{"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":"\n\n<div style=\"border-radius:20px;\n            border : black solid;\n            background-color: ##FFFFFF;\n            font-size:200%;\n            text-align: left\">\n\n<h1 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:green'><center> TITANIC </center></h1>","metadata":{}},{"cell_type":"markdown","source":"![](https://blog.aspiresys.pl/wp-content/uploads/2020/11/Blog-2.3.jpg)\n\n# **INDEX**\n- [Importing necessary libraries](#import)\n- [Importing the data](#data)\n- [Explore Data Analysis(EDA)](#eda)\n    - [Null value](#null)\n    - [Missing values percentage](#miss)\n    -[Comparision with survived](#com)\n    - [Data Visualization](#vis)\n        - [Distribution of age](#age)\n        - [Distribution of fare](#far)\n        - [Relation of various with survived](#rel)\n    - [Auto Visualization](#auto) \n    - [Data Pre-processing](#pro)\n- [Model creation and evaluation](#model)\n    - [Decision tree classifier](#dtc)\n    - [Random forest classifier](#rfc)\n    - [k nearst neighbour classifier](#knn)\n    - [Support Vector Machine](#svm)\n- [Submission file](#sv)","metadata":{}},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n\n<h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> PROBLEM STATMENT </center></h2>\n","metadata":{}},{"cell_type":"markdown","source":"The sinking of the Titanic is one of the most infamous shipwrecks in history.\n\nOn April 15, 1912, during her maiden voyage, the widely considered “unsinkable” RMS Titanic sank after colliding with an iceberg. Unfortunately, there weren’t enough lifeboats for everyone onboard, resulting in the death of 1502 out of 2224 passengers and crew.\n\nWhile there was some element of luck involved in surviving, it seems some groups of people were more likely to survive than others.\n\nIn this challenge, we ask you to build a predictive model that answers the question: “what sorts of people were more likely to survive?” using passenger data (ie name, age, gender, socio-economic class, etc).","metadata":{}},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> Importing relevant Libraries </center></h2><a id=\"import\"></a>\n\n\n","metadata":{}},{"cell_type":"markdown","source":"![](https://d6vdma9166ldh.cloudfront.net/media/images/6c4b5480-62b9-4c00-a55b-7ddb3ef8c0f7.jpg)","metadata":{}},{"cell_type":"code","source":"# For data manipulation and visualization\nimport numpy as np\nimport pandas as pd\n# import pandas_profiling\nimport matplotlib.pyplot as plt\nimport seaborn as sns\n\n# For predictive data analysis\nfrom sklearn.preprocessing import OneHotEncoder, LabelEncoder\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.tree import DecisionTreeClassifier\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.naive_bayes import GaussianNB\nfrom sklearn.neighbors import KNeighborsClassifier\nfrom sklearn.svm import SVC\nfrom sklearn.metrics import confusion_matrix, accuracy_score, precision_recall_curve ","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:38:53.076442Z","iopub.execute_input":"2022-07-12T12:38:53.076862Z","iopub.status.idle":"2022-07-12T12:38:53.085065Z","shell.execute_reply.started":"2022-07-12T12:38:53.076819Z","shell.execute_reply":"2022-07-12T12:38:53.083972Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> Loading Train and Test Datasets </center></h2><a id=\"data\"></a>\n\n","metadata":{}},{"cell_type":"code","source":"train = pd.read_csv(r\"../input/titanic/train.csv\")\n","metadata":{"id":"4ykLJdpUCpQ5","execution":{"iopub.status.busy":"2022-07-12T12:38:57.875649Z","iopub.execute_input":"2022-07-12T12:38:57.876920Z","iopub.status.idle":"2022-07-12T12:38:57.889823Z","shell.execute_reply.started":"2022-07-12T12:38:57.876863Z","shell.execute_reply":"2022-07-12T12:38:57.888649Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"test = pd.read_csv(r\"../input/titanic/test.csv\")\n","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:39:05.676905Z","iopub.execute_input":"2022-07-12T12:39:05.677378Z","iopub.status.idle":"2022-07-12T12:39:05.688444Z","shell.execute_reply.started":"2022-07-12T12:39:05.677330Z","shell.execute_reply":"2022-07-12T12:39:05.687432Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.head()","metadata":{"id":"OYcIjEYdyHeu","outputId":"c19b64d6-f61a-470e-a5dd-7a9914180144","execution":{"iopub.status.busy":"2022-07-12T12:39:11.365681Z","iopub.execute_input":"2022-07-12T12:39:11.366443Z","iopub.status.idle":"2022-07-12T12:39:11.383054Z","shell.execute_reply.started":"2022-07-12T12:39:11.366406Z","shell.execute_reply":"2022-07-12T12:39:11.381889Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.tail()","metadata":{"id":"IgZ7g-4XyaBI","outputId":"45b11647-9083-49a7-9b3e-7a75ee3ab66d","execution":{"iopub.status.busy":"2022-07-12T12:39:15.040386Z","iopub.execute_input":"2022-07-12T12:39:15.040832Z","iopub.status.idle":"2022-07-12T12:39:15.059362Z","shell.execute_reply.started":"2022-07-12T12:39:15.040796Z","shell.execute_reply":"2022-07-12T12:39:15.058227Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> Explore Data Analysis(EDA) </center></h2><a id=\"eda\"></a>\n\n","metadata":{}},{"cell_type":"markdown","source":"![](https://aienetcomclub.com/wp-content/uploads/2021/11/Untitled-1500-x-500-px-1024x341.png)","metadata":{}},{"cell_type":"code","source":"train.shape","metadata":{"id":"qhKKKydlydlR","outputId":"14ea02f9-c95d-4e19-a670-577945250d13","execution":{"iopub.status.busy":"2022-07-12T12:39:21.026368Z","iopub.execute_input":"2022-07-12T12:39:21.027485Z","iopub.status.idle":"2022-07-12T12:39:21.034844Z","shell.execute_reply.started":"2022-07-12T12:39:21.027427Z","shell.execute_reply":"2022-07-12T12:39:21.033894Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"id":"X8qerygQJf8Z","outputId":"8f3aad86-6109-42e9-9675-b16346306cf7","execution":{"iopub.status.busy":"2022-07-12T12:39:25.375497Z","iopub.execute_input":"2022-07-12T12:39:25.375876Z","iopub.status.idle":"2022-07-12T12:39:25.391474Z","shell.execute_reply.started":"2022-07-12T12:39:25.375847Z","shell.execute_reply":"2022-07-12T12:39:25.390129Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"features are available in the dataset","metadata":{"id":"iFUzPZ3p44GF"}},{"cell_type":"code","source":"train.columns","metadata":{"id":"km8zVSP-ydjA","outputId":"928a7d0e-e393-4619-99f5-79deb7027e22","execution":{"iopub.status.busy":"2022-07-12T12:39:30.448171Z","iopub.execute_input":"2022-07-12T12:39:30.448987Z","iopub.status.idle":"2022-07-12T12:39:30.455521Z","shell.execute_reply.started":"2022-07-12T12:39:30.448953Z","shell.execute_reply":"2022-07-12T12:39:30.454456Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.describe().T.style.set_properties(**{'background-color': 'grey','color': 'white','border-color': 'white'})","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:39:33.615542Z","iopub.execute_input":"2022-07-12T12:39:33.616257Z","iopub.status.idle":"2022-07-12T12:39:33.656471Z","shell.execute_reply.started":"2022-07-12T12:39:33.616222Z","shell.execute_reply":"2022-07-12T12:39:33.655081Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Check for duplicate rows and delete**","metadata":{"id":"Ct-Kat6h5j-N"}},{"cell_type":"code","source":"train.duplicated().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:39:37.415643Z","iopub.execute_input":"2022-07-12T12:39:37.416063Z","iopub.status.idle":"2022-07-12T12:39:37.428120Z","shell.execute_reply.started":"2022-07-12T12:39:37.416028Z","shell.execute_reply":"2022-07-12T12:39:37.427284Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Null value**<a id=\"null\"></a>","metadata":{"id":"wRLbydKr6MRM"}},{"cell_type":"code","source":"test.isna().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:39:40.725724Z","iopub.execute_input":"2022-07-12T12:39:40.726487Z","iopub.status.idle":"2022-07-12T12:39:40.737062Z","shell.execute_reply.started":"2022-07-12T12:39:40.726451Z","shell.execute_reply":"2022-07-12T12:39:40.735820Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.isna().sum()","metadata":{"id":"mZuGbknbydaQ","outputId":"b111d218-6d3b-4335-bd38-cd810d317973","execution":{"iopub.status.busy":"2022-07-12T12:39:44.245522Z","iopub.execute_input":"2022-07-12T12:39:44.245987Z","iopub.status.idle":"2022-07-12T12:39:44.256645Z","shell.execute_reply.started":"2022-07-12T12:39:44.245949Z","shell.execute_reply":"2022-07-12T12:39:44.255421Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Missing value filling** <a id=\"miss\"></a>","metadata":{}},{"cell_type":"code","source":"def missing (train):\n    missing_number = train.isnull().sum().sort_values(ascending=False)\n    missing_percent = ((train.isnull().sum()/train.isnull().count())*100).sort_values(ascending=False)\n    missing_values = pd.concat([missing_number, missing_percent], axis=1, keys=['Missing_Number', 'Missing_Percent'])\n    return missing_values","metadata":{"id":"VBPnt-huHzWo","execution":{"iopub.status.busy":"2022-07-12T12:39:47.985433Z","iopub.execute_input":"2022-07-12T12:39:47.986705Z","iopub.status.idle":"2022-07-12T12:39:47.994555Z","shell.execute_reply.started":"2022-07-12T12:39:47.986650Z","shell.execute_reply":"2022-07-12T12:39:47.993425Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"missing (train)","metadata":{"id":"EqkqAYdAH3fe","outputId":"8a3134cb-7ab2-4bbd-e1a2-39af85736d06","execution":{"iopub.status.busy":"2022-07-12T12:39:51.496055Z","iopub.execute_input":"2022-07-12T12:39:51.496799Z","iopub.status.idle":"2022-07-12T12:39:51.516924Z","shell.execute_reply.started":"2022-07-12T12:39:51.496759Z","shell.execute_reply":"2022-07-12T12:39:51.516090Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"missing(test)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:39:54.795779Z","iopub.execute_input":"2022-07-12T12:39:54.796612Z","iopub.status.idle":"2022-07-12T12:39:54.815267Z","shell.execute_reply.started":"2022-07-12T12:39:54.796561Z","shell.execute_reply":"2022-07-12T12:39:54.814172Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#fill null values with mean,median ,mode\nfor i in train.columns:\n    if train[i].dtypes == 'object':\n        train[i].fillna(train[i].mode()[0], inplace=True)\n    else:\n        train[i].fillna(train[i].median(), inplace=True)\nprint(train)","metadata":{"id":"_Fo5OObdIGPI","outputId":"60205250-c1c8-45b3-8963-fff230f0b81b","execution":{"iopub.status.busy":"2022-07-12T12:40:02.285759Z","iopub.execute_input":"2022-07-12T12:40:02.286625Z","iopub.status.idle":"2022-07-12T12:40:02.309533Z","shell.execute_reply.started":"2022-07-12T12:40:02.286584Z","shell.execute_reply":"2022-07-12T12:40:02.308278Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"#fill null values with mean,median ,mode\nfor i in test.columns:\n    if test[i].dtypes == 'object':\n        test[i].fillna(test[i].mode()[0], inplace=True)\n    else:\n        test[i].fillna(test[i].median(), inplace=True)\nprint(test)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:40:06.636728Z","iopub.execute_input":"2022-07-12T12:40:06.637112Z","iopub.status.idle":"2022-07-12T12:40:06.659979Z","shell.execute_reply.started":"2022-07-12T12:40:06.637081Z","shell.execute_reply":"2022-07-12T12:40:06.659167Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.isnull().sum()","metadata":{"id":"nYQJRt-XImo9","outputId":"b1a44d17-317d-4957-8c9d-ad6b5a663ac3","execution":{"iopub.status.busy":"2022-07-12T12:40:13.754904Z","iopub.execute_input":"2022-07-12T12:40:13.756003Z","iopub.status.idle":"2022-07-12T12:40:13.767077Z","shell.execute_reply.started":"2022-07-12T12:40:13.755945Z","shell.execute_reply":"2022-07-12T12:40:13.766335Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.isnull().sum()","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:40:17.795662Z","iopub.execute_input":"2022-07-12T12:40:17.796077Z","iopub.status.idle":"2022-07-12T12:40:17.806261Z","shell.execute_reply.started":"2022-07-12T12:40:17.796046Z","shell.execute_reply":"2022-07-12T12:40:17.805380Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Data type plot**<a id=\"plot\"></a>","metadata":{}},{"cell_type":"code","source":"sns.countplot(train.dtypes.map(str))\nplt.show()","metadata":{"id":"PZSrPZjcJEo0","outputId":"dda88b4f-1a90-4503-b7af-0632386e4901","execution":{"iopub.status.busy":"2022-07-12T12:40:21.935602Z","iopub.execute_input":"2022-07-12T12:40:21.935971Z","iopub.status.idle":"2022-07-12T12:40:22.114264Z","shell.execute_reply.started":"2022-07-12T12:40:21.935941Z","shell.execute_reply":"2022-07-12T12:40:22.113473Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"sns.countplot(test.dtypes.map(str))\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:40:25.535879Z","iopub.execute_input":"2022-07-12T12:40:25.537014Z","iopub.status.idle":"2022-07-12T12:40:25.715180Z","shell.execute_reply.started":"2022-07-12T12:40:25.536974Z","shell.execute_reply":"2022-07-12T12:40:25.714316Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.dtypes.value_counts()","metadata":{"id":"OQD6GhyDJRAP","outputId":"3af99f5b-16dc-4684-bf63-94052e2a2f45","execution":{"iopub.status.busy":"2022-07-12T12:40:29.316008Z","iopub.execute_input":"2022-07-12T12:40:29.316773Z","iopub.status.idle":"2022-07-12T12:40:29.325892Z","shell.execute_reply.started":"2022-07-12T12:40:29.316732Z","shell.execute_reply":"2022-07-12T12:40:29.324591Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.info()","metadata":{"id":"INIXmJK5ydQ8","outputId":"08e5e047-13a3-46cf-8dfe-239d6ae91b25","execution":{"iopub.status.busy":"2022-07-12T12:40:32.135416Z","iopub.execute_input":"2022-07-12T12:40:32.135822Z","iopub.status.idle":"2022-07-12T12:40:32.149152Z","shell.execute_reply.started":"2022-07-12T12:40:32.135791Z","shell.execute_reply":"2022-07-12T12:40:32.148195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Unique Values**","metadata":{}},{"cell_type":"code","source":"for i in train.columns:\n    print('colum_name',i)\n    print('unique',train[i].unique())\n    print('\\n')","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:40:37.105670Z","iopub.execute_input":"2022-07-12T12:40:37.106400Z","iopub.status.idle":"2022-07-12T12:40:37.128899Z","shell.execute_reply.started":"2022-07-12T12:40:37.106361Z","shell.execute_reply":"2022-07-12T12:40:37.127497Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[\"Cabin\"].unique()","metadata":{"id":"kQVI3xCm63lE","outputId":"bc1d6421-6eaf-4710-ac33-8ace4a62df67","execution":{"iopub.status.busy":"2022-07-12T12:40:52.715986Z","iopub.execute_input":"2022-07-12T12:40:52.716672Z","iopub.status.idle":"2022-07-12T12:40:52.724871Z","shell.execute_reply.started":"2022-07-12T12:40:52.716633Z","shell.execute_reply":"2022-07-12T12:40:52.723841Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Comparision with survived**<a id=\"com\"></a>","metadata":{}},{"cell_type":"code","source":"train[['Pclass', 'Survived']].groupby(['Pclass'], as_index=False).mean().sort_values(by='Survived', ascending=False)","metadata":{"id":"CyP0y_ofC-xV","outputId":"5ba10fd4-fd1a-4761-e213-4bfe050948f4","execution":{"iopub.status.busy":"2022-07-12T12:40:49.386398Z","iopub.execute_input":"2022-07-12T12:40:49.386844Z","iopub.status.idle":"2022-07-12T12:40:49.404460Z","shell.execute_reply.started":"2022-07-12T12:40:49.386807Z","shell.execute_reply":"2022-07-12T12:40:49.403236Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[[\"Sex\", \"Survived\"]].groupby(['Sex'], as_index=False).mean().sort_values(by='Survived', ascending=False)","metadata":{"id":"qM-ZfVEaDGMI","outputId":"7520e5f0-b90c-4d3f-f440-1641ae1879d8","execution":{"iopub.status.busy":"2022-07-12T12:40:55.836422Z","iopub.execute_input":"2022-07-12T12:40:55.836874Z","iopub.status.idle":"2022-07-12T12:40:55.852638Z","shell.execute_reply.started":"2022-07-12T12:40:55.836837Z","shell.execute_reply":"2022-07-12T12:40:55.851449Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[[\"SibSp\", \"Survived\"]].groupby(['SibSp'], as_index=False).mean().sort_values(by='Survived', ascending=False)","metadata":{"id":"czP8tOsfDLLo","outputId":"2947ff5c-6d6b-4e58-fbe7-bf90245f6cd5","execution":{"iopub.status.busy":"2022-07-12T12:40:59.116610Z","iopub.execute_input":"2022-07-12T12:40:59.117791Z","iopub.status.idle":"2022-07-12T12:40:59.132318Z","shell.execute_reply.started":"2022-07-12T12:40:59.117750Z","shell.execute_reply":"2022-07-12T12:40:59.131500Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train[[\"Parch\", \"Survived\"]].groupby(['Parch'], as_index=False).mean().sort_values(by='Survived', ascending=False)","metadata":{"id":"68v3zq4lDRlI","outputId":"be1d4d61-2a04-4a1e-8429-2e5a48bcc9c0","execution":{"iopub.status.busy":"2022-07-12T12:41:02.585727Z","iopub.execute_input":"2022-07-12T12:41:02.586165Z","iopub.status.idle":"2022-07-12T12:41:02.600537Z","shell.execute_reply.started":"2022-07-12T12:41:02.586129Z","shell.execute_reply":"2022-07-12T12:41:02.599396Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> Data Visualization </center></h2><a id=\"vis\"></a>\n\n","metadata":{}},{"cell_type":"markdown","source":"![](https://cdn4.vectorstock.com/i/1000x1000/10/63/machine-learning-algorithm-big-data-visualization-vector-24231063.jpg)","metadata":{}},{"cell_type":"markdown","source":"**Distribution of age**<a id=\"age\"></a>","metadata":{}},{"cell_type":"markdown","source":"1. **Histogram**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,10))\nsns.histplot(x = \"Age\", data = train)\nplt.title(\"Histogram (Age)\")\nplt.show()","metadata":{"id":"TulzlelH7vnw","outputId":"88350ddc-10e5-4878-854e-29129fc4766d","execution":{"iopub.status.busy":"2022-07-12T12:41:10.926460Z","iopub.execute_input":"2022-07-12T12:41:10.926895Z","iopub.status.idle":"2022-07-12T12:41:11.285922Z","shell.execute_reply.started":"2022-07-12T12:41:10.926862Z","shell.execute_reply":"2022-07-12T12:41:11.284757Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"2. **KDE**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,10))\nsns.kdeplot(x = \"Age\", data = train, fill = True)\nplt.title(\"KDE (Age)\")\nplt.show()","metadata":{"id":"-xqeglRX7vle","outputId":"1048e54d-8438-4f3a-e2e7-072c2d67c4b8","execution":{"iopub.status.busy":"2022-07-12T12:41:15.726103Z","iopub.execute_input":"2022-07-12T12:41:15.726558Z","iopub.status.idle":"2022-07-12T12:41:16.019138Z","shell.execute_reply.started":"2022-07-12T12:41:15.726521Z","shell.execute_reply":"2022-07-12T12:41:16.017996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"3.**Boxplot** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,2))\nsns.boxplot(x = \"Age\", data = train)\nplt.title(\"Boxplot (Age)\")\nplt.show()","metadata":{"id":"PagfntEg7vjH","outputId":"a0c04117-35df-447d-e85a-f4a66e31313b","execution":{"iopub.status.busy":"2022-07-12T12:41:21.916165Z","iopub.execute_input":"2022-07-12T12:41:21.916961Z","iopub.status.idle":"2022-07-12T12:41:22.150713Z","shell.execute_reply.started":"2022-07-12T12:41:21.916920Z","shell.execute_reply":"2022-07-12T12:41:22.149557Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"4.**Violin plot** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,2))\nsns.violinplot(x = \"Age\", data = train)\nplt.title(\"Violin plot (Age)\")\nplt.show()","metadata":{"id":"wIl9WY6J9oeF","outputId":"efbba742-16f1-4a5e-e877-a293efa620b8","execution":{"iopub.status.busy":"2022-07-12T12:41:28.982037Z","iopub.execute_input":"2022-07-12T12:41:28.982451Z","iopub.status.idle":"2022-07-12T12:41:29.204150Z","shell.execute_reply.started":"2022-07-12T12:41:28.982418Z","shell.execute_reply":"2022-07-12T12:41:29.203026Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Distribution of fare**<a id=\"fare\"></a>","metadata":{}},{"cell_type":"markdown","source":"1. **Histogram**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,10))\nsns.histplot(x = \"Fare\", data = train)\nplt.title(\"Histogram (Fare)\")\nplt.show()","metadata":{"id":"sWNIbKag9ocR","outputId":"16c7bc9a-00fe-4bc6-aa4b-d123d8b65860","execution":{"iopub.status.busy":"2022-07-12T12:41:32.576069Z","iopub.execute_input":"2022-07-12T12:41:32.576568Z","iopub.status.idle":"2022-07-12T12:41:33.046065Z","shell.execute_reply.started":"2022-07-12T12:41:32.576491Z","shell.execute_reply":"2022-07-12T12:41:33.044668Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"2.**KDE** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,10))\nsns.kdeplot(x = \"Fare\", data = train, fill = True)\nplt.title(\"KDE (Fare)\")\nplt.show()","metadata":{"id":"BAWzOIll9oaR","outputId":"523d0fd5-362a-4dcd-eeb5-74b5de5b9f9d","execution":{"iopub.status.busy":"2022-07-12T12:41:37.105858Z","iopub.execute_input":"2022-07-12T12:41:37.106320Z","iopub.status.idle":"2022-07-12T12:41:37.426209Z","shell.execute_reply.started":"2022-07-12T12:41:37.106283Z","shell.execute_reply":"2022-07-12T12:41:37.424996Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"3. **Boxplot**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,2))\nsns.boxplot(x = \"Fare\", data = train)\nplt.title(\"Boxplot (Fare)\")\nplt.show()","metadata":{"id":"gNOFuSHd9oYC","outputId":"000c7171-366d-4d08-c897-f3b7363baf6d","execution":{"iopub.status.busy":"2022-07-12T12:41:41.805564Z","iopub.execute_input":"2022-07-12T12:41:41.805969Z","iopub.status.idle":"2022-07-12T12:41:42.024650Z","shell.execute_reply.started":"2022-07-12T12:41:41.805936Z","shell.execute_reply":"2022-07-12T12:41:42.023548Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"4.**Violin plot** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20,2))\nsns.violinplot(x = \"Fare\", data = train)\nplt.title(\"Violin plot (Fare)\")\nplt.show()","metadata":{"id":"7zu5ORrs9oVe","outputId":"803c3ada-1b87-4026-8c73-f0ef81d4c1c8","execution":{"iopub.status.busy":"2022-07-12T12:41:45.533652Z","iopub.execute_input":"2022-07-12T12:41:45.534890Z","iopub.status.idle":"2022-07-12T12:41:45.709316Z","shell.execute_reply.started":"2022-07-12T12:41:45.534842Z","shell.execute_reply":"2022-07-12T12:41:45.708179Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Distribution of gender**<a id=\"gender\"></a>","metadata":{}},{"cell_type":"markdown","source":"1. **Countplot**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (10, 5))\nsns.countplot(x = \"Sex\", data = train)\nplt.title(\"Countplot (Sex)\")\nplt.xticks([0, 1], [\"Male\", \"Female\"])\nplt.show()","metadata":{"id":"DKrruzcm9_1S","outputId":"ea19cd3e-6124-4e84-e0cb-fef0a58177ab","execution":{"iopub.status.busy":"2022-07-12T12:41:52.576469Z","iopub.execute_input":"2022-07-12T12:41:52.576916Z","iopub.status.idle":"2022-07-12T12:41:52.716782Z","shell.execute_reply.started":"2022-07-12T12:41:52.576879Z","shell.execute_reply":"2022-07-12T12:41:52.715552Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Relation of various features with Survived**<a id=\"rel\"></a>","metadata":{}},{"cell_type":"markdown","source":"1. **Relation between Survived and Pclass**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20, 10))\nsns.countplot(x = \"Pclass\", hue = \"Survived\", data = train)\nplt.title(\"Survived VS Pclass\")\nplt.show()","metadata":{"id":"riapc9lt9_tK","outputId":"b9939dc0-1748-4996-daef-924315c0a548","execution":{"iopub.status.busy":"2022-07-12T12:41:57.156184Z","iopub.execute_input":"2022-07-12T12:41:57.156618Z","iopub.status.idle":"2022-07-12T12:41:57.409564Z","shell.execute_reply.started":"2022-07-12T12:41:57.156581Z","shell.execute_reply":"2022-07-12T12:41:57.408266Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"2.**Relation between Survived and SibSp** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20, 10))\nsns.countplot(x = \"SibSp\", hue = \"Survived\", data = train)\nplt.title(\"Survived VS SibSp\")\nplt.show()","metadata":{"id":"kT9LTpl_9_mr","outputId":"1f42222e-4d40-49da-b117-66497a7a5cb8","execution":{"iopub.status.busy":"2022-07-12T12:42:54.615488Z","iopub.execute_input":"2022-07-12T12:42:54.616255Z","iopub.status.idle":"2022-07-12T12:42:54.929636Z","shell.execute_reply.started":"2022-07-12T12:42:54.616214Z","shell.execute_reply":"2022-07-12T12:42:54.928542Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"3.**Realation between Survived amd Age** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20, 10))\nsns.kdeplot(x = \"Age\", hue = \"Survived\", data = train, shade = True)\nplt.title(\"Survived VS Age\")\nplt.show()","metadata":{"id":"eyDV5_fa-PWE","outputId":"eed98068-0634-494c-e475-4ead0ebdb124","execution":{"iopub.status.busy":"2022-07-12T12:25:43.160384Z","iopub.execute_input":"2022-07-12T12:25:43.161147Z","iopub.status.idle":"2022-07-12T12:25:43.445716Z","shell.execute_reply.started":"2022-07-12T12:25:43.161100Z","shell.execute_reply":"2022-07-12T12:25:43.444545Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"4.**Realation between Survived and Fare** ","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (20, 10))\nsns.kdeplot(x = \"Fare\", hue = \"Survived\", data = train, shade = True)\nplt.title(\"Survived VS Fare\")\nplt.show()","metadata":{"id":"xCT0wXoi-PTu","outputId":"d8457417-26d9-47ca-8229-a27b13750f4c","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":" **Relation of various features with Age and Survived**","metadata":{}},{"cell_type":"code","source":"fig, axes = plt.subplots(3, 2, figsize = (20, 20))\n\nsns.violinplot(x = \"Pclass\", y = \"Age\", hue = \"Survived\", split = True, data = train, ax = axes[0, 0])\nsns.violinplot(x = \"Sex\", y = \"Age\", hue = \"Survived\", split = True, data = train, ax = axes[0, 1])\nsns.violinplot(x = \"SibSp\", y = \"Age\", hue = \"Survived\", split = True, data = train, ax = axes[1, 0])\nsns.violinplot(x = \"Parch\", y = \"Age\", hue = \"Survived\", split = True, data = train, ax = axes[1, 1])\nsns.violinplot(x = \"Embarked\", y = \"Age\", hue = \"Survived\", split = True, data = train, ax = axes[2, 0])\nsns.violinplot(x = \"Cabin\", y = \"Age\", hue = \"Survived\", split = True, data = train, ax = axes[2, 1])","metadata":{"id":"KEZSk5Zj-PRV","outputId":"c7390720-0131-4d72-9de8-968e36b2cd86","execution":{"iopub.status.busy":"2022-07-12T12:25:43.748691Z","iopub.execute_input":"2022-07-12T12:25:43.749485Z","iopub.status.idle":"2022-07-12T12:25:49.466431Z","shell.execute_reply.started":"2022-07-12T12:25:43.749447Z","shell.execute_reply":"2022-07-12T12:25:49.465235Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"","metadata":{"id":"rvo5d77k-POv"},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Barplot**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (10, 5))\nsns.barplot(train['Pclass'],train['Age'],hue=train['Sex'])\nplt.show()","metadata":{"id":"4x4jOSlC-__W","outputId":"c2e5545c-2661-48cc-e2db-619b6c296267","execution":{"iopub.status.busy":"2022-07-12T12:25:49.468043Z","iopub.execute_input":"2022-07-12T12:25:49.468454Z","iopub.status.idle":"2022-07-12T12:25:49.851988Z","shell.execute_reply.started":"2022-07-12T12:25:49.468415Z","shell.execute_reply":"2022-07-12T12:25:49.850707Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**HEATMAP**","metadata":{}},{"cell_type":"code","source":"plt.figure(figsize = (10, 5))\nsns.heatmap(pd.crosstab(train['Pclass'],train['Survived']))\nplt.show()","metadata":{"id":"J2VMpGvl-_3A","outputId":"762c9459-5578-471c-8571-64f3f368fd6c","execution":{"iopub.status.busy":"2022-07-12T12:25:49.853645Z","iopub.execute_input":"2022-07-12T12:25:49.853966Z","iopub.status.idle":"2022-07-12T12:25:50.072440Z","shell.execute_reply.started":"2022-07-12T12:25:49.853937Z","shell.execute_reply":"2022-07-12T12:25:50.071231Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> Auto Visualization </center></h2><a id=\"auto\"></a>\n\n","metadata":{}},{"cell_type":"markdown","source":"\n![](https://images.idgesg.net/images/article/2018/02/big_data_analytics_analysis_thinkstock_673266772-100749739-large.jpg?auto=webp&quality=85,70)","metadata":{}},{"cell_type":"code","source":"!pip install autoviz","metadata":{"id":"nyymIO1I-_nt","execution":{"iopub.status.busy":"2022-07-12T12:25:50.073875Z","iopub.execute_input":"2022-07-12T12:25:50.074196Z","iopub.status.idle":"2022-07-12T12:26:02.285328Z","shell.execute_reply.started":"2022-07-12T12:25:50.074165Z","shell.execute_reply":"2022-07-12T12:26:02.283777Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize = (10, 5))\nfrom autoviz.AutoViz_Class import AutoViz_Class\nAV = AutoViz_Class()\ndf_av = AV.AutoViz('../input/titanic/train.csv')\nplt.show()","metadata":{"id":"Gz9fc8Y7D4q8","outputId":"be520e7c-1917-4e99-b757-f8ab3fe9c27b","execution":{"iopub.status.busy":"2022-07-12T12:26:02.298656Z","iopub.execute_input":"2022-07-12T12:26:02.299099Z","iopub.status.idle":"2022-07-12T12:26:07.844370Z","shell.execute_reply.started":"2022-07-12T12:26:02.299058Z","shell.execute_reply":"2022-07-12T12:26:07.843463Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Data pre-processing** <a id=\"pro\"></a>","metadata":{}},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\nfor col in train.columns:\n    if train[col].dtypes == 'object':\n        train[col] = le.fit_transform(train[col])","metadata":{"id":"prSxxhuiFtkD","execution":{"iopub.status.busy":"2022-07-12T12:26:07.845701Z","iopub.execute_input":"2022-07-12T12:26:07.846613Z","iopub.status.idle":"2022-07-12T12:26:07.860017Z","shell.execute_reply.started":"2022-07-12T12:26:07.846576Z","shell.execute_reply":"2022-07-12T12:26:07.859009Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder\nle = LabelEncoder()\nfor col in test.columns:\n    if test[col].dtypes == 'object':\n        test[col] = le.fit_transform(test[col])","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:07.861968Z","iopub.execute_input":"2022-07-12T12:26:07.862837Z","iopub.status.idle":"2022-07-12T12:26:07.878148Z","shell.execute_reply.started":"2022-07-12T12:26:07.862789Z","shell.execute_reply":"2022-07-12T12:26:07.877195Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.corr()","metadata":{"id":"lY3a_tASGS2D","outputId":"9ff0da54-caa9-48c2-a0d4-01a3ef76a8a5","execution":{"iopub.status.busy":"2022-07-12T12:26:07.879202Z","iopub.execute_input":"2022-07-12T12:26:07.880060Z","iopub.status.idle":"2022-07-12T12:26:07.910580Z","shell.execute_reply.started":"2022-07-12T12:26:07.880025Z","shell.execute_reply":"2022-07-12T12:26:07.909474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize=(40,15))\na=sns.heatmap(train.corr(),annot=True)","metadata":{"id":"puN0Kq5WGYt_","outputId":"f14006eb-30be-428c-960c-4523ffa6fd00","execution":{"iopub.status.busy":"2022-07-12T12:26:07.912102Z","iopub.execute_input":"2022-07-12T12:26:07.912765Z","iopub.status.idle":"2022-07-12T12:26:08.898334Z","shell.execute_reply.started":"2022-07-12T12:26:07.912722Z","shell.execute_reply":"2022-07-12T12:26:08.897062Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"X=train.drop(['Survived'], axis=1)\ny=train['Survived']\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.2, random_state = 1)\nX_train.shape, X_test.shape, y_train.shape, y_test.shape","metadata":{"id":"8-3XPj6JGeoS","execution":{"iopub.status.busy":"2022-07-12T12:26:08.899805Z","iopub.execute_input":"2022-07-12T12:26:08.900269Z","iopub.status.idle":"2022-07-12T12:26:08.915316Z","shell.execute_reply.started":"2022-07-12T12:26:08.900232Z","shell.execute_reply":"2022-07-12T12:26:08.914196Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> Model Creation and Evalutation </center></h2><a id=\"model\"></a>\n\n","metadata":{}},{"cell_type":"markdown","source":"![](https://miro.medium.com/max/1400/0*yni8--v-iw517vnQ.jpg)","metadata":{}},{"cell_type":"markdown","source":"**Decision tree classifier**<a id=\"dtc\"></a>\n\nIt is a tree-structured classifier, where internal nodes represent the features of a dataset, branches represent the decision rules and each leaf node represents the outcome. In a Decision tree, there are two nodes, which are the Decision Node and Leaf Node. There are generally two types of decision trees. Models where the target variable can take a finite set of values are called classification trees. Trees where the target variable can take continuous values (typically real numbers) are called regression trees.\n![0_J2l5dvJ2jqRwGDfG.png](attachment:5a15f43b-6bbe-4350-97f4-52fe56a037db.png)\n![download.png](attachment:a6b20555-5c67-4a12-9a26-522b65513ed9.png)\n","metadata":{},"attachments":{"5a15f43b-6bbe-4350-97f4-52fe56a037db.png":{"image/png":"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"},"a6b20555-5c67-4a12-9a26-522b65513ed9.png":{"image/png":"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"}}},{"cell_type":"code","source":"decision_tree_model = DecisionTreeClassifier(random_state = 2)\ndecision_tree_model.fit(X_train, y_train)\ny_pred = decision_tree_model.predict(X_test)\ndecision_tree_model_acc = accuracy_score(y_pred, y_test) * 100\nprint(\"Accuracy:\", decision_tree_model_acc)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:08.917243Z","iopub.execute_input":"2022-07-12T12:26:08.917605Z","iopub.status.idle":"2022-07-12T12:26:08.934641Z","shell.execute_reply.started":"2022-07-12T12:26:08.917571Z","shell.execute_reply":"2022-07-12T12:26:08.933097Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Random forest classifier**<a id=\"rfc\"></a>\n","metadata":{}},{"cell_type":"markdown","source":"\n\nThe random forest classifier is an improvement over decision tree classifiers. Based on ensemble learning, a random forest classifier contains a number of decision trees on various subsets of the given dataset and takes the average to improve the predictive accuracy of that dataset. In general, a greater number of trees in the forest leads to higher accuracy and prevents the problem of overfitting.\n![random-forest-algorithm.png](attachment:d5fb4d7e-9211-4334-a9f6-a6b37d7987fd.png)","metadata":{},"attachments":{"d5fb4d7e-9211-4334-a9f6-a6b37d7987fd.png":{"image/png":"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"}}},{"cell_type":"code","source":"random_forest_model = RandomForestClassifier(criterion='gini',\n                                            n_estimators=1750,\n                                            max_depth=7,\n                                            min_samples_split=6,\n                                            min_samples_leaf=6,\n                                            max_features='auto',\n                                            verbose=1,\n                                            random_state = 3)\nrandom_forest_model.fit(X_train, y_train)\ny_pred = random_forest_model.predict(X_test)\nrandom_forest_model_acc = accuracy_score(y_pred, y_test) * 100\nprint(\"Accuracy:\", random_forest_model_acc)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:08.936107Z","iopub.execute_input":"2022-07-12T12:26:08.936480Z","iopub.status.idle":"2022-07-12T12:26:13.015525Z","shell.execute_reply.started":"2022-07-12T12:26:08.936446Z","shell.execute_reply":"2022-07-12T12:26:13.014474Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Naive Bayes classifier**<a id=\"nbc\"></a>","metadata":{}},{"cell_type":"markdown","source":"\n\nThe Naïve Bayes classifier is a probabilistic classifier that uses Bayes theorem. It assumes complete independance between the features.\n![204.png](attachment:b511e981-94b9-4503-b8ed-ec94ba954e81.png)","metadata":{},"attachments":{"b511e981-94b9-4503-b8ed-ec94ba954e81.png":{"image/png":"iVBORw0KGgoAAAANSUhEUgAAAjwAAAFoCAMAAABkJtHUAAAACXBIWXMAAAsTAAALEwEAmpwYAAAKT2lDQ1BQaG90b3Nob3AgSUNDIHByb2ZpbGUAAHjanVNnVFPpFj333vRCS4iAlEtvUhUIIFJCi4AUkSYqIQkQSoghodkVUcERRUUEG8igiAOOjoCMFVEsDIoK2AfkIaKOg6OIisr74Xuja9a89+bN/rXXPues852zzwfACAyWSDNRNYAMqUIeEeCDx8TG4eQuQIEKJHAAEAizZCFz/SMBAPh+PDwrIsAHvgABeNMLCADATZvAMByH/w/qQplcAYCEAcB0kThLCIAUAEB6jkKmAEBGAYCdmCZTAKAEAGDLY2LjAFAtAGAnf+bTAICd+Jl7AQBblCEVAaCRACATZYhEAGg7AKzPVopFAFgwABRmS8Q5ANgtADBJV2ZIALC3AMDOEAuyAAgMADBRiIUpAAR7AGDIIyN4AISZABRG8lc88SuuEOcqAAB4mbI8uSQ5RYFbCC1xB1dXLh4ozkkXKxQ2YQJhmkAuwnmZGTKBNA/g88wAAKCRFRHgg/P9eM4Ors7ONo62Dl8t6r8G/yJiYuP+5c+rcEAAAOF0ftH+LC+zGoA7BoBt/qIl7gRoXgugdfeLZrIPQLUAoOnaV/Nw+H48PEWhkLnZ2eXk5NhKxEJbYcpXff5nwl/AV/1s+X48/Pf14L7iJIEyXYFHBPjgwsz0TKUcz5IJhGLc5o9H/LcL//wd0yLESWK5WCoU41EScY5EmozzMqUiiUKSKcUl0v9k4t8s+wM+3zUAsGo+AXuRLahdYwP2SycQWHTA4vcAAPK7b8HUKAgDgGiD4c93/+8//UegJQCAZkmScQAAXkQkLlTKsz/HCAAARKCBKrBBG/TBGCzABhzBBdzBC/xgNoRCJMTCQhBCCmSAHHJgKayCQiiGzbAdKmAv1EAdNMBRaIaTcA4uwlW4Dj1wD/phCJ7BKLyBCQRByAgTYSHaiAFiilgjjggXmYX4IcFIBBKLJCDJiBRRIkuRNUgxUopUIFVIHfI9cgI5h1xGupE7yAAygvyGvEcxlIGyUT3UDLVDuag3GoRGogvQZHQxmo8WoJvQcrQaPYw2oefQq2gP2o8+Q8cwwOgYBzPEbDAuxsNCsTgsCZNjy7EirAyrxhqwVqwDu4n1Y8+xdwQSgUXACTYEd0IgYR5BSFhMWE7YSKggHCQ0EdoJNwkDhFHCJyKTqEu0JroR+cQYYjIxh1hILCPWEo8TLxB7iEPENyQSiUMyJ7mQAkmxpFTSEtJG0m5SI+ksqZs0SBojk8naZGuyBzmULCAryIXkneTD5DPkG+Qh8lsKnWJAcaT4U+IoUspqShnlEOU05QZlmDJBVaOaUt2ooVQRNY9aQq2htlKvUYeoEzR1mjnNgxZJS6WtopXTGmgXaPdpr+h0uhHdlR5Ol9BX0svpR+iX6AP0dwwNhhWDx4hnKBmbGAcYZxl3GK+YTKYZ04sZx1QwNzHrmOeZD5lvVVgqtip8FZHKCpVKlSaVGyovVKmqpqreqgtV81XLVI+pXlN9rkZVM1PjqQnUlqtVqp1Q61MbU2epO6iHqmeob1Q/pH5Z/YkGWcNMw09DpFGgsV/jvMYgC2MZs3gsIWsNq4Z1gTXEJrHN2Xx2KruY/R27iz2qqaE5QzNKM1ezUvOUZj8H45hx+Jx0TgnnKKeX836K3hTvKeIpG6Y0TLkxZVxrqpaXllirSKtRq0frvTau7aedpr1Fu1n7gQ5Bx0onXCdHZ4/OBZ3nU9lT3acKpxZNPTr1ri6qa6UbobtEd79up+6Ynr5egJ5Mb6feeb3n+hx9L/1U/W36p/VHDFgGswwkBtsMzhg8xTVxbzwdL8fb8VFDXcNAQ6VhlWGX4YSRudE8o9VGjUYPjGnGXOMk423GbcajJgYmISZLTepN7ppSTbmmKaY7TDtMx83MzaLN1pk1mz0x1zLnm+eb15vft2BaeFostqi2uGVJsuRaplnutrxuhVo5WaVYVVpds0atna0l1rutu6cRp7lOk06rntZnw7Dxtsm2qbcZsOXYBtuutm22fWFnYhdnt8Wuw+6TvZN9un2N/T0HDYfZDqsdWh1+c7RyFDpWOt6azpzuP33F9JbpL2dYzxDP2DPjthPLKcRpnVOb00dnF2e5c4PziIuJS4LLLpc+Lpsbxt3IveRKdPVxXeF60vWdm7Obwu2o26/uNu5p7ofcn8w0nymeWTNz0MPIQ+BR5dE/C5+VMGvfrH5PQ0+BZ7XnIy9jL5FXrdewt6V3qvdh7xc+9j5yn+M+4zw33jLeWV/MN8C3yLfLT8Nvnl+F30N/I/9k/3r/0QCngCUBZwOJgUGBWwL7+Hp8Ib+OPzrbZfay2e1BjKC5QRVBj4KtguXBrSFoyOyQrSH355jOkc5pDoVQfujW0Adh5mGLw34MJ4WHhVeGP45wiFga0TGXNXfR3ENz30T6RJZE3ptnMU85ry1KNSo+qi5qPNo3ujS6P8YuZlnM1VidWElsSxw5LiquNm5svt/87fOH4p3iC+N7F5gvyF1weaHOwvSFpxapLhIsOpZATIhOOJTwQRAqqBaMJfITdyWOCnnCHcJnIi/RNtGI2ENcKh5O8kgqTXqS7JG8NXkkxTOlLOW5hCepkLxMDUzdmzqeFpp2IG0yPTq9MYOSkZBxQqohTZO2Z+pn5mZ2y6xlhbL+xW6Lty8elQfJa7OQrAVZLQq2QqboVFoo1yoHsmdlV2a/zYnKOZarnivN7cyzytuQN5zvn//tEsIS4ZK2pYZLVy0dWOa9rGo5sjxxedsK4xUFK4ZWBqw8uIq2Km3VT6vtV5eufr0mek1rgV7ByoLBtQFr6wtVCuWFfevc1+1dT1gvWd+1YfqGnRs+FYmKrhTbF5cVf9go3HjlG4dvyr+Z3JS0qavEuWTPZtJm6ebeLZ5bDpaql+aXDm4N2dq0Dd9WtO319kXbL5fNKNu7g7ZDuaO/PLi8ZafJzs07P1SkVPRU+lQ27tLdtWHX+G7R7ht7vPY07NXbW7z3/T7JvttVAVVN1WbVZftJ+7P3P66Jqun4lvttXa1ObXHtxwPSA/0HIw6217nU1R3SPVRSj9Yr60cOxx++/p3vdy0NNg1VjZzG4iNwRHnk6fcJ3/ceDTradox7rOEH0x92HWcdL2pCmvKaRptTmvtbYlu6T8w+0dbq3nr8R9sfD5w0PFl5SvNUyWna6YLTk2fyz4ydlZ19fi753GDborZ752PO32oPb++6EHTh0kX/i+c7vDvOXPK4dPKy2+UTV7hXmq86X23qdOo8/pPTT8e7nLuarrlca7nuer21e2b36RueN87d9L158Rb/1tWeOT3dvfN6b/fF9/XfFt1+cif9zsu72Xcn7q28T7xf9EDtQdlD3YfVP1v+3Njv3H9qwHeg89HcR/cGhYPP/pH1jw9DBY+Zj8uGDYbrnjg+OTniP3L96fynQ89kzyaeF/6i/suuFxYvfvjV69fO0ZjRoZfyl5O/bXyl/erA6xmv28bCxh6+yXgzMV70VvvtwXfcdx3vo98PT+R8IH8o/2j5sfVT0Kf7kxmTk/8EA5jz/GMzLdsAAAAgY0hSTQAAeiUAAICDAAD5/wAAgOkAAHUwAADqYAAAOpgAABdvkl/FRgAAAwBQTFRFr4lm8bdszpBPVZHOdcn9kLDW9f7/1bGQx/v/MYrV//vIb0Ulyer92KpxT6v01dDX14kyMG2ydqfTjDUFtWwr//y6SkdJXBhi///1b5nKJ0lty9nrp7nZtrW48KlWx3gl/Oi5DC2M/tyWSXi0dDAKuOn9/OvGBwUHlEgKl5aX2+n2hmxWp+n9/cVy7f7/hVyNzJdoufv///7tbmVqqlIK6tbMqXBJ5ubm+9qma05J/uip5+73GHbJCkiPz7KjNDI0bESU/tiKD1Ssmej+hdj/s5ONs8bXkFMpz8i5Zrr96cyZqNv8UGuS/OzY5v7/3f7/UoW7mNr9///l/cyF/ueYlJmxRlJuLAQF5LuEK0ySTQsFiMr67vX8BAcrazYrh8bnuqiXVScQ///d9vX2rnJvBjFxTzMx1eLuYnCPBQhOqvX+6MWM0/7/kFRO9e7ukI/GLTFMqsfjcnCtebrmCiZUmMnqud75t8zlcoq0tGIUhoaF1PX+boaS//7VinVsbBUG5ptEzJiNnqiwlcfaTFOPc2dP0L3Ohrvm+d+29Pf8BBBt79enF2W4+/evqFgo/vbd7tq1YjKH/vTSRZvm/fbt3fT+5fX97+/vY6rnl2UxLjNvlM/5qNXv//blTGNzdbz2M2SQY1tjJVqswXtSvNXqTwo3jkZxiTVjLRBJarfozui2XaDa+s+TLw8m7tabFB8tl9js5cei/Pb0vtClzOfG7OXWc6iu5Mm55vbbWYyTsJu07+an1cWbLR8Z7vL2QHfE7vvtqeLsoldI9e31c67imYN/dFqj7uXi2KBe6ei57+PIbw0+m5WAaYpulauJ88ykNg9uUF6ktefn9/PvpND14+TtioyQ9//z+s67YrD15fX2oFl8wYA8jdbp7PzD4N3fvPfpVF5W6NGL9f/myeLthpae4LioGV6QMX7A8//e5OvvPEA3loCg9vLP+//////7+/v/+vv6//v4//v/8uri4v/j+PHirqDJ7/e275p1x/vv+v/55//zw4mhwf3T////jo5e8wAAPRtJREFUeNrsvXtAU1e6/w2EREgAhUDYQe4EVlSgECkFFFMBRbwkECyBSMCggFxsUfECiKD1AlG8gIqiiNdKB2laZ1pPx6KnDraM7Znq0TrHlvlxnGOrx4x7U6an83vfOX2f94+dkAsBFG8g6/sXZF/Xsz/7Wc961mVbARbWCGWFTYCF4cHC8GBheLAwPFhYGB4sDA8WhgcLw4OF4cHCwvBgYXiwMDxYGB4sLAwPFoYHC8ODheHBwvBgYWF4sDA8WBgeLAwPFhaGBwvDg4XhwcLwYGF4sLAwPFgYHiwMDxaGBwsLw4OF4cHC8GBheLAwPFhYGB4sDA8WhgcLw4OFheF5efrlx3us53j2C/lmZ6f2Tjxg+G//hcmZGJ4xJ+pmY2PjpV6Yz21zGHyvvpuNjY2Ntf0HnTf8bX6uxkvkwC1FgrYK018I1+gE3VFvX2LVcJMDzzfWkn3LajE8Y0fsSDlCfmthPtf88Zo8/MQOhErb9P/KTp1psOApFvl0IKRxllg4nntoADwnaHgoNrcpwZfLKO460yBJ3dSA4RkzfidmW9rG8vLo5AVRQ8LTpfIoL+eUuITqnvyF36/rHbjXTq7HivJtHQH3LMEjHQwe2SwvB18uw27v70+TIdvsMTxjhZ1HPq1tLIDUtxZEcdsqiGtzpkyZKwGonzVlylsVpGjnlClvrWcBUDZ5TgDWKj876vWJv5vz1r1/ff0gCYtmTZmy5R4AcaFn4py3KkiYz7UvBt8I9Q7y5+3/MuutuaHwzdIpb/1DAlDEfd9rzhRPKQlU/dIpU+ZKgXDdlr15ypbTLIBrb4T6chkOv7z+3Y+R2tgpty7MWwcA1+atIzE8o1iivyoYOn8zn9tW8chKjpDHEZLwViGk/vCf30QgpEyWAlA2WU69EHNFHU6civ43ecEaR0FS7f4wBULKgAoq58qmbXL1hyyYz32wDvZ4F3Syfsz6k0rpXBy0W45QQbYE5nM/yZKjghYJVd8lR6ikhSRct32qQOh4ISWLOBbvy2XYWQsOJSoQQvaR2pkkEN15Tr0YnlEsWfr1bEk/PP+zfN/nPel5J6Ux7qvv9XzLYi/f93nPtzNIPTx1V9SFlI3C7/P8zC5O0j8niR/09PiIGaTMtT3j379lkUbwFFUVuOTP+GNELLPnM2HsWpgvKOD3TBDGLpBtdv8wvyjaz47olvv9e4+P2J4lK9PDk/TQ++7Mnhmzo2OLSfaVknjseUaz6rvU2SyD57mwHYC9sil8tsJZCgBuiQWFuurNJssJwFoVJ6W68xgsgC5OC/vs1niA2VkZdrIyXidJn8O+GHwj/NaS6QJnBxAVnWmrAJl3K18yn3syECptWjv/9/V/AOScao0nfPLaWLCY0xQuK5tOw8NJYqVuswdgX2mNZ80+YSnwxvCMHgXZmMBDBU25/XVeU3DQYd6nb62DHEfO8durDgIAFaY6fvt2tEcLEN0n4gGgi9My2z0gFKDyinuhLGIFDdkHXI+Nt6eJ26ZCOtf2ILC71J+zgIj5Krl4PjfpAIg+OMMvBvaUKV9zWlP+6To9HqAy0j3eCJ7QkG32AERXlhOr+tgdHDCPcs9TkB1qgOeiK0IIZRSSlZFy5YN7pChdgWJ3sACoLgVCKLcFgOiOTqDhCWl1lgJUXtlXKItYEa9rbSGESu0BIJ175wAE2aj/wgKi7qsNxfO5hyqAuPgVv9i3GyGESlP+6XMiASBnuQV4ICpy13/vnh6M4Rk7AfOhf4ls+ssbF1c2FZLUzWth7YwK6vyXHwg8UgAom6yGnjce1hrDs9h9tRTAbWWTAZ75XOdVbzw8qIen0vH6hywQ+Z9JLp7PvXMAZEVn2v4nrHVN/h8jr6f80/VECgD7ynUL8LCtrv/GfXUxhmd0N9WDykoP6Zvqhz7I8pPC4qzcQhIA/BUMOwDI4TbF62MeAGN43ARN8QAhqjipETwPdFnqdO6dAyBLVzCKQTapwIU1X+CXAmwfdbbbFbUd1CWqU/7Z3e4sgZC82GITeKJnAgCRXqXNdWFheEa3+s5llXxaXh6dvOCcoO1aZMnG8k3tTcE1U8rLN+279S+zysvLeRuKASgbVQNLl9uLtgUAm6yk/7LJ21pezknbATkRx1JoeATO63TwCJwOAOV7uGlF+aa8gHXwkaBkYfk01QMHtlXrp+WbVK0Jfz6l8Nh4m+PRCXRTPdnOWnBHErWydOO7B6FGiGJTxlmS8PzHM8xfl1++zNRtGa7duf/nqeRLuOdUDkLI7xbsTOyU+icidJ/3WmBIHkIap9CYwwgh50AAoLqi7/Tq2l3TUwDAceWSWiJMgZBfNoDMdSMdn+xMZOg8T1Fiy0EAqExsR5qTxUBdWPnbaLkmww6gpgwhj7T3gv9sdfVPClTKZ1Gi7o3BQbtdiosSWw4SjirNAwdYNAk9qBhn8OwVmncuUjZ0999O4SGHYQ4+N+2k9GX4Hl3HaN/NWrLvZmPjpUvLyL63Gxsba0nqZmNjYyZJ76XvsDy/jAUAfTd7Ac6/3dh46ScA6nwtqTuX7g/ou8kiQd/rSgL8dPOnm/Rf1M3GxkuXbpJw/vxPb9N9reeXkdTNWrLvJouEvrcba0mo9y7oDB0P8OyN7DwAQLGv3FgQxWWYw9Mdbcu+ciM4asg+a9oFJMYWAxadQvDxu0WOB3jSq2Y6AFCVyzcE1gxAhOqOTqhcviEwits2HBmzE+MwPLqonLbpOICniGvvAACw/ydyJ7fNgfpl4kES9r8+ceLkg7Tngf0/kR9w29ZPnDiZBQDUxxMnTsxnAQBxbeLEifkkAPXLxIkT07dhePQZhPSvWg6OJ3hkZSsKa7htdmybgjUSokiBUO4h2vPklK0ojOJ+Ei1XqgtZAI8i5EjpF04C1HARUmYUk5DTJUcFJzA8hkBsWS85ruCJWBgcw217dKqV4cBKTzy+ZSmnKZikuqMTciIWBkdxS1d4WSkeOMDew7k/bLFSOTvA/MTct7ZEqh5UQHriyS1LORoMz7PTWINnRXANl381OqAYZJHu8QDeWQ29NDwrCqO4TUfAN8LvlsjxTIME2D4F2X8OO+NEQoyrOkV2Ki8BZDYdGJ7xDc/d1q3FAHUrm+bOm+e4bWatAZ5DFbDIJncJ+9T1cBJkRWc6/8/y63YkyBzPtNStbComwf8whmc8w+PLRcoAKcDiRIQQQsqZRp6nzQHqvf2OuEWqC1kg+uCrzotX/MJJkKV/tcQ/2s+OhNSVGJ7x7XkCtmkbAOpWNr3r5eU19x5pAs8eb78l7FPXw1k6z+PX73kysOcZt/BIdfBEce/MO1zSApVXrhca8jzGnidbFnbGlgVsn4Id/32qNQGgzlV9pPJKazyOecYnPIL7W7y85v5LxIrgKC6j+Bwndv2/hmU5e3l5zZ1KUt3RtjkRK4J18ORmU0WCjC1eczjODoRj1nEvLyuOc4UoTOXs9dtE3Noaf/DMFyCEUOlfhCuCa7gMB1G64kGgKF2BECp1GhDzZANxsQoh5cliEkR/VSCkdJaQUBkmR+rbVrh7YtzBc/PCPC8vr7nfvd4Tuv/1qSxovjA5E5rn0Z4HPu45SOi39C2aPANAdMHLa+5kAN1f+QBALZrnNfeNnyez8EMfZ/BgYXiwMDxYz0a9tRgerJGp9vQqDA/WyLSe4YLhwRqJyHy+M5/E8GCNgJ0Z/IDL/EsYHqwn1yVmwOXLjHwSwzNmXvdRFC1P9uQn81fVYnjGimbkPxw9N5PPZK6fjOEZM8p3cZkxaryPJ3PqGDfn+IJnqksAf/1ouRm+J4nhGUvVlotzAGN0vPBkJn8VYHjGkGqZzgHJLvmj4VZ6J7tMxvCMqdYW83Iyf3REGrWenlMxPGNJvUy+Z/KocDxwib8qE8MzpjzP1PyHLqtGRVr3YfJkEsMz1vg5zT89KkIexpivtcZh90QvnzkK6osZq5gzMDxjT+tdRkGqJ5+5vhbDM/aUyRwFrmcyYyqJ4RmTruelp+fIVYxewPCMRdfjyX/ZVcYMTyaJ4RmTmuzysgOOycxVGJ6xqdpV/Jfc1Fnl8hDDM0Y1lf+SXQ+T/wqwM07hqV31cnslM5lMwPCMVV16uYNpJjPXY3jGrjxfquvxZOZjeMauZrgwX2KixYVZi+EZw3qZUU8t3xMwPGM56mG+tLm+vZNdTmN4xrTW81/WjLtaT898DM/YjnqYLi9pVFjtGJ/rh+EBmJw8+eXEzDOSX41aazzDM4P5cibh9E7m52N4xrjIqYyXkqq7tIr5EMMz5sV8Kbm6qS7razE8Y15TX0onxSsxiBDDA0yXlxD1rGe8Io5nnMPz8CX0bs/wZGJ4XgmtevGTjyczV/VieF4F5TNfuBtY5fKqhDzjfk3C08kv2vUw+a+M8cY7PA+Zni+2k+LSqzGIEMMDAL35jBc7NGMycxWG55Whx8Xzhc6kWMXMx/C8KiLzX+zybutflfQyhgcAepnMFxn11L467GB4ACa7eGIjYHhG3HiegY2A4RlxA4jEVsDwjCzqWc/E8GB4RqhL5kPhK//2hKtNzpoY+ng7yn7/D9PPK/+4XYLheYVEXJvzxfong2fzVeZjMVA55wszeCZc3SLF8Lwyoh5ZXS98wq+vy5a7fzj8IdSe9OtMMxclC3PPPkhieF4RVS7f9znrSYFbZOW+YNiDciZcf9ccFOoXR/e1EgzPKyLvaAbryY+KurLLYbh9/rr7cvHAX4N2n1yA4Xk15MtZGD6Cw0SpJS4Hh96lPpIXb6GCIvxLGAcwPK+CRJOaGINt62sc4lNvQREZR4aMXShr3i6LLi2nzKOFxPC8AtGyG9djyWAb/ac7D94ib55UwBiyvZ6zu9XJMpPVrZclGJ4xV0VZaXl37/K0Wi2PTzeYm63lzoPWWrNPxA2OR1+qIiPYUEWF9Z95o+58qaqmeMvA+quaUjA8YxAeOUIaHo8nL2U4AAAElSkZ0sE9z67B4SHqBKV3DPA48joQUvJ4vA5lwLpeACAmyU8WD+LthAUNJIZnzKm+DKl3AFA2cmUDC4D6QFDQGToieCi2UPnAePMkeQEDAKyr0EwHevNly1hSlbuVu6QkhmesqSYCxd0CgLpE5BdOgsxRrs6GkcEjc5VnGNV4533kuS0AwO5G6r+wgPCvKmAMAoioW55biOEZc9rJRQ/sACAnUq6xzYQgH+R3a2TwADVJXmpr+HdPmfx+MACIHBWorQKaveXqQ4MdaaMoTarF8IwxEemKgjWhAFAZKdc4HYQoIYpbN0J4wFtV0GA4c4xAmSwBAJmjHD1wgEU+KHfQZpy1SmmfieEZY6q0kfsdBbra0rQchCIumukwUnisVcoH/ZWPLESh7gS62kKMCrgWgWKPDHZkqkA58zsMzxhTULcOlhAB8itkQXrV08Gzqz8kbvZGsbcAAKKEqCA7FPZyh4AnRKCMc8DwjDGdEyrvSAFA5ipX2ocCpFehXf3VVmr01iUAcO5wGmOGRXgqrcRiccba/v05yC9c73qCfOhgiupSoDgH0hweIkQsFjfpO9H8E5FfMAvDM7ZCni6FXzgABFnJlc4LAAhHBbKnXQCxd7kAKS9L4JwQIb91FuARbZ6mTbt7N2+hnjZ/DvIL1yFA7RSoswFA5qhC94/UAvVBFbpv6P/8ZhPH4+4JHu8IHenEJCJ1PIZnjIU8kfJYz3nz5lnJNc7BACALk6OGChqN9CqNHDXFL+rOE5ccdxgAD7Xnr1XKgGIgXMVOFuCROcpLP5k3b56jQumxBABEf1Ug50A9s3sTUVMhgLXKnp4pH5WI1NjzjDHFJCJafkdJ0hQeoPpkrvLSturkWz/9RA6MeWTWCvUOEqhUVWmLBXiCunVnVrv0kgBAGMHTFyNQXg4lwfew0v4AhmesylqlSfby8vLyWk8/OWN4ACBEhTT3b4VaCpiJIoGyrQKgz1ueG2wBnnNC5LzFy8vLay6Nh5Hnodi70fFAuo1lG4rheW4Sbfd8Mpu+/kTjyW0UpSZ9lUYxDwCAWyIqcGJZbG0FuaJYOwCgvjGMXjaGJ71KmWR854Qh5mm2lpeuAQDwnbOhgsQxz/OS7LPX3nkym/64/N3H7iWiZK7yWNNugfQqNNOQJBTZKPppMIWHsBYok8zTerMNrS0iTKE+YtIy629tUTUR6IFZuxy3tp6D35l9nf+EA11kE77KftxDqDqBaVcmmOd5zgmVdw5agqfSVW6ClT7Pc1KX52G7olhTQPrhEemT2jjP81z9zkfu/Cddgo36ZYI78zHpoUJUBfam5y/iorijBnhPyZUNFuFxS0Qni8mB8MzUJ26Eyl2mKeNrESi3BQAgp0uuXmt2aKrAfHcMz1Nqp2uG3Qia37uPL3lMxzZJ3t9S0udfhCjWAM9/hPHkxsPaDfAs5igfDKhmjPq2vKuUDaY9nYt8UO77AADsbhRr3n1mLcB9W89WzVZ5CZbjgOaeoSZ0LuYFPNZ4cipIiO4Hmv7m62MEj+zX3/1W4XcU3u5hmcPjL1Da03/V5Otdk1GvusxVXppieu/N1fLSTl0jXtf3uuh13X1S1bhX/alE/dQvHRgh0XGD1D/+0+Ikg9MjcuUlPZbjSVUpA6Smv+Xox/NQP5GEP3/duaqC7J9m/U0XgxtXW8qTUhKAuumzcYEh/M4opP+M4aAMO9M7FOnH81SGyXPXkgDwU/U0HWtEtzx3DMbLowaeZmuxRiwWd2g0mpIlJP32tg42NnNoeMA776TkMUKl+gi50nyGFjW/qqCTBQDeJ9rY73nW1kSgO0ut/jLA84i65QX2LAD/quTPdfUNxRYqnSU6GBTKDDMsKbZQeVkCAFR6FTq5AKBSmPYu7XmonN00ihieETasoso5cqQ8tmlTtNyj8wAA+AsGHRU+DDyLOaUJwz0KasI0rRwhzbFDptVFUJkyuQIAJskLFvKnQr0NKj22pXhgnmdvpELJu3vixKZbevyIOkHBIQCAbyLvyhFSHmOYtp+ISfKMQACARZsFqOTuiRPTmbrzUm5CJR7D/HSyVil3SQB8d6PctSRQ1e2DhsvDwFPp2m4/3KIVRFiWWMvjaUvMAtVmb3r8X/pKbYYdgGhntDjZbmDADFDfrRWLS24Y/EtfqiJjAQBAEUes5fG0Yud7Zk0qVWmCzjVGi8Xipv6pFnj2xNOrS6VxqgWQFSmUDCnklCmdpSODR3ZKHlcxwpsg3KqGmrc1xHie5uoChmToZmDrHYt33eeN5209bcRsoyhNYAEQF6vQ8UAiRqBMZo0MHipMYd7WeYL6c1Lr5dCRwPMoImPJ0DNGvVWxFiMbGZ4x+rTssHejjGISQPRBFbofL7JWFLTByOABxypl24hnf/sKPOJHAI+oqMRlmGvWR7bbWvhmichfzKgADM/TwLNYoGSQAJDjLUfHw/foJq6MCJ7UIUciD1t9Rl9mPTk8vqd2BQ535vmJJy1QUj/p5FHA8DwVPKkqOsVW44oK+KGLykxGbVJ9jY2NjZmkRXj6bl6qBYC+m/odooQo7t6I70T2675B1nYaAp7zE86mDLuynOgj9w8HBDfnPzqL1+d5Sv19Ep1io4qqUOwtskZoOuTXugMhjT6sNIMnlVPSAAA1uzuc1+nh8Rv5y0z5WmVYDtVnRw86V72L05k5fNyyx3HrgPtK57QdwCuDPZ3jqRQqGQAgmqBCsTsOQo0QxRpaPUUr845vLN/GW3NwADyE70oVQrF2cC4RIfUO0Dkv9VoWAECUFc9EAY+zjBLxx6urT1t6nvXbB1tzd8KmTx6nG45iz1lhtvLqj5E/OABgeJ5GosUK5fEpU6Z8rVIea2EBdZGLYvW5D9FnHGVGIIC1ShfJmMBzMZHXgQpsr9nweHcX0u91UDcqyA4FAIiKFJto4ZHHaq/HrH7SBS29ih9vR7e/mcEzYakdYHieTnu8O+gxv6UMAHrgnX7IL+EvUDIAIGa3fsivecDcpVA+6N5ocFS+rnp4sMYDPNfK0P21PT09Pd/O0MNznE7BUm5cpbMDAJzjFthKLMITlYhQ7LuZGJ5xCs9eIXpg5PmNxos3W8tz1wAALJq1RRdZmsNTaSM3SexgeMYVPERRVUGbUYPVMF6c2mthyK8ZPFSRwAQW3+5h4dkyZbRpGYZnhKrskueuNf6hv7UlSlcUrGENDQ/UlBlPeqA9DwsAoO/nN0z0UNeHTorRKJOmEcMzQvm6Gg//BIAa/XjxnC65ei0MDY/IUYFmGuV3oyJQ7lESAOBcoukj6m/+vzHqhMfzjFRFArO6qX+8eH23GVYW4PmPCf8m91trAo9umPCiWaZ1A3PM5lQwPIOGPF0KZYtJjn6Rj7z0kB4eGgTfzwItd0/kzPL6v1UFnXB++3f0r+eEaNcLo4R4fbtZrfr2GP6QzRiEp+4wUgeb+O3mah08Mke5urMWgPrSZprtQHj2fzmV+OCtI75CJeO7j15zoH9NF+gzQi+AnWtXvzDrpf14+bsVJIbnRalLgdTBJr+IZqvo8eLU/CoUewSgkpumH0psDI81Z9f/ee0d1qJJ6MGWU/o5ml0KfUboBXB/9oaDGSmimK82FGN4XoiuHc6TI4Q0x43j4v7x4vDLj0KkEYubNs6VWoh5vKuUTfx8EIXIlR5M3VArkY3cL/DFvPpE0NkVA3oyKNmEsxukGJ4XoaDI6LvTp0+/u9BkGdL+8eIAIZvu8nhbAy0GzHutTmwNBKDqrU7oV1qHSlf5zBfkeOonNa218LPo1L73MTwvUSH948UHaJjBYHWJrUm9L+Qe+9IF71t0MXXTYsdB2DN64WEntiaNDJ6QPD+7F/PkoiJj11m8EhWW5VSL4XlporxVcYPMhBsGnkl5DS9m+iXhWDVzkFZdqvBFAYzhsRgLHW4dZK76kPBQdZzjgc/hdkRR5eW3b5dvKi8v1w/f8j3cPtgU86Bu5fsHMTwvT0WJzhVPDo/IO+PQ87ibZmt6xJFGg5D9OhYAgLVq0CnmMkf5rnUYnpcn2Wfun4c+MTz1ifznMzaP+qlapYx1WLZMv1gzYSM3rLtsjnC6wm8thuclak/YVovj2Jt7Tg/KTs3u5HXPK+LxVintWQD1NnJ1JwuAPcT6BNT8qgIXCYbnJcbM7KurPZ8s7HzdalPK82KHslGU2pIAhL8CBdgBzBZYWOFJr71Cw7rLGJ6XIrdy/hMuaGlV+NxQznGVx4aTupFqwQDeCqOv3JjrWtkQ35rA8LwQkU/a3qWenx+M0a1/KUtXoOPBQE2Slw6+itQiH5S7A8ODRavPX1V6hwSARZOQMrkCZK7DwEN/MgnDgwXwd295bDwAQBQX5e5gQU6ZETw5E8p3ZAJA+tW3dMPQqtEwn8rG8Dyz6unSaM/HUs1l6LIUgNgbKdcwHICq3N2/FgNxIUyF/I6S+4sESPeh4j3eSJksxfC8CM3wHO1dQURdVUEbSZJuh5HS/gAA4cZFHim6VmGiHCFlmzRKiJDuM7QYnhen/OQZo9xSzSFyhDo0mg5lxtyppAk8QLy+3UqB7GeFBWyfN5H+ChKG5wXCEzDa4Vnkg0qOTZ8+ffoGetwR4SbohwcAgspQadpGwzoKGB7seQyqESJ748GllBsX5RpGHMms5SjX+MvYGB4MT7/mC5QMk5HJJq0tIC5WKY0XtMTwYHgMnsVRod5h0iI0am0BADRPkhsPBVk0CRXwSQwPhgcAgrrNVxsT+chLDd0T1COhYUUhGh6cJMTw0PpGiMwH6FQrCuz7/9n/V448932DqwnyMV7aDMMznuGhHBXokNmQU2uVAR7q9c3/H1f5gAU/6Ybe10QYfwobwzOe4cnplqs/NOttWGz0oUD2Z/z/LlOelBK/zqWHAezkomQ7DA+GBwCKBEgdbg6UqzyumARYFLbhfz772wKiWh4b3PUDPU6NKKoasDIMhmc8wvPLrKUchAo+NV9jo0uRG8wC2MlV/tvGdwBmC5QBm45K9I0zo8U9MmsxPOMVnr1chJAGIXp5O4POCZVJmQDXyjoKGBIAt0i5Jkn/BVsbudFyU/mTH2J4xik8fR/39PT09PTkm30HdE9ku1MmQN/PPT0zSADi556eg7r2Vszhgr8YQqSpfCaGZxw31S02wdIFg03ts+buMpo2VLuK74nhwfCYqN6m3fLUvhwr7RLj6fK9q/jrazE8GB6TaEjobHGyeur0maZNrdpVjNO9GB4Mj5FEF92Zlsaanppu/s2uS578yRgeDI8JPWFbB8bCRPf0gUjNYLpMxvBgeIzFvrrC0ywZeDP9sIuF5PJUF5d8DA+Gx1huV2+YL2gZmWJxonG+i0smhgfDY9xeX2Y+8YO6ybLYficn85m1GB4Mz4hUe5rPvIThwfCMSOR6vuclDM8zNiqZn/yQHA8LX3vyV9VieJ6pLs1Ynzx56qVxAE8vk78ew/NsKy0mI5n/yqVBLGoGk38aw/NsLeoc4MzPHw/wwFTmK1PQURIwT04OCFgP40NTXZj5JIbn2ekhM2CcOB4AciqfORXD8wwNejpgVS2MF+XzmTMwPM+wvbXqEowfreczMzE8WCPTKv6qS/lTezE8WCOoplclrxr7dReG5yVV056MgDE/OgzD87JiZufLyaswPFgjCZkZycnOTBLDg/Xk6s335Ae4XMLwYI0kZL409fT6qRgerJFGzdjzYI1XYXiwMDxYGB4sDA8WhgcLC8ODNW7goSbMMf+2654wT6PFkj6as+AVWCyyZin/xXzN7aM5C8w6QmQm5tw5Z0Hmi4Jn/wWvLVu2rLfUMdN3zULWlJL96OVgYedF85Zu2eJ5zwI8Pnm2Zmf35QYE09seLV0f2iVI+tcfvRyoa6M7RztoAWmFcGKLiQsG0yyaOMgXv6/NWrpli2f/KtAiy+b85cLSLVu8LF2tW5Vk9q494i7UmXPPrLkSR4HTdxe8HCBoff5zh2evECGkjHWwUNL9k2LXDGSBzW2ytXAeawFCqCDg4IDzUN3R5vsHCZNpZ0T8tcrZzpGTVCkssRVVx47qFfqtBQgh5eWDg/R/pkbHSSt3t/Z//CR120yLQ3GpSQqEkNpFt5GqFJZY+rZpugAhpHS2cDUbjq0ZPPXCZBoe4mLVycB0QdJ/725Noqo9Dj13eIq4znMnhqlOrrNQzur7FtbMp96eYcEqlE2W/cSJkR2XJRbgSRgID70MMtX39iWyi5OU+fZDFnjfbxnF7FBddAEfSAeHh3q7sd80/tNmWjyNqIzXNnGesKSN1Juz0RJkXYIHEydGdjhXWIIHzOEJoD8hThFvzyAdBUnf3XzIAu/jSc8fHoF9Bfi6qrNZIDsVzUvbEApQ38XjpTF/c0WlKTm2BKjN0TweowKg+dd5X0ff+H8neDkAOEbzeDeKgfp4zu828VYXk5RNnhNAapafHTFr1m+jt64l60/xeGl8FlDd29as5KXxJQCyCdE83g4JBAk/uR3N27qABYvCbkm6OEmsCV5zI1WakoU7wj5ZB0B0/TDqFuunbLKcAFI5fuHUrKW/jU57lwy6wuMtPAIAxEfRvK1W2+KkkL40EIjN0by7H27mdGh4DAeQ2dA2pS7M+c3KNBcJJStLswXwbj0pkW2etzR6639O8HIASF/J491wAPj4199d5a0uJiEsywlgNsevkPpx6W+j03awck5F89L4oQA2nOyVvLQNUgBRejSPx5RCvfCTH1byth5lwS9hqyTpgiRJEW3OY2vCPlkAQDn+cOt5eZ4HDlDpXbCGtShMJdZ2lKyRyCZwtNom5m8SO5SatCXUXzlirbjURUI94t69q936nxFpCaIijlgrVjIcqI+qjvFKAopJyibLqRfqItXhxKmsY3lN2desOsTajpJsFmWTdTwrr6PElhRNWKnVdmRkk0HCY2lZYvmDQPhAwCh25CT9ueyuy+4OpeaYi0/uIZJicz0SRiM8teAWqS6kC7jjmk27WKw5WUFC1GGNtomjPSklyni2RBFHrNUGbOJ0aMTJ62ibtq45SIVVHdM28SWUrCytBWBxXkZxpTD6rjbjP8t4OnO2JztQewV3edobxSR0ZTVkgtspdSF1SnUsr4n5Mf1wskMhTHA8K6+j5H2W6MeVWm2HxxpWfcTdY1liufPnUMNNtrMWJIW6RnceVmk0aZ0+pQ0kxeZ62D4veOwdIMhGnU05qmYehHNCv0C3lU12AABE9f0lQFUKj6cAm7s1GB5FKJNDQVa2Ij6GG5sCe3xKO8kPuAVrSJ1tSfBf6RdOTZL7FQNlo5pJQggn1gFsFH7hYJ0VJ2W/t1oKs1udpUFCJYMl8iltI3dy24odOUl/dj2RQnnfbwFRSGuAVDT7THLxaISnF2JW+oVTNnI/O6DCVE4k0X0miUV05yUBe7dyl5TyOZHAFh5PAbc31y2eNhOAclTNPAD+Qr8FpKNCXQgAOnhS805KK8uUlyVAuJ5ICeLGLgGRT2kbWcMtOMQCAOjKaqiFmEh1Idgo/OyAclTNlMA5oV8gdCnU4RDCia2o/P4LKSx2Pymtj1BeDqUmlTJIXy7DzlqQFNodnQDex+8AMbvVWUr4nwmwe27wSOEcN3Zd5fLrwSxg27Rms3e3JgAA7K++vwOIxe58CUD18UPwSLhwAYCsbEV80Zk1UhCFnEmWfsBlOBi8erVqJovojm4hgb28qZAE9qnWIywbzvssqIu8Hs/6Qy1AXdZWuyBhwAIgUs8EFEf1w5NAVN9fA0Rd1dbC5urYHeTorLa8VbtYlK6A+8IBzh2emem2cl84UNbRcVLK50SCvztfCsQfes9Nm9kLlVbX41lQGda6JrQr69BBHTy2QPiUNpCVEQuPkCByPZFy7oyLFIjZZwKKa7i6pkSX7moHoZvzPgvY/Q+HZZN1JxTcIltTQv9QC+CWlRFeH7EwhSRm592wM4KH8j5+CCg3QVqwyNujk3w+8MwXaLQ8scfazJiVajsSROln1vxv0eESXlsFDc/+kHYNj8dT5R6CR8INgUDJylYc7VL/hQWE21eriz/gHqoAAKDCVKVaXsnxBUD4nEgAWBztV0yCzPHMElZ3dAKAzOpMSmiOI4+nbb9hFyRkBALh9tVqOyN4RNX3O4ES+aTZBpU9WDcKA2ZVqZYnPn5U1wKIOazk8Xh5ml2Zi7MyiklI3RYnpXxOLLEucAkFAEidNrMWYq6ow0kQFZ3plHRxbHsBgJK5dpTwtCXJDlAZsTEYQOQ6/Yh3wQ4WUG5f3bCr4bbRDXdHlUbLEx8/+nfd1Vb66R5OqA0ngQRZ2JkEicyRx9O2bw2vFyYHAsXO2hpuDg8Qk9KS9pQFPE4EOVJ4tGlJADEr/cLp+5NS30TnlfAPNNPwdGi0Wi0v4Cg8EiYHD4SnTQ+PRqtdmAJA+ERbhMc95b8cOSXaoeBZAwCz05IvVnVWjEZ4dAXsh0er1fKOdbIWR5vA02oGD0sPT0utHh6tNtkBoDJiRT88a/rhYRjg0S48Qmc6SIvw6Mw5JDww+4Tz/63iV8Bzq7boU7OXXy+kPaMEANyqmuKbq++v0VdbAGCAZ0HRmR0SEKWeSZb2w2OT5UTvRcPjdqUpXF9tRbewwC3yevzirzLsoC5ra7jFaktUfb8TANze4/3p+tHRl3I2FJCGh738uu6rS2bV1hm+FKjG2nPTZrKAbXW9UF9t6eEpS9NFr3p4TKstHTxdRlezJY0ejqHaqstqstNXWwtgYLXlcQgA3L53/9P1d0OfHzz07cpsFA2h4C/0W0cCQOXZreHNk3I7gXCrykgxgyd+tsI5kA6Y5xvBQxrBkxPZ7gQQIqADZjuwzoqTpraelIB3+0k7SwFzgqg69xAAEDYKTdw9GJXw9BrBk3OqXVfgyt3tScBO1AXMdVUZweD25mn/xDipwaYLSCN4WszgiV9cdTKYDpj3GuBpqDWCR3ZK7sTSB8x+4RAiiLWb7X5SCiEdGeH1EcpklnnATFU3tQEAEabQxK4jnxM86VUz6dul9lq1i7Vij+xMXyutVtvElBD+Ks2xJbIJWWKtVhuwDh5xA4KBkkWkJdQ75om14hKXqTBf0EAHzN2qBtq2RBnPFoDYG9mu1YrT1rKIU6pjWm2Hx1qyPrJDq70r3xoexL2bphW3JzvABwJGcZcg6c9lvATCP0uT1kJCugA1HByF8HSrdI+TcM2zBaD2RraLtdq0FhYxP1GjTZvGiy0myni2sq48jVZ72aHeSi5OvnfN6oxYK/bIPgg2qqRMAKBkEfqMciV3YQqAKIKXkOOYJdZqS/j5sFMfMNuo7DONeneovafaxVqxx7uhVJjqGE/b0ZTN0plzX3g9l5emFbcnr9M11Z1CfXi2lH+WJm1NLRQJkP1jBQEj6p6w2qHvZ2Ff4fHSOgF8rXg8XlsFULKwaH2SkJe8DvaEMSsAiLAtgXQ+MVkCcM1q7UEAACr96hGab8pxSiAAgO8VHm/rDgBi1tLfRvPSmCSAfySP9+lr/yje8+vvvo7m3bADuGa1VvKN1YJ/Ok4JpERh0ceWkBCTWJAQOvrggfSruq+XUBPoAgZd4fF4x3b0AjE/mndj3jy+hHKcEgg5VtG8tCOh1N4rPIZDv03hI6sFvQAARJg+ASoL2+IAQDhOCQQiLJrHC5ACBFm9Sz+Nj65m1+r7lRcYPxzqxzm/WclLc2EBREXyeJ++9vti2a/zlkbzbgQCPLLylO60usWaMCUQRJujj62pBd/dStvQ5wXPqNPilYN9uQhrBIqJVIeT4wYeb85MzM4z7M/l7Hq8ERqvAjyy3e1J+JE/O3O6tjv1jh94Nv8tED/zZ2pOctzAg/WShOHBwvBgYXiwMDxYGB4sLAwPFoYHC8ODheHBwvBgYWF4sDA8WBgeLAwPFhaGBwvDg4XhwcLwYGF4sLAwPFgYHiwMDxaGBwsLw4OF4cHC8GBheLAwPFhYGB4sDA8WhgcLw4OFheHBwvBgYXiwMDxYGB4sLAwPFoYHC8ODheHBwsLwYGF4sDA8WBgeLAwPFhaGBwvDg4XhwcLwYGFheLAwPFgYHiwMDxaGBwsLw4M1SuER9UwmB/w28VvS8s7bDz7NLcq2Pxx8I/HzRJb5b1TPwN+GF7Vn+3dDbhdNnDGwfMT2GeTzfD6WDG1y/S8tlJX6cgQGoH6Zm2ny//7toU8PD/XTMp1q9eXouzj9hvmZKbfX3qFvmeqjdyeBOr9s2bJl186+W/GYFu7TX2pZb/8zLWryHPzonFlvDjg38etr/8l64uvUT8g4PdRdiur2DbwPqv69LRXPih5Lho7ZdGPIR5iz9E3pgOsTs94rDCWHN8BNIwNQjxwz7hkfQ107++4B8mnh8Y3UaDo6EEIa50Ddea1bne+Rg8KzyKdDI+7o8FsL18o6OjpK2tIFC8Mfj53UPI24AyGkKbmje/y+rursITyCJXiooMh22yHpabYW64rk0aL7yf+K+sPMIX1A3ZsWICbmC7YWPiN4grrNDQ0hrcfvkU8MDzwKaz8kHdrQHJ2hNU60pfwT/T40xbQ5XRUQ/rTw7JmwTa48Vl5eflhz/AgAABEVfWPVwPemH579E64qEMrdcA9+cYxEpRuO5oRlrbB7rHfP92sVKi0vL9/EKWU4AACw53hsGMoMluABYue0kh2SoWxX87UK5ZaXl0/Ly22bAQDAvurxztBe2jI8kBPG2Rr+bODZM2GbXJlGGzqbNvSJrauGfvktw0P4WuXxi4c2dBYq3VhevolTmuwAAOxNaeblpyqt8oZ+bI8V8yyuigsEADch2hVKAtS4xgXCEPAAUJuzUJwUAOD/2ecCAGBzpiH0sQwo6m5vAADCWq5eQwJQ3tH2QxvPEjwAbtyMtUNaXba71QkAZF1yv1skAFHt0TDcnVmGB6Cryl76jHxPXVVcsJGhfV1jg4c5wjI8ALKIpveHDpZoQ1MhcnUnC0TVTU4WHmn3mQbWU8KT4yhnVAAAZSP3CydB5qi4c0D/Cr/d2LiMHAAPQFGV8pAURBfdmaEAAHWR6sLHiuHcElsTSADwFSoZEqDY3KZ4XUFuLiOButlYOxQ81M3GxkssAOhLbQ3QPVHqD730Dn1/MLJmjKApBQDgA27BmlCg6qq26h5T381aEvrevlQ7NDzU+cbGRjo0YZ9Sx7MAAKhlelP8oZYcLrzR3Uz/MQAAMmt5soPB0CJHxaEDuqu9zSKp842XyKHhoW426vdZnJdhpy+/LhI1Lj+4JbbasgAgSKhkSIi6qhuFFooWs3LIx/Y48AR1K9ukAAB0maIi/QJ1t0GkKpBmoZ0FeOpt5H5HYe9Klwp6R0eV04HHgSdVlRtvgOfv1iUBOo/lxllYCHWCAgZrCHjcrsiVpUdCAajKxLQj9JXddPwSH7kHGo61VmQUAgDs5BasCYX93iV83baYrORwyl+ldhkaHlmYHGn4UgAAIl3Q4AAAUPn9F1IAAIp9ljmML5Jt3mdHAgDkfP9FsbGhGcUAADYKv3AW1ET6raOvKOvKWyLJsWmPXTc0PG6JcmVTCgsAQOTKawEAIOrcPUMBAEQT3MONbJcqKI1nAcCjCGWypNm7xKV/W+UpOSpdIwEAIMJUTgefDp6oMnU2CwDYicpdEhKsObt0Jwyy0i68fXi6rQV4qJoypfOWsB/sdCWbL4xb9zjweKviikkAKkSh7mSByCe3TRe8cVDujnPHym+bxQDG8BCp0WkbrybST9JHTNdDVM6cN98JBSBmvfeOEWbVHc4SABB1yXPXkvCoLHcNHXY4qlDsu0XHyn84PSQ8MdN4n94+HJACAAA7hXFHAQBks77/QgpABb23+vQwbpa4sPzNQBIg5/vXPA3BWU2ZegdtaBQnISGdE3dA12SRI/uor4/dZh4YCh5RSHTaxk3RDfT7Wp1nzwIAas+cN5ksANHm994xruC8VbHFJACVqlB3soLKYrP1G/y38TbeTkxeAAAA6dxdDk/XVE8X7KoAgJpueW42gKi7o4H26XvCVBl2VPUJJwvwAOXPKfWY0h9vRUXQAOrfsVlT9Npy1Nio9DOXpQuVD+4BFcT1WKJrHvHyStO+drYbIuYhvhGWriFrdts70HSc1L39suVvMkOJH99bLTXK2ZSV3AGAPY4CJWMqEDsF92/RDtNRm1d67OplyZAxD1Xv2hEgFfkstNU/8zUs2rmdfacC9i5/027Y1jvFPrv6NOzZvM/T6IUr4sY5AEBQtzy3BUBk02GfqUNV25F7dcWhoWMe0Uec0mwyKpEuP1irYunbkC1/05NFzHpvtWSgoUXpiUrndcT8ql0L9KH2bg0jtLLMmbbHOWHuh6yngUcWprCf/MYbr/sgdSddWS7pBQCgUvNi7aCOo4tKzOABsFaU3jG09111VZ8uJOIivUrtjYNubsn7b7zxRrpAGecAIEpV9DdaIVWgtB8yYPZ1LVjCyulqp+OEEFWuvhaX/brv3/941ogdIOqqmrLfeOMNR5XypJSONfqxDFEVNAwTMDd7Kx9IRf6qhfTNBU3S1TZAXHRnfrx8Xz87fW8/rCUBYP/PD2sBAPp+nsEyoif/M/fPjUwm61I8OE0b2gUA3A4bEg71Pij21jABs69rQQKr0qb9fbpeOMdRJ9CH5yzf9+9/PPuOxIRdnaGFytjA/qAWAOqrlW0SWZEimf6/xlX5vvRp4AmKRGINQgg9OJ0JADEcDV0mkU9JAwnEl9+yLMPjrUAZ4WR/DITsKwzbzn/Zo9e3M4ya0LNVSIwQQqXvTyUBmq3lBnjqhK22Q8KTLohzAOrmG5kkAMBsQWmC3lH8MqGq1MU4E9wc0qERI4SQR/YMEqC+Gj3o986LBU0Jw8ATFJG7hqREX+pI2GM4XHQxUXPDkJmpKWvtlAKAdVZTCwAQ86ti1xqScJEdGZ+HmsSWOkM7H80EgJhEZT88OY7yyw7DwOMoiDtgKD/EJCpbMnXld1SVunxnkgHUG1rz/lSW8cPZKYy9RVL7v9SF3UHdqKHiaeBJFRR8MuX27SlT6OjNXwdPn78qNmGQpjoAEP4b/5SInPXRYH01sncY9lLnq9s9tty+fXuKp5R+w5EBHlF3nu3fh4Cn3rWjwSjL5y8oXdJvrtkKpQl4iyYpj9PXkehuzgCPbDdvGHiareW7jHMVe4xuk12FdoUatTnRAzsACJErkwAgp0te0NlvI5ErUptUw+eEJoaOEmr64aEuCpIDh4Yn6LDGqddoS0yiMklvj7/KC0zL9JOJoesn6eHZYyM3eUz1k54Sni5VrLHn0sPT7I2cKwaFR7Tz6iFJapXykMQiPNeW9sc8bxm54+aygjbjHKcxPPu7xfahQ8DjzylIYVmEh3p9+fQTq9cbbbwWoV5jbCJjePa4ihvIIeHpb30OhCdn87QTK/7Rf5t7I0+4VACA76YVgQAgK5q+dZX+NkSzNp1Y8Y7UpLHgZ5zYM4an7xvB/SNDwzNb13waCA9xYfn0E6tN+l5EZQUM0hgRXbUVU6ZskTxDeIhusb3xG6+vtpqrCxihALBsmQV4qBqrmQeh3gbFrmVZqrYsxzxUEDe2xaQXQX5SDw/1H4c1cbRt93/5beZAeEKy/OxIAEp3O4Zqi7q2fF9x5XtfGGoTaic37tYg8FDfHNaclOhczJc937IGwuPrqs5mAVDLfgLTaovaM8F9AbHZ/fPHSIiKLrq/w4pyZxq6jwibDnsz19GizzYtCuOoXcgh4QnJ8ys2Kr+h2qKuff9mceXZ1Q5G+aBHQmND19vo32z/RHUwC4DS93g9bbXF3t3uZJpdUjrVGuAhvDwtwMOes9WBBKrGFe1aZylgPv/zG3o9NNQ1otmKWOP3S5SqyEjR//0Px0h1OAkAlLUqt2UweKiP31oGpgFz5XtvOpBU0Pf7+l9rWbpil3HiQGYtP6n/X/Z7x2g/XW1SrUJNwSxL8PyFBSD7/UQwDZhlm90/D4U9E9yDh02IEjFfMQ+A6KK7IY5lH25vMIbH7bDSSWcbomeKdysjdGh4svyKSaA+fkuHdH/AXHn2CweSCvr+TYNbE/lXGRs6x1HuTJc/KlEdzAJK9ta38EwCZqNmiy726LCvpeuU++FAndrw+UB43DZtpR96qkKZXGyhqT5IKnuSkiE16eHk0pjULG2zZv7x1PXCzfOkADVWx5wsVlu2AB9tyq4F46Y6wX7vi7ksOrOi72tnuyrvhJr0hQloW0ZtcbHecfFKU/jmyRLYn/rDD1acmQ4Dqy0fZC+FykgXBzBpqucsf5MZCkDVb97HlAzTgp119p0KEkA0wZBBGGBom46ZmQDQl+6y5cfs2WcY9zbbsYaqtgoSANI3ZevedF1TnQh6b/V6FgBx4fs3+w+XTZInGzc+51fpPHFMmdIpFGoiOw/A0zfV9++8LUCln6417m/WJQn7ohI1x2+XT/eUmsPzy+bDqOCTdSxo/miaHCkXMiWPlSSsnzVNgTw+MY7X9EnCVGHppqP/G6Y4vmKuFAAWL7UAT71NR+7G29PLde1kfZKQYH9PRzvU3tdo4wUt3SZHx5nG19EnCa05pVfX/dep9oWvnZZA37lb0pwuta7eNQ6Y01WlC2+XTz8qAZMkYc6vOjeS873ncPD8+JpUl0b4m5SOEW8LUIGpodM5uw4AwP5JpR5ednWCpoW3i4eAp767I7b89vTb+jyBLklIPPqejnaIC7ry6w1t9Dz6k4R7HFW5K25v2qTPxT9VknCPd4dG06FpMM5s9ndPpHIQKrANHRAw1wg7NB0lLZkQZIM0HR2akxVAOKoahuueiDmMNB0duqyg7py67oka1w77AzCfq6uAZ39tAR4I6u5AygBdX0llYtqSQa7jz0Gajg6T+FPfPXEuUeNUC+kCzR1dDl20132VZEBTvc86D6GmYH1yUt898VQ96rSh7aca/VYT6fc5CbDfWxV7BETdHR7xAND3S8+Mvp979IkHo6Z6UHcH0vl5o+6JwQ3dYtwy0XdPNFd3IJShHybwdN0T1PnGxv5uMv1b46igbdt3s7GxkUUOgIe62djY2MjqP/oS+Vgdo303Gxt1/ZpGuaymeHpTJgl9b+tuxDI81P7GxkZdksOoY3Sw6xiHF1Rd1dZCelMtGK4DIPvjF/nkwO6JPuMbZZ8qiGc9LTxU30BDixwVh6QAcL7xUi9Q5+krBnUr7b85rHyQOQAe6qah/EYdo49jaEPHKHW+sdHQ/1p35ak7Rs1V46pOsVB88ySh8bbHHpJhfqB13smBB1qGxyTKH25Ihnn8Wt162dL+iyb0jxB7EUMyzOTrqh7QPt/vqDp2fNO0XZmWOkaN3vDhhmSYtf0slv9ZDMkYYOmo6GM7Qp8AHuJxB4MNVKVVSbID+aTw1ETm7ZA80XXYy0s2FA840Z4fDYmYQeAhHJ/ZYDBLhk5jmht6JzfNfmmX/dDwVJ4aejDYwPJvahpQftFwj21kA+D98zI+Jx8bHtFOwY0R27eyS9NmHi35DwPPIpsztk/q6NinSteYV++i+V/fEWXWDgUPsZf7zIahWtDiAYaWpSt2VVgn6rqtBoHnF8eqQ0/oDd0iS7NNy7//g6qnH4ZqqdZ8dHW15HHhoYIS+XYjHiRONV8c8NCGgYcIW5nyxEEIteezfeYD4GdvbKAWe97Tw2NxAPyVDeHPcfpE36OrX0hMzh9k47cux9D3WmkJHmrC2SUHyScvv+kA+L2JLhXkc4AHqJ6Jjz/1Zv/2qU8TUIq2PzQ5LxXCQaX2urfE4tSb1ydKRnQd04F6+71VSCku2aHze5an3oguTGXBc9SAWTTnImdKYjhKfbVlceoNfLldOpLyZ5qWf/swkyfG5KS/c5tOTG/LfO6X6SvaNH36iRuB5KgqfNCsI6ygOStcakfBveAZo1gYHiwMDxaGBwvDg4WF4cHC8GBheLAwPFgYHiwsDA8WhgcLw4OF4cHCwvBgYXiwMDxYGB4sDA8WFoYHC8ODheHBwvBgYWF4sDA8WBgerLGu/38AHMoE6bl/zB4AAAAASUVORK5CYII="}}},{"cell_type":"code","source":"NB_model = GaussianNB()\nNB_model.fit(X_train, y_train)\ny_pred = NB_model.predict(X_test)\nNB_model_acc = accuracy_score(y_pred, y_test) * 100\nprint(\"Accuracy:\", NB_model_acc)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:13.017005Z","iopub.execute_input":"2022-07-12T12:26:13.017351Z","iopub.status.idle":"2022-07-12T12:26:13.030204Z","shell.execute_reply.started":"2022-07-12T12:26:13.017320Z","shell.execute_reply":"2022-07-12T12:26:13.028832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**K-nearest neighbours classifier**<a id=\"knn\"></a>\n","metadata":{}},{"cell_type":"markdown","source":"\n\nThe K-nearest neighbours (KNN) classifier uses proximity to make classifications or predictions about independent data points. This technique may be used for both classification and regression scenarios and the output will vary. In classification instances, a decision is made based on majority vote, i.e., the class assigned to the new data point is taken to be the one that is most frequently seen in the vicinity of the point. KNN is also known as a lazy learner technique since a model is not learned. Instead, the raw data is stored and used everytime a prediction must be made.\n![](https://analyticsjobs.in/wp-content/uploads/2020/02/Calculate-the-Euclidean-distance-between-the-data-points.jpg)\n","metadata":{}},{"cell_type":"code","source":"knn_model = KNeighborsClassifier(n_neighbors = 5)\nknn_model.fit(X_train, y_train)\ny_pred = knn_model.predict(X_test)\nknn_model_acc = accuracy_score(y_pred, y_test) * 100\nprint(\"Accuracy:\", knn_model_acc)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:13.031790Z","iopub.execute_input":"2022-07-12T12:26:13.032158Z","iopub.status.idle":"2022-07-12T12:26:13.056029Z","shell.execute_reply.started":"2022-07-12T12:26:13.032118Z","shell.execute_reply":"2022-07-12T12:26:13.054865Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"**Support vector machines**<a id=\"svm\"></a>","metadata":{}},{"cell_type":"markdown","source":"\n\nSupport vector machines (SVM) are a class of machine learning algorithms that map data to a high dimensionality feature space in such a manner that the data points can be categorized, even when they are not otherwise linearly seperable. A seperator between the categories is found and a hyperplane is drawn accordingly. Support vectors are those data points that are close to the hyperplane and influence the position and orientation of the hyperplane. The function used to map data to a high dimensionality feature space is called a kernel function.\n![](https://www.analyticssteps.com/backend/media/thumbnail/338466/8680904_1588569086_SVM.jpg)\n","metadata":{}},{"cell_type":"code","source":"svm_model = SVC()\nsvm_model.fit(X_train, y_train)\ny_pred = svm_model.predict(X_test)\nsvm_model_acc = accuracy_score(y_pred, y_test) * 100\nprint(\"Accuracy:\", svm_model_acc)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:13.060002Z","iopub.execute_input":"2022-07-12T12:26:13.060989Z","iopub.status.idle":"2022-07-12T12:26:13.100949Z","shell.execute_reply.started":"2022-07-12T12:26:13.060947Z","shell.execute_reply":"2022-07-12T12:26:13.099985Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color:  #FFA07A;\n            font-size:110%;\n            text-align: left\">\n    <h2 style='; border:0; border-radius: 15px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center>Submission file </center></h2><a id=\"sv\"></a>\n\n","metadata":{}},{"cell_type":"markdown","source":"![](https://ncats.nih.gov/files/AI_banner_1100x420.png)","metadata":{}},{"cell_type":"code","source":"all_models = pd.DataFrame({\n    \"Model\" : [\"Decision tree classifier\", \"Random forest classifier\", \"Naive Bayes classifier\", \"KNN\", \"SVM\"],\n    \"Accuracy score\" : [decision_tree_model_acc, random_forest_model_acc, NB_model_acc, knn_model_acc, svm_model_acc]\n})\nall_models.sort_values(by = \"Accuracy score\")","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:13.102356Z","iopub.execute_input":"2022-07-12T12:26:13.102715Z","iopub.status.idle":"2022-07-12T12:26:13.117116Z","shell.execute_reply.started":"2022-07-12T12:26:13.102683Z","shell.execute_reply":"2022-07-12T12:26:13.115876Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"random_forest_model = RandomForestClassifier(criterion='gini',\n                                            n_estimators=1750,\n                                            max_depth=7,\n                                            min_samples_split=6,\n                                            min_samples_leaf=6,\n                                            max_features='auto',\n                                            verbose=1,\n                                            random_state = 3)\nrandom_forest_model.fit(X, y)\ny_pred = random_forest_model.predict(test)\nprint(\"Accuracy:\", random_forest_model_acc)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:13.118755Z","iopub.execute_input":"2022-07-12T12:26:13.119358Z","iopub.status.idle":"2022-07-12T12:26:17.439891Z","shell.execute_reply.started":"2022-07-12T12:26:13.119322Z","shell.execute_reply":"2022-07-12T12:26:17.438767Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission = pd.DataFrame({\n    \"PassengerId\" : test[\"PassengerId\"],\n    \"Survived\" : y_pred\n})\nsubmission.head(10)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:17.441740Z","iopub.execute_input":"2022-07-12T12:26:17.442092Z","iopub.status.idle":"2022-07-12T12:26:17.453703Z","shell.execute_reply.started":"2022-07-12T12:26:17.442059Z","shell.execute_reply":"2022-07-12T12:26:17.452832Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"submission.to_csv('submission.csv', index = False)","metadata":{"execution":{"iopub.status.busy":"2022-07-12T12:26:17.454916Z","iopub.execute_input":"2022-07-12T12:26:17.455611Z","iopub.status.idle":"2022-07-12T12:26:17.463737Z","shell.execute_reply.started":"2022-07-12T12:26:17.455564Z","shell.execute_reply":"2022-07-12T12:26:17.462568Z"},"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"<div style=\"border-radius:10px;\n            border : black solid;\n            background-color: #DA70D6;\n            font-size:200%;\n            text-align: left\">\n\n<h1 style='; border:0; border-radius: 10px; text-shadow: 1px 1px black; font-weight: bold; color:black'><center> YOUR FEEDBACKS IS SO VALUABLE FOR ME </center></h1>","metadata":{}},{"cell_type":"markdown","source":"![](https://st2.depositphotos.com/1006899/7664/i/600/depositphotos_76643019-stock-photo-thank-you-words.jpg)","metadata":{}}]}