61tDkSlZ8P4qPqxWZ4ZTLAc6BTuH9HcBpOAbzmBzXZJCrRwN8CEAkolrb5morBEqeiatKinLiFbJmeje+UxLNvNTk6edwrKJV2/AZCeJ8J5I2PelprR9NBU2krW5FBC4Y2FdomiFpY1ull4Rg666pmD7zWeTmLUJl5QpUVa5FYd5afDykO2ZNex6BftOx3v1rvPTsHTiw93MUFvyIkpIlKC1fjpyS9fC3LceGg7OQUOonk5qkryjzx7qNX+J4wASUFq9ARckyVJa6i4ny268fwtxZzyEoYDGGffwE3nmjB+KjF6C8aAVqSlejunQjiou3Y+vuqULamPYgSyogMCt7AAIjlyAi5HsU5a9EUb47dm75GG/9sy38PScgyG8Ktm3+FPPn/AObN3yMLRs/wuJFr2Dzpo8xZeJT2LV9JNav/hBH9k3A6JEPY++Oz1BashZ5hTsxZfb78Apbh0z2b6bqqFWkbeGid3GyZgeqK91RUeaG/Ny12LPzG3z5eR8c3P8ldu34Cg/3bYaVy95CduYiVFasgL1qMWrsO7Bv/zS88+EzyLDHIq1GRU1KTch6xE33X25JAHQgAn3aSNqmzP8W1nxf8YfSv6Nj3Ne71+9N09YQaVOYqBZqHOvERY514hcDEujjqrVismBjlYKKhjRtdUmbYCJdTAysrY8ngn0GgSIGCWmrNJM2RYRE+1cZqsyfxsKSJM0Z3MUggFBFrgytmF6ECuHSx6q5IOd5FKVVkwW6xldD00j8Fi2agckMWmOb8D3YHskyZyi/NraFaPk0caMmjgthLqiZZLlev2moP6njirSRsDHIqknT9htgWZf5EZpI28WSNpIWO+tesmC58ungoOM+RangDZW9REmdj7QF1SFtBCCSQK5SCUAEKO7XWdEa0VL8jATPQZYMcNAETo47SJtS+yuydn7Cps8hyXOK0tppzZ2euBoibfxuAe4yRXQJUAy24PPqa7lVmrafTtoIThefp+23Gz2qJ3tF2vg7hCOtJBhbdv+AH2Y+h9y8haiqXA57xVrkZqzGy8+1xaa1nyIvYwsswavxzxe6YNe2T1BeuhRlpUtRWr4CuSRt1uVYf2COkDYmbhVtcqk/1q//EkH+E1FWpEgbza5HDozE6C8egL/XBORn7sPU8a9j8Jv3Iyt5CezFK3CidA1qSjehpGgbtuyegj2+q5FujzFKN5G0+SPQshgRIeNQVLASpYVr4Oc5DsM/6gFr6ELs2PQF3JcNwcI5r2HB7FewZf3H8Dj4DRKif8SYr/ti89qhOHpgDLJTtmDY0N5YtfR1VJRvRH7RdkyZ8x68w9fKgiKd+d5qYnA8YhN+XPQeTtt3orbcHZUlbshMWQn35R9i5rTnkBi3BFGRS/HPFzthw5ohyM1ejIpyEt/FqKnaiX37puPtD59xFKjXxbr1b6EnSnP/1aQtNjsSQtpubI5pi767skibCWPSuIAjDtKJ3nDT4KJTFmuSakbluGMbXgxp04ti3of35f/EExIxkkEz5tGBn4SH2KIXhkK6DJOtJke8Rp6Rz2mIdvEwkzTX+8pPzfyZxk393vKsEi3vtDwQx4mL9O1lWykiaswZpoU736kOabuoqjqatPkhqsC/ibRdZsL0W7hdE2m7VNLGiCBN2oxwdAdp0wOQ9z6vpu1c0sbVqQYkrc0jSDnU8Y0kbQJkDhW+yTlW+1bQ7GAKi3fuK/OA0sgp04CYB0z3kmcxVP6uNG0ELr4Dn5v72kRKsCJoErQ1oF4OTZstzw/JNAc3OvO3cthNKlfJeX9rKT80UaAzezq1bVzFlwRjs5A2atoWwF65DNXla1GQtRZvvNwRG9w/RlrCavgfm4X3/tUFXke/RGX5UlSULUNZ+XIhbQHWFVh/YJ6YR3W2/czSAGxY/6UEIFCDRk0bSZuPx9cYO7oPju4fjfSEzZgy9kV89kEPFGQsRE3JCpwsXY3a0o1C2qhp2+O7Bun2WFWHUeofkrQtQkTIWBQXLEdV2XqEB07F8I/ux95tX+HHOa9iyfw3MGvKC1g46yXs3zkCkcFTUZDljh8mPILdWz/Ece+xKC/YijFf9cPGNe+iqnIT8oq2Y+rc9+AdoUhbGktM1cQgMGITFi96F2fsO3Ci3A1VxW7ITnXDxjXDMG3yM7BFzkNY0Dy8/EJ77Nj6IYoKlqGibJWQ39qq3di/bzre+ugZiaqmho0BDirPWl2foQZJ29B3cH2rFpixeBxsTHHjIl2IJn56e/k0bRacOXsCZ3EKZ3BWyuA2dnKpk1y3ESk/6vq0BSqzHvGOpj2NgyRthi8riYks1oxxL+bJi9C0URvMBSrxhAtl3peaKlo1GiJtNEGSUImG2ggmc2jajEU3MYx+bqxQQLKmxUzELmbfgZ9CVkNEk8b20ISS3y84yPagFs0gbcR7WejrOcNY6F8W0pbfRNoaOw5+T+ddwaRNJ9dllnaVqV0nMiVoixZC8gYpnzYCAQe6gLYBOoklSrvGwUjCpkmKGdgbS9rEbCAr0BAJc9f3FHW/OSfRxZA2k/bNFQA5gKYOeXNB2uifR5OraeVIQOQ9zyFtxnfKittoExW2T/A2taFB3H4yacvzBR1uU6QwcsPJcfVE6dz+NjRtq1wUjD+XtFHTFoTNu6fih1l/R27efNgrl6K6Yg2Kc9dj9tQXMW70Y1i5+F+YPO4JzP7hacTaJqG89EdUli1FWfky5dNmkLb4En8pkST9vYyk7SuE+E9EedFyVJTwvquRED0b82b8DV+P7Am3JR/g0yE9MGfaU6gsXogTZcsM0rYBpUXbxDzqWtO2CJEh9GlbgsrSNUhLXILtGz/B0QNfYO+OT7BmxevYum4wfI+Ohi10EjIS56IkdzmOHfwU1tBxSI79AfbStTi6bzgigsajqmIDist3Y+rcwULaWGqLpI2atsBwTdq240T5KlSVrEJh9joc956FL4b3wtxZz2LO9Bfxxqu3ISx4vBC2yjJ3VFW6obZqr5C2tz/8q4O00ezaaNKWFYl3hr4tpG3W0u8RXegvKT8kKOM8pq3zkjaSDVfRq0ZUu6qIcAgzFnyN+KTLSNrczp+nzSVpM4iQEBNqk4oMt5FS5dMqpMQ4RxZtXDg20jxKkkfclcUsTaSGtorbOnhkaM6Il/QhJgkjvnG8C/aZNG0aw7X/mCZs3LrCycYcc2CpYSGRucBE2oif1L5pLORzKkJLv2QGSNS1zvwmSFspAyvq5qxz4qc6rpPrNgUi/HK07wokbUlYuWt+nYoI6ZKmwDAXucjTxkAEkjYOcg54tUoLUyZSY/BxQHJV5Rh8xsqJg5WAw4Hv6PBGlBSBh0DHe5K06YhU3otBCvxc1Ow0AfB6TcLq+bTxO/VnQq7M5wqY1U1kq0HIATSXjbQZ5I6rV74DAZQ52wiiBDA+l25D+U5Gj/5E8+glkTYmm2SNxHqaNoOsO34n04R7uSoinAVwGmdxGieRlhcDtzqkjUDIYBjt02YkxeQioSQYG3f/gMkzX0BW7o+oKFsuRKi0YAtS4tZg89rhmDnlWSye/08kRM1BUT5No8tQVroCJaUrkFO0HgGWFdhwYL6Yr/iOUmGhNBBr143Gcd8pKC1chXL6tRW7o6xwI6yhc7BqyduYMekf2LXlc6QnLUBF0SJUl6xELSM6izeiuGAbtu6ahL0+DESIctTnTCk7jsDIxQgLGoei3BUoZaRo3mYUZW9CSf5qFGSvRH7WCpTkr0Fp/hqU5a+BvWSjRMOW5K5Gad5qVBQpv7myvA0oy9+A8hJq2nZj8pz34RW+DtlMcGuk/CBp+3HhezhVtRM1pe6oLHZDedEWFGZvw8G9ozB3xrOYP+tleHtMQH7OCgm6KC9dg8ryNaguP4i9e2bgraFPq6Lfpkz4+rfQfcK8IDObR9/54G3c0KoFZi+bgCghbaqWbf3r9X24dZI2P6Miwq3Y5bdWFYwn2TBIh76G99KkiXgRmXoYMxZ8g/gkmwRZXaqm7fTZ00jLS8AKatrOQ9r4/YJTXMwaSXRlPGvCwTFtHGeutQRGcpqc7HXb8Rpq3UlaNLHiO3KfeMCgL95Hzjfure6rMFHuy8AwjYfGliROTI51SJtaXEq6Df0sWjNoWB0UaaPGzeyn5hoziZ1mkqeJngNLqb2T6H2VONf8jJrU8vn1Ip+fKyKrtJUayxVp46KEvq11tb26P7jeOgMRorSmrdEWCF0R4bgshBPKmkjbL0fFGv9NVzhpo/qY2hmrJNh1VcaKg5Skjc72ko+M+cWYS4hCYsIISX5WHizH+ZlZeDy+JBAsI+QYZAQnI4mk4zrJ3aOccHlvpglhrb0Ekp769zZyvElUKgkdwVJHHhk5gNQzhApZEiDk8XpiNg04/ToUeKlzVa45huEL6DH/kdmsKpq2EGkfPqNDKtgegUgsM4S52NhW5nO4X8Fjql21KcPRRibC5PqYET3aKNJm/MZCyFXlB2YuTywLBR12xTwqmjonYar/nZdK2jgUSdS0qP/P4gxOIj0vBu7bZ8DLsgnJpSw6raOX6z4vV7upZaHYsGc2Rn7zAvYdGodjXv+Gp9dYHPOchEMHJ2LLpjFwW/kV1q39EkePjoWX93fw9BmLYz7jcNTnexw4Nhkbdk7Alv0LkFSkvovfl1oahEXuo7Bq7Uh4eEyE17Hx8Do2AV7HpuDQ/knYvOFbrF71JXbvHANPj+/h6fEdvDwmwOfYJPgcmwJPj6lYvOQT7Dq2WKJHWVydi4+08mDsO7YA06e/gbVrvsD6daOwYf0obFz/FTZuGIkNG4bLdtNGPvPnWO02Eu4rR2DDulHYtGE0Nm0cjc0bv8bmjaNku2njKGzY+DXcN3yLYd+8AM/Qdci1RyKnOgoF1dEItW7H1GnvwNd3Nry9J8LH+3v4eI+Hr9f3OLh3NLZs+BLrVn+NPTu/k/bx9GIbjgO3Pl5zMH/BCLw5ZJDUnaSWTfm0nTtZauLBrYO0ZUXirfffFE0bSVt0YYAKRDDKOtXvS/p/ln1iYuAAm6+QtnZ33oLtPm5IoBnQcEAnUdLC5K/ZUmZLldqKTD2C6Qu+RVxSNM6cPY2zFJwxetuFJwH2yTNnATNpm2aQNldlrPjc+lmIB/Qfc4x5x9hWeEi8FFzUeKixx/g/gUFW9N2tQ0wVadN4Wh9viR9a+L18huQKE+4YSdD53So4QLlhcJ94yGsFxwxzKDFOcJz3MDCd52msq0/OzP9rLOV1PN9B2ujvzOCrerhN8qq+z5gzSoPUYrZOzk+F/xon67bNuX1R9yPzlos+vr9Var8y5Qd/s3p4Uk8xYb6e8x2TwvN63oe4zN/cfI7e5/Hza9rUElWh34X7Y9MZjWuBK5y0BSCN9RFZyqmBgvEcOBxE7MCS0ZqaNUNI5tjBowo48ftLEl6d9dq8VSBSj7QR9CRD9nFjq7Jlx5c5s2bLfZlpnN8n5xrnlAYaRDLQ0OA503gQWPh9FBIiDXJ6S6KkAUoRKXUej2kgcoKZQU7lsxCHycEBUMbKWNqDfibG9+otkxKzXaLyfRBd6GdUiDguz8530mSY36eBoPHbiyFtxm8sJbs4IdvEQTexLERWlJxkaV6lT1yDAMVJtDocEVkeGD9vOLbtX4v8olw1yjQj47YRf/Q6OouTyMiNwertM+AduQkpQtpIKOs+q0Qy1lglH+ChwHUYPWmwaJp+mPcWKNPmvYups9/Fm4Mfw4P9u6D/43fj+x9extS5r2HKvDcwef5bmDj/bYyf8x6mLhyOQ8c3IK2chEMVR08tD4Xbrmn4ftb7mDr3fUyb+56SOe/j+ynv4PW3H8VDfbrgjXf7YvLMNzFl1juYMus9h0ye8TamzfsAnuHrDVMKa2pakF4Rhj3eqzD8m9fwzfh3MWbSYIyZ9A7GTH4LYya/iTGT38CYyW/j2wnv4N2Pnkbv/neiV5+OGD7qNXw99h2M/v5dfDP+HXwz/i2MHv8mRsv2bXw94W2MnfEBguN2I686ErnVNuTZo2FJ8sCClWMwYfYQ/DB/CKbPH4wZ89/DrAXvYPa8DzDqmzfxxFO90av37fj822cwde5bIj/MfQvT5g7F19/9CxNmfIwcu/Jna8g/siHS9ub7bzg0bdF0kq9VyXUb6k/s54q02RBg9cYjTz2GNrffjI1Hl8hYVy4bTpJEDZcibaqwPclbZMpRTF8wBnFJMThz9oyQNlwkaTt9Fjhl0rRNN0gbS1jVL2NlHptc8HGcOzBMMEphIzGR4501Nvm5xgPn+Qq/OP7rExNiAa/R+KBxj/+r+yqs1fd0fH+pxpUAwTeSD1kIihsHE9o6KxPoa0kOBSNl6ySETqx0Jg03EzYhiwYJ5bn8rD4myoLbjIcO/Dbeo8BXarNS40ZrhBaSPd1m9dvG3P4N7bO/8f2seV6IKvCR51KkzYwrJHGuS1sp0uZvkLZAiTJvqA/zeONIW+MXEo2Azyv+lCbSdgHSxsGhBmS4I8qIWik1iEMFXCysr1nkL2BB0HFqsJzqdnN2a/q68J4cIK6EBIqgx6LCEg1FfwwJL3dGOunrSCTM9zb7aZx7jYp60gDE79EAplam9GfT4iSCAh6yIq57zPEOjggstlGkQxgcEFccBGuut7yPBjj9/dzyPeT+DazmGgIngk5SRZhoyi7s01Z3pUkQYyi8kLZcX9GM/Fyk7ezZc5mcIm0nhLRR03YuaXM+bxqf1VgpM0I2KtcHUTmeiMrxQHSOB+LyfJFcEILRU4bhutZXo3XnFjgashaRGftgyTqEyKwjCM8+grBMT0RkcxKleT9KzIqsM5tdG4WUslBE5fjAluWFKENsmT7wjNiDD758G1dfexU++PxVhCbthy3zGCLTj8KiJcMDtmxPMYXrvkitJDWZSWV8Xn9E5/ojKodbP/X8fIdcH8TkBSAmNwRLt8xBl153oGuPLth3fBvCU31hzQqANdvfkADYspXE5PgjqfA4sirDkFdjgSrwHiNF6GMKQhCW4YnILE9Ys7xgy/RGTJYP4rKDsHanOzrd1xV/+OMf4L57NqJzvRFLLWsOz/FGfI4vUouCkCspSzjB8Tc4V8PgkrRlK02bNo+aSZure+hjmrT5G6StdftWcN8/XzBFkTa1iJDJ0UHaqGVT4iRtseclbeyDWswznuhB6pE2rWlriLTpCdwx9utjmCwaAx2aHtH4GwRHj3vip4x7EitTG/Pecl8Hviqc5fnEVRI3rUEilvAejnsa6TdIqDSm8F71n1MsBcQcQ3iuOl/hEM8nLpLMkejpzxva8vt5jSaIfB/+L/OAUQFBP6NsGZBQHiTYHpl1TNxfxIRquI7QDKzbx9w2jd1nGyrS5l2PtDkxRfXtxpA2VV5Q/+b1n4HHm0ibeUT9MvtNpK0RpM3cWdlRdSfm4OSqyJLrJVuaQHlMBrEJjNSqhoPEEKOgPFXZjmOOfZUMklo2AlS84Q+n73vuliBhlnOJletrFLDw/gQpBVyNufZ85/A5SEiVkMDFlQTBwgmyyF/MCGxLlTWfW5PUaa9zJ0vzb6D2naSNJs7U8wYi1AWsX4K0uSJrekibNW2uSBufzywkbam1ViTWWhBfHYkkuyLGTAyaWR2LohOZGDfnOzRv0wK3dr0JIYlHxEk7jefZrUi2W5FotyDZbkNKdbTUn1WO9jRlMmEyEyfbhPikV8aAklYRh7DUYHw15Wtcc901+Hj0e4grDEZ2bYxo6cSUa1dZ4emjpAgbJ2FV9kdKQHFhUmUS+uaJcKKkST8KafY4rNm/Et363YN7e3eDb5wnEsvoWxOFVLvN2MYgzR6DdHs0Mqss4svGou65NRHIqaafl01SdaTYo5BUZUNylUW+lxNgpj0EWXYLNh1ejU497sIfrv4DtnmtQWpVFFIqo4x3tiKj0iIVFphMWmk7G0/a4nOtePuDt3B9q+b4YeEYVXvURRCB9H2TifFc0nYj1h5ciDimDmJyWMOXSSZHo3yUJmyiaUttnKbtzBlq4VwtHmgaratpayxpU2PwXCzgcWqZtKaHBETjj7qmMWP73HN4D1oGLLmeQkZIitgu+t6Xc0tCSOLD77ic95V70aWkIljewZbrJT5/ytSu/AX13KK3F9tmvO63Ttpc9UWNjU3bC7fAFU7aDJ+2Wvq0kYw1bL9vaPCQ9FhyfRBfypWfIi2KiNUlCmp1YxyrVmRNT8x1PuMKv9oiOXasjvsSHM3ETO87CZImSmqrP3e11ddEiqYqrjgQieVcnbo692KP6Xtr0haB+BKlaeMqmcRQETZVWsW5fy5IN9TezuMGacv3A9sppZJkwfVEW799eR7b6VI0bZFZHpgwf0Rd8yjHWb058cSJEygrK0NRURFOnTp1zqRJp/GM3Fi4b59paNqChUAxYtEs8qw1VqSQtJ2wIvakFcm1VnGYz6qOQm5NHEpPZWL83H+jRZtmaHPPDQhL9kBmVYRRQ1P1uTTWi5SFgTKTkJhk1EQpqWbFC5KxWGQxbYdIPKwZIRg7awyuu/46fPrNYKnRmH8qDjm1NuTQH0sKqzMYQJE1SU/CfVO9Rqmd6iBymtBxy+v4rjFYf2gl7u13H+578F4EJHgitYITmBWZtRQbMmujRZi4N6vWiuzaSGTXRiC7hu/I+3A88T2jkFYTJfvKnBiO3Npw5NVEYfMhd3R98G40a/dnHAjaJN/L7+Z7Z1RHSXvq8aj6Ee95br+sq2mLRE6NFYkFUXj3o3fQ/Prr8M3kzxCeccwgsXWv54SqHfnl+cSnjeZRHzz81EDc3O4GB2kza8/1daz5SVJJIWmOSD2CaQtpHj2/pq28vFz6IfukecL8KZo2Z9so4mb2SVWkgeY5LqYuF2kjXoXIApn3FdJmWCwuN7Hi8xOv+H2X+970PeZ9+Q4kbZIGSQeimRQCzvat24cudNxJ2uqbR425R8YJ9133b2J0bLE2j14OTRtNo2rRQBwsKCgA+6MrTLwwXWk6gy1whZK2BeeJHtUTQP1OXv9/nmcRsmbN9UVCaQjS7OZrzT4E9ffVver7L4lvnZA2K6IL6AzqB0bw8L51SdlP+z+92gpqYZLKQxFbh7T9tPvWJ4wpVQziCIRVNJHKf8WhZTNpHAg0FwKjcz+3SG42+qORNJN4ktieex6P1f3tLom0Gat6S/YxTNSkrdjwaXOBJSRsBw8exKxZs2CxWFBSUoKTJ086Jk3Gj2bkxhmkbTNSS4OlHqgqVm4RIkIyQm0syVYK63mesCDxhAVptRbDv8mK3NpolJ1Kw/i5X6NFm6vR9p7rEZ7sgawqkhpO8noxQp89XZqJ/ZR9klq3aGTUkLRFI9ss9lhEZ4dg1oqpuL51S3z6zXtIKQ1H/skY5NZakEMtV004smvCkcXajDVhyJAKDgZpq1XHePxcYSkzRSpJwtYfWo77+nXHfQ92w/F4D6RW8p4kZhQLsmttYICDEqv4zGWKlla/j/7d1fjj78vrc6ojUFBrQZ49Cut3r8DdD3RGv7/cC7+ovciuiRbJJGGjj6NhhlamaLNvo243tT2XtNmQUhyNYaM/QfNW1+HdYf9EYMIBpNvDpNA4NY9O7aMirSS5WWy72ghkVdvgb/XDw08/htbtb8TGI0sk6tI5JhTOsB+YyTxJW3jqEdHsxSbH4vTZMzgjccnnZmqLjo7G/PnzcfjwYWRnZ8Nut0O0b4xk/kmaNt3udbcMpLDm+SCK+epYm9NYcNYfhxfzP7ElqSJUtPa8L10vMrjY1hYK0e5f7CKz/vkWwUUuxGOZroi1QcVyUv+8n/C/PRKJ5SGw5fsKLtKcm2Gk1eBv7vzd67apa1xzfQ41hXStoS8xTbJqMcLxbsZB9qtzryfJph+yDkTg+zf0TDx+IfMocY4rWvY3krXFixdj1apViI2NRWVlpZA3F/DZdOg8LXAFkjZde5R52lR0jfIfYeckWLNj1ydZLv5n1Gm11SBtPkgoDRZiVXdgmAfJxe2TjNDsJ6TNZHK8HOSNmjyCKTVNMYXMa0TzKIHocpE2tfomIBEAInM8kVBurNouEFHnCkhcH1Ph6fElNJloTWf9SVyDUt2216SNbUvC3ahABAJcdQQs2Z6YuICatjUqEIFmJxGlbaMmg1JYUIBJkyahZcuWeOKJJ7B8+XIkJyejurramDBJ2uLhvn0OvCO3Iq00GNnVigCRBGnJqAlDem0Y0ign1H52TRhyqsNFcmsiUXYqEePnfI4Wba5C23tuRHiyFzIrGWmoSFumQaCcWi9ODqqvK40bgxK0g7uxtUchPi8MK7ctxs1tW+GzbwYjtdSCvNp4idhUZrpISP1S1jCtJgkjGTOL1oRRG1ZflNYou8aGDYeW4b5+3dD9wW4IjPdAWoUidGbSRuKmRJM2cyFsjl0lJKZKyxaJbHsksisikFoQjm8mfo5bb2+Nj0e/AUuGF7IlEIPvrUgbx21arTJDO8sGGcmNzWTUSOWjTVo5NTbk1CRjycZFuOXOm3HfgC44KMEedat/8P35jCqpsUEASTyro+ET6Yf+gx5F+ztvwR7fdUKOGSiSwXq/1VEOoUaQvxOJZqbdhvCUo/hh4XeISY7FqbNnJAqUUaQqKMHpx+bj44O+ffvirrvuwqhRoxASEoKKigqcOs1rfop5VI8vteUEz7GqSJuvWAvoIqFxRWGjCyy9IN5SM24VywDHOjP9K9KmgorU4ldpz/V3XdqWi1mLLGSJCfSZvbT7NIyjxFlaZRSp9RXrg2t8q9u2F3MOtZDiE21EgKrFbF0MdKVpIwlTpM3PQdr4vbLQdkHwhLQJnkdIUIX7jipt7ysAACAASURBVAXwCDiMwvISnJJgK/ZBRjWfwenTp0XLRixs06YNXnnlFezfvx+5ubl1FrPn4SpNHxktcAWSNuZpo6bNXWqziVpfMs+bSVv9Dt7A/y5Im1rVNHB+nZXOec6ptiCGpC3fTwjV5QYOIW32SNEO8jvod3b5SJsBWMb9GSSgzRkXAzwXPld9D4GV38H34ApZJg7tGEzNkvgPWoRgk2RroaaR2lGSNra1DkQ43/fy3tYckraR2LzHDVm56aDJyZXk5eUJafvzn/8MStu2bfH6669j3bp1Al4nTjEQIRmrty+Cd8QepJdSM2Q1NFjUYikRMyBNgYbweF5NJPKrLSIFNVZUnErCxDlfoOWtV6FD19awJAcgpzIWufYY5FTbRONEQihijxAyQz+vLNYKraJYkV1lRU6lU7Iro5CUH4nthzehTYdb8NnXQ5FaFI08exJyKuOQXRGL7IoYZFdSopBdaUN2pQU5lZEi2ZVWOZZVGY3MyiiHZFVFQUk0svl89lhsPLAS3ft2xf0P3ouQeB9kVEQjtzoOuTWxhnDfkFqaZ2NEWAkhu4YVEWzIrrGKZlGZbC0SUMD3Ty+24ZDfDjz6l/64ud2NmLxoNBKLg8QPLqNamRmFxBukjcSNmkzlT0YSojSHYvql2bcOaVO1R/NPJOFI0D48/uyj+NNV/4OvJnyMgOhDSCqKRFqpDWllUUgrj0JKeRSSy6OQWKEkuTIaaRUJ2LB7E+7p0Q2du3bEseP7kF4Yg4yyOKSXxSG1LN6QOKSVxSK9LEYkrTQaofFemDp3HKxxVlTX1qDmRA1qRWrr9Mljx46hV69e+OMf/4hmzZphwIABmDFjBuITElB74iROnTnlyNOmfNoOixbLVfRoQ1oX87hxkLZ8f0PT5tSAXuqilhjIsS6kjWXrDHcItchW4/qy4KQ9UlIAKezVbiMNk7CL+k57JFIqI+T+JG2MhtVE19x+P3WfJk6ad235PohhGbEKpoUiBppFLULNARTcZxAdo355Lc242oWloWfi57wuOs8HJG2H/Q4ir7gANQ5crMGJE7WyWKWW97HHHsNVV12F6667DnfeeSdGjBgBT09P0cKZTfdNDK3hFrhiSds2fzdZ7VB9nGwPRbJdpbSgSY8T+DlSGSF+UwQLs9C8SCAh8eHgMH/GfQJNo6Q8TPKGUevF/GHKPOrrMF/S/MfjdYXRn07hOXW+i/fkdfVEzikPU5GdRp4y87X13+Fi/+czsV2Y3JH+ZjSRsp0bGviXdlxNBPydYouOC/mi5pRASMBSaUiMVCklQaBGTgt/K/ry8fnUJOAvvx8nG1dpUmhuEOfk0kCEph3CmJkf4/MxH2PK9ElYsHAhFs5fgIXzuVX7C+bPx/Tp0/H888/jv//7v/Ef//Ef+K//+i+ZMDt37ixA5eF1FCGWACxyn4UVm5fggN9eHArchUOB2+vI4cBtOHR8Gw4GbMWhgC04HLAVRwO249jxXfAI2IEjftvgGbAHQ4e/jetuuAq33nEzNu10x2FffrYD+7w2Yc+xddh9bC12HV2D7YdWY8sBN2ze74ZNe92wYfdKrN+1HOt3LseGOrIS7puXYfy0cWjV+kY8+9JfsHTNPKzesgTumxeLrN68GBT3zYvgvmkh3DYtgNvGeYYswKpNC7Fy06I64sZrti3Fmu3LsG7nCqzfuRLfTv4Cd9zdDnd1vRNrt6/Efu8dOOy/2yFHAvbgSMBeHD2+F0cD9+JI8B4cCdqDoyK7cSRolyE7cCRoh7TXft+tWL9nFcZO/wZ/ffFJ3NK+NQY83Rc+tgNIrTQ06sYkJqZRIWta29YwadM+aaJpowm2hqbiaMTlhGHW0mlo17E9unTvhOde/SuGDH8Hoyd8gXHT/43xM7/D94aMnTkG380cgzHT/40RY0Zg4JMD0bxFC7Rp1wZfjh6BSdO/x+SZEzBx5gRMmGWW8Zg4axwmzhqLCTPH4svvRuJv//grvh33DWbPm4258+dizvw5mDtvLubNm+eQYcOGyaLh//2//wcKFxHUdvzz1Vfh5r4GicmJSMyKwbKts/HDyi8QnLbfgXVJTA5eFSpCDc6FhMECDKTQBcuJV8kV4UJW6HdKETwhVppEYdK5WOXArrIQ8Y+NzPGWMUt8oXuH+XMHFpYyT1rjxHG9xs5yaqnUgpkaMVeYfl48rGgY82mNoWWDi8zoAv+fAROdGk/+TrRy2AwzNXNRss2IeyIlgY7UVTqtCrdyTb63aNqIpUxB0pCo6xTWRmR6YPmWOZg6bzKmz52JOfPmYa70wTmYN28OZs+eLYvYTp06CRb+53/+Jyg33HADHn74YUycOFE0wDShNpG3hgkbP7lCSdt8bPVdidAMD8QU+iO6yBdRRTST+UkJGg7axgpV9Uqb5O/yGn7eKMnnAOMKRwnvSUJBIRmR4/y8jhjHjWtIQig8V2/rnq+uV+c5v4fPR5JofudGPXMD7yb+GtR+GYSQwCfRgob55NJIWn1zgSJt2mxCQOL30RfjXPGR34ht6pBcHyF61LSpNmabKa0gNYOuhKtP//g9+HrKEAx4qhc6demILl3uRpfOXeoIiVnHjh3RqlUrASaSNj1hClDdeAOee/FZLFo5D5+OGoIHBz6IPo/2Q98n+qLvE31E+j3RB5T+j/dB/8f6oM/DvfFg/wfwUL8H8NCA3uj3yEMYMLAvBjzWF48+MQB33HUbrml2lTjD9xnQC48O6otHnuiL/gMfQj9D+j76EPo8/CAeHMB79ULvfr3Qq28vPNC3J3r1qSd9H0CPB3vi7vu64roW14m27d6ed+P+3veiR+/76sm9uL9XN3TvdQ+6P9DVEO53w329zHIvuve+F/c/eB96PNQdPR+6Hz373I+77rkTLVs1xw03tcRDA3phwOP98MigAUqe6I+HB5nkyf4Y8GQ/hzw8qB8G1JG+6M92fKwPevS9Hx3u6oBWt7RCv0F98eP6Bci0xyNT/PjO1XQrLZsNqQ5NG/ucWdOmTK+auInfXI1KeJtREYPI1FB8N2McHnn6Ydx65624/uaWaHt7G3To2A63dWqP2zoq4f8d7myHdre3QatbbsA1za7GVdf+GS2ub472t7fH7R1vx+2dbsdtnW5HhzpyG27r1EGkQ6cOaHt7W7S4sYVc06lzJ9zV+S506nyXmEFpCtVCgnb11Vc7+iD7Ivvk1ddcg/t79MRytxWwJYXhx43T8f2iT+EVs1X80UgsbEw9VOgLGx3nC4hFroU5wfSY0eOfCzbij+CLCVNdYouBWxr/XG2j8v0UJuZ4y1h33sfATcGc+hjZ0P/EJ4559XzmZ9RYa8bDxu0TRxvAe2I08SdXmY1JMC8PDtbHRSdxY5Sq8k9T84gQXoP0MqKfkbgURvpqzGQmBC08ZqM08JvzuD4nOOUgFq6dhmf/+Tfc3a0rOt11F0jQtBAP77jjDumHf/jDH6T/6X74pz/9Cbfffju++uorcSGh/1vTX8MtcEWTtuC0w9LpLHmeEMn1kpximixxy44ekeWFiGwv2ecxIWlCjDjgTaKPObYkVY0XAZB8P0QXKOH/jusNEuT437ivAh3n+SQePEdv65+vPjMIigAWryXYGPcoqPudiuTwnRsSEiGCs/5eEl9FfmmuTGa9UnFENqLMXPhGXBp4kbQ5zS4khdSUUctG4SrRKfy/rsQUBUALa0UqYRuQvLsWTkzHE/fh22kf4pW3/47nX34OL738Cl556WW88hK3r+Dll17CSy+9hBdeeAHdunVzkDZOkgSr//3f/8X999+Pb8d+iw3bV+NfH7yIWzrchNZtW6HNbTej7e03o93trdHujtbi49Sh463o0LEtml/fDP/xn+oef/zTf+O6ltegze2t0fn+O3Ffn664t09XdO97D3r074oeAzqj54C70PPhLuj5cDc88HB3PPBID5GeD9+PBx7piV6PPoBeA3ufIw881hu9Hn8QvR9/CA890Qd9nuyLBwc9iIee7IGHnrwffZ58AP2e7IX+T/ZCv0EPGNIT/QZp6YF+g3qg76Ce6DOoF/o82QsP1ZdBvfDQoAfkOD9/8Ime6P1YN/R8pAseeLQbuvfvivv68Z264J7ed6FzzztwZ/cOuL1bO3To0gbtOt4q737rbTdDpMPN0oa3tL8Jt3a4Ge3vaovOD3TEAwO74/HnH8Gn3wzFAb+dyKhIQFZ1nETMms102sTm1LgZ9Yilryr/MxXEUZe0kbwx2IOm2ZxaRt0mIKHQhoDoY5jy4zi8/P5zeP7Nv+DpVx7Fky8OwJPP9xd56rl+eOq5vnjy2b4Y9GxfPP5cPzzxfH8Men4ABr3wCB57bgAGPtdfyfP9MVCExwbIZ489/zAoD//1Idx17x147Kkn8OJLL+MfL71sbF/CP4x+yL44cOBAtGjRwkHa2BdpKm3brh1efe11HPM5huScGCxcOwVj5n4AD+tGRGYfgyXHC5G5nojMPWYIJ3niIHP+HUN4lodsuc/jegLnZC74IySF2KAXngYWmhdPjdg3Y4vCSBeY6sAn08LsvPdWeKZwUpE3MwYqTOQiWH3mCkfNx1zjo3kBqTAytoi+cjS7Kv+/S8M+10TN1b1o4WDggw6uMGOeJtncKswmbjuxj1Gk+jjJnyvh5zTBhqUdxpINMzHks/fw6r9exWuvvobXXn0Vr776Ml7958t45ZWXxfJw0003CQ5qPKQF4sYbb8QzzzyDTZs2obi4uEnT1jBfk0+uWNK2zX8VInK8VMWAiiAksvSSVAugCUCp8Kkep1aKxIWaKKqVqeKmKp/niLq/XiJIDpLfutDZtCHhs2sTCH0aGivJFcp0opJbqiS+9NcwiytQuZzH6Mvxk9vekRxZJ0l2bplsMzJTVURYsWEBwiwhSEtLR4ZIBjLSMpCRno60tDRYrVaMHj0a11xzjawqSda6dOmCEcOH43hgIAoKCxCXYsOc5ROxwH0Sth5cht1eblLDc5+vG/b7ueOg/xoc9F+LzftX4IlnHsZV1/wZd3S7DaMmDIP7zoXY67cBR0K3wSNiB45F7sSxiN3witgrPnI+kXvgY9lbV6zqf1/rXvha99URH9s+eNv2wcu2F15R++DtUvbDJ2of/Gx74W/bYxL+r2WPfO4btRe+UfvgE7Uf3hcQH9t+07Psha9lD/j8XhG74BG6HYeOb8bBgE04ELAR+/03Yq/veuzyWiuyx2cd9nivw27vtQ45ELAJnhG74B+1D8HxhxCT7Ye0sgjx4WNOOu247iRuKlqU/lpmuVDfFEdsSePB1CXMmReJNCZ3pWmqwA9h6UcQnHIAgUn7EJC4B34Ju0V84nbBJ26niG/cTvjF7oS/Q3bJ/76xO1FXdsE3di/84vbBL26/yF7/NRg94TN4+nkjNZX9LgMZGdnIyMxCZmamQzgZ3nPPPTJZcuFw8803y8Ji27ZtSElNRaW9Ahn58Vi6aRqmLB2G4OTdUjs4pZzjn7gYqLZG/jJO1CRuJGqcyCWnmamiCjFAxmFlGFK0mHFRH7uIbX28OmecX8S9zM9EzNBSP+GuPi5Jys3PX3/fbDYmDroQwUUjjyf7VWN8Ay/U/xr9ubFo5nvwOTS+X65tSmUIonK8sXrbAuzYvxkxcdHIzMhEVkYGsjJSkZWRjvT0dMFE+lPSZYT9kNrfxx9/HD/++CPi4+MlOIYBC01/52+BK5i0uYmWTOo6VochlSJJQp3RTiRtXOVx1UXfDPpP0fHUDPaNHjiXTcPU+FXWpT6bmWg1Zl+cWc0THp1THe97uTVsP+/7u3pf9X6qgoWk/FgwEpv2uCG3MFtFgp45i7MUI3KU6v3CwkJMmTJF/Nio+n/jjTdkJckI0traWqkVmZmXBLet83AkaAvi8wKFWKSWhyGN6UvKw5BREY60knAcOb4T3R+8Bx273oH5q2YiNNELicXhSK9UiXEZaZjJKgdMPmuPVo7+LN5eR2wq8IDBB3YbMqsoVodkVDFy7kJik/qiTHCbWRV5QcmwW5Fut13wvhn6WSqtyKSYnov7THzL0lsZFRb5PKPSirRy1mONQHp5pAg/F6mIRHoFy2jp52MABlNrREqt0Ay7jhA3m0fN/fXi+pcieYr0URsnE79RVUT3G51EOp0BTzynmkRBYU5aNSMUVXJitc//6wsz+PPeOqCGbWpBqESPjkVMYjxOn2ZaBYoRzGzqi3T07tOnj2jbGL1Hf0suKug/dOLkSZw8XSukbcXWmZi2YiTC0vYho1oFXaRXU1POMnPqGVWOMZrbFGEjeeKYcY73i2u/X/s6M0k/3/4Fn1MHP51ve55IzAve34GnF9e+8k6OgvMGFsvvVVeDrDXJ5245H6rrXG3l/OpwxOb7Yd2uH+Hpfxil5SUKD5nU+cwpkVMnTyI/Px+DBg3C9ddfj+7du2PkyJHw8/MTrGTetqa/xrXAlUfaCpOwcvd8ydNGPwXm+kmtCRdRnVKRNonyKQxQjvTFQSq6kNnj62RMJ/BfOuD/XAPVfF9XA+1Cx8zXN3bfAXgMAXeQtt8vmJvfWwEff+cIsGQZk+tu2bsaebr2qIuxVlpaKjmJCFKcJKOiolBVVYWzhr8GC3sLadsyFx4h25BYxHxNUbIokIUB03VU2yT6cOHqOejQuR2ef/UZ2NICkVkRJTnVsmqikVUbDUk6y30mn5VoSkZURkmJKpapMgurB7gSVkZgZG0q08E4ttx3Cv0HGYFGjRKLpast911LhqSQUekazPcx7/NdeR4JnhAqkipDMlkH1JCMKgso6n+1n1EVKcf0Z7KVayORYY9ABpM520ORWa1EERFqOcyE7ecdw7rvCHGro2ExT5qciFU6EKmEIPn06n0uQRN8VqbMYD+xISztGGYsnoC4pAQp/K4WDTr1DMmbWkgEBQXhtddew9ChQyVSTyd85uLi9NmzOHmmFul5cVi1bTZmrPwcoWn7wCoXDLZIF0JpkEh7uFgmmHeRecAYnEMs0Ys285hp2r84cvVLtdfP8ntVR4imzX3bAngfPyqkzQmJp4Gzp3Hq1ElJ8DxkyBCJol+/fj0yMjIkytl5rtprCkSo3yJ1/7/ySFtRMlbtXohtfqsQVeSPjBMkbQRMXYJKkTZGPNEhlY6j1LIxRYQmbMq8QvD8eQH/cgzkCxE0V59fyvc6SJuxItT/X8q9fkvXqPegJoVh/+EIzzgiBeN3H9mEorLCBv0vqE1LTU2VxLrc1xOo5HSTHOGnkZmfhNXb58MjdCsSi+mYbEMqE+kykW8tk6lGIz4vAv9463nc1PZGfPTFO8gotSG3NlbKSQlhqzWImpAznYD24rdM3Mr+bCZUrvYVyWJ+sQhDG8PJ3ZXwczWWXN3HfIxEUBO1y7NVz0fCQU1RRjUJMbe61qUmPzpn2K+78NJjpeGt6n/8fdKYCLiWpM2KEBaM/3ECktKTVapAV6Wqzp4VDQcT7FL7q/sht6KZOwucPHMCWYWJWL1rHma6fYGwdKVpIxk3kzZaIkjU6LtG309q2ThW9XObx60+9lvfmp/5Qvvne5cLXcvPeX1jzvu5zjnf81/cZ6o/6muoNY5IP4ql62ciKNJfzO1SIUb6I82dZ3DmzGkhaFy8Ehd1RYQmglaXkDXmvyuHtDH7N04jqyQNaw4sw2afFbAW+CD9BCdI1vlTWiG9CmcouAQZ5PuJDxs1aoq0qcnt90DYZPDrlfDFbH9lcPm5QOvS7ssJnb95pBSQPp6wD+PnjsQRv72osJeLedTVQCMYEZjqlw7iuSwfdOrsSWQVJmHj3sU4FLgB8UVMPmwVwpbCRQSrHtRGIz4nDAP/OgA3t70RX3z3ETLLrMq8qUtQOSoFnEvUnAlpdWLahrckbSSmKq8dJ2tXovI8KWJFbdaFxfV9nPeWxJ/MCN+Ie13sOfxuycbv0GJx0tS/5+9nHOvJkc/OGrSMbk0oD8XRiO1YtmEBsvOyXHVBOab7IfuiK38h3RdzS1Kx+eBSzFj1BULT9oqW0hVpo/8aIwpZS5gkrqHEq5c21n5dUtP0zI1tf6UFln5Zy4S8IQhK2ou5KycgKiFC8gXSXUQtUBVpY4JdanZZFUYTNvbHJtLW4NBt8IMrjrQV2vNxKHQPlu2ZhZDMw0irDXcIB60ibRaJuNHRNckVKjxbZZEn6GtpbCdvOu/3CIjMjK8SrTJ/VwTiS4/jYNAGTP9xLIKtAag5WSN5vxscXef54PTZk8gvy8AB341Yu2eOmBdoGiNhS+Ei4kQksmqjkJgfjoFP90Prtjfi35NHIK86DtmmLP4076v6nKzRqet1smqAkmyp1cl6necXVTKLJKdh/xVFsBqvFVOk6Xz3c/rYmJPWXq599jkmyTWL6od6/Ortb3t8OklbJFJr2T/CYc33xbqDS7DzyBaUVpbWL33r6HmcFOuL/pDHObeeOnsKZdX58AzbhSlLRsA7erMEU9Q3j1KjwtxcJG2M0BZTW9MC71fVnv06uKoqhbBsHSWxLACe1g2Yt3I8UrLicfLUCZw9bThXShkr7qv6o2aS1kTa9Ei8uO0VQ9pkRYkzKD1RivDU41iwZTI847YjyR6MVIO4cQCItqGGpC3YyDvkIxoW9dmvr+L+dQbpb3tS+7nahDU/qdUQqQmX1AXrDyyB29YlSMtLxcmzOtKJvYvS+D/Wiaw8UQJrsj8WrR8P76gtEqXHvsiJOf0EqyBYkZIfhsef6o9b2rXCmCkjkF8bD/qyiYne8B90kjULMmlWvQQhMWA7np+0kWRRS6Y0bhfeNuZ+TuImvlEXoxG+wLniH+aStP3++rP+fVJPhCOpOgQ+cXuxdNMchMWGwF5rN/qf7ofOvlifsNX/n6Tt9NnTqD5djrjsMExbMRq7/Fcgofi4+AWKebRG+bQJaWOmfYO0Nfmy/f760eXBSk3aaB4PhTXPAzt8lmLNjoXILc7AqTMnJRBBomJckDbdB11pfhuPoFfumVcMaeNPfBpnYD9TgbTSWCzfOR1bfRcjqti7DmnTWjRm9laatibSdnkG+u8H4LRmQ0gb/bxqI5BkD4WHbRdmu/0AzxAvFFcVS71H5UbEZJAU52R5IUhhge/as7UorM7E6t1zsP7gHFhyjiLjJLVsJG0sKG5Bal4YnjiHtMUgXTL4Ky1SxolIaGEhdYecYEHnxomjdqf4gdEXrGFRxM4wPWoTpMutcmQ/372Uz5SOnry8W/FV/T9C2mQM1kYgtSYMtkIfbPZYCfetK5BfWiCTpLP/aeKmeqCeIBvaCmnDGZxANfL+P3tfAZ7Vla1973/d587csc60Y21n2ulQoF5a3N3d3YuUIqW4U9wCIe4Q3AkRIPpJEiS4hLgTiOv7P+9ODnyEBELyfSGyTp79nC9H9jnn3evs9Z611l47IwqOx62w9/BGBN85hcjMMMTk0xr5PGnjjCNC2upOn2b+PpwuUj3uZgbCL+Ig9nhuhHfIcaRlJqKwmCNGn3WPmlraNFkU0vYyLVH+/gZF2opRjILibDwqiMX5y56wO7YKZ8IccfNRkJpzjYHmKgZHWdr0TzJ8Mz+XRuZkrbmU6tK68p1rCWEzDfy+jLtZRhhizsGeCm2/Le4nxiGzIFt9BJS8Vhphqzxp4xkFKERmYRou378A20PrcfDCHlxP88e9HAM412XcE9LW3MTSdqvU0nYJKoVEXqgieSVEr8RCF6VIX8lvWuwqVUqtzfdzDHhxMaqBOyRELy8clf2y+l5tf2SOAZUrpffJmBuT8uBJ+oPKy4T5Fd7Lr619OGghGVwzV9mN1Is4eN4aNvu2wXDZgLyCfDUhd8kHg0bYnsqhpiArWlO3FrFfRD4eFzxGROxl2BzaBofjmxAe7YX7mRwhalADOpjOhGSNAxHEPfryNnwdcmOJaz6VxRJP01OZ1MEYdRQuZ7bB7ZQDYtMjkV34WKUzUt+vJgMRhLSVT8CqsrVBkTZ2bEXIR25xOmLTI3AywAn2RzfAO2w/bqQEqy9L5R7Nvow7j4wqsS6T63IaJgaJ0yVVUYnOuQIptRGD0sSnKglqOLQpiMqutY5JKXVOY8TBB9lX1DyVoZE+8PDaA8cj1gi7dRkZ+XnIKy7gmKjSd05TlpV/BXkGz88rzsLD3Fj4h5+C/aGN8PS1QnjMOdzLCFHzWt5PuIR2nVqUkrZZiM+5iZjsCJXMNSo3DCympEzbVpW1mhSd0za9tJimo3jZb747lamz8sdE5YTipUUbKUqSVlq0fGlaW9eqdW44nt6fNjqvdPATU7A8YloFfxz0tYa1x3r4BJ9E2uOHKFKKUZM/03WJLFZE1rTtJaRNk8UCPMx/jKCIC7DevwHOJ7cj7IEX7j4KxoMso0oDwnko6R4ta2kri6UlyIPUWbNEkW2q9ZOcso0lmil/si7jXnoo9HdOwuXkJjgf24XwO6HIKMhAQXGu0rJPnQ7sI0vi2zSZ09YyXVXl9YXpkQ2MtJXQNhK3vKIs3Iu7heM+HrDx2IBzhoO4GheAe49CcT8jHHfTQ3EtIRAR8QG4+4iKiYTtKqLLKTHZVyGlNmNwWXU4WsdT3pqdE5U7rTJ3WDLCcCvVCP0tb7gd3w1b923QXw1Cdn4u8ouLlZWNFgqqyaouPJ8jmguRj5SMeASGn4GV8yq4n96FwOtHcTMxEDdjwtG6Qwu88btfYuHqWYjJuKYS6T7IonvSiMgsTolTUvg/lWtJfjLmKKunJTMUUS8rT56d+dpqd3mgEueG436pi5lTHLFwxhV+PEYkBCL4hhc8z9hhp8M6+AafQkJatCL91ZE/Ci85n0b1qF7zUIy07EfQXQvCTpdNcD6xExcjDuJagi/uPAzGzdRAXIn3xe2HQYrE8d5Z1OCRUiVPZS8Eq7ZjQJ324g8lfhhF5zAxdagqUZwJIk2PG3FB8L90As6Hd8Dp4G6EXjcgPTsDeUX8kGWcb+WkkuRNlldHoMGRNg0iikteYT4exN3BwROO2O6wBm5nSQRevwAAIABJREFU9uJCxElEJHK6KiOuJgTictxF3EzT424GhzZfQmQGp6opLfw/85IieSR6Lyw87mXHasfIugQrc+GQQQVoAKdbebZwW8l2usDvZOpx43EIrqQFQhd5DscDXLHVbiXs3Lfhyk0jsvIyUahc7OrbUbmVqOg0pVf5Lkg7Q5NG1leIR9nJuHpbD3vPndjhvBYep+zgE3IWX7b6HL968+f4dukU3EwyqJxu1zmpfaIPriR4l5REX1xNPK9KRNIFsFyrQtHOrS/rshjUxudiaqErLGpydn9cTfZHaKwvAu6cwrlLB+B0fAe22q+GjdsOhEaEICM7vfqETRM9TRRLhZfyzNz0j/OyEXo7FNYeW7DNcSlcTmzCxWsHYYg8BUPkaVxPuqCm7NJy9CnlrkhbCRlQeS+Z+1JKLcXAiMgcPSJzdBUWxqxFZetx71Egrif4IizyNAKuHIbH8V2wclgH90O2uH3/BjJzclBQSv41sZK15RBosKSNkBYXFyIvPxMp6TEIveYPzzNO2LNvC/Ye3AqXs9Zw87HF/ouOOGnwxNmwQ/AKO4RzYYfgHcZ5Hg/DO/wwzoUfxlmWS6Vr7f+ya+5/2TFlz5H/S7CtJg5nwg/gTLgnzoTvr7CcDtuPE3o37PO1ht2xzdjtsR7Oh6zgG3xCJcHNzHukXKJUaCWZhzTi9nRdedL2/Aut4i0LC5CVk4X41Dj19Xrs3BHsdbLGBx++h5/87L/QY1BH7HbdjL37Nql5Ind7rIaVx2rs9FiFHe6rsN19FbaWli3uKyGlDmDgtgpb3FZji9sak7IaW93XYJv7OuzevxkHz7nCEOGPuJRIZOWmo6CI9rDqSFsZ+TMhbvypiFsxRzdn4EHyLYRc9caBMzbY474WG2wWYoPtD7Devw4eZ3fjgM9eeHpb44D3XvVb/e9jA09fKbUXg73w9LWGp+9uFY7BkIyKykGf3XA/uQ22+9dgp8NS2Lj/iCOnHWG8fAFJqVHIzctCEdN5lBEp+ddyCDRo0lZiIylEUXEuMnNTEZ10B6HXg+AVeBxWrlsxY/FkzFw6Bbtct8DpiDVcjtnC9Zgt3I+z2MH9hD3cT9rD7YQ9XE9KqZ0Y2MHlhA1cTljD5cSeZ4rz8d1g4XbXE9ZwPrYHDod24fA5d4SEX8CdyOtIz0hRGeMLOBWLCtimJYKxkU/Jmva7Wh1XqeKky4AjS7Nys5GUmghjuAEtWzbDL375M4ydNBJ+QV7w1/vigt4bF3ReOK/zgp/eC766s/DVn4G3/jR89KfhrT+l1vwtpRZjoDsNH93ZJ8Vbdxbn9GdwIdwHhhvBiLh3CTHJD/A4J13FCxUVmw48ML9iKBVDJd8cbV9QlI2MnBREJdxGSPh5rN6yGF37t8W8ZTOw/4STKh7HHaGVffx9gsVJSq3FgO3jAI8TdvA4YfvCsu+4LY6cdcX54BPQX/LDtduhiE98gMysdBQV5T/rX69WB2h+Wa6vNTZw0qY1q7JzoBC5yC/KQnpWCrz8TqFdp9Zo07EFjp89gqu3L+HGvauq3LwfgZuREbgVeQ23TcuDa7gtpfZgUNo2tyKv4FbkpSfl5v1w3Lx/CTfUuuT3zfuXcSsyAvfj7iDtcUpJgkg11Q9UAlLO0WhaNKJmuq5Wn6VpS+VmoDyW1JyWlopuXTrirbd+i2UrliIzNwu5BbnILchDTn6+KrkF+er/ku3ZyC2QUrcwyClt01zkFOQguzALuUU5KECeinfkgJUSy5oWhFYtSdM6vQrXJqKo7MoqgrO4AKkPU7Fjzy78+a9/xvxFC5CQmoi45HjEJsU9LclxiOU2KbUYA7ZRLGKTYxCbHF1hiUuOBktqehJy8jJVCIfql7ROj4Ki/ebasmJZobw2tB1C2kpbnJ0iBVKN6CvIhV4XguZff43PP/sUly9fQm5ujhrKzESUyupSXKgsIpyeg8OZSyf/k7WKbDZRLrXi/5JJi1FcgJJCB2eZohLlmvQ6JprrySOofqk0w3yZWDaTM6veh5RekzJFRckekaSta2eStjexevVqFBQUqjkjC1VSVCZGLRG5KgTWVf0+5UwzI2AibKX9EPsirTyNmjTzZV9QnXZHppr40ePHsLaxxbt/fg9Lli4v92ztPFk/bbV6gQVn1tBanD9MyZr2+8kB2oGytgQCQtpMUFWyWFyMvPx86HQ6fK1I2+e4fOkytEm/OcReK5oyN6lCftZaBNi6WqnkTSpCpE0DVMlzzHKYdp/FirR16dwJv3vrLUXa8vMLSif6phyW2GBMFatZLi+V1DACmtZ7fq0sG080JOXi9S0ZGRlwdnHBe++9jyVLl8q8ka+vKWr0ylqKjqdrTklVMi1VSZda8uUoo0FrplmEtJXBmYLHSW010vbZZ58hPDz8CWl7KriaMn+9HWmZ25d/zYyA1t5PPzPNfIGXVJeWlobOnTvjrbfewqpVq5Vsap2jybfvS2qR3bUbgefJWm00ZWRlZcHT0xN//etfsWTJkheTtqffHU+/lWRb3cOCn7rlzF9b0bba/Z7Vj7sT0lZOOxYUFDwhbZ9++ilCQ0OFtJWDk2yyPAKmpG3lypXPkDbLX12uUDMI1A3Slp2djUOHDuGDDz5QpK3C5KhCzuoeOauozUpfgOdImnLjlwQVme6rmfelYV9FSFs57V+WtBmNRuTk5FT4xVFOFbJJEDALAmVJG2WTnaQs9QkBkraKEslo+7j/9bY7Sdvhw4cVaVu8eDFI2sqVxYoIgGyve2SuEq+ZkLZKgGTGQ4S0lQMmFaPBYFAxbR999BH0er1Y2srBSTZZHgGNtL355pugpU1Im+Uxr/krvAqbqfm7065oStoWLVoETvitKWztGFkLAoKAZREQ0lYGX3ZCVIx0iXIgQtOmTZWrVBuIoHVSpusyVci/goDZEDAlbStWrBDSZjZkpaJXRcCUtC1cuPCJLLIvlEUQEARqBgEhbWVwZgfEgQhhYWFo3rw5mjRpguDgYHGPlsFJ/q0ZBDTS9tvf/hbLly9/oihr5upyFUHgKQJC2p5iIb8EgdeFgJC2cpCnpe3SpUuKtDVu3BhBQUFC2srBSTZZHgGNtP3mN78BXVLiHrU85nKF8hHg6NGjR4+qmLbvvvsOJHFiZSsfK9kqCFgKASFt5SBLxXj58mW0aNECH374IQIDA4W0lYOTbLI8AiRtXbp0wRtvvAG6pGgFFkVpedzlCs8iQJnLzMx8QtpmzJgB5m0TWXwWJ/lPELA0AkLaykGYpO3KlSuKtDVq1EhIWzkYyaaaQYCkrXfv3qClbf78+cjLyxNFWTPQy1VMENBI27Fjx5SlberUqXj06JEaQWpymPwUBAQBCyMgpK0cgE1J29/+9jf4+/ur0aM8lJ1X2VJOFbJJEDALAunp6Rg9erRKrjtv3rwno5jNUrlUIghUEgH2eXSPaqRt/PjxSE1NVSNIK1mFHCYICAJmQEBIWzkgkrRFRESgVatWKvu3n5+fuEfLwUk2WR4BWjOmTZuG3//+95g7d+4TObT8leUKgsCzCGikjTMijBw5EgkJCWJpexYi+U8QsDgCQtrKQMwvSpK2a9euKdL2/vvvw9vbWylLHlrWysb/ZREELIXA48ePMW/efLz99tuQ4G9LoSz1VgYBkrbjx4+rD9khQ4YgNjb2ycAY6QUrg6AcIwhUHwEhbWUw1EjbjRs30Lp1a7z33nvw8vJSI6VQjmtUSFsZAOVfsyLAYO+lS5fhnXfexZw53yErK1tNGG/Wi0hlgkAlEDAlbX379kVUVJQMjKkEbnKIIGBOBIS0lUGTJIyZvu/cuYOuXbuAKT+8zp17Qto4kwyPKSot8oVZBkD51wwIUKpKJIuKctPGTeCAmPnzv0d2Vs4zpO3pkWa4rFQhCJQioMnVkzVj2rKzcPLUSZW7smfPnoiMjFSWtqeza2lHC4yCgCBgKQSEtD1BtmSAQVFhIQry8xEXG4sVK5Zj4sQJCDUakVs69yg7KM4GmAcgHyW/n1QhPwQBsyCgzTdZjNzcHBw+dBhjx4yDzV5b5GTnlpI2TtZchAIUo1BN3sxzWDTFqf02yw1JJfUWAcqLJislv4tQhHwUIQ9FSraKiotQUFSIrJwsBIeEYOToUZi/YAFiYmJKSFspNprk1Vuo5MEEgVqAQAMmbVoXUwQUl5TCwgJkZWYiJuoBjHodjhw6iH3ubvA/fx7379xGRloqCnOZUJLdWhHYmYl7tBZIcX26BRUjWYDCgmxkZ2cgJiYKPt4+cHfzwJHDx6DT6XHv3l08fvwQBfnZpZStACjWSiFQrE0+ThmXRRB4EQIlRK2EuJG88ROgQH0OFHJdXIi8glykPkzG5YjLOOdzDu77PXDoyEEYjHrExkQjK+MRigsLgKJSuaMMi+i9CHTZJwhUGYEGS9pIvBT5KipAXl4u7j+Iwhnv89i22xbzF6/AmMnfYMSEqRgxfipGT5iOb+cuxNZtu3D27DmlNKlQCwsl0WmVJU9OLIMALb1FyM/PQUzcA/j5+2KXjTXmLVmGsdNmY8jYqRg0ahJGTfwGM7/7Hhu3bMeRY8dw8+Y15GRnoLgwr4SskbBpRVlQylxG/hUEnkHAlLQVoriIfVoBCgpykfYwFcbwS3Da54ll6zZg0uy5GDZxGoaMn4LhE6dhwjffqr7Sxs4JQYFBiI2KREFeDoqLSP5kEQQEAUsg0GBJW1FREfIL8vEwPR2XI25gwfIf0aL7MDRu0w/dRs/B+B82Y8Yaa8xaZ4vpy3eh15jv8FGrXmjVdQDmLFyKYIMByWlpKCjk16UsgkD1EOCI5ccZj3Hzzm2s2bwZrXv1wfst2qH14AkYs3Ajpq+2xvRV1pi2fCeGTP0Bn7bpg2Zte2HSlFkICAjCQ8piQX6p1djU2la9+5Kz6zsCT0kbPxoKC/KRnZWJ6JgYuLh5oteQ8WjUvBuath+AIbNWYMpKK0xbbY1pK3dj/MKN+LrXaDRt0Q1deg3C2jXrceP6DTVzAuOCZREEBAHzI9CASBtN9nSD0qIBFBQVIzH1IVwPHMVXHXrigxa9MPz7HVjnqcde33twCkmEmzENrsY0uBtS4ewfjW0HdZi6zAqNW3ZH8849YevmgaSH6eIJML9cNogaGZWm/oqBx5nZOHbWFx37DsGfv+qAfrOXYoW7F6z8bsMmKB72+lQ4GdPgrEuG04VIWB0NxZw19mjWvj+aftEaO632qrxZJe560xilBgGlPGS1ECjxZRYVA7kFxQi9FIHps+bhvaYt0GbgdMzffhjbj12GY0AsXIxpcNAlw1mfDFddIvZ43cCPbr4YOm0xGn3SEh269MSps154lJFREl9Z6ikVb2m1GkhOFgSeINCgSBvjLqjUCgqLkfQwCzvtDqJlrzHoPnEhFjuexbZz12AXHAMnfTxcjIlwC02GqzEJrmFJcDEmwCkkGja+17BpnzdGzF6Cll364scftyItOQ2FBaVfluydpId6ImDy41kENPHguogRacWFyM7Ohev+o2jXZyQ6jJ6F760PY8eZK7ALjIG9LhkOulQ469PhangEV/1DOOvS4BycBEff29i53xdT5q/B1227Yv7CH1SMES1uJcMUnr22/CcIVIRAYVERMrKyEay/hEHDx6F1z8GYt9kOW46FwM7/Hpx18XDUJ6kPB0dDKhwNaXA0PIRDSDIcAmJhc+Yq1u09jL6jv0Hrzt1g7eCAjIxMFBdSEqVLrAh32S4IvCoCDYi0secoRlFBIR5n5sD9iC86DfwGvSavxLrDBliHxMImNAl2oUlwDE2AszEebqXFJSwBTmEJcA6Lh0toLNx197HryEUMn74Q7dv1hJuDOx6nP0YxP1Wlh3pVGWxQx5eQtZKw74LiIjzOycaJ0z7oMXAcOo6YhfUH/OEQGAkXYzKcqRxJ2HSpcNM9hLs+Xa1J4JwN/D8RB4Ij4XRSh8lzV6BN5+7YsGEDkpMSkMdR0KIsG5RsVeVhlTwWA5nZOdCHXcWgEZPQutdwLNjhAlv/G3AMi4NjaBIcDMmwN6TAwZCqir0hDXaGdNjr0+FEuQxJgsfFu9jucQ7dhk1Au+594HnwKLKzONpZSFtV2kbOEQTKQ6BhkbYiICc7D+HX7qHLoCnoPX4xftwXBGdDCuzC0mAdmgqb0BTYGxPhoI+Fsz4WrkYStUQ4hSap4hKaADdDNPbp78HqoB/GTf0enTv2Q5jxKnJzGAwumrI8QZNtJQhopI1j9LIK8nE3LgEDRk5F+36TscLuNPYb4+HBjwVDApxD4uEckgBXXTLc9Clw06XANSQZziHJcOJvfTI89XE4YoiB0xk9Js9fjo++aIazXmeQnpmhUtLwerIIAhUhwO/MgiLgfnQi5i1ZjybNumLhVjfsPX8D9qEJsAlLhq0xGXa6JNiGJMHRSCtbCXmz16fBgaRNlw5XXQo8gmPUR8Q6x2PoNHg8OvYYiLt3o5GXSw+HELeK2kC2CwKvgkDDIW3Mr1YExCWkYv0OR3zcfigW7zwKO68b2Ot3F3aGBNiw6OJhHfAA271vYLffbTgGx8CVVo/QVDiFpqnibEyCS2g8PHSR2OV2Di3aDcTS5Zvx4EGckLZXkb4GfCytbIkPH8L+wFF88FVPzNvkCZeLD+BhSMI+YwLs/G7D2usaXAIewC0kDvsMiXALiYeN331Y+dyDXVACnPUpitDtD03Ffn0stnn6oF2fYZj+7RzcuHMHBYzfbMAYy6O/GAFGPuYVAZn5hThwwgeNmnXGwvV22HE4BHv8I2Efnga78CQ4GxNgc+E+tnvdhn1IApwMyXDUp8BRn6qKky4NLro0uOqS4KaLh3PQHaywO4hmHfph5y4HJCamCGl7cVPIXkGg0gg0GNLGL728/CJcDA5HszZ9MXbBVqy080KP8SvQfuT32HJCB8eQe7D2jcCEdc5o2msqJv7oBjv/B3AzJMOFgxFCH8Ip9KEicC5hVK5xcPeOwMwftqJdpwHw8w1AUaEMd6+09DXQAymLhcXFMF6NQN+xUzF01lpYn7iGfSHJcNcnwyU4BmOX2eCzPtMwba0THPxuwT0kBuv3BaLV8B/QYfwqrD96GU60voWmwSX0ETzC0uB68TZW7HRBk8+/hpvnAWTm5qqZOxoozPLYL0FAI223HsTjmwWr0bhVH0xbsgOfdZ+IMSvtYRMSBUdjFDYfDsSAWT/iq6ELYH0hCi6GFDUQwVmXolz3dN+7qELrb5LyRNh5h2H6og1o0aordCFGMbO9pC1ktyBQWQQaDGnjtFMcoedy4KSybKyw98LO4+EYNX8XfvNBe4yatx67Dp/HCuuD+FubQWjadQJWul2Aa0gs3PSJcCVxM6bCmSP4jClwCUuGe2gi9gdEYbuLNz76vB327LEDpx2SRRB4EQIcDJObXwDPk6fx+0afYf7OQ3C8EA0PfRrcjFSAcVjueA6fdh2DD1oMwDrHM9hxwB/9pq3Grxp1wdBFttjtcw+uxhS4UoGGPoRbWDr26eNgf0qHL9v1wMKlKxCflASmtpFFECgPAbpG8wuBs+dD0KbHMAyZuQpb3X3RrNs4vNeiP37Y4wkHLz1Gz12Pdz7tjl6zNsMpOF4RMxddElx0yXDRpahCAsffroYkuBqi4RZ0ExsdDuOvH36OwwePIi8nV/K3ldcIsk0QeEUEGhBpK0JicirWbrPBx51HYOvxy3AKjMaG/cFo238G3vukA8ZMX4SuAyfhD43b4dutnnC4eBf7DPHK8kHi5mYkcUuBs5HugQQ46eLhFhQHd58b6Np/FObNX4jYmJhnvyolxu0VRbL+H07S9igzCz/utsUbTb7G2gPBcA5JgqvxIVxCH8KVo5cD72PWj8749Xst0XPYTAyZuBBvf9wZrYfNh9WZG3AzJMGNbnp9gpJJ19A0eFA+L9xCp4HjMHT0BNy4eUvNo1v/EZUnrAoCzICUX1AMW9dDaDtgPJbbnoCH/x3M+dEJf2veC1917IdvF6/HXz7tjBYDZmHL8ctw05OsJcAlOB4uIYnKJaoIHC3EeqYC4Sj7SLgF34Lt8Qto1qoTVi5fheREfkBwaIwsgoAgUB0EGg5pKyrCvQdRmDpnMb7sPg67fe7CRZ8E14AYbNt3AR9+3Qk/eeNPeOMvX2DUd5vh6HsLHrpYOAdGYve560qRuhoT4WJMgpMhEZtPR2DjyQjYXYjCoZAoTJi5EGPGjEN4aOjT9tAImwQWPcVEfqmRKjEJCZi1fB0a9xwNK987cKSryZiu3O8uhgTsN8TC/txVjF+4BT9780P8x89+j8/aDIDVkTC4h5QMVLAPjIZdQLQaSONsSFNuK6cLd9Bt+FR06NIDeoNBplkTeasQAY52zy8owpqtu9Fu8BTsOXMJ+wLvwc33KiYuWI+f/uZd/Pv//gaftu2PVQ5eKt6SHwaOATFwCIiBc3A83HSJJSSOZM6QDNvAKGw4psOWY/5wPBuMdt36YOSIUbgREQFOEyiLICAIVA+BBkHaaNlgtu+bd+5i7PS5aD1gOqy878JZlwjXwFi4eF9FxwGj8B8//TXeadIGPzqegzsDwIOjsfGwDsOWWGPdIT1s/CPhbEiEgy4e03Yew6ClDljmGoQjuhhMmbMEw4aPhEGne9oiQtqeYiG/TBAoRmRMDKYsXI4mfcZil99dOBk4yOWRGujioucglyi4XbyFtfbH8du3P8G//fev0GfMXOzzf6BIm63/fXzv6I1p247ANiAGjqUJT50u3kOfsbPRuVd/6A1GNbk8Y+hkEQSeQYDpj9SsMIWYs3g12g6eDGf/Ozige4ADAbewxtoTv/tLE/zDP/07+oz5DlbHjNhnLEmoO2vncXy35zT2+NxRljeSN0eOdNYlqY/ZwUutMHzxFuw6eA7tu/XBiOEjcP3qVSFtzzSA/CMIVA2BBkPaGNN24+59jJk2D637TYXVuVtwDo6Dnc9tLN9zFH/7oiPeeqcJ3mnSGqO+2wgbr2twDYrCInsvfNh7GiZv2o9tZ6/BNiAadkExWOIegKErnDDX+iwO6x5g0uyFGDZsOPSmpK1qbSJn1XsEinE/KhpTFy7FR33GYIfPLTgb0uFsfAxnY4l7dJ8uGlbHQtBvymL88YOv8du3P8VnHYdho9tFuAVFY+fZCAxavAdtJq3C9nO3FOlz1qfCWZG2WejUoy90eoOQtnovS1V7QH7IlpC2AsxfthatBk6Ag991eOoiYX0sCEOmL8Zv322KP7zbBB+37ofFu4/ANTgWDgHR6D5rMzpOXYfV+0OUtW3LyQhsPX0dTrpE7L5wD9O378Pg+euxxe0EOijSNlJIW9WaSc4SBJ5DoMGQNs5XcDcmHlPnLsfnnUdh95nrcLgYiXWuF/Bl57F4/4seGDdnLToMmILfNGqHebsOw9r7Opa7+qHl2EVY4eGPNQdCsMozRLmzdnnfxuTNBzF3zwl4Bt7E2OnfYuSYUbgUHvZsTNtzkMsGQYCpZxIxd8UafNJ7BLaeiVAJSl2MGYq0uenj4eB3AxOWWuFX736JfpMWYsTMlUpGO42cDxuvCNj43cLs3Scweq0rbAKiVeoFJuN1uXAHvUZMQaeuvWAwhJYkNhVLm4hcGQQ00sY5bzfssEb7IZOw44QebgG3MHWlFf7yaQe06zcBc1Za4f3PuuCrvlOw7XgYXELiMGypPcauccVev3vY5XULM3edwBzrM7Dxj4ZDSBxWevhh7JJt2Op0BO079cC4MeNw5+ZNFIl7tEwryL+CwKsj0DBIG4D8YiA25RHW7nBE0w7DsO1oGLYeDUO/Kavx8983w9S1DrDxjsAKu1P4oOUg/K3TaCx28MIaz0B0mLJSBYsvcfbDXJsz2OV9Ezu8rmPCBg/M2XUITl56dOk/CEtWLEFCQtyrt4Kc0bAQKC5GVk4Ottk54JcffIKVHhfhGMJBLo/gZEiFuy5ejSj9y9f98OdW/bHpiD9svMMxaOYq/OSNxhi31Bo7Tl/GImc/TNp8QLlHOYDBPTQN7hdvo9uAURg7cQpu3rotMW0NS7Je6WlJ3AoKC2Dv7on2gybghz2HsWG/Hz5o3Q8fdRmBLYcC4BlwD8PmbMTvmnZB92lr4BgYjfHrPDBtyyHYX4zC5uNXMGqVM0avccPW0zfgqIvDIoczGP7dOqzcbI8vvmiJrZu2ID01FZxGUBZBQBCoHgINhrQVFAOPsvPgfuQc3v20E1bZn8Uyu7PoOn4ZBs3ZjO1eV2Gni8Iev5uYue0Amg2dg8kb3LDxmBEjlttgge0ZbDt9FTbn78IpKBrL3C6qWLexS62wfKczPmnRAk6ujsjJyX4yKQINHEy4IEkXqiek9e1slaetqAgnfXzx9mdfY+YWN9hejFKjRx1CEmF7/h4GzN2C5sPnYr71MdgH3oGLLgobDgSi49hF6Dx5JdYf1mOVZzDGrHPD7vORKo8gk/A6nNKhWasOWLtuPVJSmNRUzGz1TX7M9TyUjcLCQvj6B6NNz2HoMeF7jFq4BW1GzMZ8q4NwDYrGAX0Sth3RY9C8TWgzZgl2nL6ORY7n8c22I1h/yAi7iw/wg6MflroFwi4wFlbn72HGFg8MmrYMIyfMw7t/fB9HDx1Bfh5niymdn9lcDyD1CAINEIEGQ9rYXeQVFkEXfgOd+o3FkBmrsNrBCxs8g5TVzMYQD5uwRNgZ47H34j2s8QzC5hNhsDl/W03evdMrAvb+kXDVxamy/UwE1u0LxKq9xzBi8lz06NsPQSEBKCriBEVPyZpG2kR1NsC3q4JHpixQSq7dvYNxcxeg05hZ2HpUBzdDokqZYHPxPlZ5BilSZuv/ACWjlhNhFxyNTScvY+X+IOz2vQUet+nkFdgGxatcgo7eV7Fw7U60aN0Wp06eRG5ubgV3IJsFgRIEOII0OjYBC5dvQOOWvTB/syt+3HcB1n634MrkzfqHcA6KxvbT4VjpHgBr37tqAML209eUa9QlJAHWfvex98KrhrXkAAAgAElEQVQDlXDXNjgGm4+EYNFWN3TvNx49OvXCJWM4wPwiLLIIAoJAtRBoEKSNCClFWQzEp6Rjj9NBNG7dD99vOwCPoFh4hD+EXWga9oamwj40FW6hyfAwJqg5IDkPpIcxrvR3AtwNCWDMkbsxEe6B0dhsexotWvfC5s1bERcfC04cZErUeF2tVKul5OR6gwDloQjFSHmcjn2nT+OvzTtg9nobOF28DffQBDiFJsCB892GpcA1LA1uYWlwDkuFU3gqnMNT4RKarIicqzEBriR6xjRlFdnqchJtuvTBDz8sQlTUA0msW28kxnIPoqy+hUXw8QtEs7Z9MPmHndjrfROO+kQ4Gx7CWf9YpUZy4TzMOs6Dm6hGjDJfm0o6zm36RHWMm4FJx5PgcPEWFmxyxOfNu8NhrzNSk1JQMo+VkDbLtaTU3FAQaDCkjQ1KZZmTX4Dr92LQb9Q36DRkJja4XIQnOydDOhyYJ8uYrrLSexiT4GFMVIUEreR3EtwNidinj4G77gG2eAZg8Njv0avXcNy4cQt5BXkoVOpYxiI0lBeoqs9JWcwrKkRkYiKGTJiG5j2GYYXtSXiSiIUlwfFSqiouJG2cqorELZyFCXg5dVWymlSesyC46RNge/YSRs/8AU0+awYfHx9kZ2VW9dbkvAaGQFEhkJiUilUbduH//vQ5ZmxwAy28ioQZHpcMcmF6JFWS4aZLhps+Wc2MwGmrXDgLgj4R+5mqxhiD5fbH0Lr3aPTsMxIxkfEoLCiUL9cGJlPyuJZDoEGRNsLIOR8zcvLgfT4IfYeMQdehM7HBPRjOgXFwMj6EY+ijkrQLhlS4GlPhyjWDw41pcDekwF0fjwP6SGzbfxa9R09D2y69cOz4aTzOyEBRceHzcz2Kmc1y0lvHa2YamqzcXASF6DB83DS06z9FxVo6BkTCyZikrGqu4SVTVLmFPYKrKulwDX0EF2OaIm37g+5i71F/jJyxAO169IWtgzPS0tJQVCjxQ3VcPGrs9mlty8nJw/WbdzF24nS06DYYszc4weH8HTjp02CnT4e9LhXOnLZKn/qkOOuTYR+aDEdjElxDYuDpfwub7I+hR/8JGDBgHHx9gpCbzVg2cTfUWGPKheo9Ag2OtLFFFXHLyMDBI0fRZcA4tBv8LebvOIwtJ69gz8UHcNQlwNnA6YHoeiqJM3LRxcMh4D52nwnDKruD6D1mCjr2GYA9dnZIS09HfmGBImwq8JudFBfprEqBkFVFCDCmKC83F2e8LmDgmNn4qtsYzNrggs1HjbC5GAknztphfAi30Eclha5QfYqagm336XCstTuKYVPmoF23XthmtRsJiUkydVVFYMv2ChEgcWMMpNFgwLRvF+CLzoMxfvF2rNkfjO3n7sEmgNNTcZqqNDjrHyoy56RPga0uAbt8b2HLwQAs3uyIbn3HYMTQSTh15CxysvNA+VaL1hdWeAeyQxAQBCqDQIMkbQSGfUja4wyc9AlEz+FT8VH7gej/zQossT4Cq5M67PXhIITL2Ot3Cbu9DNh5MggrHY5g+Jxl+Lhdd3QZOAwex04iOT1d1cUYJZJBkjbVTWmdlLauTGvIMQ0WgczsXPgFhmLYxFn4uG0f9Jn4PRbtOojtR3WwPhsBW5/bqth5X8feU6HY7HoWU37YiOZdBqFDz4Fw2XcQyampCr+XjRh92f4G2wgN/MHZc+UXFuHSjTtYtG47PmzZHa0GTsW0NXbY6BmAPWeuwsbnNqx9bmOvz23sOXcNW4/pMXerG7qNmolPW3XHqAkzERhoRHZmDkfbPPvhqjrGBg6yPL4gUE0EGixpI250T2Xm5OL2gxjYunmix8DRaPxle3zapju+6NgDLXsOQJu+Q/FFx+74uHVHNGrWCq279sQmqz24dOMmHmVlo4CZxUutd6zviULUyJq2rmZDyen1G4Gi4iLk5OUiJj4enoeOoe/AEWj6RWt82qoLPmnTDa17D0X7/iPRvHNffN6qC774uiM6dOqDDRt3wRh2BY8zslBYWPRU/uo3XPJ0FkKA3VVuQSHiUx/irF8gho6bii9adcanrbvjk7a98HmHvmjWZSCadR6AT9r2QKMWndHoi9boPXgUDh45gwcP4pVLtLiwuGQIvdb/aWsL3bdUKwg0FAQaNGljP1JYXIS8/HykpD1EaNhV7Nt/BGvWb8LMb7/DhCnTMH7KNEz7ZgZWrV0LFw93hBj0SExORnZuHgqKipR1jWSNVrZnSBslSOuouJZFEKgQAQoICVc+CgtzkZ6ejmsR13HsyDFs3rwFs+d8iynTp2LKtGmY/s03WLZsOTxc90EfZEBCfBJycnMVYaO8SVq2CkGWHZVEgNKYV1iIx5lZuHXnLrx9/LDX1gELFi3DxCnTMX7SVEyYMh0z5szFph1W8Dx6HJeuXsfD9Azk5xVAETbTvs/0dyXvQQ4TBASB8hFo0KSNrIp2shKHZrEa5ZSZkYWE+ATERMfg7t27uHPnDqIePEByUhKysjJQUJCvuJhG0gqLihRZI2F7jrSVj7lsFQTKQaCEuGk+peKiIuRmZyM1OQnRUfdx/95t3Lt7Cw/u30VSfByyMjKejsrTatOUo/a/rAWBKiCgxIgfAKXnMubyYVoq4uLicO/ePdUnsm+MjolGSmoqsrKzkV9QUDLPbWFxSRybJovaugr3IacIAoLA8wg0YNKm9SZ0bmrd07MAqfi0ckwXPJpUTyNp2nHa+tla5D9BoPoIUAzLEcXnK9bEWls/f8RzW0Run4OkgW94GuZB2Xh2KRXE57bzqNKYXiWsJp6GZyuQ/wQBQaAaCDRg0lYN1NgfaYMOyllXr2Y5WxCoBgIaWdPWL6nKVI5fcqjsFgQEAUFAEHjNCAhpq0YDmCo809/VqFJOFQSqjoBG1EzXVa9NzhQEBAFBQBCoZQgIaatmg5iSNe13NauU0wWBqiFgSta031WrSc4SBAQBQUAQqIUICGkzQ6NoZI1rWQSB14qARtZEFF9rM8jFBQFBQBCwBAJC2iyBqtQpCAgCgoAgIAgIAoKAmREQ0mZmQKU6QUAQEAQEAUFAEBAELIGAkDZLoCp1CgKCgCAgCAgCgoAgYGYEhLSZGVCpThAQBAQBQUAQEAQEAUsgIKTNEqhKnYKAICAICAKCgCAgCJgZASFtZgZUqhMEBAFBQBAQBAQBQcASCAhpswSqUqcgIAgIAoKAICAICAJmRkBIm5kBleoEAUFAEBAEBAFBQBCwBAJC2iyBqtQpCAgCgoAgIAgIAoKAmREQ0mZmQKU6QUAQEAQEAUFAEBAELIGAkDZLoCp1CgKCgCAgCAgCgoAgYGYEhLSZGVCpThAQBAQBQUAQEAQEAUsgIKTNEqhKnYKAICAICAKCgCAgCJgZASFtZgZUqhMEBAFBQBAQBAQBQcASCAhpswSqUqcgIAgIAoKAICAICAJmRkBIm5kBleoEAUFAEBAEBAFBQBCwBAJC2iyBqtQpCAgCgoAgIAgIAoKAmREQ0mZmQKU6QUAQEAQEAUFAEBAELIGAkDZLoCp1CgKCgCAgCAgCgoAgYGYEhLSZGVCpThAQBAQBQUAQEAQEAUsgIKTNEqhKnYKAICAICAKCgCAgCJgZASFtZgZUqhMEBAFBQBAQBAQBQcASCAhpswSqUqcgIAgIAoKAICAICAJmRkBIm5kBleoEAUFAEBAEBAFBQBCwBAJC2iyBqtQpCAgCgoAgIAgIAoKAmREQ0mZmQKU6QUAQEAQEAUFAEBAELIGAkDZLoCp1CgKCgCAgCAgCgoAgYGYEhLSZGVCpThAQBAQBQUAQEAQEAUsgIKTNEqhKnYKAICAICAKCgCAgCJgZASFtZgZUqhMEBAFBQBAQBAQBQcASCAhpswSqUqcgIAgIAoKAICAICAJmRkBIm5kBleoEAUFAEBAEBAFBQBCwBAJC2iyBqtQpCAgCgoAgIAgIAoKAmREQ0mZmQKU6QUAQEAQEAUFAEBAELIGAkDZLoCp1CgKCgCAgCAgC9RyB4uJivEqp53DUyOMJaasRmOUigoAgIAgIAoJA3USgqKgIBQUFyM3NfVJycnLwqiUvLw+sS5aqIyCkrerYyZmCgCAgCAgCgkC9R+DRo0cIDQ3FkSNHcOjQIVUOHjwIlgMHDqji6ekJrezfvx8s+/btU8XDw0Md4+/vj4cPHyrrXL0HzUIPKKTNQsBKtYKAICAICAKCQH1AIC0tDY6OjmjWrBkaN26MRo0aVVj+9re/oWzh8Tx3z549SElJqQ+QvLZnENL22qCXC9cFBBivQbdAVlYW+LXJr0SWx48fK9dAYWFhXXgMuUdBQBAQBKqMAPs/Wsk+++wz/Pu//zv+7u/+7pXKv/3bv+Hjjz/GhQsXkJmZWeX7kBOBBkXaqIDz8/OVAqbg1JeSlZUJiRUw7+uskTXKSGRkJM77+SlXgJOTE1xcXHDs6FHodDokJCSoGA+SN54jiyBQ0wgwRkhkr6ZRb1jXo3ylpqbixx9/xFtvvYW///u/fyXS9pvf/AaLFy9WH7wS01Y92WlQpC09PV351wcMGIA+ffqgT+/e9aL069dXvUz37t2Tzrt674M6W+ugvL29MWfOHHTu3Bkd27RBj/bt0b9rV/Tt0gVd27VDh7Zt0b9fP6xbtw5XrlxBdna2Ga4uVQgClUOAcsqPtdu3byuXk3w4VA43OapqCGiyxv7wVaxt//zP/4wOHTogLCxMGU2qdnU5S0OgQZG2+Ph4zJo1E2+88Qu0b9sEPbt/hl49Pq/TpUO7Jnj33TfRrVtXBAUFycgcTbKrsKYSpGXt0qVLWLliBYb0748xAwZg3Zw5cNuwAWesrXHR2RnnnZxwwsoK9qtXY9HUqRjcsydGDx8Oezs7PHjwQLlTWZcsgoAlEaDb/v79+xg7diymTp0KOzs7FSyenJysrL9i0bAk+g2vbvZpHC1qb2+P9957r1LWNlrk/vjHP2Lnzp0qpET6xerLTYMibdHR0Zg0aQLefPNnOHZwFkIuLoE+YOkzRRewFOWVssdp/5d3rOk27ThtbbqPvyva/rLjtPNOHvkWbVp/gDZtWsLX11dIWxXfCXYmtMQGBgRg8sSJ6NmhA1bMmIEQDw+kBAYi02hETljYk5IdFobHej2ifXxwas8eTBs6FL27dsX6deuU5YOdmyy1CwG2cX0iMoyx5Oi9N998E//5n/+J3//+9+jVqxc2bdqEs2fP4saNG8qlxTQN9em5a5dUNZy7oSWXH7XUM126dMH/+3//74UuUu6nRW706NFKFoWwmUdWGhxpmzxpIt55+1e4GrYaj5P3IDPVuk6XG5fXoXfPT9CuXSshbdV4J2j6v3jxIkYMG4Ze7drh1O7dSA4IQG54OPIuXXphyQkPR7SvL6yWLEHHVq3w/YIFyuImgxSq0SAWOJVtTGLOdV0nMVSAtLJNmzYN//u//6sUKK0amqKkJWTIkCFqtN7ly5fB0X/ac9dG5cl7qo33ZQExrHNV8l2h7DCmzc/PT1l133777ZeSNrpF3333XRw9elTFkde5B6+lN9xgSVtE2Bo8TtmDrLS9dbrcvCKkrbrvFpUFrRLTp05Fv86dofPwQGpQkLKqvYywafuzQ0MRd/489m/Zgs+aNsW2rVuRmJhY3VuT882IwLVr17BkyRL4+PiAoRJ0L9bVhTIbExOj4im/+OIL/PrXv8a//uu/KpcVyds//dM/KevbL37xC3zwwQdK0Z46dQqMe+XI59r2QcHRiSSWtAoKeasdUsl2IFmLjY1VBoFZs2YpEvY///M/Sr5eNIKUMvjTn/4UM2fOVB8Xdf0jqXa0SMldNFzSFi6krTYJ4uu6F3ZMVBSbN2/GwJ494bFxIx6GhIDWM42QVXZNl2mUjw9Wz5qFfr16gUqSnZ4stQMBvV6P9u3bq3xRHGDi5eWlRv/WVfJGFzwVKi3Eu3btwpgxY0ACx5F6dEtRcbLQ4vHzn/9c5dXq168f1qxZg5MnT4IkljmzOKL+dS58ByMiItRgKsZL3bx5ExkZGULeXlOj8H2gXHDggIODAyZOnKhSffzyl79UZI0yxQ8EyhRd8/xdlsAxxcenn36KgIAASfFh5nYU0iaWNjOLVN2qjqSKSqJ7ly5YNn06Yv38KuUSrYjIMfbt3tmzGNy9OxYuWKAsOmI5qB0yERwcrEgNlcz//d//oXnz5ir+i+5D5t6rbdanyqJGKwZJDlPTnDlzBsuWLVOj9ejC+tnPfqZIG92mLLTA0fr20UcfYfjw4dixY4cawEQLHN1fJHCsryZlltc6f/48OnbsCN4zSQIJNQkpCURN3ktlMa9PxxFfyj6tnbRAh4eHq48AEvx33nkH//Vf/4V/+Id/UB8AmvyQkM2ePRs//PCDSgFC2dKIG0kd04IsX75cWXXFymZeaRHSJqTNvBJVx2qjS2br1q3o07mzGlDAwQYVEbLKbGcMXJbRiG0LF2LYwIHqS7OukoE61pQvvV2NtNHyRAXzj//4j8qF07ZtW5V7LykpSZGWukwSqCAZLE4Sdvz4cdCl9Ze//EUpXj43latmgaMC/slPfqL29+/fXxE4pg9h3B/T15gSOEtiwroZK0USzXYhqWZG/blz56rYUN6LvEMvFe9XOoCYU1bYxrTYcsQxE98Sc1pr+VHD90OTFf7+j//4D/zhD3/AvHnzVKJdkvyoqCiVPss0BQjlrHv37irkRNrtlZqlUgcLaRPSVilBqa8HsdMZPHgw5k2YgNt0Z75k0EFl9tO1ytQgI/v3x+7du1WnaEmlV1/bxtzPVZa0USHRgqApoxEjRiiiQwVGZVZX24z3zfun9Y3Jn5nChnLIgQl//vOfocUkadY3Ktn//u//VnFxHMDQs2dPLF26VI1MpQuVeNAKQ6uXJaxwvF9T0sZ2+Zd/+RflfmMG/u3bt+P69evyHpnhhWD7sR0Z10jL7OnTp5VFrFOnTvjTn/6kLLN0bfK9oHxQNn71q1+hTZs2WLlyJRhiQGsc5YGEjKElbm5uaNq06ROCRxmztrZWx9TVd8gMUFusCiFtQtosJlx1oWK6Rj//7DPsXbECSf7+ZiFtJHYkgDNGjVKWDqZmqOudF++fhZ1+XS2BgYH4/PPPlSLSXDnaWrO6cf93332Hc+fOgZY3PmtdXbQ2I4FjjBITQHOy79WrV6sPFVqz6D4lQdIIHHGgO4xxcU2aNEHXrl0xadIkpdhtbGyU25JEjoqbck2lzfqpwIlVVeSc55iSNq1NeE+8N7ro+GHFeDcSDVqGqnKdutqOVb1vYsQ2YRvResqUV/xwcXZ2VrMTEFPK+29/+1s1aEUjapQBEnsS+JEjRyoLLOMm6a5mXabvBK/BUczffvutslrzA4jyQpJtelxVn0HOex4BIW1C2p6XigayhR0OrRAcln5o2zak63RmI22Mjft+0iQMGzJExQrV1Q6M982v6ri4OJV/jiS3rpb9+/erya7pFtSIQdk1FRdHvbVq1UrF9XBUMckJrRN1faG88zkYv8fAfxI4Dsjgs5IY0SVGpUvrCnGgxYvEiZYXkjtaYr788kv07t1bxTNx8MOxY8dUPJrBYFADG0iqSOhonWPoAa9F/GjZoduWskTSxUICwMLfjGH76quvym0X3gfviySCSYTpxuPIbJ7b0Be2KQkzY3OJI62rxJwfHPQisH8jtrRWTpgwAQwFoLtci3XU2phtTrJOq9qHH36IYcOGwdXVVb3rLxttzGszL2CLFi3U+8UUH2xrWSyDgJA2IW2Wkaw6UCs7O84fyqSknO0gw2AwG2lLuHgRS6ZORa+ePZUCq6ukjYpAi3VhYDJdZ3W1MGaKhIxEpCxZK/s/lRkVG5PVenp6KtJKealPCxU+rWS0lHh4eCgixsEAVOrM/UZyq1lfiIeGkabouZ/xZ2+88YZS1jyXlhkSwVWrVmHbtm3Yu3evihckQaQrjhY1ztxCkhcaGqpGKHKUIq14HByhXaO8Na/La3LicY6AvXr1qiIrdeHdItYsvNfKFspb2ULSrRW2HUkwXeD8uKAVjXGMxJKuTJK0r7/+WrmZiVt5bcj2pWuchJiyzvM4KITxarzfyi68hz179qiUOiTur3JuZa8hx5UgIKRNSFuDfRfYsXCk1Dtvv40jO3fikRktbczZtnDyZAwZNKhOW9poNWGQOvOAMes+LR51tZBgVIawaYSBCo3PzGl4pk+fjpCQkHqnjPgOUPnTQkPrGBUuiRWnHeIzc87I999/X1nhqPg1bLgmCWChO41uTAaj01rDwQ0kvEwJwTQRlB26W+mG+93vfqcs28wd17hxY+WCZTwUrd0kD6b1l/eb12M70iJEqxFHv3LwBD8uavOiDQ4hQTUajU8KySvjxPjxSPki8aIb39/fX30skUBxDmSmaKGlmFOVkQzTxf3999+r5MoDBw5Ey5YtFfEizsSc+BNPYqVZTTU8+T/306JGFykngec1OAUfyVpVBn7Q2kYXPOsQC6hlJVFIm5A2y0pYLa+dX6gff/QRHNasQXJgoNksbUz7MXvMGEybOlW5h+rqlyfdUAxgZ5oIKm0q6LpayiovTYlVtNZcg3/961+xcOFC5VKsC1adqr5ylFE+H5U2FfDdu3cVkaClkYqdlhu6MCkLxLIi3Ey3a8ROWxNTnksZojyx0DXH/1+FUPNYEmqSPd4XY65qc9vcunVLxUrSGslcge3atVOkk8STQf6tW7dWxIvWYGLcrFkzFW/G1BqffPKJIrckugzy5whOEmCSM1qOSc7owiaGGs7amlgTJ5I5kuRu3bopMs68lCdOnFAyzXecFrvq4KfJDi2DdbWvq+p7U9PnCWkT0lbTMlerrkfLQp8+ffDDlCkqv1plRoe+7Bim/Qj28MCoAQNU0l4qwbrakbEzZ9wSv+apSJgOoK4WKj1agl5GDqjwaDWiYqQytbW1VRYEWqTq80IZpdKlpYRxUQxcZ+wbE6QeOXIEa9euVQMTSBZeRNo0wqCtiTdLeWSNhI2F5O1l7WJKBnks24j5wDgPJmOqeO+1daEljeSMz0kcTDHRfpuuNezKrk0xeNFvnkcrG62cdJHOnz9fkTQOEGC8G/skulnrar9UW9u5Ju5LSJuQtpqQs1p7DVoU6GoY1KMHfOztX2nqqvLIW+6lS8gKDYX18uUYNmCAmv6lNiuTyjQM759uExJc5v+qq4WTq3NEJBVneQqPio4Kle5fjqqjXHDQBUlMfVZufDYqcBJ0Wl0Ya8YgdI4IJNGgdYcWHbpANWuOhp8pqSDpIH4kYSQMJFW08tASRJcpBzow/o2WItbJOCoSaY5ipQuauGv1vmjNa7BODoqgBZDuUbrnanMbkbTxA0CzKFaGoJliq/1+ES6m+4gR24yEjVO3kXQziTQJG121/ACpzXhVpl9qqMcIaRPS1lBlXz03FTIDmju0bYu1335b7bQfnMoq0d8fI/v0weyZM9X8kPWhcyRxo2JnZ19XC+OEKkr5QaVIFxNHSC5YsEAFypPQ11flRplkmzIWjKMMGdNEFzBJGmPYSK44GIGYaNYhjTiQcHAb9zE1BI/l6FO63zgSlSMPmYB1w4YNKiie7lVawjighYMQGMNFYsh4Uo5uJJlgOo/KDEQgIdTc1TyfI1RrO2FjR0OLJQdpkKDy/omxVjjwgySWGFL+SGoZ+8cpoujWpLWMhFdzg5I8EwcSQJIztospYeNvbuM+thHj12iRbNSokXLLMoEuB4bQ6saRofVVxuurYhPSJqStvsp2pZ5Li+FZvmwZBvfogRNWVsjQ66s0lRVnU+AAhJ2LF6NHly44dPBgrQ+QrhRI9eSgssl1NeVGCw9jo5hclwSDwdR12aVdUXNR1klwaG1hrjXOjctRnnR9k3CRHNA6plnTqPj525SYcdAAByeMHz8eK1asUCMGOfKUdTGAnrng7ty5o1yrtNrRQsuUH7TikSDyI4n3UJb4kzTSKlSWfGhtRLc2iQ2Jz+HDhxXRZF11ZWGeNJJTX1/fJ8XHx0eRZabk4PRjHGzA0Z9MmUFSRVnct2+fSl7LOUCtrKwUEabljDNdjB07FhzRTaLMdiH5IzljzCHbjNZOEmy2o0a02b4cxEErJ9uR9TBvGwdE0B1OEsePs1ddeA7bmaNI2b6yWA4BIW1C2iwnXXWkZlodDHo9xo8Zg7H9+8Owfz8eBge/EnFjHFvChQs4umsX2jRrhpXLlyt3Yh2BoEHcpilpoyLTYn4YHM7RknSF1nVXdtmGpGxTiTJGjWSUxGrTpk1qcAlHD9KFRqsZ8WChdYYEiSM/ae2h9Wvo0KHKxcbYPlrMaB2LiYlRI05JBHkNlqouPPdFyXVJJhm3xvQhTE9S20eKVoSDhlNl18TWtFA22ZYkVloeNsosR6OS+JF80brJlCtsM44opfWO1jpa2+iqNrXMkchp1mW+A7QwHzhwQBF6bXBCZdqVx5Cck2RyNC+JG+9bFssgIKRNSJtlJKuO1covf+aR6tW9OwZ37YogNzeVt41krLzYNdNtPCY9JAQeGzaga5s2mDRxIm7euFHvCEAda9LnblcjbXQvsdA6sX79euUmomWtPi1UpFSclGtavphDi4q8vMEYmiWGLjdaYZiHj1Y0KnASNBIEkoXKKPCqYMh6y5I23hMJBd2JGzduVO7FumRZqwoO1T1Ha3PKMtuMI+OJK13PHIjQuXNn1b5sZ80CR5w1aya3c/ANLXckcAwn0EaVvqjtSSZ5LIk1ww84m4hY26rbmhWfL6RNSFvF0tGA9rBTogvDx9tbEbce7dqpNCC3T59W+duyQ0OV5Y0EjYXzi3Ji+JTAQFw6dAgrZ8xA5zZt8O2sWaqzrI/utbouDsyDResDY4mYg4zxVRohqQ+WAVOlTYsUP0Jmz56tUkZQGTMmSlPYmruMVjW6yjiCmvm/GG/GgSbM2cbcbVS+VMovUtrVlQvWTXLBjPokEbSAso04EIKkkfdCwsm85IkAACAASURBVGbJe6juM9Sm84mTZpVjP6S5LUne6QalRW7y5MlqIActqsSbFjjKBN3hdKFyO2PvRo8erUaPcxASLZxl3xNei1a5ZcuWKbcsZYzTwFH+pL0sIxUNl7SFrcHj5D3ITN1bp8vNy+vQu+cnaNeulYqVKPtSWUZs6metxI4dHGNNFi5YgBEDB6r5QzfPnw/PzZvhY2eHEA8PZYU7u3cvnNetw+pZszBh8GCMHDIEW7dsURYBCeytnfLBvGN0H3GCaxKT+kKsqaDpMuMzMbaMz8jYL84cwAB2U6LG39zG3F8cMLB8+XLl1uJgHG3gBd+DmlS4vBYHKXDScrrzSBQ4epXPw1ipmryX2im51b8rYsh21WLPSKrYz3F6q2nTpqn4Ng6AIImnu1wj9RyMQhc54+cYU0drtamcsK9jSiDGI2rEjxZsvmNCtKvfbuXV0OBI26RJE/DHP/wC/j4Lcff6Bty/ubFOl6Dzi9GlU2O0bdtSSFt5El6FbezcOKKOMRoTJ0xA5/bt0aNjRwzt1QvjBg7EmAEDVIqQLu3bo2f37sqVcN7PT3VmPFeW2okALQWawqkPRIAKk6MnOaiAsjpjxgzlnqKVhO5fKl4WEjUGpnO6NiZvZcwTA91peaE17XUTI7YFLWrM8E8SwfuqL4S6dr4JUESYfRUtqZz1hLn4aGmlC52jTMvKEF3VHOTQvXt3NScvB5zQSs3BC2PGjFExc9ogEhI/zrTAjyR+UMhiXgQaIGmbiJ///L8xbkwrzJnVBXNnd63TZdL4Nvjr+4xDaKFcDEIazPeCEEvGdPCrlDm+aMFgrMcPP/ygAm454o1Bt2JZMx/mUlPlECDRoVuK80zSrUiLCC0dmuKkm5H/a7MGUBlzBGJcXJxF49Mqd/fPH8V3iERN+q/nsampLcSeOdzoqqZrmgNVSMAoR6axb/wA4MjTXbt2qcTTHHmt7dfi45h3b+vWrUK+LdB4DYq0cQTV9u3b0Lz512jXtiU6tG+FDh2eLR07tEJ5pexx2v/lHWu6TTtOW5vu4++Ktr/sOO28tm1boEWLr1XsCr+464MFwQJyXuUq2ZFRobAzo/zQUsORUox/o5J53VaKKj+YnFinEeB7TmswUzbQKqIRNipPxhUx/QMHFHAWA8apkaxp6RxqYx/Be6qN91WnhaQKN699qNKKRusnB+pwAANHEtN6q30MME0O5Y45+hgTp30saGvup8uUOqmujvatAnw1ckqDIm00BbOjY/wEvybqS+GkwhwpxE5ZFkFAEGgYCPAjgrFfHGRA6wfjwahgmdiW+b2YfJaWYIktahjyYM6nJIGmvqT8cDYHa2trlceQA0RovdUsa9paI2vamm55jkReunRpvUkwbk58q1NXgyJt1QFKzhUEBAFBoDYhQCsv44YYwM+JwJ2cnFSuOca50TosiyBgDgRI4Bgmwjx/TKTMCe05LVlFhE0jbrTM0cXKAQ9ibTNHS5TUIaTNfFhKTYKAICAI1BgCVKYkZwzcp8teXPU1Bn2DvBDljTJGd3v//v1VehCNoJW3JqnjAAamACHh4/myVB8BIW3Vx1BqEAQEAUHgtSCgETdL51J7LQ8nF61VCGikbf/+/SqH28ssbSRydJMyvpJufLpbhbhVv0mFtFUfQ6lBEBAEBAFBQBCo1wjQqssku0znQfdoeda18rYxBo7JmzkogZY6WaqHgJC26uEnZwsCgoAgIAgIAvUaAVrIGCvJKbH+9Kc/KQtaeQStvG20yPEcpgBh8nJJ61I9URHSVj385GxBQBAQBAQBQaBeI0ArG0cjMycg03mUR85etI2xbUwBwjQiMods9URFSFv18JOzBQFBQBAQBASBeosArWycNWHz5s349a9/reYm5cjQ8gpn3yivMJcbz121ahViY2Mltq0a0iKkrRrgyamCgCAgCAgCgkB9RoCkLTk5GUeOHFFz1S5evBiLFi16pnCWmPLKwoULoRVOKs+UIUzcKwMSqi4xQtqqjp2cKQgIAoKAICAI1HsEGIfGQQR0k3IUaFUL65CYtuqJi5C26uEnZwsCgoAgIAgIAoKAIFAjCAhpqxGY5SKCgCAgCAgCgoAgIAhUDwEhbdXDT84WBAQBQUAQEAQEAUGgRhAQ0lYNmBlMWR8DKuvrc2lNXZNtVpPX0p5P1oKAICAICAL1E4E6QdrKU3zlbavJJuL1GZT5ogzPPKa8+yxvW03e+4uuxXvTAk5ra8Cohqvp+kXPpO3j8Zzup6amUyF+vFZtxVHDxRxrYlvR8qJ9FZ0j2wUBQUAQEASeR6DWkjZ29Bxm7O/vj5MnTyI9PV0pP27PzMyEj4+PmoT2RaTp+cc1zxbew8OHD7Fv3z6cO3dOkRxTxcTfKSkp8Pb2Vvt5LBU3tycmJqptcXFxLyR8vFOek5WVpYZIkyCaXsM8T/J8LbzexYsXwfnlYmJiauSaz99FxVuYUdvLy0th7+7ujqNHj8JgMCj5ICF70cJnCwkJUfPgsZ6XLUwCSbl7/PixInsvO950P9vq9u3bsLOze21yano/lvpNUnr9+nXVBpy03HThPk57w/aq6jB/tinfpYyMjJe+L6bXlt+CgCAgCNRHBGo1aaMymDlzJtq2bYvTp0+rKTDYiSckJGD8+PGK/JhmVybJ4X4WU4LD31rRGlH7v+xaq0Pbzv9JDE3r5DaSrvnz52Pnzp0qwzOP1xbu5zxrY8aMQe/evXHmzBlFNFlHWFgYRo4ciaCgIOTk5GinKILG/TxXq4tKj4Rk06ZN6pl5H9xneozp//xdtvAC3Ma6tfq1i5oeyzpZOFWJo6Mjvv/+e/UM2jGm19TOfx3r6OhoheukSZOwdOlSlStowoQJsLGxeUIyec+837LPm52djcDAQDg5OSkipj2bdryGgfZcTCjJaVvYfiRuGgZca4t2LtfaotVD0rZ7925FXEzbrry24LlaXdp9m9ap1V3b1nz/zp8/jzlz5uDChQsKc+0e+dFF0sr8TPwA0HCp6PnKe34SbQcHBzg7O4OkUGuDl+HFurSiXU+7L1kLAoKAIFBXEai1pI2ds9FoVJPTct6ycePG4ebNm8rdFBUVhfbt2+PAgQOgIuaxVKokUnfv3lVKktYtzX3JfezwNYLH46lQaEWhMuV2KmhawZitmdYBKgtaY0gSqHzv3bunvvh5LM/ncbNmzVJZornNVMFSSZBsderUCY0aNcI333yj6iEJo+WQU4HQ+sBr8FhaEajUeO98NhIn3jstDC4uLujZsycCAgLUNbmPpJXWRt47n5/n8vlYPwvP472zDv5PK8f9+/fVM/BcDTPeN+sjFnx+XvvOnTuwtrbGt99+i8uXL6s6eH/EhnXy2V/nwvtr3bo11qxZo6ZV0ev16l67deumMNWe/8GDBwpPtpOGM/fx+fkxQAy4nc9N7Hgc25hYkkwTW065QnK4evVqXL16VeFELChnPEZrO16L24kNMaXMsH2IK69F3Fgft/E6lCc+B+9Fkx3eG9uCskc54HGs01SuXifuFV2bz3Xr1i0MHToUW7ZsUbjwnokF8Rs7dqwibsSZz0es+OzEme+l9nyUVb6zfH7iw+N4PGV38uTJmDZtmuoPiD2x4vF8f7V2Llsf25TXZBuwTr4Tr1t2K8JQtgsCgoAgUFkEajVpI/Fhh01LChU1symzozclbVSE3Hbo0CFl+Zo4cSKmTp0KW1tbpTzZsZ84cQLbtm1T51FJUFnTAsIMz9xPQrNgwQKsXbtWZXWeN2+eUkR0f3733XdgnbTs0eIVERGhlDWV6stI26BBg9C/f3+0adNGWQWpvOl61Egb753K5fDhw8pSwevQsrhnzx6lcEhISFY/+OADRR5+/PFH5Q7kfZ49e1bdO0kBFdquXbvU81JR8VmPHz+uFBYVJAnOlClTFI7MZk0XoUb2aAmxsrJS1hBaDmlZ4vVJ2qh0qexY1/r166HT6RT5qKxwWeI4jbTxnqmQ2ZYktLTG8lmooDds2KBkgNjxOeimpoyQBPn6+mLHjh2KENAayizetJYywzfbmPjTGkrCQMLM+fI6dOig2poWOmJC+eC5bD9al4YNGwY/Pz+FKe+P7Ug54bFsM27jfdKlP336dGUp5DEkg/wQIfmjDBJ3yjv38b5PnTqlCIolcDRXnXyfKEu0zNKyzDYhOSKp8vT0VLJPOSax4zupySEtc8eOHXtC8kiY+fx819kO/NChi54fbmxbtgPlnHKofVzR+kaseDzfRfYBvC4XthXbie/FjBkzlKXO1LJtrueXegQBQUAQqEkEaj1pY+e9bt06pVRJKq5cuaK+rjVLG7/EqTipoEk4SEgYAzdkyBClNKjEaTlih08FSSVDBU6lsX37dvUlT4tSs2bNlEKlgqeyJZmjsiHJohLndip0Kg2eT2vKy0jb8OHDFZEkIeS5tNbwXjXSxnunIu/Vq5ciCCRFVDyDBw9W5OzGjRuKXNJix2ciQWOhW3DJkiVKEdJi165dO2Xp4LPzGgMHDlQKkeeToIwaNUoRABKLFStWYMSIEYokcD9JKQmxq6srQkNDlXWNeM2ePVudw+1UpFSwJJiaZaQmhdT0WiRArVq1wsaNG1V78hlIYjt27KhIAV1pdEmTCJPMcb68rl27KssnCQXj4NgWVPzEi/tIJOgCZVtwyhXupwUnODhYYUdCQgspZYlkjSSc7cFjtm7disaNGysrE2WCRIuWUZIUnkNLE+WH1jMSZhIMusY5+TI/SngftBytXLlSERCScRIVyubcuXPVuSR1tXkhSSPelDtavzULLucZ1GSNz0M5Is58Po1M8V0j+WUb8n0hrsSLGHEfLWgkg3y/GT9K+ScBJgEkWeb1+N7wg4phB3y/eP3ly5crOWH7UA7YVrQKyiIICAKCQF1GoNaTNhIjWkLYYVO5klBQUZOosMPmFzo7aCoHWuJIsqj42NFT2ZLE8HwqSypckg5avGjxYEdPpUkF2rx5cxXLRcuS5n6h9YP10dJEZU+lQ0XBc2jtexlp4z2R5FF59+3bF25ubkqpa6SNbiAqNip5BtTzWlyPHj1aWWH4nCRxAwYMUASFlgJagGiBoILjczKWi5YE3tfBgwcVuSShJSEgKeF2WhXpiiMR5TkkaSShfG6SV2JDUsH6SST37t2rSC8xorJkvcSlNig9jbTxuUh0SF6JD3+TWGptQmVPyxqJ9yeffKJIMbfRekZrFvGgMu/evbsiAJorjdiSlBF7ygvJKy2XPJ7PT2JGUk1MSRCIPYkZyS//J0kg8eNxjPXifZKkEF/KI/9nfCY/PnhNEhZabUkeSdJoCWTcHeMKiT0tRiQhtX0hSSUWdCdTRinzvH9iRyxodeaHk/Z8fC7KOd9nfkzxXeHHGd9Nvn+03lEe6TJlm/KDjaSZ+7id1+IHHT8k+D8xZruyHVgHLad0mfP9J8Zsu9f9wVHb21DuTxAQBGo/AnWCtLFjZywLXU3s6GkxorWFpI1f3lSaJF39+vVT+6kAqASpJKkc+VVPBUIlTKsAyQsViEba+EWvxUTRvaIRO7rbSI5YPwtdNF26dFFKtrKkjRYGXo9KhCSIyp73SvJEiwIVzUcffaSIAJ+NSp2WN7rOSBxI4kgSqPRpcaHSInGh9Y1WNFrdSCjpTuPzkHCRBJKg0ApHUkILEq0TPJ/X5DOQ4JLY8b54j5oVjQqXeH/xxRfKgkRSSQtVbSBsfJ000kYSTHLEOCqSNZIqkia2M59biwejoifelAES/LKkje5rEgkqdip/nsv2oNxQtkgCSPqJDxfiQysfr02caNElsSZZIf5sY1qdeJwpaaMMcDvvm5ZAEg6SYRIaWjhJ5L/66islv5QDxohRFmhR4n3V9oX3yHvlcxA3Ws5I1ChjxJ0fWV9++eWT5yNutMzRlU2rGt8zWknLEiviRtkm3iS33M+24vtIy6V2PNufxxBbfmBwH2WBVnHtmNqOYdn7432zv+K7x3eXv+vqs5R9Nvm/egiYygblQ2SjenjWpbPrBGkjEWFHTUsUlSPJGEkFSRu/0vklTpcWrXEkZiyMKSKxojWD1igqQipidn5UwPyfCoNWM5I2Eh2SG74ALFo8GS0FJIxUGCRIJFT8XVnSRmJFhUblResfFdnnn3+uSBvvh8/C7bT6aPfONUkXFRYJCZUbyQrviy8rFRGVHskpSR8tanQDMpaPVjNanzRrB5UYiR/P4fk8lgqU20gWeCzxpUWDdfM8/k+XKu+LRFiL/asNCkMjbWwXYkSLDIk2Oy22Ga2xJFHEjttoAaKskFDQRVYeaSPZo3zRokXS1rRp0yekjdYvXotEgAuvR5JHqysxInkgMaRcEisSYlowSZJNSRtlgOfyHmiF4ohKtg0JM+WAJJyua40sUgYo25RPPkdtXygbJF+08tKK1qNHD2WlZDuQUJEck1TxvSSp4/Pxo4TvEf8nQWWcoqZ8WB8LrWYkznxPSHC5nzgylo1tw/eZxxFXWo1JdinDJG08RiPvtR2/svfHZ+L7yveWz0ZZJxZaH1D2+Jr8n/fGdqhpueT1tPauyeetbdfSZIOyTdngO6QNvOM+Weo3ArWatNHlQUJG0kUlSMVJQsEYIgbn05VFQkWrERUmiQiFmNuo8LjmOXRvanFhFHAqTVpTaM2iUmRMG8kYlTE7RRYqIM0SQJJG0kUrSefOnZ+QNrrOSJZo/TJ9Wdix8HjG2NBKQ1JB5UVLTJMmTfCHP/xBuUl5f4wZa9mypSILVP68Ft2mvC+ewxgpEgESSh5PHFjoDvz4448VceMz0eVG4klrzf9v7w5244aRIIB+R65BkATxJYfkS3IMkP//jMUboJJeQZadXccj0SVgMGOJpMhqkl2spmQ4ICF5wIKqw0lS62BpYz1yIHSEtDk3SZu/kWD7j9Qv2MJytvMeQwNpE96lWG7rw7EJsVEm2VRfoGaFJCMPSBti5zeiLLQ6SRviH9LGHsgVYqw8GCF27IB8Swc/WCNcDw8Pt711rusTyqUg6cfUSufZio2RcQRDaF+5VCH3oYSqm3Tqn43998D6b+8Jf2OK2maPKAXYWNJfESwEF6G1kELAtE84HjER7tR+RI5dYeQax2RxJa8x4BwbUPIQPdjCC1FnE/dE6tgFkb4iaUNOYGR++/Hjx00tp5hrr4cvkNLXJkzpC8a//m5xo3+/1nzA5mxtrjde3vJBdDA3WzSKEOkb+r4Hec4UFXnLNvqXbT8taTMZWIF78pHjpVRwAJyaDoqEISomfA7OJO5pMaErITP5TCy5LhyKZCFOQn4mQJ3cBEiNoVJRahAuEyKnQlmjNsljb5qVO4UFoeIo3IOqkJBqDCU/RUF94riUq3zlCbOa8DgUJIQqwKlxTkggx0elsbJGrJAuDzMgrMo1gXH6yJQ6SKcNiBYiADd1Uj6Cqs7IgbRCTdrNMSIlVCSKJZwcvuGN/HCgHDG10FOWNnwr954Hu1BJTd5I7TyQAxhz8OqrDUi/diMB0sMNFiY+CivMEGz9C9FC1pFzduEcbIxHvOShOHJYMKAaSWdBoF8KfVLOKEIwZG9KJruyGQIt3C7ED3P2pAzpB8pDFvUX9dZ/9WO4s8G9HPTE9jm/4a/fetrTeLNQMI7VXzthIxyf9unrFijw0359M+035jgmfd0DIewIS4op4sZOyrLXTVqkj72NTdhn64A6vRaxeA5GT6VRV2PTWLf4gJk2e8hKOy3WhJu1Ub/RpxE8eWZb4aav6tPmOJhJO7FQhjwcvflMf2cL9kJ8jRELDXmV5byP+dZcap6SV39XF9fcV12y6HQP91SuMs1J6iGfdFnwSqMMdVAX+c1rygwmxo2FtAWnMtzLoQx/yzPLfArrq12HBQzNfQib+cMWDftfYWOhYs6BB7zZDJawjv20Gc7KYbf0jani6hOus10OedKf1KPH/RA4NWkzAK3MM7GDSecyiXuNB9KhY/lw5kicTmz/kpW3yU0H9uGgqUY6OIWFc+EQdU4TBXJj8kuH9O060oXkIIDSyKtT68DqJs3s3OqYSQbJQaaU5ZxBgiAgSUiEgWUwuK/2uA8FKXudTEomOcQNYaC6IRPuh0xxhCawDFD3oxaq37yn8/YLUdA8gGAyVoaJTtnKzATomyIHLwNa2fCxj9A5WN7zgCEHP+s866PtVDG25viQLpOWdmibPoPYsbsJjT05Jddhwhb6kbbDEEYwZbPY3v2s+vUhjoJt9T/2sKhQlnPK11fh7SM0jbiZYJF9aSfuyLb+5jpbKU8+9bjCoZ5wQ2D1FUQ4h9/Ubw5H+9gGrvqWfOyB5FGSEC4P7SC7rulzsDKmkW55lGdssbPxTl1GjIOV+7Oz8XWlQ99BSIWTqbf6pn6pP5kLzIX6pPbrc9Q45Ne8p73mJemlYwfzA8wRZfiZU133YSs2EJZGCJWlzyqbLfRRC0khfH3RONJfjSnqvxA4MmluZBNzs7lG33U/YwbBY7+MI4sc+dlMndNP1AdBVAd5fdjUeHRP482i2XsvLdDNh+ZQZZuD9QN5jC/jCA6rHfoynyY6YBGj/8NN39Be/QGGxhLc4OzBKFibqzLvszGbUa4zHtlKfvfgo8yx7K1sH1iznTF2tTG1Wj84LWkDtM5iEs5EPM+ls8Yg0jpn0osDnvn8ntekdS6dMr9Tnu/H8sx6SLN3/D91V0/5533UN3We53P/3E+aeeT8bPu27JSRfMkz0817J909vtVJXVK3bR1S9732SpvrvufvlOPcLD9/Kw9O/nb4Pf9OWRPLnPOd36lXyst9U+a8Pusx0535t3Y+1ldgc9S+7fWJpd/KnZjM9Nt7ujbznxmz1A12Fh0crUiAPbzalSN9yLfFB/KCOFEYKY0UYSSMA0d4PIwl5JwoBGUeYUagkCwLWBELiiXShvxZiLqO8FH1EDbX7Z+1tUD9XPOKHcQNwebMkTMLT1s0pKduI1lC1MLgyAZ1zkNB1FEqnS0B2olgIopIJwUb+UJYKeq2JyAiFjz+ti1GBMQ7NC3cEDbRC5ESKjblnNKO+MJppQP2FpRsblEzF9Damg+irw8Jm7I9hVrfQGj1DWocpS77aGHsOrsh3uyZ1yAhaMYsAshWifSshOvV2nJq0nY1MFvfIlAEisD/igCny2kKk+cVRXtlSUeNFypElKggFCuEB4Hxt+ucO1KF4CFGyJ2tJRQVr5WRFilDqKgqVDhqHjJAqUGIqNbIIzJkmwanL70tF8gX9Yb6zZkL1wnRUcXkpezZ30jloX5Rh5A95EykAAGxv5aCjbQhktJR/51DIj3YomyKtvp7iCrEUhnSCKtTjSi5lG3bFGxnmaRmD8erndM3REzsc6SETUI/2yKawrYUVHYUOYEToqYvIMBIuCfd/Q1HhBzJZzs28PAPcsy2SDPF1cKAja62GJrYrPC7pG0FK7YNRaAIXB6BkDb7HY9IG2dtz6M9lQl5UceEKr0KCXkR7rInjqqCECFbQu/2G3LilBphNiTH9RzqILzGsXP6tmsgfsoSsnUfRIDD59Sl58QRO9c5dnmyfxPposwhYogAdU1+Cg7yhVgiIMpFLG0RcV9kEgkUDhWuc905D4IlDO7bw14IJFKi/UKzykQeEY6VDu0RskbahDcfI20wRNps55GGfSmvVFAknApJSaO6Cj2zHxKvP1EwQ+Lsj0a+3Yti6t6rEeEr9o+StitarXUuAkXgNwKIg8/VD20QArMHicO0j1RoKu3jXJEdjlb4EUlCxpzn0KklnkTnaJE2ygoHrAxEzL8Vcx05othw0oiT8hzuoyxKHMJEXePs7aVF0jh9++AoL/5GjKRHDKg7yBLShgyEfGmLe1DLKHNCpNlDar+dOnhnpRCqJ+2VgRwI0QnZfvny5UYgJ2mj9Lmn8KiQL4JLCUIWfdwfEYTNSoe+gUAJe9r7yaazb8DER/uRNoqmv9lXeJMCyRYIGtUUVkgYG9qLiJgLmVNcKW76D1voC0LdFDhpe9wXgZK2Z+BvYPQ4DwJxLiYQn7PaR704TBPnWev4t1bdYh8bxA6v2c7UBZHxUYerH/oLB4qQ2WMkLMixOo+YISrCZBQligsnzHkLidrThfQIeQmPcrrOT9ImXKkMRMk+JhvRESJ9VDoOXpmUFaqLcCllTAjS6yWQNhvZkTNhXLjLJ4/9cxQvRBFhklc4jdLjnkibcvJgUEibp4T9Ft61j05+9/DU7MePH3+TNgqc8ChS6r7SedqY4kdBck8f93Tv1+yLr9Hv4My2wuJIlwcR0je0175CuHmYg+3Zjz3ZlwqpTyHslDbX4S0f+yDJVEwLBRjqd2wpjz5jkVCV7TWs/PQ9StoOMDJIrCpNSFY5q00CB00/5SVO2SQj1GLlSDmwl8VEZuK5p304EXXjUFMPDo5z5FDU78qHNlFIrNKpKpQMq34fv33sqzJmXuuAr/1SFBpPD1Jrgv1r1eGl76P+SAfFAymjdnnKEkmzqRzx4XjNSQiQ0CDVBWGzUZzaxkkLSVJbzF8IGWJHffMv2ihVCI88FD1kiINH4BAiZAABo64Io3LeHDpCqGx93P4yf8vL9urEBvbMUciUpS5CmsKYQrJeX0K1CWkzjpECfUid7EOzOV57fYQ+P336dCOx5l+qn/dQ2jjvtzCwvW8eUPDaJPcXAnZP88LV+8K2b2mPecReQbZmI31fKJrSqD8g/HCBEfwoZcLb+oIHPPQtaRB2NqWIyk85RQTZRn+Bt5C3F5OziaeHV1gUbTG94t8lbQdWM9FZgdiLYbWpM28PA0ln9nnuJLFNlzK25+e9/qb8mW+V37Cx+uOM7MfgzKz0vQ+MI7AHZ7uHRZ589nBw7Slct2m2f6dce4s4PqoBAiedMIMJEbHQl3I8Vkau+35Ompn+X/+GE4eep9E8rSe0RX2xwdwY4Rys7Ld1z9/KODqSbpsm57e2YnMhHWoLkiCsJ61D2r375brvfLb3u/ff6q0tiAm168PzhwAADXNJREFUDVHTRkQprzzR1+318s5JShMnDQNKi/5nLxuih9gqj0oivTI4Zn8jWpy+vMpAwJAreYREkSzXhDhdQ4Y4c+V7BQsypz9QdhB6qh7i5MlQ5VHNhODMna5bZKmjxY06IY7uj7whgupsP582I34Ih3YjdBYD0quH8o0r5+FgzGmXe3qfonqpX2x9b3u+5P21CZYWTvDVNyhm+gF11RwJXwtFJA0mwtiUNmSc7fQDc6j5E86u+0bmXHfoH8KhnhD2JO8cWy/Znpb19wiUtB1gZkLQ2a0oM3HM5Dq2ladJyYTFcXPOBpbOb/CY5HKYeFx3PuEIUrRBaEVssoxiZFKTTpkmNJOx+jj/Fg9YcyRWhx5hp/jYJ4NU2+NBFTBRBWOYsQ1s2QeWmZDgB2erTtdgm+uxHaxdh7807MaWHB7nEXu4nzxWt1a6HApbsit7coz+Vn+2c19kzjllSee8MtzD/dzbNfdVhr7i+j0P94eH93dxrgiFjexW4TY829AOf/VXZ3WXXrud014f14JZVvTay1YcjnwwSZvZTH7jywd2rklDJfCfTdyfnWGr7NhVWcrN/RBKZbG1eihL/e6N7Z5d1Unb1Z/D1BZ92rnUV7tgpz9qSwhz8vo7bc85fThziG99Tl+etnFeXmUqG17SwTd52cA591dm7AVP2CpPubnmujJnHZ2LzdQvtktdXEtfgFHq5Z7OBwv5YAMjfcRv51Y+tC+2h1fGWvoGbGHkGjuyFfx87Fez0KXmGg/GnX4mj0PZbIgYmlspoezW4xwIlLQd2MGgeIy06fycFEnf/g9PRVn1CIeZuJA8q0hEw2AwmDhi0rbVprLtQbCaJHPbTGtVSdY3GZkorVKtoqyCSNdeKGkie4uHCZmi49+NCbfAAa4maOEZe10oAiYhK292sfq28Vn4xMtchVHZTT5hFSoCsgd7K3g2MzkhYMINPlajJjhEhaKgDjMPhyqP/P7ThY3eVECKg/5BEbBPhD3ZXJjBfiD3ZFMbwp1nc0SU0qAs95XGKljbM6He0/b6sHr4UN2obcJhHIZVvP5OjdEGY0Jft3qn2OjjQnn6MyKrvRyDNPKxlfKkEZJDwuDqPlQ8795yzRgTBhUe51DevXt3w0kojoNStlCZ+7snBUJ/4YgoOuomnGisUSHY/AzYPmZXmMfZxiHPtLnue+/6TOv3Nk3yu8e85neu5fdeWXvXkm9b5jb/UX1Sru/tkWvz/N/cc+a78u+n2pzrEy82oUIakyIDIb7S5EDiqOa/fv36rXTK1+McCJS0HdjhiLTp5JyBl1n6WJVwAmRnsrKOz0FxvoiEwUGNoMYgXxwxh44ACPkhHhyMcF/yczr+z6YVkXvsqX0H1V/qEtL08+fPGyHKqlEDOWNYezIK1pQBCgwSx3nDFTEwAWW/D3zZAbGzikQA7PmwjwZZEHbzPikkwrukkCkreASEnYU77Q9yXQiCmoCM2UPCfmyF+LmPOiEhiI1y7EXxugbkXvhKvYS8rIbV0//sFI5wXX2RFft05D/TgRzZByM8aZzYz2ZzM1UauYWBND4wQ1y9U0z4CgnOpmlkzbu6PPEmHXLNltQztkTEpTdG4K4cWBh7iNfnz59vtoC1zezwt2naYokKK42y2c8eHZuq2U157ElhmA7rTBi3LkXgpRHQ1/kj49UY2iNj5jMhVGPNAyTm2x7nQaCk7cAWT5E2zoNzptpwOBQxe3w4DAqQPRxeYkiOlpaTRtKs+DkYygGnjiQgJZy7R9jtTaDgcNgcGLKWMMNbdTAcLmwQmqwOmc6kIwwwXxZJ7bEXQwgvCheFRlgViaCeegIL3nBnH9eRZM4fuULaKJ3sSDml7CERJjMEDSGg5rivSdBeIGXY3K3fIJMmPMoc0k1l9ZZy78kS1lUvdbEvhZIkrZWvN8ZTCqlQykQsXUc6znSo+yRtcERAqYPCYvDy0Q4OAgkzLpDc79+/33DUJgsVdmUDdoQNwg0L/d6eKQQbJtQ8pBq2PsbTt2/ffjsW40a4FMlFyNiRYmCzO3WBim1jNaVNHfWjPad1JpxblyLw0gjo8xlDe2W7bmyY9/x+qz5nD5sznCtpO7DCEWkTUuGMEoJDvjgtL5MU8owDcl64izPiwDlpq3uOH3FAykjVFAFO0NNcnLwQEILnM0nKQXWXvkSlFIqDlckkEwk7wBOWQqFwy9NS3lOUwzn4cuY2OtsbR5WBO0WU7YQtkQfOnqpHgYtTR8yQcDZE/ny8QZz9kA+r1oSyhfXUD+kKaZNGqFP/0K9cV2+qq3bpS4iKeiGObI7oCZ8ihkK7Zzr2SBsSK6RsgeHwzW5CktQyYwGp+/Dhw22RgwQbP84ndO3b+8CMIQoqJdSYoGIi7PBiC3aHDQLI5giiMOv79+9vYWd21VeoajBld6TN05P6BRv1KAJFoAhcDYGStgOLPUbaOFwKDBWAo+IQOG0hF4/pU3KQNioDNUcISYiGckahscrJu3Lsq6IiUeuoEVQ3oSMOi/KDWIQ4HFR1+UucOYePnMVpazTna+8YBYs97GuitCFhCEPInSfKkDJKGczZQogT7kga7JUDd38jCUKUWWki2eyBTCAs7I382WNHFQ1pE/rcI23C4UKDVCT9QrnUV0RQyJTyKqyICCofadNO93Nd+Wc69kgbgiScKZwS0oqwwYQSpw0Us4eHhxu2cKMkwlGfhwk7w1S7kT5kDImlmlIykV52Mb4maYO5sLj/TSnMzK756AewFLLVT6huiH+PIlAEisDVEChpO7AY0uYFj/bccOTCNZwLZ2N1T9lB2jxR5xqVwR40e9WEvzhehI6j4aypMxwX56QcYR+b0aksyqPMcIYUFp+Stj/G4cDtd4KlbzghaMgAYutJRnsw4Ia0sQPyTM2BLSztOWS7PPnoYQGYOyfMLR3nvkfa7G2j+AjBUc2QbgqZzfDyI2WUHcoaG+s7yozSZs+a+lB6hNLVS99gf3uw9IfVSJtxYXxQOT1QQG2mNFPaEC+4IW32Hu6RNrZE4lwzvqhuSDuyRqWcpM1CCCnzMAic3Vs+9nVv6SdpMzZ7FIEiUASuhkBJ24HFrOY96em1BtQZigHFBingAOx5svnaOftrhIA4cupJ1AYO3MMJX79+ve2lUSYVgjIg/CZkh+xxNMqgFnBQyINwG6IRteigqstfinIjnOZpUERHOAxGQpn2MdnvRMVCEpA7T3Ei0OwmzEzlQf6QvYS1PXwgHC2ETSmVHxFEyCk1wd4+RGE8ah2yoEwPL1D/EDYkzXkKnbIQSAoRdQ3Ro8z6m/KkHPfVp5Aa6p/riKEyERUkBNGQF/FDFM90ILjCvTCGKZIkJIkIR2mEs318UeCocNriCVvY2ldmDNkLCkOLGe1kK2oZYqu82AjBgzdSbXxRSqly7pO8FG33MEbZ1XjSNxBAKjbijTyWtJ2pN7UuRaAIPBeBkrYDpIRQhK1M/BwxB+ODCHDsNo9TbRAApMueGQoCB8Yp2HdDTaAuCHHJw7nk4Oi92ZxTsoGdw0HkEAeOUEjOJ8Qh+d7qNzwRs2xo9040tuGMYQlb2CFznDubUOWQao4eCYKldAgBrJEKZIBN858vEAikHDEJ9ogI+yGENtOrA8UMEUTEY2tPSLqvJx2RL/el9Ajz6U/O2QiPqLgnwua8/NRD+YVN1VEeah2FSd3PdKijkLL+rv7s4m/kFuF0GAPULmq19lrM2DOIiDnPZkKVFEe/Ye2bXbTbwoWiieyxEbvCPAsfuFInkxdm6oX8SmtM6R8wpnwbi4g5AidtjyJQBIrA1RAoaTuwGCfC8XAS84NQOc85caychnNxzK5xCpwOh+uJUo6LswgJcNuUL68yOBZlyOsaZ+jT4w8CsEGgYAUzdoF3cEXaOHkKJoIAW2nhOB01kjTLiU2lcU36kI9pK/eLneT3SbnysZ+ykj/f6ucjTeqUe6bu7jfLc3577g8S9/2lzdqmvmmXv6ctcj7tpY657lu7lOFvn2DoW5m5rkyYx9a5n9ZLo6zkdc5vNtjrH7GP7x5FoAgUgSsiUNL2DKtxPtvPzJZrOedvDoUKJ2Rqo7W9NRzQ3pH8+d5L03P/jUCw8j0PzpqiQ/2EedLNNPN3rm/LmWnm7236vXx7547KmNf2fj9V3l6e1zr3nLpJk496PSfPrH/y7uV77NxjefbSz3v1dxEoAkXgzAiUtP0j61jNC/HYuyOMavVfh/GPwB7FIsbCmkJn9on1KAJFoAgUgSKwCgIlbatYsu0oAkWgCBSBIlAElkagpG1p87ZxRaAIFIEiUASKwCoIlLStYsm2owgUgSJQBIpAEVgagZK2pc3bxhWBIlAEikARKAKrIFDStool244iUASKQBEoAkVgaQRK2pY2bxtXBIpAESgCRaAIrIJASdsqlmw7ikARKAJFoAgUgaURKGlb2rxtXBEoAkWgCBSBIrAKAiVtq1iy7SgCRaAIFIEiUASWRqCkbWnztnFFoAgUgSJQBIrAKgiUtK1iybajCBSBIlAEikARWBqBkralzdvGFYEiUASKQBEoAqsgUNK2iiXbjiJQBIpAESgCRWBpBEraljZvG1cEikARKAJFoAisgsB/AFUGaVVW36diAAAAAElFTkSuQmCC"}}},{"cell_type":"markdown","source":"Yellow shows 4 neural network layer, 3 of them is having sigmoid activation function (output will be 0 or 1) and one is having tanh activation function( output will range from -1 to 1).","metadata":{}},{"cell_type":"markdown","source":"LSTM has 3 gates:\n\n* \tForget Gate: - It decides which information from the previous timestamp is irrelevant and can be forgotten. It has first neural network layer with sigmoid function.\n\n* \tInput Gate: Try to learn new information from the input to the cell. It has 2 neural layers first one with sigmoid activation function and second one with tanh function. First, a sigmoid layer called the “input gate layer” decides which values to update. Next, is the tanh layer creates a vector of new candidate values.\n\n* \tOutput Gate: It passes the information from the current timestamp to the next. It has sigmoid activation function.\n\nIn input gate the sigmoid layer which decides what parts of the cell state is going to output. Then, we put the cell state through to tanh and multiply it by the output of the sigmoid gate, so that we only output the parts we decided to.","metadata":{}},{"cell_type":"code","source":"os.environ['TF_XLA_FLAGS'] = '--tf_xla_enable_xla_devices'","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.608681Z","iopub.execute_input":"2022-05-08T16:15:36.609124Z","iopub.status.idle":"2022-05-08T16:15:36.614467Z","shell.execute_reply.started":"2022-05-08T16:15:36.609090Z","shell.execute_reply":"2022-05-08T16:15:36.613865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"embed_dim = 32\nlstm_out = 32\nmodel = Sequential()\nmodel.add(Embedding(max_features, embed_dim,input_length = X.shape[1]))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(lstm_out, dropout=0.2, recurrent_dropout=0.4))\nmodel.add(Dense(1,activation='sigmoid'))\nadam = optimizers.Adam(learning_rate=0.002)\nmodel.compile(loss = 'binary_crossentropy', optimizer=adam ,metrics = ['accuracy'])\nprint(model.summary())","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.615426Z","iopub.execute_input":"2022-05-08T16:15:36.616021Z","iopub.status.idle":"2022-05-08T16:15:36.898271Z","shell.execute_reply.started":"2022-05-08T16:15:36.615987Z","shell.execute_reply":"2022-05-08T16:15:36.896155Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* Activation Function of Dense layer, i.e, is output layer is taken as Sigmoid function is taken as it is good at binary classification and our target column have value either 0 or 1.  \n \n* Dropout : It is added to avoid overfitting.\n\n* Loss Function : The cross-entropy loss function is an optimization function that is used in the case of training a classification model and binary_crossentropy function computes the cross-entropy loss between true labels and predicted labels.\n\n* optimizer : Adam is used as optimizer which is replacement optimization algorithm for stochastic gradient descent for training deep learning models. Default learning rate of Adam is 0.001, but here I have initialized it to 0.002.","metadata":{}},{"cell_type":"code","source":"model.fit(X_train, y_train, epochs = 10, batch_size=32, validation_data=(X_test, y_test))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:15:36.899653Z","iopub.execute_input":"2022-05-08T16:15:36.900036Z","iopub.status.idle":"2022-05-08T16:16:12.005738Z","shell.execute_reply.started":"2022-05-08T16:15:36.900007Z","shell.execute_reply":"2022-05-08T16:16:12.005162Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"  y_pred = model.predict(X_test).round()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:12.006981Z","iopub.execute_input":"2022-05-08T16:16:12.007200Z","iopub.status.idle":"2022-05-08T16:16:12.408271Z","shell.execute_reply.started":"2022-05-08T16:16:12.007178Z","shell.execute_reply":"2022-05-08T16:16:12.407512Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_pred","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:12.409892Z","iopub.execute_input":"2022-05-08T16:16:12.410196Z","iopub.status.idle":"2022-05-08T16:16:12.416390Z","shell.execute_reply.started":"2022-05-08T16:16:12.410153Z","shell.execute_reply":"2022-05-08T16:16:12.415458Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"11\"></a> <br>\n# 11. Evaluation","metadata":{}},{"cell_type":"code","source":"train_accuracy = round(metrics.accuracy_score(y_train,model.predict(X_train).round())*100)\ntrain_accuracy","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:12.417550Z","iopub.execute_input":"2022-05-08T16:16:12.417739Z","iopub.status.idle":"2022-05-08T16:16:12.941066Z","shell.execute_reply.started":"2022-05-08T16:16:12.417718Z","shell.execute_reply":"2022-05-08T16:16:12.940295Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('Accuracy  is  : ', (metrics.accuracy_score(y_test, y_pred)))\nprint('Recall  is    : ', (metrics.recall_score(y_test, y_pred)))\nprint('Precision  is : ', (metrics.precision_score(y_test, y_pred)))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:12.942189Z","iopub.execute_input":"2022-05-08T16:16:12.942406Z","iopub.status.idle":"2022-05-08T16:16:12.954064Z","shell.execute_reply.started":"2022-05-08T16:16:12.942381Z","shell.execute_reply":"2022-05-08T16:16:12.953236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* Confusion Matrix","metadata":{}},{"cell_type":"code","source":"conm = confusion_matrix(y_test,y_pred)\nconm","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:12.955504Z","iopub.execute_input":"2022-05-08T16:16:12.956400Z","iopub.status.idle":"2022-05-08T16:16:12.968689Z","shell.execute_reply.started":"2022-05-08T16:16:12.956352Z","shell.execute_reply":"2022-05-08T16:16:12.968160Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(7, 5))\nsns.heatmap(conm, annot=True, fmt='d', cmap='cool')\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:12.969704Z","iopub.execute_input":"2022-05-08T16:16:12.970588Z","iopub.status.idle":"2022-05-08T16:16:13.187165Z","shell.execute_reply.started":"2022-05-08T16:16:12.970549Z","shell.execute_reply":"2022-05-08T16:16:13.186393Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"* Classification Report","metadata":{}},{"cell_type":"code","source":"print(classification_report(y_test, y_pred))","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.188240Z","iopub.execute_input":"2022-05-08T16:16:13.188437Z","iopub.status.idle":"2022-05-08T16:16:13.200968Z","shell.execute_reply.started":"2022-05-08T16:16:13.188414Z","shell.execute_reply":"2022-05-08T16:16:13.200249Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"\n","metadata":{}},{"cell_type":"markdown","source":"As Accuracy, Precision, recall and F1 score are above 70 % this model can be considered as good model. \n\nBy changing dimension on Embedding Layer, max_features, LSTM can check if the evalution factors are improving or not.","metadata":{}},{"cell_type":"markdown","source":"<a id=\"12\"></a> <br>\n# 12. Submission","metadata":{}},{"cell_type":"code","source":"test_data = pd.read_csv('../input/nlp-getting-started/test.csv')","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.201951Z","iopub.execute_input":"2022-05-08T16:16:13.203206Z","iopub.status.idle":"2022-05-08T16:16:13.223761Z","shell.execute_reply.started":"2022-05-08T16:16:13.203173Z","shell.execute_reply":"2022-05-08T16:16:13.223224Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data.head().style.background_gradient(cmap='coolwarm')","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.224815Z","iopub.execute_input":"2022-05-08T16:16:13.225195Z","iopub.status.idle":"2022-05-08T16:16:13.236768Z","shell.execute_reply.started":"2022-05-08T16:16:13.225168Z","shell.execute_reply":"2022-05-08T16:16:13.236264Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"For submission stopwords are not removing, as words like 'not' has a major role in distinguishing disaster and non-disaster tweet.","metadata":{}},{"cell_type":"code","source":"test_data['clean_text'] = test_data['text'].apply(toclean_text)\ntest_data[\"clean_text\"] = test_data[\"clean_text\"].apply(clean_tweet)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.237787Z","iopub.execute_input":"2022-05-08T16:16:13.238172Z","iopub.status.idle":"2022-05-08T16:16:13.395780Z","shell.execute_reply.started":"2022-05-08T16:16:13.238146Z","shell.execute_reply":"2022-05-08T16:16:13.395175Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test_data['clean_text'].head()","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.396953Z","iopub.execute_input":"2022-05-08T16:16:13.397348Z","iopub.status.idle":"2022-05-08T16:16:13.404377Z","shell.execute_reply.started":"2022-05-08T16:16:13.397302Z","shell.execute_reply":"2022-05-08T16:16:13.403581Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"## Creating New Model for submission with \n\nmax_features = 5000\n\nl =50\n\nlearning_rate=2e-3\n\nlstm_out = 100\n\nAdding two layers of LSTM\n\n","metadata":{}},{"cell_type":"code","source":"l =50\nmax_features=5000\ntokenizer=Tokenizer(num_words=max_features,split=' ')\ntokenizer.fit_on_texts(train_data['clean_text'].values)\nX = tokenizer.texts_to_sequences(train_data['clean_text'].values)\nX = pad_sequences(X, maxlen =l)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.405249Z","iopub.execute_input":"2022-05-08T16:16:13.405555Z","iopub.status.idle":"2022-05-08T16:16:13.563120Z","shell.execute_reply.started":"2022-05-08T16:16:13.405527Z","shell.execute_reply":"2022-05-08T16:16:13.562449Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"tokenizer.fit_on_texts(train_data['clean_text'].values)\ntest_token = tokenizer.texts_to_sequences(test_data['clean_text'].values)\ntest_token = pad_sequences(test_token, maxlen =l)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.564110Z","iopub.execute_input":"2022-05-08T16:16:13.564328Z","iopub.status.idle":"2022-05-08T16:16:13.705824Z","shell.execute_reply.started":"2022-05-08T16:16:13.564304Z","shell.execute_reply":"2022-05-08T16:16:13.705022Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"embed_dim = 100\nlstm_out = 100\nmodel = Sequential()\nmodel.add(Embedding(max_features, embed_dim,input_length = X.shape[1]))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(lstm_out, dropout=0.2, return_sequences=True,recurrent_dropout=0.4))\nmodel.add(Dropout(0.2))\nmodel.add(LSTM(lstm_out,dropout=0.2, recurrent_dropout=0.2))\nmodel.add(Dropout(0.2))\nmodel.add(Dense(1,activation='sigmoid'))\nadam = optimizers.Adam(learning_rate=2e-3)\nmodel.compile(loss = 'binary_crossentropy', optimizer=adam ,metrics = ['accuracy'])\nprint(model.summary())","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.706898Z","iopub.execute_input":"2022-05-08T16:16:13.707136Z","iopub.status.idle":"2022-05-08T16:16:13.977198Z","shell.execute_reply.started":"2022-05-08T16:16:13.707108Z","shell.execute_reply":"2022-05-08T16:16:13.976410Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plot_model(model, to_file='model.png')","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:13.978482Z","iopub.execute_input":"2022-05-08T16:16:13.978695Z","iopub.status.idle":"2022-05-08T16:16:15.002452Z","shell.execute_reply.started":"2022-05-08T16:16:13.978670Z","shell.execute_reply":"2022-05-08T16:16:15.001534Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"es_callback = keras.callbacks.EarlyStopping(monitor='val_loss', patience=3)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:15.003755Z","iopub.execute_input":"2022-05-08T16:16:15.003974Z","iopub.status.idle":"2022-05-08T16:16:15.008356Z","shell.execute_reply.started":"2022-05-08T16:16:15.003948Z","shell.execute_reply":"2022-05-08T16:16:15.007610Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model.fit(X,y, epochs = 10,validation_split = 0.2 ,callbacks=[es_callback], batch_size=32)","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:16:15.009175Z","iopub.execute_input":"2022-05-08T16:16:15.009383Z","iopub.status.idle":"2022-05-08T16:17:57.161120Z","shell.execute_reply.started":"2022-05-08T16:16:15.009360Z","shell.execute_reply":"2022-05-08T16:17:57.160350Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"y_hat = model.predict(test_token).round()\nsubmission = pd.read_csv(\"/kaggle/input/nlp-getting-started/sample_submission.csv\")\nsubmission['target'] = np.round(y_hat).astype('int')\nsubmission.to_csv('submission.csv', index=False)\nsubmission.describe().style.background_gradient(cmap='coolwarm')\n","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:17:57.162135Z","iopub.execute_input":"2022-05-08T16:17:57.162408Z","iopub.status.idle":"2022-05-08T16:17:59.388568Z","shell.execute_reply.started":"2022-05-08T16:17:57.162380Z","shell.execute_reply":"2022-05-08T16:17:59.387708Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.target.value_counts().plot.bar();","metadata":{"execution":{"iopub.status.busy":"2022-05-08T16:17:59.389730Z","iopub.execute_input":"2022-05-08T16:17:59.389995Z","iopub.status.idle":"2022-05-08T16:17:59.633568Z","shell.execute_reply.started":"2022-05-08T16:17:59.389964Z","shell.execute_reply":"2022-05-08T16:17:59.633013Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<a id=\"13\"></a> <br>\n# 13. Reference","metadata":{}},{"cell_type":"markdown","source":"https://en.wikipedia.org/wiki/Cosine_similarity\n\nhttps://www.tensorflow.org/api_docs/python/tf/keras/preprocessing/text/Tokenizer\n\nhttps://colah.github.io/posts/2015-08-Understanding-LSTMs/","metadata":{}}]}