{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.7.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"nvidiaTeslaT4","dataSources":[{"sourceId":45533,"databundleVersionId":5748852,"sourceType":"competition"}],"dockerImageVersionId":30381,"isInternetEnabled":false,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"### **💳 Notebook Workflow At a Glance**","metadata":{}},{"cell_type":"markdown","source":"\n 📌 Notebook Overview:
\n \n* This is log data, which means each session has multiple events. For modeling, it's important to decide analysis unit.For this, please refer to basic submission demo. https://www.kaggle.com/code/philculliton/basic-submission-demo
\n \n* For each (session_id) _(question #), you are predicting the correct column, identifying whether you believe the user for this particular session will answer this question correctly, using only the previous information for the session.
\n \n* In this case, you can treat each session_id as one user. Simply speaking, I will look at all the log data of each session and predict whether user could answer each questions correctly.
\n \n* I assumed that user's behavior on each game level is important. Therefore, I will aggregate the data by each sessions' (users) game level. Also, I will make dummies of event_name variables so that model could learn more about each event.
\n \n* In sum, we build three models. \n - learn log behavior of level group 0-4, predict questions 1-3.\n - learn log behavior of level group 5-12, predict questions 4~13\n - learn log behavior of level group 13-22, predict questions 14~18.\n
\n \n* In terms of modeling code, original work is done by https://www.kaggle.com/code/cdeotte/random-forest-baseline-0-664 ; Also, When ti comes to feature engineering, I modified part of this notebook.
\n \n
","metadata":{}},{"cell_type":"markdown","source":"","metadata":{},"attachments":{"35b0fc1f-246c-4790-ba55-317c1bd850d9.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"#### **Exploratory Data Analysis**","metadata":{}},{"cell_type":"markdown","source":"- session_id - the ID of the session the event took place in\n- index - the index of the event for the session\n- elapsed_time - how much time has passed (in milliseconds) between the start of the session and when the event was recorded\n- event_name - the name of the event type\n- name - the event name (e.g. identifies whether a notebook_click is is opening or closing the notebook)\n- level - what level of the game the event occurred in (0 to 22)\n- page - the page number of the event (only for notebook-related events)\n- room_coor_x - the coordinates of the click in reference to the in-game room (only for click events)\n- room_coor_y - the coordinates of the click in reference to the in-game room (only for click events)\n- screen_coor_x - the coordinates of the click in reference to the player’s screen (only for click events)\n- screen_coor_y - the coordinates of the click in reference to the player’s screen (only for click events)\n- hover_duration - how long (in milliseconds) the hover happened for (only for hover events)\n- text - the text the player sees during this event\n- fqid - the fully qualified ID of the event\n- room_fqid - the fully qualified ID of the room the event took place in\n- text_fqid - the fully qualified ID of the\n- fullscreen - whether the player is in fullscreen mode\n- hq - whether the game is in high-quality\n- music - whether the game music is on or off\n- level_group - which group of levels - and group of questions - this row belongs to (0-4, 5-12, 13-22)","metadata":{}},{"cell_type":"markdown","source":"\n 📌 EDA summary:
\n \n* There are 21 columns in total - 20 X variables and 1 Y variable(correct) /1 extra variables (session_id)
\n* Some variables have missing data. While variables has missing data only.
\n* In terms of data type,there are 7 object type ,3 int type and 9 float64 type.
\n* There are only 3 unique session_id on test dataset. Therefore, we need to predict 3 x 18(questions) = 54 rows.
\n
","metadata":{}},{"cell_type":"code","source":"import numpy as np\nimport pandas as pd\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nimport plotly.express as px\nfrom plotly.subplots import make_subplots\nimport plotly.graph_objects as go\n\n\nfrom sklearn.model_selection import StratifiedKFold\nfrom sklearn.preprocessing import OrdinalEncoder\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.metrics import roc_auc_score\nfrom sklearn.model_selection import train_test_split\n\nfrom sklearn.metrics import confusion_matrix, accuracy_score, precision_score, recall_score, f1_score\nfrom sklearn.metrics import roc_auc_score\n\n\nfrom xgboost import XGBClassifier\nfrom catboost import CatBoostClassifier\nfrom lightgbm import LGBMClassifier\n\n\nfrom matplotlib import ticker\nimport time\nimport warnings\nwarnings.filterwarnings('ignore')\n\n\nfrom sklearn.model_selection import KFold, GroupKFold\nfrom sklearn.ensemble import RandomForestClassifier\nfrom sklearn.metrics import f1_score","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","execution":{"iopub.status.busy":"2023-12-09T23:49:22.329288Z","iopub.execute_input":"2023-12-09T23:49:22.330336Z","iopub.status.idle":"2023-12-09T23:49:27.734412Z","shell.execute_reply.started":"2023-12-09T23:49:22.330291Z","shell.execute_reply":"2023-12-09T23:49:27.733425Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Reduce Memory Usage\n# reference : https://www.kaggle.com/code/arjanso/reducing-dataframe-memory-size-by-65 @ARJANGROEN\n\ndef reduce_memory_usage(df):\n \n start_mem = df.memory_usage().sum() / 1024**2\n print('Memory usage of dataframe is {:.2f} MB'.format(start_mem))\n \n for col in df.columns:\n col_type = df[col].dtype.name\n if ((col_type != 'datetime64[ns]') & (col_type != 'category')):\n if (col_type != 'object'):\n c_min = df[col].min()\n c_max = df[col].max()\n\n if str(col_type)[:3] == 'int':\n if c_min > np.iinfo(np.int8).min and c_max < np.iinfo(np.int8).max:\n df[col] = df[col].astype(np.int8)\n elif c_min > np.iinfo(np.int16).min and c_max < np.iinfo(np.int16).max:\n df[col] = df[col].astype(np.int16)\n elif c_min > np.iinfo(np.int32).min and c_max < np.iinfo(np.int32).max:\n df[col] = df[col].astype(np.int32)\n elif c_min > np.iinfo(np.int64).min and c_max < np.iinfo(np.int64).max:\n df[col] = df[col].astype(np.int64)\n\n else:\n if c_min > np.finfo(np.float16).min and c_max < np.finfo(np.float16).max:\n df[col] = df[col].astype(np.float16)\n elif c_min > np.finfo(np.float32).min and c_max < np.finfo(np.float32).max:\n df[col] = df[col].astype(np.float32)\n else:\n pass\n else:\n df[col] = df[col].astype('category')\n mem_usg = df.memory_usage().sum() / 1024**2 \n print(\"Memory usage became: \",mem_usg,\" MB\")\n \n return df","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:49:27.736639Z","iopub.execute_input":"2023-12-09T23:49:27.737542Z","iopub.status.idle":"2023-12-09T23:49:27.753374Z","shell.execute_reply.started":"2023-12-09T23:49:27.737494Z","shell.execute_reply":"2023-12-09T23:49:27.752351Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df = pd.read_csv('/kaggle/input/predict-student-performance-from-game-play/train.csv')\ntrain_df.info()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:49:27.754631Z","iopub.execute_input":"2023-12-09T23:49:27.754905Z","iopub.status.idle":"2023-12-09T23:51:20.793341Z","shell.execute_reply.started":"2023-12-09T23:49:27.754878Z","shell.execute_reply":"2023-12-09T23:51:20.792332Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:17:31.830551Z","iopub.execute_input":"2023-12-10T00:17:31.830951Z","iopub.status.idle":"2023-12-10T00:17:33.718855Z","shell.execute_reply.started":"2023-12-10T00:17:31.830918Z","shell.execute_reply":"2023-12-10T00:17:33.717808Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df = reduce_memory_usage(train_df)\ntrain_df.info()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:20.795626Z","iopub.execute_input":"2023-12-09T23:51:20.795952Z","iopub.status.idle":"2023-12-09T23:51:51.058699Z","shell.execute_reply.started":"2023-12-09T23:51:20.79592Z","shell.execute_reply":"2023-12-09T23:51:51.057522Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import gc\ngc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:51.060167Z","iopub.execute_input":"2023-12-09T23:51:51.060567Z","iopub.status.idle":"2023-12-09T23:51:51.195668Z","shell.execute_reply.started":"2023-12-09T23:51:51.060525Z","shell.execute_reply":"2023-12-09T23:51:51.194574Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_label = pd.read_csv('/kaggle/input/predict-student-performance-from-game-play/train_labels.csv')\ntrain_label = reduce_memory_usage(train_label)\ntrain_label['session'] = train_label.session_id.apply(lambda x: int(x.split('_')[0]) )\ntrain_label['q'] = train_label.session_id.apply(lambda x: int(x.split('_')[-1][1:]) )\nprint( 'shape of label dataset is:',train_label.shape )","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:51.196985Z","iopub.execute_input":"2023-12-09T23:51:51.197318Z","iopub.status.idle":"2023-12-09T23:51:53.564545Z","shell.execute_reply.started":"2023-12-09T23:51:51.19729Z","shell.execute_reply":"2023-12-09T23:51:53.563379Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_label.head()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:53.565807Z","iopub.execute_input":"2023-12-09T23:51:53.566139Z","iopub.status.idle":"2023-12-09T23:51:53.582098Z","shell.execute_reply.started":"2023-12-09T23:51:53.566104Z","shell.execute_reply":"2023-12-09T23:51:53.581092Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"gc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:53.583393Z","iopub.execute_input":"2023-12-09T23:51:53.583659Z","iopub.status.idle":"2023-12-09T23:51:53.712063Z","shell.execute_reply.started":"2023-12-09T23:51:53.583633Z","shell.execute_reply":"2023-12-09T23:51:53.710975Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def summary(df):\n print(f'data shape: {df.shape}')\n summ = pd.DataFrame(df.dtypes, columns=['data type'])\n summ['#missing'] = df.isnull().sum().values * 100\n summ['%missing'] = df.isnull().sum().values / len(df)\n summ['#unique'] = df.nunique().values\n desc = pd.DataFrame(df.describe(include='all').transpose())\n summ['min'] = desc['min'].values\n summ['max'] = desc['max'].values\n summ['first value'] = df.loc[0].values\n summ['second value'] = df.loc[1].values\n summ['third value'] = df.loc[2].values\n \n return summ","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:53.713436Z","iopub.execute_input":"2023-12-09T23:51:53.713728Z","iopub.status.idle":"2023-12-09T23:51:53.7222Z","shell.execute_reply.started":"2023-12-09T23:51:53.713699Z","shell.execute_reply":"2023-12-09T23:51:53.721306Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"summary_table = summary(train_df)\nsummary_table","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:51:53.726493Z","iopub.execute_input":"2023-12-09T23:51:53.726855Z","iopub.status.idle":"2023-12-09T23:52:25.569038Z","shell.execute_reply.started":"2023-12-09T23:51:53.726827Z","shell.execute_reply":"2023-12-09T23:52:25.568063Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"#### I will skip detailed EDA process.\n I assumes:\n - text matters\n - level of game matters\n - event type matters\n - elapsed time matters\\\n \n Also assumes:\n - 'page', 'room_coor_x', 'room_coor_y', 'screen_coor_x', 'screen_coor_y',\n 'hover_duration', 'text_fqid', 'fullscreen', 'hq',\n 'music', 'level_group'\n these data is not useful. (As there are too many missing values....)\n For coordinates variables, I am not sure how to leverage it due to lack of domain knowledge.\n \n\n\n#### I will try to aggregate data by user level (session level).","metadata":{}},{"cell_type":"markdown","source":"\n 📌 Feature engineering:
\n \n* Very smart and useful function from https://www.kaggle.com/code/cdeotte/random-forest-baseline-0-664
\n* I assumed event is important factor for prediction. Therefore, I made dummies of event_name.
\n* I only added sum, count, mean values. You can create more variables thru EDA or domain knowledge.
\n* We will train with 16 features and train with 11779 users info
\n
","metadata":{}},{"cell_type":"code","source":"#create dummies\njust_dummies = pd.get_dummies(train_df['event_name'])\n\ntrain_df = pd.concat([train_df, just_dummies], axis=1)","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:25.570136Z","iopub.execute_input":"2023-12-09T23:52:25.570396Z","iopub.status.idle":"2023-12-09T23:52:27.638716Z","shell.execute_reply.started":"2023-12-09T23:52:25.57037Z","shell.execute_reply":"2023-12-09T23:52:27.637726Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df.head()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:27.639951Z","iopub.execute_input":"2023-12-09T23:52:27.640609Z","iopub.status.idle":"2023-12-09T23:52:27.664839Z","shell.execute_reply.started":"2023-12-09T23:52:27.640574Z","shell.execute_reply":"2023-12-09T23:52:27.663566Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_df['event_name'].value_counts()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:27.665883Z","iopub.execute_input":"2023-12-09T23:52:27.666159Z","iopub.status.idle":"2023-12-09T23:52:27.804102Z","shell.execute_reply.started":"2023-12-09T23:52:27.666131Z","shell.execute_reply":"2023-12-09T23:52:27.80301Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"count_var = ['event_name', 'fqid','room_fqid', 'text']\nmean_var = ['elapsed_time','level']\nevent_var = ['navigate_click','person_click','cutscene_click','object_click','map_hover','notification_click',\n 'map_click','observation_click','checkpoint','elapsed_time']","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:27.80545Z","iopub.execute_input":"2023-12-09T23:52:27.805854Z","iopub.status.idle":"2023-12-09T23:52:27.813377Z","shell.execute_reply.started":"2023-12-09T23:52:27.805813Z","shell.execute_reply":"2023-12-09T23:52:27.812471Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# reference: https://www.kaggle.com/code/cdeotte/random-forest-baseline-0-664/notebook\ndef feature_engineer(train):\n dfs = []\n for c in count_var:\n tmp = train.groupby(['session_id','level_group'])[c].agg('nunique')\n tmp.name = tmp.name + '_nunique'\n dfs.append(tmp)\n for c in mean_var:\n tmp = train.groupby(['session_id','level_group'])[c].agg('mean')\n dfs.append(tmp)\n for c in event_var:\n tmp = train.groupby(['session_id','level_group'])[c].agg('sum')\n tmp.name = tmp.name + '_sum'\n dfs.append(tmp)\n df = pd.concat(dfs,axis=1)\n df = df.fillna(-1)\n df = df.reset_index()\n df = df.set_index('session_id')\n return df","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:27.814518Z","iopub.execute_input":"2023-12-09T23:52:27.815417Z","iopub.status.idle":"2023-12-09T23:52:27.825068Z","shell.execute_reply.started":"2023-12-09T23:52:27.815378Z","shell.execute_reply":"2023-12-09T23:52:27.824207Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df_tr = feature_engineer(train_df)\nprint( df_tr.shape )","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:27.826419Z","iopub.execute_input":"2023-12-09T23:52:27.826803Z","iopub.status.idle":"2023-12-09T23:52:54.373368Z","shell.execute_reply.started":"2023-12-09T23:52:27.826777Z","shell.execute_reply":"2023-12-09T23:52:54.372321Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"df_tr.head()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:54.375953Z","iopub.execute_input":"2023-12-09T23:52:54.376379Z","iopub.status.idle":"2023-12-09T23:52:54.401641Z","shell.execute_reply.started":"2023-12-09T23:52:54.376337Z","shell.execute_reply":"2023-12-09T23:52:54.40051Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"gc.collect()","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:54.403083Z","iopub.execute_input":"2023-12-09T23:52:54.403471Z","iopub.status.idle":"2023-12-09T23:52:54.540983Z","shell.execute_reply.started":"2023-12-09T23:52:54.40343Z","shell.execute_reply":"2023-12-09T23:52:54.539917Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"#check data type\ndf_tr.dtypes","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:54.542354Z","iopub.execute_input":"2023-12-09T23:52:54.542788Z","iopub.status.idle":"2023-12-09T23:52:54.55323Z","shell.execute_reply.started":"2023-12-09T23:52:54.542743Z","shell.execute_reply":"2023-12-09T23:52:54.552308Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"FEATURES = [c for c in df_tr.columns if c != 'level_group']\nprint('We will train with', len(FEATURES) ,'features')\nALL_USERS = df_tr.index.unique()\nprint('We will train with', len(ALL_USERS) ,'users info')","metadata":{"execution":{"iopub.status.busy":"2023-12-09T23:52:54.5545Z","iopub.execute_input":"2023-12-09T23:52:54.554872Z","iopub.status.idle":"2023-12-09T23:52:54.565716Z","shell.execute_reply.started":"2023-12-09T23:52:54.554835Z","shell.execute_reply":"2023-12-09T23:52:54.564815Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"","metadata":{}},{"cell_type":"markdown","source":"\n 📌 Modeling:
\n \n* Very smart and useful function from https://www.kaggle.com/code/cdeotte/random-forest-baseline-0-664
\n* I used LGBM classifier instead of RF from original code.
\n* Choose best threhold based on F1 Score, which is same with the original code.
\n* Do not forget that you need to transform test dataset from API.
\n
","metadata":{}},{"cell_type":"code","source":"gkf = GroupKFold(n_splits=5)\noof = pd.DataFrame(data=np.zeros((len(ALL_USERS),18)), index=ALL_USERS)\nmodels = {}\n\n# COMPUTE CV SCORE WITH 5 GROUP K FOLD\nfor i, (train_index, test_index) in enumerate(gkf.split(X=df_tr, groups=df_tr.index)):\n print('#'*25)\n print('### Fold',i+1)\n print('#'*25)\n \n \n lgb_params = {\n 'objective' : 'binary',\n 'metric' : 'auc',\n 'learning_rate': 0.002,\n 'max_depth': 6,\n 'num_iterations': 1000}\n \n \n # ITERATE THRU QUESTIONS 1 THRU 18\n for t in range(1,14):\n print(t,', ',end='')\n \n # USE THIS TRAIN DATA WITH THESE QUESTIONS\n if t<=3: grp = '0-4'\n elif t<=13: grp = '5-12'\n elif t<=22: grp = '13-22'\n \n # TRAIN DATA\n train_x = df_tr.iloc[train_index]\n train_x = train_x.loc[train_x.level_group == grp]\n train_users = train_x.index.values\n train_y = train_label.loc[train_label.q==t].set_index('session').loc[train_users]\n \n # VALID DATA\n valid_x = df_tr.iloc[test_index]\n valid_x = valid_x.loc[valid_x.level_group == grp]\n valid_users = valid_x.index.values\n valid_y = train_label.loc[train_label.q==t].set_index('session').loc[valid_users]\n \n # TRAIN MODEL\n clf = LGBMClassifier(**lgb_params)\n clf.fit(train_x[FEATURES].astype('float32'), train_y['correct'])\n \n # SAVE MODEL, PREDICT VALID OOF\n models[f'{grp}_{t}'] = clf\n oof.loc[valid_users, t-1] = clf.predict_proba(valid_x[FEATURES].astype('float32'))[:,1]\n \n print()","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:53:42.20195Z","iopub.execute_input":"2023-12-10T00:53:42.202371Z","iopub.status.idle":"2023-12-10T00:56:32.771774Z","shell.execute_reply.started":"2023-12-10T00:53:42.202337Z","shell.execute_reply":"2023-12-10T00:56:32.770826Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"valid_x","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:56:32.774286Z","iopub.execute_input":"2023-12-10T00:56:32.775148Z","iopub.status.idle":"2023-12-10T00:56:32.817637Z","shell.execute_reply.started":"2023-12-10T00:56:32.7751Z","shell.execute_reply":"2023-12-10T00:56:32.816617Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_x ","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:56:32.818856Z","iopub.execute_input":"2023-12-10T00:56:32.819161Z","iopub.status.idle":"2023-12-10T00:56:32.855096Z","shell.execute_reply.started":"2023-12-10T00:56:32.819132Z","shell.execute_reply":"2023-12-10T00:56:32.854181Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"valid_y","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:57:02.031043Z","iopub.execute_input":"2023-12-10T00:57:02.031393Z","iopub.status.idle":"2023-12-10T00:57:02.045147Z","shell.execute_reply.started":"2023-12-10T00:57:02.031364Z","shell.execute_reply":"2023-12-10T00:57:02.044182Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"grouped_df = valid_y.groupby(['correct']).size().reset_index(name='Count')\n\n# Display the result\nprint(grouped_df)","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:56:32.856951Z","iopub.execute_input":"2023-12-10T00:56:32.857291Z","iopub.status.idle":"2023-12-10T00:56:32.866255Z","shell.execute_reply.started":"2023-12-10T00:56:32.857262Z","shell.execute_reply":"2023-12-10T00:56:32.86523Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"train_y","metadata":{"execution":{"iopub.status.busy":"2023-12-10T01:10:34.878267Z","iopub.execute_input":"2023-12-10T01:10:34.879027Z","iopub.status.idle":"2023-12-10T01:10:34.892762Z","shell.execute_reply.started":"2023-12-10T01:10:34.878988Z","shell.execute_reply":"2023-12-10T01:10:34.891703Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"grouped_df = train_y.groupby(['correct']).size().reset_index(name='Count')\n\n# Display the result\nprint(grouped_df)","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:56:32.867715Z","iopub.execute_input":"2023-12-10T00:56:32.868105Z","iopub.status.idle":"2023-12-10T00:56:32.876835Z","shell.execute_reply.started":"2023-12-10T00:56:32.868065Z","shell.execute_reply":"2023-12-10T00:56:32.875851Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"","metadata":{},"attachments":{"7af14217-e770-4af2-9c07-e280e9412cf9.png":{"image/png":"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"},"9237aea4-4972-4fd8-ac56-8ccd1cdfa3d3.png":{"image/png":"iVBORw0KGgoAAAANSUhEUgAABR0AAAMcCAYAAADdcAJ1AAAAAXNSR0IArs4c6QAAAARnQU1BAACxjwv8YQUAAAAJcEhZcwAAFiUAABYlAUlSJPAAAABjaVRYdFNuaXBNZXRhZGF0YQAAAAAAeyJjbGlwUG9pbnRzIjpbeyJ4IjowLCJ5IjowfSx7IngiOjEzMDksInkiOjB9LHsieCI6MTMwOSwieSI6Nzk3fSx7IngiOjAsInkiOjc5N31dfcRkj/QAAI9uSURBVHhe7P0PnBX1fS/+vxV1FXT9E9cokpi4xsRV26I0ha+3F79UJbaBGtNtvjdBiYptVZpvhJsbibkR0iomqZj6E23qv6DYxJBYL5hY1Fr8JgSiwKrAqsiixAXRRdFV0UWR38w5s8Ky55xFnZUDPJ8+hj2fz8w5c87MfD5nzsv5s9umRAAAAAAA5GT37C8AAAAAQC6EjgAAAABAroSOAAAAAECuhI4AAAAAQK7cSAYAdkRr5sX1186Ipe0dWUWmT03sf9CAGDDgY9EwaEgMbhgQNX2ycTuQ9gXT4+rb50Xbxto49oyL4txhyedob47b//nGmLemI2qOHBkXXzA8BvTNnvBhKfkeOqL1gZvi+ruWxit96mLIV8bFVwbVZk/obdtz3hWsa4n5c+fEvN/Mi3vvmxcdRw+P04YOiSEnnZxsk3Xdt8l1zTHr326LOU+2J5+oJgYMHRMXntEQtT1su+0rm5L5/FfMS+Y1697miKMHxuDBn4uRX2qM047eYjlsbIv5t0yJ6U3tEQceG41jz4uhh9ZkIwEA6A1CRwDYAXWsnBHjR06Ie9dnFWUMHDM1rvj74VH/PsO59sdnx+ymttjQpzbq/3h4DD7ywwlq2u6dEGdcNCPakseDJ82OG75cHzVt82JS41lx+6qkctCEuOtH50XDe83XOlpj/n3zoqW9I/Y6+Ng4eejAqHsvH6nke+iIln8bE6dfNi+prIvGqTPj8tPqCpPnpfx66P15v1dtC6bHpIsnxr1rsoqtpNvkVck2+W5gvLE9mm44L750VVNWEVE/5ra4438OKR86Js9pvmtyjL9kRrRkVV01xFd+cGVcPCILLpP1PuuS4TH+7o6ImuFx+cwp0fghbcsAALsqp1cDwE6s6caLYuxVs6N1qwMit01HtDVNj0svmxiTvj05Zi1vz+p3YOufjdn/NCEmJZ/p0lvmRdv7Wi4fth1nPbQvvim+9dXygWOqsE3+cM7mZd/eErNnbQ4ce9YRLbMmxvllA8dUc9z+jVEx6a6WZGoAALYHoSMA7OiGTY57liyPZU8Vh8UPzYm7rrkwBmcHcrXcOiVmpKeVfiBVEN3UDYnL5mSf8yfv4yjHPGz397D1eqiJ+i/flq37edv3KMeNbdH089viwewt1p0+IW745bxYsGRpLP7tnLjjylHRUBwVzbdOj3tXZhO+/Up0dG6egyfEXQuXxz3frHCU47pFMfPmmYWjYFPpkZP3JM9Z9sSimPvLG+OSL9ZnY9pj1rT/E83rsiIAAB+qPhMT2WMAYAex8ZXmuPcn/xktbyWFT54So04/Ng7aozhuj31qo+5Tx8an93ksfvrr1qRmXWw8+i9i5Al1kU1SuBbeg//5m1j0eEusWvNStL+1dxx0QL/YY4v/Hdn2yK9i1qyZMX95eg53R8Q++yfzfSn2OOyoqNunOE10tEXz3P+MOb97LJqfaY21L22IPfrVRu0+nXPaBhs7ovXJh6Ppd03x8OInY+2GflHT/nD8+z3Nkc55wP99Vow8/qDYY31rzJ89Ox5c0BRPPrcxDhlwWPTbcjbr26Ll0cdiwaKm5L08F+s37BH9amujpnOa9S3x4N13xq9mPhaFA/HeqIm+/TpiXcf+8YkBtbFHeur1f8yOeU3N0bx6Q+zfb320LHw4Fq94NWLfg+KgdGYl38PGWLd4Ztw+J13W/eLYz50Zf7BXSyyYlzz36Zdi/W77x0EH1ry77NNl1nTfr+I3i5L5PLMhDjlii8/RlqzX/5gTixY3x4rXiu9rXQ/rIT31euZ98+OR5mdifd9PxIADt1woHcm6XhZNjy6KpkeaY82L62PjXsln2XfLadLXmBMzH3g4mpe2xKt9D4vaZFk1zZ8XTS3JctzYr9u2UdKLyfZ2zbRoSkO+2pHxD/88Lk6rT5f/HoVt4rBPnxCfePv++PcFyQSbnouaPzgz/mxAW8y9e2b8+68eK4aIHXvEgft0xNqNyWfvn6yTtG4r7UtnxA//5eHC9DWnT44bLh0Z9fsmhd1rot9HPhED/6//Kw5dOSMeWL4xYu3bcdTpn4uBH+mIZfdPj3uXJXV7HBV/9j+Gx7FbLqd0G3zsN/Hggw/HY08mbaJtfXTs2S/qasudgp0t10XJcn20Jda8/Gps3KP7cu3U0dYSix9Jt83HYuXzL0XHO3tH7YHJMs3GAwDsjFzTEQB2QF2u6Zge6XhNY9RvlY+0L5gSX/of1xVOQR1wzm1xxzeHRN3rzTHr2sviW7c0dTtmru60cXHVt86LwYenL9QRzTeOijO+t/VpryfHZb+cGl85OqJ17vS4+rLJMWtlNupdW11Pr5L1rXHvDy+Msbc0ZxXd9XhNx40d0XLvlPjWN26Kpq0/VE1DjBh7UVz45eFRv352XHrmRTGj8xC5zLvL5qUtXr+E2qHJ8vl/j4s5f39uhWs6phMmy6/LDX5q47RJ0+OKL2XLo70prv5qY1y/OHl89IVxx/RxMfDAwoTR8fhNcfbIyZEu9QFn3xh3fGtItN1SeT2Uvabj+paYddXFMf7WrZdtXYyYdF1c9qWB2frZ6v2X0DDmxrjh6ydXvP5lx4oZMfbPJ8SDG5NCmW2y7cGJ8aUx0yONZ+v/7ra4tbE9rvyri2LWVkcjVrqmY+s9E+KMr82I9ODIgd+cGbeOaYit31bHmpZoXdeRfLKaqD28PgbUlL+mY8eKOXHd9ybE9Q9stWEkzx38d1Pisgu6XhO1o60pfn7FxTHp7vRTdDVg6Ki44O8uipGD6orvqaM1HrxlYoy/ak7h/XZx5PC44IKL4rxtaScAADsgp1cDwM5qj703hzEb0xCsI1ruuzEmlQgcU233TonzvzsjmrflTOy2RTHjh6UCx1R6Pb2L4+oHW0vOZ7OOaE3DwgqBY8+S17hnYpz9tRKBY6qjOWZdNSGuuy+Ha/vtVxcD9t8zK1Sw9R3Foz3uveyy+PniD3qK+3vREc0/n1wicEy1xazLLonr5m8dspXXfOOE+OEDPazPtzuiIw0cEzU1Nd2CwFRNTe3m+rezv+9VYVsuqtmr1FyS+kPro/6Yhmg4pj4GVDoFvqMtHrx9conAMdUR8//lomT7TO+inlWta4qbv9ZYMnBMtT44PS694rZoSl8ufe2rzovzSwWOqRWz4/pvT46fb1ODAwDY8QgdAWCXURP1X5wcd/14QjSeNiouu3FG3DVzZtxx48QYcXhxio4HpsaMBWlikkz7+Ulx7ZjOq/DVxNBv3hh3/XJinHZETeHahhf/68y4aszwGHHRlLjjzplx150z4qq/G5hN3xK33zI7WirdXXt9azx498wskKmLEf87ef3k/dz6gwtj6KGFyp6lr3FX8S7XEQNixDenxA23zYhbr5kYF5wxMNKIa/D4m+KSM+qjJnnPFyT1p3WGUEeOiqt+MjNuGH1s1JU40qz+ixPj1uRzpcvn3C+Ni6v+58io7zytvKJknudMjhtunBqXfH5AVtcUN/38/dy4pof1UEbHqjlx+7/MyUr10fitqXHrj2+My88ZkrxCqiVuvmFmmYB5YJz7g9uK63NM5/psixk3/GzbAun3oObgZDvacp0cU1wn1ybr5EM5+q+mLk77X9Pjjkmj4rQvjotrk3kXtsEtrj/Z9K/TY352J6a25v9I2kfhYdQMPi8un3pb3HHbjXHV+FEx9Mik8sjGuOqfLorBdck6WLsoZt6V3eqmbnhccOWNcetPbotr/3FcNJ6UbhcNce41k+Mrx3/oFwYFAPhQCB0BYJdSEwNOSsOSifGVoQOj4ZiGGDi0MS684ORsfFu0rGkvHNFWOFrsY/sXq5PnHfLxY6Ph6AGbT7E9sCFGfHNqXPX1kTHw+IZoOH5gjDh7XJybhi+pZ5+N9tezx6W8/kIsX549/qOz4rwzTi68n8FnjIsr/ndjbNMtUdKj6zrnUXtCnDxseAwdPDAGnz4qLv7BjJj70Ly44fyBxVCxT20MqK+Puv2Kk8dBh0T90Q1Rf3iJ0OeP0lPNR8Xg5HMNHDoqLvnHC2No4bTzng0cPz2u/WZjDB06PL7yP8fFiOzl25qWRmulELaMHtdDCe1L58Sc7OC9AWdPiK+fPTwGn3RyNI6dEBcPLtbH3DnRtGbrFLQ2RlxzdVxyxpDi+rxgUlzSOf2atmh7NXucl5p0nSSfpfP05f0/FvUNyTo59EMM4mrqYuCXJ8a1V14Ypw1Kj45MtsHPXxQXfjF7D+ufLZyqXfB6sW2k6k88OYb/2ZAYOPjkGPF3E+OGmYti7oyJMSI7bTu9O05H5/o++oQYfurJMXjQkDjtSxfG5TfNjgW/nR6XDBuQhcAAADsfoSMA7GI61rXE/Humx/VXTYxLL74oxn5tXEy6tfOouMS2nvaa3nxj8ZyYcct1ceVl42L815LX+vaUmLWic3wyr+xhScnzN2zIHvfb4oYv70W/uqhvyI4mbJ8Z44cfG0d/6qgYdOZFMelfZrx7hNp7tsf7jYLq4qgjB7x7lF7NfkfFsUcXH0d7e7S/31OK35OOaF/Tmh39WRdD/mSLIzn7DYiBgzuP4Xshnn1p6+VTE3v32eKz19TGfp03U+noiI633+fyrHLpjZXuveOmuPqKCcXteFx6Sn7nYZ0d8Wa23mo/dmx03hu7eepZMegzRyXb28lx9iVT4vYHWqJ94+ZlV3PgUVHfue7nTo4zTkynPTZOHzMhrr9jTrR0bvsAADspoSMA7ELaH7kpzv/T4XH21ybG1f8yPWbcPTvuvWd2zF+WTbCtOlrj3u+OjGFnjolLr5gSN//bzJiVvM69DzRlYdeHpE9dDD53YlwwKCtn2hfPjtuvmhDnnzkkTr9sZuXTvHvTHjVR05lDpdci7Lw2YC/rvLZiqstlD/uk76ezoiM6OvINEbec1Y6hI1ruGBenn9IYY789Oa6/ZUZxO753TslTyWuOHhmX/OPIrY7CbY35v7guJn2tMU7/07Pi+s5rZR44MEZ9a0IM7XLQZjK/B2fE1ZddFF86+eQYe2tztH9I2wQAwIdN6AgAO6s3X4nOSCm94UZNR0vMvmFKzO+sPHxgDD19eJyWDIM7j8jaRu1NP4ur/y27Xl3URMPQ4uucNmzgtp0WnaOaw0+Oi3+8KO66ZlycdkRWuYXWOybHzb/5UKPQLWy+uUoh/fswrlOYqNliPhu2zBU3bhk0bhlA5qCmNmqzgK2jva1L8Nkpre/M8mr33/99LY/Ctpw9bn+pvft8NrZH8x0Ti0csXjwxbq90A59Vc+Lma2e+G5TX/dHJxe34tJOLd0bfWp/aaPjSlHhgzm1x2ZcHdg9ZO+bF1f+8+VqZdYPOixv+a3bc8K2R0dDts7bHvd+fGrNX5hv8AgBUC6EjAOyMOtqiee68KMaCtdFw7Meipv3ZeKTzFs/HnBe3/nRG3HDN1Lj2milxxfkj38NRah3R+njna9fEaf+Y3mwlfZ1k+MG34q+OKYzoWZ+a2Guv7PHrW5563BEd6ztK3/G3hI62pph1X0vUDbswrr1/eSx7KhmWzItbv7n5OpXPrmp7N4D9ULW/kF7asqjukOw6jDWxf+fCXtfW5eYy7S88m8ORojVRO6A+C3/bYlHT8s13X369NZqbsjta9/lY1B+y7Wu9JzV1x8YJx2eFuf8RDy7bag12tMb8++Zkn29ADDy+Ltky37vaT2xxivMD/xHNL2WFTMfKOXHTP08vHrF4X2vs1a/8Z2x/bmksWlN8XPelKXHH9BuL2/E1k+Piz5eIzzemRyrOjPmvHxtfmTQjFqfbWjIs+OWU+ErntUxXJss7O7K2/fHZMWtxemOhKXHXE9m2+dDMuKzztTuWR2u3U9wBAHYOQkcA2NE9OSdm3jE9ZtwxIxmmx+23TIlLv3pynP0vWbh0+PAYPrAuavrUxH6dN+xY3x5tbW3R3t5eCBBn3T27dCj37vX92uPZp5ZG07LWQkhW07fzxiYd0b6ueKON9jUt0XTfz+Lex7NRPel3SBx1VPb4kdvipl/MiabHm6N57oy4/vqZ2xQSdqyZFzePa4zxFzfG+ZddF7MeaIrm9DWWLY+WpUuzqWqirm5zvPXutSOfezaWNjdHy6ptjTe3RVvMuGJiXH3H7Hhw7uy4+arJcfuq4pj6gQOjrl/yoF9dDDgiC53aZsSk790UDz7SHE33XheTJkyP1uKYrsqsh3JqPz0kTs5m0XLjuLjy1mTZLp4XM/75kpj0YLE+Bg+JYw/NL3SMvgNi8GmdQW9TXPk/J8b1d88rro8Fc+L2718c4+/KItVjRsbJR5cI9bZBzYAhMeL07H0/flOM//aUmDG3uN7n331djP+bcTErm03d5xtjSHoDoPQ0987rdHY8Gy3Jem9e0RYde+69OWxP2kLb2vboWNcWLfNnx4z7top/N7ZHy10T4/wx4+L8rybL9N9mx/xkvaXzbUm2t+bOa5keWhe1STtrf2R6fGvURTH+q6PiW1NnxL3zi9M2P7k0ljd3vvYhcUjnNTMBAHYyQkcA2NGtmh3X/8PEuPTbE5JhYky64rqYsaAzkaqLEX8/pnjn5dqPxbGDsqBn5YwYf+aQGHTiCTFs5Ji4+sFSCVbxiLnsNi0x/4dj4kt/MTHuXZm86qdPiIGd9VeNidM/e2wM+tPh8aVLZmRHQG6DvgNi6OdHZke7tcW9VySvP3JknPHViTGjM8CpqCPammbGjPnFUvMvpsT4v22MM9LXOPOsmHR3Fuz0PTkGN9QVw6WaQ+JjnyjUJsttRlx61sg4f9rSzUcC5iFdH9++KM7/6kVx5V2dS2NgNP55dkOXPnUx8PSR7x6t13b35Di/cWR86aIpce9WOVdRufVQPnVMTzk/d/zmZTsrXbbJMrn01iyITt7PxWMbo6EzhM5FTdSfMSGu+mL2TlfOjKsvPqu4Pv7HmJh0a1OxvmZIXPyds2Lw+8sck/VZH8PPHReDs6yu7YHr4tKvFtf72RcnyzDZPgsOb4zLLjg5BhRXfNR9onMJNsfNFyfTf3NGtO03MAZnRyi23TMxvnTyCXH8Z4fE6ck22G1dtLfEg7NmFEPhtjlx82UXxdnJekvn+6WLr4vs00XDSUOifu+2aPrPn8W9hTy7NWb9cEKMTba1wrI4a0Lc3rl9Dz45BuYZ/AIAVBGhIwDsrPoMjHOvmR6XnVGfBW4DYujocTHiPYQ9dcf/ZZx3WveTYGuPaYwL/64zdny/amLAaePiinM676b8XiXPP31i3Hrb5PjKSWVO1K09OS6+bkKMPDILdtKg88vnxfud4/tTG6dNmhR/dfzm91j338bFtVdv+/sotx7Kq4n6z5dbtnUx4h8nxVcGvpfX20Z962PEN6+Lyz7fGfBtpWZgXDB1cpzbGX6/T7V/dF5c+5PJ0VjmWqQ1g5LxN0+I047I1nt6LcbTx8SIw4vFdx18Qoz6+qh3A+CKDkzb0+y4dvzmwHhr9V+aHFecPyRq96qLoWNvijt+cGEM3XqendLPMGlU6WtHAgDsBHbblMgeAwA7ivSoqwcWRev6Eke79amNuiOOioF/0BB1JY5k61jXGi1PLo2WlelNPYrT1u/9Qix6sjU2bKyJuuOHx2lbBGTp9SFbmhbFomT62KMujh02PBoOTOo3dkRbS3PhVOYX0iO6auviqPpDoqMlee32jtirb30MOW1IDOjpaLqN7dHaNC/mtbTFhs730++FaG5ujfb0/QxM3s8xyftZ3xrzH5hXfO2Dj42Thw7MrpGYvcbiRdH0ZPKZkve1V01tHFJ/bDQcU795mi20r2yKpqblyfJL3vaRQ+K0wQOipnDNwTKv36nMe0iv3Te7KXn/ybIf8AcnRP3bzybLpTVeiZo4pGFIDD4mO9JyKx2rmuLBh5dHW0dNDKhPPvdBHdHctLRQfvd9ZdOWWw9bzrv+j4fH4M6AtSBZRyuao+mx4nUG96odEMcOOiEatjq6ruxrpKcUPzg7Fq1JtrO+A+KEYSdH/TaFZB3Rns63Od02OgqvW3fEsck2mayPrbeHdJnemyzTZFve6+AT4uQ/S7bbbb3BTLrem4unm7d3JM9P3uNRA5PPd0Rt6eW9riWaH14ay9cmG+yByfpLb3yUTNi+qjlpE8tjeVtSnyzbjx19VNS+tDSWrmovvPf0RklbHpHY0dYSTQsWxbPrks+WzKn24AFRf2yyvR1eYuGsb0vmOS+WrkleK9me9+qbtJOGZNr69JIH2TQAADshoSMAAAAAkCunVwMAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAudptUyJ7XLVW3zcpLp2+PHl0VJx51WUx4uBifbVavi5i5SvJwk0eH3lgxCf2L9Z/mB5rfjHWPL8+9tl7jzjm6APi4I/sk40BAAAAgN5VHaHj2vvj0vHTYnVW7NR/1JS4/NS6HSZ0vPPJiH9+KGJxW1aR+ZP+EeP+JOLUT2YVJbXFrO+OiztbsmKcEmOnjY4Ts9K2mnrTkviXW5bG6jXrs5qivzjtiLjk/x0YDZ8+MKuppDmuHT054hu3xdjjsioAAAAA2Ebb+fTqNGg7K84pETjuaC6fGzHml90Dx9Tvkg/3pX+PuG5hVtFNFjgeMSFumXZbYRg77P649rv3v6flct7X5sR3Jj/cLXBM/fLelfGnf3FX/McDz2Y1JSyZFueMTtbH6MlR9q0CAAAAQA+2Y+i41ZF9wzYHboXhG6dkI6rfzY9GXPW7rFDBtx+MmPVUVtjSkl8ly+GUGDu6IauIOHH0hDixZVrcuSSr6ME3J82Pu371dFYq7yt/c38sX/FKVupq4cL7C0eX3jItmXdWBwAAAADv1fYLHQtBW/Y4DRy3CNwKjhtdOLW6rPSU7MJReVsOk2LW2mx8Jj01u/w06WnEW45LhmnN2bhts/GdiMm/zQrboNS0adgXw/54q6CvLo6oT8f1/H4eXfJi3Hjb41mpZ/809dHsUVcnjr6t8jIHAAAAgG2w3ULHQtBWcFSc+RdbBY7bYs2qEqceL487x28OFRdOOyu7FmQJhdDyg59G/KuWiBffyArb4IkXIx7q8sbbYvXKiP79tw776qL/Ecmflat7PMV65n88kz3aNjP+T0t0bNiYlQAAAAAgX9spdCwGbUWfiP7v58Ywx43uejr2VaOjf2HE8pjflF5YsTnmPVCo6HLq9uWjPlGoWt00Nwvz0pvTdL7Oez+t+PGtjqzcFk++mD3owWH9j8oeVfbEsnXZo233VJlTrAEAAADgg9rON5L54N49fXqLm9GsXp2GjsXTkwsemJxMM61wVGP/U0cX7n7d/7Bi+Fg8OvKsuPS+9DkNXa6ruC3eeid78B5seB/PqeTN93HU4lt5vwkAAAAAyFRB6PhMrH4fRwt2ho1lT5+OuhhxYefRj6n7s+s3FsPH9EjJscMKIwpWTx9XfL1C+LjtBtRmD96Dw/fNHvTgudXJZzui/xafobSPb+sLbqH/of2yRwAAAACQr+0UOtbFiUM6Tx1eHnf+8r3dvCU9dfrOzrCxfnRcXu7U6INPKY5799Tr1P1xbXazmPTGKelp1V3Dx+u63Yymkv/+sezBNtqrT/Kcj2eFguK1G4tHZ3bX/VqP3f3ff3p49mjbnPiHdfHRQ/bJSgAAAACQr+12pGP/Uxs3h4Tp6c9b3zV6ybTyRx2uXR3PZQ9PPPOUYqC45OGtbgrTHNd+9/7iKdeF8LFrKJkeKXntkuLjwl2bR23b9RO39skDIs4+Pitsg78fFNF3z6yQKVy78YHu7z+9JuVhh/UcOo783CfijwcekpV6dsG5x2aPAAAAACB/2/H06oYYu+URiIXrLqanP2fDDzrvbl3Cwf3jsOzhwh9UmL5lWlz67mtuvlP1iScWr9v47nOT4d3TtOtPihPf441tvj8s4k+24WDDz9VHXHpSVthCMYDdfARmauG05P0OmxBjj8sqenDVPwyJgz+yd1Yqb+yY4+ILf/HJrAQAAAAA+du+13TMTn/e8vTmzY6KwQPLHeW3VWBZuAP1ttx5unin6rJBXnqX6+9kR06+B+kp03d+MaLxmKyihPP+KOLf/jIrdJN8nvRIzC2C12sjeS/v4aY2x37moPg/00+Pkz57aFbT3Xe+MSgmXfLHWQkAAAAAesdumxLZY3KwaE3EfU9HPPNyxO67Rxx1YMTwIyMa3uPRkx/Ef/5/q+I385+L1Wtej3323iOO/cyB8ZenfzIOqXMdRwAAAAB6n9ARAAAAAMjV9j29GgAAAADY6QgdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBc7bYpkT0GAAA+ZN+75pGY/rNlWSl/v/zpn8fHB+yblQAAPhxCRwAA2I7S0PH71zRlpfw1zWkUOgIAHzqnVwMAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALkSOgIAAAAAuRI6AgAAAAC5EjoCAAAAALnabVMiewwAANvd079/NXvUez758f2yR9vf9655JL5/TVNWyl/TnMb4+IB9sxIAwIdD6AgAQFVZ9GhbnPrFu7NS/r4/cXCcN+qYrLT9CR0BgJ2R06sBAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBcCR0BAAAAgFwJHQEAAACAXAkdAQAAAIBc7bYpkT0GAIDtbtGjbXHqF+/OSvn7/sTBcd6oY7LS9ve9ax6J71/TlJXy1zSnMT4+YN+stP2d//UHs0e944YfDs0eAQDbk9ARAICqInTMV7WFjn/2hVnxyOK1WSlfn/nUATH3ni9kJQBge3J6NQAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQq902JbLHALuk625eElNvXJqV8nfHTafGcccclJUA6MmiR9vi1C/enZXy9/2Jg+O8Ucdkpe3ve9c8Et+/pikr5a9pTmN8fMC+WWn7+7MvzIpHFq/NSvn6zKcOiLn3fCErAQDbkyMdARJrXljfawMAAADsaoSOAAAAAECuhI4AAAAAQK52odCxLWZ996w4Z/Tm4dL72rJxnbaa5rv3x+psTGr1fZO61cXa++PSEtMCAAAAwK5q1wkdl/wqVp55W9wyLRuuGh0xfVxcuyQbXwgcx8WdR0zIppkSZ8a0uHRacza+lOa4dvy0WD0sec53Ton+WS0AAAAA7Mp2ndDxuNEx9rjscergU+LMYRELF2ah4pJfxZ0tp8TY0Q3FctTFiAtHR/8HZsSskjfXS0PKybEwDRzffQ4AAAAA4JqOmYUL748Y9sdxYlYuOLh/HBbLY+WarLyFhdPGxZ0xOi4XOAIAAABAF7tw6Ngc8x6IOPHENDRsi9UrI/r3ryuOelddHFEf8dxzXa/9uHDaWXHtytFxuVOqAQAAAKCbXTR0zE6Nrh8dZ255yvW2aJkWd6Zh5ZkfPHB8++234qH5v43XXn01q+lq3UsvFcaX8/uVz8TjS9+9KGU3S5c8Fq3P/j4rdZe+9ssvr8tKXb36anth/MaNG7Oarp5bvSoWP/ZIVupu2ROPxzNPr8hK3S18+Hfx4tqtb+RT9Mb69YV5b+joyGq6euH5NdG08OGs1F3L8qdi+bIns1J3jzYtjDVrnstKXW3YsKEw79dffy2r6erFF9fGgofmZ6XuVj6zIp54fGlW6m7JY4/GqtZns1JXmzZtKsy7/ZVXspqu0vp0/KZN72Q1XaWvu3TxY1mpu/R9/X7l01mpu/RzvfTSi1mpq9dff70w77feeiur6er5ZHk+kizXctL1ka6XcpoWLiis11I63nyzMO90uyhlbVtbYXsq5+kVLYXtsZzHHm2K9vbSy7y3pe332d+vzErdpZ/75XWl22jab6TjN258O6vpKm2jjz3SlJW6W/bkE8myWZ6Vulu04KFoa3shK3X1xhtvFOb9ZrJuSnnhhecrttEVLU/FUxXb6KJY81zpW3O91dlGXyvdRtN+8+HfzctK3aX95hPN5dto2m/21EZfeeXlrKardDtKx7/zTuk2unpVa8V+88nHmyv2m2kbfXFtyet9xPqsjW7YULrfLLTRRRXa6FPLkja6LCt117SoQhtN+up03uvLtNG036zURlcmn/nJCm007TfTZVfKO8l3VDrvV9vbs5quXnn55cL4ctLvyEr95uPNSwrbTDnptlau33zttWIbLddvPpds4489sigrdfdU0kZXtPTQRl8o3UbffLeNvpHVdNWWtNFFC8q30bTffGrZE1mpu7TfLNdG33777cK8XyvXRtdV3rd5NlnezUsXZ6UPV6GNPlqhjT6RttGWrNTdggr7NuvXF9to2l5KKbffkZd03yd9D6W8lLTRSv3mymeerrxvs7j8vk3aH6afu1y/2dsKbfTFMvs2yTaavre33tqQ1XSVbuPp91E56fdY+n1WTtpvpm2tlM5+M/0+LWVtsh1V6jefSdpopX4z3Y7L9ZudbTTd1y8l3e/43by5Wam7dL+lUhtNx1Xat/ldMu+Xk36glM7fH+l7LGX1quT3R9L/lJPu76X9Vzlpv5nuN5bS2W92dJTet+mp30z760r95qNJf1923yb5nkjnXa7fTL9nemyjlfZtku+5cr8Je2qjnb8/yu3bpG0/7QPKSfuO9P2Vk/abaR9USme/mf4+K+X5NWsKfVs5Lcm+Tbp/U84jSRtNX6OU9HdoOu9y/Wba1y94qEIbLezblL83RLo/WK6Npr+/03mX27dJf7+n49P90lIKbXRJ+Taa/v7oad8m/a4upbPfLNdG02083UcoJ20jFfdtkt8P5frNdJ8mnXe5fpPq1WdiInu8a0jvNn3B9+OhgRPilv/3T2K/QuX6WPbg7Gj92PD4s/p+hZqirvWvrngwHnh9RIz9i9fj//zLg9HnT0+OT/fNJn1fdot+++4b/frtG7vv3j3/7dOnT+xXWxv77LNPVtNVTU1N7LtfbeFvKX336Zu8/n6x5557ZjVd9e3XL/ZNxqfz2Vpat+9++yXz7hu77bZbVrvZnnvuFbUV5l2z9z6xX/L89zPvdFl0zrvUctkjec3a2v2Teeyd1XRVU7N3Yd577bVXVtPVPn37xn7JvPfYY4+sZrP0sxbWSd9+peedPGe/5HPvXWadpPNMx+9VZrmk804/d/oZSknnvW8y7L57iXWSzLtzuZTSOe9y6yR9z+nzK6+TfStuD32T5VJ6e0jWyX4V1klSn27L6XZTSt90uey3b8l1kq6HdLmk76/09pCsk+S19062uVJq9kraSW26PZRZJ8nyXLrs9Xhwbumdjjyc8+XPxCF13d9f2rYrrZO0b0g/+/tpo3slyzpdLml7KGXvZJ2k/UfZ7SFZ1+nrV2qj6Xor3U72zNZJ+TaaPr9cG01fN+27KrXRcttD+n5r03mXaaN79tRG03XSQxtN10vpddLZRvcp3U6SeVfqN/feJ+27KqyT5DOnfVfJdZJtD/2SaUq30WTe6fZQto3WFOddYZ3sm3zuSm20X79y20MP/WZNsk6Sz1VunXT2Xel21U22PaRDue2h0vdoYd6FdlJhe0jmXamNpuMrbQ/l+s299iq2k0ptdL+k7yrfb1Zoo0ldoZ2U+S7bM22j+1doo2m/mbx2pX6zfBvtbCdl+uye1knaRpPxL63bGLf9rPyPxQ/q1JMHxAl/0PUMl0L/kCzzcutkn+R7plK/mX7mdLmUXCfJ93ql7WHegraY93DpH1p5+PqFg+LQjx5Qup0k6zHdryq/b1PsHyq10cJ+VYV+M+0/0u2y0613LIs1L5T+HxUf1MEf2TvOG3VM4XFh3sn+Rek22sO+TfZ9Ua7fLLTRfXvoNwtttMK+TZk2mratwjopM+90XRT3dSv3XaX6zfSzFttomX5zj7SN7l+5jabLpWy/WdynK9dO0m2hXDvZI5l3cZ2U2bdJ5r1vxX6zs89+H/1muk4K8y6zPfTUb6brJFluZfdtKvabneuk3L5NcV+3/Dqp/Juwx++ybHsouVySus55l14nxf6h/L5N30L/UGnfpvxvwsrbQ/qaldpoum+T7neVa6OF34Tp9lBqnWRttPxvwuLv0fJtNGknSf/wfvY3390e9k3nXarv6twe3t9vwn369rA9pPs2yfxLrZO0ruI6Sfdtks9dsd8szLunNlqq3yzu26Tvr9S8qV67bSoXke+MlkyLc35wf5z4jdu63lQmUThlOra+KUxzXDt6ckQ2/er7JsWl804qnFYd6ePpEWdedVmMODibHNghXXfzkvjfV5T/v9cf1IOz/jKOO+agrARATxY92hanfvHurJS/708c/G4wVQ2+d80j8f1ryh8d8kE1zWmMjw/YNyttf3/2hVnxyOLSRzd9UJ/51AEx954vZCUAYHvqHtvvrAqB4zNx5lXdA8fUYf2Pili5Oroc9L52dTwXp8SQEtP3P/WyGDtsedw5flqUP6gbAAAAAHY9u0zomN6duv+oC8seldj/1MY4sWVaTL2v8zofbTHrumkRo/686x2tt3Di6ClxZv39ce1owSMAAAAAdNpFQsfi3alXTx8X54w+a6thUswqnN3REGOnTYjD3p1mXMwfMiUuP3XrO1pvqS5GfGdCnBhp8Nj5OgAAAACwa9u1rukIUIJrOgJUF9d0zJdrOgIA28Ouc01HAAAAAOBDIXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAA6AVta9+IZ1e91qsDAFSr3TYlsscAu6Trbl4S//uKh7NS/h6c9Zdx3DEHZSUAerLo0bY49Yt3Z6X8fX/i4Dhv1DFZafv73jWPxPevacpK+Wua0xgfH7BvVtr+/uwLs+KRxWuzUr4+86kDYu49X8hK218aOn5m8E+zUv6+9jfHx2X/a1BWAoDq4khHAAAAACBXQkcAAAAAIFdCRwAAAAAgV0JHAAAAACBXQkcAAAAAIFdCRwAAAAAgV0JHAAAAACBXQkcAAAAAIFdCRwAAAAAgV0JHAAAAACBXQkcAAAAAIFdCRwAAAAAgV0JHAAAAeI/Wvvhmrw4AOzqhIwAAALxH47/z2/j0n/ykV4YTh/08mwvAjkvoCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAACwi1r74pu9Orz8Skc2J3Y1u21KZI8BdknX3bwk/vcVD2el/D046y/juGMOykpAXh5ZvDZ71Dv+4NiPxO6775aV+DAterQtTv3i3Vkpf9+fODjOG3VMVtr+vnfNI/H9a5qyUv6a5jTGxwfsm5W2vz/7wqxea7+f+dQBMfeeL2Sl7a9t7RvxmcE/zUr5+9rfHB+X/a9BWYkP2+iLHoi7Z6/MSvnat9+esfLRUVmpOhzxh9OzR/k77f/+WNzww6FZiQ/bt694KK6/eWlWyl/Lwi/HAfvXZCV2JY50BAB2SDfd/kQhvOitAQDY7K233onXXn+rVwZg5yR0BAAAAAByJXQEAAAAAHIldAQAAAAAciV05H37zuSHe3V4pX1DNicAAAAAdiRCR963tze+E1NvWtJrAwAAAAA7JqEjQJX5aXPE0df33vDg77MZAQAAQC8ROgJUobVv9N4AAAAAvU3oCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AjATuvNNzfGK+0benUAAACgO6EjADu1I0+4vdeGf/inhdlcAAAA2JLQEQAAAADIldARAAAAAMiV0BEAAAAAyJXQEQAAAADIldARAAAAAMhVVYaObb8YE0d/akzMWJNVbKXpe0cl4ydHU1YGAAAAAKpH9YSOHa3RNHdezE+HJ19IKl6IlgVZecvhgenx8weKTwEAAAAAqk/1hI7r5sV1Xz0rzk6G8bc0JxXNcfPFxXKX4W8nxowVEfUXfS4ais8EAAAAAKpI9YSOBw6JC398W9yaDFedk8aJDXHu1cVy12FG3PPrpXHP1wdGTfGZAAAAAEAVqZ7QsWZADDxpSAxOhhHjp8eCh6bHxacXy12HgVF/qLgRAAAAAKpVVd5IJmpqo7ZP8jcdSuhY1549AgAAAACqTXWGjh1NcXXjkBh7a0t0ZFXvWjUjxp48JMbfI3gEAHYd35n8cK8OAACQp6oMHdsfuC2uX9ER0a+2+3UbDxwQ9Qd2xKybZ0ZrVgUAsLO7467lMfWmJb0yPLn85WwuAACQj6oMHVsem5n8OypGfb6uWLGlvkNi+OnJ30cWRbODHQEAAACg6lTpNR3T4xvbon19sbi1jo3pv7XFyQAAAACAqlKVoWPDHzdGTcyO6743M1oLAeNm7fMnx6Rbkgd/dFTUCx0BAAAAoOpUZehYM3hMfGdYTbT8YlwMGzI8zv7G5Lj6hxNj7PATYtBZN0VL1McFlzbGgGx6AAAAAKB6VOfp1X0GRON1c+LWb46MgdES8++6Ka6fOj3uXdERdcPOi6t+OTMu/iOHOQIAAABANarO0DHVpy4Gj5kSdzy0PBYvXBQLHloUi59YGnN/NCFGHC1wBAAAAIBqVb2h4xZqamuj9sDaqOmTVQAAAAAAVauqQ8f2FXPi9ssuijPOHJkMN0VTVt/y4JxuN5gBAAAAAKpDlYaOHdH0w5Fx0vAxMenfZkfz4uZkeKE4ZvF1MX7MmBh/R2uhDAAAAABUl6oMHTvmTo6zpzZHDLowbr1/adw6JhuRqDl+ZDT+UUTTv86MZAoAAAAAoMpUZejY/PCM6IjhccV142LwETXR9bYxA6JhUPJn1aJoaSvWAAAAAADVo4qv6VhT5sYxHdG+Pv07IGprCxUAAAAAQBWpytCx4Y8boyZmxtX/PCdaO7LKTNsDk+PKf0senH5CDOx6CCQAAAAAUAWqMnSsGTwmrji9NlpuHRPDjjs2zk5DxpgR53/2qDjpb6dHS9+T4/JvjgwHOgIAAABA9anO06v7DIgRV8+Je340IUYMqo0onE7dHh01DXHamMlxx/03RuPhhSkBAAAAgCpTvdd07FMb9cPOi6t+Mi8WP7U8liXD4l/PjGu/2RgD67JpAAAAAICqU52h47rZcfWNTdG+MSsDAAAAADuMqgwd2x6YEdd/b1Rc9/BWd5EBAAAAAKpeVYaOrcvnJP82xhC3pwYAAACAHU5Vho71xw5P/m2NF9YVywAAAADAjqMqQ8faYRfFJYPmxHcvmxEt69qjveTg1GsAAAAAqEbVeU3He6bElQsiOh6YEKd/9oQYVHKYEk3Z9AAAAABA9ajK0LHmiJPjgosu7GE4Ieqy6QEAAACA6lGdp1cPGhUXf31cD8PwGJBNDwAAAABUj6oMHWPl9Dj7a9OjZX1WBgAAAAB2GFUZOrY8+LOYf8+NcW9LVpG3tffHpaOnxcKs2GnhtLPinNFdh0vva8vGRqy+b1Kc8937Y3VWLii8VjLt1vUAAAAAsIuqytCx/bnm5N/hMbChWM7NkmnFMHH8tLIBYf9RU+KWabe9O1x+aqUrRzbHtelrDZsQt3znlOif1cKObvmKV+JL593Xa8PV1z+azQkAAADYGVVl6Njw30ZFTcyL5lyPdGyOa39wf5z4jdvilm+cktVtqS1Wr8webpO2mPXdybEwDRxH552OwvZ3/4OtvTYAAAAAO7fqvKbjJ06Ocwc1x5V/PzFmzJ0X80sOLdGeTb5tGmLstNti7HFZsYzDDtu2e2IvnDYu7ozRcbnAEQAAAAC6qM7Tq+dPj+sXJA9WTI9Lv3pWnF1y+Fnke8nHtliZvODCH5S+nuOW0ms/XrtydFzulGoAAAAA6KYqQ8fawRfFrT++rYfhr6M+mz4fxSMh372e41WjI6aP6x48tkyLOx+IOPHMDx44bnrnnVj30kvx9ttvZzVdvfXWhli37qWs1N0bb6yPV9vLH+/56qvt8eYbb2Sl7grzfuutrNRVWp+O37RpU1bTVfq6GzZ0ZKXe8c7GjdmjrjZ0dMQrr7yclbpb//rr8frrr2Wl7tpfeSU6Ot7MSl29k62TjRtLr5MNGzbEyy+vy0rdvbF+fbz22qtZqbt0fb35Zul1ki7ryttDcZ2U80ayTtrbX8lK3b326quxPnl/5by8bl3h820PryTLtCNZr6VsXidltofkPb/ycoXtIfnMr79WYXtIllm5Zd7bemqjvSndTtO2Uk66nadtrZS0bVZeJ0kbrbhOkjbawzrpeLOHNlqunfTQRntTZxut1G/23EYrrJNCGy29TtJ1UWneafuq1G+m66NSv5muzw/WRsuvk7SN9txvlt4eeturyTpJ+9ZyXk6+o9P1Xkrar1TcHpLPlH4flZMuk9crtNHetC1ttNw66fm7LNm3ScaXk+7bpG1he0i/n3taJ++33+xso+XaSbn6vKRtuFy/+eHs25RuJ70t7Tc/SBvtud8svz1U6jd7W6V+s+c22vP+ZqU2mu7b9F6/+cHbaPnvsg+2b9Ob0n6zYhvtod+stL/57vZQbp1k20O5ddKbOvvN9DdzKem+4gfft+npN2H5fZve7zfffxtN13k56bZSqY32ptd67Dff/29CqldVho41hw+MwScN6WGoj9ps+l5x8Clx+TdOidXTf9X1Ltf1o2PsqKNi4Q8mxay1Wd37tDH5clv25ONlvwRee/W1eOrJJ7JSd2vb2qL12d9npe6e/f3KaGt7ISt1l877tTId8RtJJ5iOTxt3KS8lOwztSWfZm8p1tGkH/3TL8qzU3XPPrY41q8vfS3zFiuWxLtkJLSWdZ2GdlNlRSzvwSuuk7YXnK66T3698Jl5cW37DSeddbmcp/fJKx2/aVGadvLg2nk1ev5zW1t8X3l85Ty17ouKXY29akazPcqFEGiKln7vcD7n2ZGdj+VNPZqXuXnh+TaxqfTYrdbfymacr7qD2ptbfJ+ukQhvtTatXtRaWTTktTz0Vr5QJyDqydVLuR8PLyU5cy/KnslJ3zz/3XKxeXf7ans+saCn7P1zSwLNSG013Ziq10d6U7vQX22jpHfMXkzaa9gHlpNtp2wvlt4d0O3+1vXQbTXe8C+skWTelpD/yKvebqyr2m08n66TcznVnv1luJ7HQby5blpW667mNrij0b6X09o+g1mdXxtoK/eayZFsrt2Of/phIl0u577J0x/npp8ufs5Guj+fXPJeVPlzPr1lT6CPKeWbFirJtNP0xUGyjZfZt0jaafN+Uk7aBZ5Plvj289OKLhe+EcnruN5dFe5ntIQ0sKm0P5fq0vDyd7PuUa6OvJe95+bIK36NJG1j1bOXv0XTZlZK20fRzb68AvdhvllknyfIorpPS32Xpfkn6fVRO2m8+n+xzlpPu26T7KNvDM0nfsu6l0uuks42m+5WlvJ7sC1Zqo2uT/ZZK32Xpvk06TTlpv1luf7Oz3ywXKqT95jPJd0I5q1cl66RCG12R7JuU3x6K+zblt4eXk3Vaft+mN6Xf/U9VaqPPP1+x30zb6Nq1pc/g66mNpuFUOr63v29LSQPBdN5vlf1N+HJh/6Scwm/CZJ+znLRfLBckp/u46bzLhZKvJvvIaZ9fzvPPP1ex33zm6XTfpnQbTX9/p/Mud7BI+j8GK62TF5N1XamNpttKpd+Evem5wvdo+XWS/n5Il20pnd+j2+sgGd6/3ZKN9cPvQd6LjvZof7e91UTtgTXZ4w8gvYv1DyLGThsdJ2ZVJW013er7JsWl804qnFYd6ePpEWdedVmMOLg4+a7mW//4u/jRj9M7jfeOFYu+EvvX7pWV+DCld6/+k9PuzEr5+/b4E+LiC/4wK21/1928JP73FQ9npfw9OOsv47hjDspKPftp0qwu/I+s0Av+/a8ihn48K+zk3nxzYxx+3K1ZKX/nfPkz8U/fHZKV+LD9/SW/iX/7ee/9CGxb9tXYfffdstL29+k/+UmsfbF3wqlThg6IO246NSttf4sebYtTv3h3Vsrf9ycOjvNGHZOVtr/vXfNIfP+apqyUv6Y5jfHxAftmpe3vz74wKx5Z/AH/730Zn/nUATH3ni9kpe2vbe0b8ZnBP81K+fva3xwfl/2vQVmJD9voix6Iu2f3zv8o2bffnrHy0VFZqTr0b7g1Ojb0zpFmZ37+yLjhh0OzEh+2b1/xUFx/89KslL+WhV+OA/bPIcthh1OdN5JJtc2L6/92SBx/3Akx6LOdw7Fx9GcbY9IvWqL0/6vN1+rnnomoPzwOy8pb6n/qZTF22PK4c/y0rkdCAgAAAMAurjpDx/VNceWos+LqB9qjdtiouOCiC4vDOSNjYDTF7ZeMjLF3lT5E/H1be39cu+X1G5Py1OnLo/+QPyx77cYTR0+JM+uT540WPAIAAABAp6oMHdvumRo3r6iJr/xoXsz90cS4+OvjisO3psQdc2bEuUd2xIM/nBF5n9j73PRx7965+pzx0+Kwb9wWl59al40tpS5GfGdCnBhp8PjBr/EIAAAAADuDqgwdW5fPSf4dFcOHlrhVTN+BMXxY8nfVomh5vwc7Hjc6btn6eo7pjWO2vHt1Mow9LhuXSU+pvuU7W9+1uvOu17vutR0BAAAAYEvVeffq/Qck/y6KlpLX5O2I9sINNOujbtvvywAAAAAAfEiqMnRsOG1M4dqNky6YELfPbYm2de3Rng4rm2LGFaNi7C8ias4+OQb2yZ4AAAAAAFSN6ryRzJGj4qprGqN+xYyY9NXhcVLn3atPaYxLb2mKmpMmxB3jh4QbrgMAAABA9anO0DEx4PTJcc+SOXHX1RM33736m5Pj1tmLYsGPz4uGvtmEAAAAAEBVqdrQsaBmQDR8ftTmu1ePaYzBR5a4uQwAAAAAUDWqNnTsWNYcrRuzwlZaH2mKtjLjAAAAAN6vtS+92esD7AqqM3RcNzu+1Tgyzv/unGjLqjp1PHJdnN/YGGPvaM1qAAAAAPKx9PGX4tOf/UmvDQ/8f/IMdg1VGTq2PTAjZq2vicHDhkRdVtep5vjhMeqPIpr+dWY0Z3UAAAAAQPWoytCxdfmc5N9RMfy/lbg/dZ/6aBiU/F21KFq2PgwSAAAAANjuqjJ0rNl/QPLvomgpecRxR7SvS//WR91BhQoAAAAAoIpUZejYcNJfx4Boiiv/fnI8uCarTG1sj+ZbL4qxv4io+fwJ0dAnqwcAAAAAqkZ13kjm+PPiqosaIh6/Kc7/06Pi+D8dGWecOTwGfeaEOOMf5kTHgcPjiv85PGqzyQEAAACA6lGdoWPUxMCvz4wHfjI5zj2tIWrbm6N5cWvUHDMkRnzzxrjn/qkx4vBsUgAAAACgqlRp6FhUN6gxLpk6M+Y+ujyWPbU05s68La4ac3LUO8QRAAAAAKpWVYeOAAAAAMCOp2pDx/ZHpsf4kcfG0Z86qswwOZqyaQEAAACA6lGdoePK6XF+48SY9XhN1B/fEA0lh0OyiQEAAACAalKVoWPzPTdGU9TEV26cF/fcOTPuKjmcFwOz6QEAAACA6lGVoWPHK63Jv6Ni+H+rKVYAAAAAADuMqgwdG/7bqKiJRdGSZo8AAAAAwA6lKkPHmoF/HRcPaoorr5gRLevao73k0JFNDQAAAABUk6oMHdvumRJXLojoeGBCnP7ZE2JQyWGKu1cDAAAAQBWqziMdjzg5Lrjowh6GE6Iumx4AAAAAqB5VGTrWDhoVF399XA/D8BiQTQ8AAAAAVI+qDB0BAAAAgB1XdYSO61pi/tx573Foifbs6QAAAABA9aiO0LHlZ3H2V896j8PPoiV7OgAAAABQPaojdKz/67j1x7e9x+Gvoz57OgAAAABQPaojdDywPgafNOQ9DvVRmz0dAAAAAKgebiQDAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAOSqekPHjdlfAAAAAGCHUp2h4+LrYtifT4h7V2VlAAAAAGCHUZWhY/Pcn0XriqXR1pFVAAAAAAA7jKoMHTvebEv+HRL1RxTLAAAAAMCOoypDx4HDL4r6mB1zHnaoIwAAAADsaKoydGx/vTYajmmNm/92VFz6wylxdclhdrRm0wMAAAAA1aM6T69eOSdmPZ48WN8UM6ZeF9eXHBZFehI2AAAAAFBdqjJ0rPv8lFjw0KIehnExMJseAAAAAKgeVRk6Rk1t1B7Y01CTTQwAAAAAVJPqDB231NEe7es6BzeWAQAAAIBqV72hY9u8uP5vh8Txx50Qgz7bORwbR3+2MSb9oiXEjwAAAABQnaozdFzfFFeOOiuufqA9aoeNigsuurA4nDMyBkZT3H7JyBh7l9vIAAAAAEA1qsrQse2eqXHzipr4yo/mxdwfTYyLvz6uOHxrStwxZ0ace2RHPPjDGdGcTQ8AAAAAVI+qDB1bl89J/h0Vw4fWFiu21HdgDB+W/F21KFoc7AgAAAAAVacqQ8ea/Qck/y6KlpXFclcd0b4u/VsfdQcVKgAAAACAKlKVoWPDaWMK126cdMGEuH1uS7R13r16ZVPMuGJUjP1FRM3ZJ8fAPtkTAAAAAICqUZ03kjlyVFx1TWPUr5gRk746PE7qvHv1KY1x6S1NUXPShLhj/JCoySYHAABg+7p9xrK48Bu/7rXhtw+tyeYEwI6gOkPHxIDTJ8c9S+bEXVdP3Hz36m9OjltnL4oFPz4vGvpmEwIAAFAV7vj35b02ALBjqdrQsaBmQDR8ftTmu1ePaYzBR5a4uQwAAAAAUDWqO3QEAAAAAHY4QkcAAAAAIFdCRwAAAAAgV0JHAAAAACBXQkcAAAAAIFdVGTp2rGqK+XOborUjq9hK+7J5yfiWaM/KAAAAAED1qMrQsX3+1Dj7q1Nj3rqsYivNPz8rGf+zaMnKAAAAAED1qJ7QsW12XHrmyDgjGc7/4bykYl788G+K5S7DyCFx/i3J6MP3j5rCEwEAAACAalI9oePG9nhhcXM0p8Oa9Lzqjmh7PCtvOTzeHrXHDI9L/n/nRUPxmQAAAABAFame0PHQxrjhqeWxLBnmXtMYDcc3xrW/LZa7Dktj7sypce7xjnMEAAAAgGpUldd0rDt9ctx15+Q4rS6rAAAAAAB2GFUZOqZa75kRTeuzQhcd0fRv06O55DgAAAAAYHurztBx5fQY/7UJcfals6Mtq+rUMX9KnH/ZxBh7S3NWAwAAAABUk6oMHVse/Fk0xYC48NzhsfUZ1jWDL4rLTo9o/df/SKYBAAAAAKpNVYaO7c+lRzEOj8HHF8td1caAw5M/65tj+ZpiDQAAAABQPaoydKw9rCH5d3bMX1wsd7GxNZY/lT6oj6MOLdQAwA5jSVvvDgAAANWgKkPH+qF/HQOjNa4e1RhXz22N9o5ifcfKprj90vPi0gcjBoz5XKTRJADsSD7304j/flvvDP/0u2wmAAAA21l13kjmiFFx1TWNUb++Ka7/6skx6Lij4uhPHRXHn9IYk37REjWDxsW1fz8warLJAQAAAIDqUZ2hY2LA6ZPjnodmxw2TzosRJzVEw/FDYsQ5E+Lyn8yJBdMvjIa+2YQAAAAAQFWp2tCx4MD6GPrlCXHVj2fGXXfeFld967xoHDQgavpk4wEAAACAqlPdoWNqY0e0r2tPhuzCjqmN2V8AAAAAoOpUb+jY3hS3f6MxBn3m2Bj02ROSYUo0pfUbW2PGxRfFjFWFqQAAAACAKlOdoeP6priysTEm3dUUceTwGPxHWX1qzby4957Z8d2b58UWxz4CAAAAAFWiKkPHtnumxs0ramLoP86JBbOnxsWDshGpw0fGqC9HdNw6J5qcZg0AAAAAVacqQ8fW5XOSf0fFeX81oFjRRU3UFu5c3RLPthUq4ENx/tcf7NUBAAAAYGdRlaFj7WENyb/zormlWO5iY0s0L0j+9m2Iow4tVsGHoWnx2rjz7hW9Mqx67vVsLgAAAAA7vqoMHeuH/nUMjOa4ctRZceUv5kXzurS2I1oXz4zrz2uMSY8k01zwuWQaAAAAAKDaVOeNZI4YFdfeeF40dMyLmy85Kyb9Iq2cHuPPHBdXz22P+i9OjRvOT4+GBAAAAACqTXWGjom6oRPirkWL4p4fT45LLrowLkiGS668Me6aszTuuXJ4DOiTTQgAAAAAVJWqDR0jvTN1n9qoP6kxzv36uLg4Gc794snRcHhNcTwAAAAAUJWqM3RcfF0M+/MJce+qrAwAAAAA7DCqMnRsnvuzaF2xNNo6sgrYBj+YHzF0eu8Nb72TzQgAAACAiqoydOx4sy35d0jUH1Esw7Za/ELvDQAAAABsm6oMHQcOvyjqY3bMedihjgAAAACwo6nK0LH99dpoOKY1bv7bUXHpD6fE1SWH2dGaTQ8AAAAAVI/qPL165ZyY9XjyYH1TzJh6XVxfclgU6UnYAAAAAEB1qcrQse7zU2LBQ4t6GMbFwGx6AAAAAKB6VGXoGNEaTU92RO2BtRWGmmxaAAAAAKCaVOc1HR+4Mc4/6+S4cq4byQAAAADAjqYqQ8eWx2Ym/w6PE453NCMAbKsXHm+N//z/encAAADYFtV5TcePuVojALxXGzvejr8+975eG956e1M2JwAAgMqqMnQccMa34twjZ8bV1zeFE6wBAAAAYMdSlaFj2z1T4+YVES03Nsbxnzoqji45TI6mbHoAAAAAoHpUZegYfeui4fiGHoZDsokBAAAAgGpSndd0PH1y3HXnzB6G88KVHwEAAACg+lTnkY4AAAAAwA6rukPHjR3RtqIp5s+dlw3N0bo+GwcAAAAAVKWqDR07Ft8UZw85Nk4a3hhnf/WsbBgZw/7w2Djj27OjdWM2IQAAAABQVaozdFwzM8aOmhzzOxpixDenxK0/vq04/GhynHtSTTTfcVGcf0NzNjEAAAAAUE2qMnRsuffGeHD9gLh4+sy4aszIGHzSkOIwrDEuuWlmXD40meb6/4imbHoAAAAAoHpUZejY/lx6FOPwGHx8sdxFnwFx1KeSv+ubY/maYhUAAAAAUD2qMnSsPawh+Xd2zJ7fUazY0sbWWP5U8rdvQxx1aLEKAAAAAKgeVRk61o+4KEb0bY2b/7Yxxv9wRjzYeffqu2+K8f/PyLj0wWSaCz4XA7PpAQAAAIDqUZ03kjlweFwxY2KMqG2JWVMnxPmdd6++eHLMeiRi8Ndvi1vPT4+GBAAAAACqTXWGjomao0fFVb9eGovvn7n57tU/mR1zlyyKWy8aEnV9sgkBAAAAgKpStaFjp5ojGjbfvXpQfdTVZCMAAAAAgKpUXaFje0s8+G8TY8YjWbmLtrj3qolx+9y2rAwAAAAAVKPqCR1XzYyxpwyP8y+bHi1vZ3VbeeXx6THpq0Ni0NdmRuvGrBIAAAAAqCrVETpubInbvz4u7l1XH41XzowLS96Wui4afzAzLju9NtrvGRfj72jN6gEAAOjJxk0R/9e03htuX5rNCAAS1RE6LpsdNz0SMeDrV8flX2yI2nI3iTmwIb7yg5vi3MMjmv51ZjRn1QAAAPTsiRd7bwCALVVF6Nj25KJIj1s87U8aihWV1AyM4acnf1ctj9b2YhUAAAAAUD2q60Yy26jD9RwBAAAAoGpVRehY9+kTYkDy995750VHsaq89fNizr3J3+NPiPraYhUAAAAAUD2q40jHYxrjgqERrbeMibN/OCda1rRH+7ruQ9uKOXH1eWPi5lU1MfTs4VGfPR0AAAAAqB5Vcnp1XTROmhqNR3ZE09QxcfqfnhCDPtt9OGn4mLh+QUTDOVPjihF12XMBAAAAgGpSPdd0PHx4XP6rRXHPjybGBV8eHg3HN2w1DI+vXDQxbpg9L+761slRV+4O1wAAAADAdlVdN5LpUxv1w0bFxZOmxl13ztxqmBqXfX1UDD3ShRwBAAAAoJpVV+gIAAAAAOzwhI4AAAAAQK6EjgAAAABArnbN0HHt/XHp6GmxMCtu1hazvntWnDM6G757f6zOxqRW3zepW13xtbpPCwAAAAC7ql0rdFwyrRgmjp9WIiBMA8dxcecRE+KWabclw5Q4M6bFpdOas/GlNMe16WsNS57znVOif1YLAAAAALuy6ggdH7kpzjhzZNz8SLHYds+EpDwh7m0rlvPRHNf+4P448Ru3xS3fOCWr28KSX8WdLafE2NENWUVdjLhwdPR/YEbMWptVdZGGlJNjYRo4vvscAAAAAKA6Qse3X4jmxc2x6JnWaF/XHm1trUm5NdrWthfKpYeO7MnbqiHGTrstxh6XFbeycOH9EcP+OE7MygUH94/DYnmsXJOVt7Bw2ri4M0bH5QJHAAAAAOiiOkLHAUfF0OTPvd84OQZ99oQ44x/mJaV5MWnkCYVy6WFKNBWenIe2WL0yon//uqzcqS6OqI947rmuh1wunHZWXLtydFzulGoAAAAA6KY6QsdDG+OGX8+MqyZdGBdcdGF8ZdiApHJADD27WC49nBBbR4QfipZpcecDESee+cEDx40bN8bTK5ZHR8ebWU1X619/PVa0LM9K3b344tp4bvWqrNTd6lWt8dKLL2al7tJ5r1+/Pit19eabbxbGv/POO1lNVy+vWxevvfpqVuodb7/9dvaoq/b2V+L3K5/JSjuPTZs2FZb5G2+UXidvJOsqHZ9OV8q6dS8V1nk56bby4tqS1wooeHpFS7z22mtZ6cOVrs9X29uzUlfpdpB+7g0bNmQ1Xb2abIfPPL0iK3W3tq0tnl/zXFbqrvXZ3yfL/I2s9OEqttHy66Q3pcskXTblpMs0XbalpOsiXSfl2mi6Llc+83RW6u6FF56P558vcQh55tnfr4xXXn45K3W1ud8sfbT760m/mW7L20Padiu10ZeTNrqq9dms1DvKzbs3bW6jpddJ+l1RsY2ubYs1PbTR9DunlN7+vIV+s0IbTbe19Lu6lHQbTZdLus2Wkm7j6bZezvNr1iRt9IWs9OFK51up30zf98svl14nPe7brK/cRtPlvXpV+X2b3pR+pnR7K2fNc6t77DfL7Rv11G9uKNOn5SVdZ+X6zddeS9popXWSttHks5fT+uyzhX2QUtL9yPRzl9u36W3p53r99dL7NukyL7bR0uvklVcqt9EXku+xthfKt9H0e7Dcvk1vq9Rvltu3z0u5/bW8vPD889mj7or7NpXWSbpvU3qdvNXZRt96K6vpKn3e9vr98Xqyf95Tv1mpjab7HuteKt1GU+nnLvebMN1HTsdvj/2LdL+isE7K/SZM2mildVJso+W3l/S56e/KUtLtoNIyzUO5/YfOfvPNN0v/PunpN+FLL73Y42/CShlBb0r3/9sqttHy/eZbyTpJP3f6lx1L9dxI5tCGGPHlcXHx18fFJd+5Om798dVx2f8qlksPwyONJj909aNj7KijYuEPJpW51uN7k3ai5TqMtL7cj5VU2iFVGp+Oq/QFUZx36R2P9HnFDr70899JnlfptfNQdrm80/nedjbZ5yqzWNPqSp/7nY3vVB6fbi/vVN5ekoWelT5c6ftOt6mSsm2x7PaQPK/cD4bUO8lnrtxOyreD3pa+r97e+S8nnXfF5VboP8q/t8I6KfPe03VZaZmnz0u313LS5/Y47zLj09eu1A56U7qJFuddelt9J+m7Ki2XHVlxnWSFraRtd2OFdZJuCxXHp9tLmfW9227Zg17SUxtNP3e58ek2WmlbTMdX2h7S9rm9tpd0vpXmnfarlfYBCttDsr2Xki6vt98u/4MhbcOV+qbeVNjWKnxP9jQ+3Y7Lbavp8ipsD2WW26ZyX/45KS7Tco00WWeVtsXCOulheyizvndLGmml/qG3VdwWO9dJlO5I0udV/tw9bA/Jc8v1D72tMO8y22Kvr4xefv0PssyL22Lp99fZRsu9+/R1K/VdvSntH3raZytuy6UVl0vp5fZu31S2f6i8H96b0llWem9pG+6pjW6ssL9Z+Fxl+oe0ttJr56HSMi0u86ywlc6+K+1fS+mp70rHVfpN2JvSbTUdyknfW/nlsv22RT6Y6gkdt1Bz+MAYfNLAGFCTVfS6uuh/RMTq1Vv/3+u2WNkScdhhXY+pPOzUy+LyURF3jv9gwWOfPn3iU0d/Jvbee5+spqt+++6bjP90Vuquru6QGPCxj2el7j728SPiIwcfnJW6S+fdr9++WamrffbZpzB+9937ZDVdHXTQR2K/2tqs1Dv23HPP7FFX+x9wQBxZf1RW2nnsttvuhWW+T9++WU1XfZP6dHy5L5h0XX/8iE9kpe4OH/CxOOSQj2al7o761NGx7377ZaUPV7o+99//gKzU1R7JdpB+7pqa0h1Cbe3+UX/U0Vmpu0M+emj0P7z8/6I44hNHJsu2X1b6cKVt9OCkHW8P6TL56KGHZaXujjzqU4VlW8pee+1VWCd7Jn9LSddlpTaazvew/uWPFf/EJ4+MAw48KCt11VO/mW7DlfrN3rS5jZb+aj3oIx+p2EbzUK5/6E177LFHxTaaflfUJ/1LOYd89KOF/qmcdJml3zml9e7nTb9j0+/actJtrVy/mW6j6XJJt9lS0m083dbL6amN9qZ0vj31mwf21EaT/YhS9t03baOfyUrdpX1i2jduD+l29vEjPpmVukuXSfqdUk66nZfrN9P2kX7u9DutlJqavbNHveMTn6wvO490G073AcpJ9x16bKNJ/1ZK2ielnzvtH7eHoyq20b17aKMHVmyjhx7Wv/L3aLpvk+yzbg9HfOKTZfvN3ct83rzsVea7IC/pci+nxzaa7C+W3bfJ2mjZ3x+FfZtPZaUPV9pvHvWpCr8JkzZa6Tdh2kY/cnDpcwQ3t9HS+8Lp75J0/O67f/ixwbv95h6l18kBBxwYnzyyPit1l24rhx72/tpouh1U6vfykP7WLyVd1unnTn+Pl9KvX7/C+HLS34SVvkd72rfpTYf1P7zHfrN2/9JtdM89i78/0t8h7FiqK3Tc2BZNv5gS4786snA3662Hs78xJWYsyPWW1u86rH/yA3nl6uhyEPXa1fFcnBJDStx8pv+pl8XYYcvjzvHTYmFWBwAAAABUU+i4amaMHTIkvnTJdTFrbnPhbtZbD/Pvui4u/R9DYtDXZkZrzkcE9z+1MU5smRZT7+sMNdti1nXTIkb9edc7Wm/hxNFT4sz6++Pa0YJHAAAAAOhUHaHjxpa4/evj4t519dF45cyYu2R5LHuq+7D4tzPj8i/WR/s942L8HeUvjvr+NMTYaRPisOnj4pzRZyXDuJg/ZEpcfmql29XUxYjvTIgTIw0e87nGIwAAAADs6KojdFw2O256JGLA16+Oy7/YEHVlLgVSU9cQjZdfHRcfHtH0rzOjOat/z44bHbdMG13iCMY0eLwtGVcctg4c01Oqb/nO1net7nzOZTGi/OUTAQAAAGCXURWhY9uTiyI9bvG0P2koVlTSpyEGn578XbU8WkvfTR0AAAAA2I6q60Yy26hj+9zhHQAAAADYBlUROtZ9+oQYkPy999550VGsKm/9vJhzb/L3+BOivrZYBQAAAABUj+o40vGYxrhgaETrLWPi7B/OiZY17dG+rvvQtmJOXH3emLh5VU0MPXt41GdPBwAAAACqR5WcXl0XjZNvjHOPiWiaOiZO/9MTYtBnuw8nDR8T1y+IaLjoxrhqRKW7SgMAAAAA20v1XNOx7uS45N/nxT0/mhgXnDMyBh/fEA1bDieNjHMvmhg3zJ4Xd319SNT2yZ4HAAAAAFSV6rqRTJ/aqB82Ki7+1pS49c6ZcdeWw4+nxCVfHxVDj3QhRwAAAACoZtUVOgIAAAAAOzyhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwAAAACQq6oMHTtWNcX8uU3R2pFVbKV92bxkfEu0Z2UAAAAAoHpUZejYPn9qnP3VqTFvXVaxleafn5WM/1m0ZGUAAAAAoHpUT+jYNjsuPXNknJEM5/9wXlIxL374N8Vyl2HkkDj/lmT04ftHTeGJAAAAAEA1qZ7QcWN7vLC4OZrTYU16XnVHtD2elbccHm+P2mOGxyX/v/OiofhMAAAAAKCKVE/oeGhj3PDU8liWDHOvaYyG4xvj2t8Wy12HpTF35tQ493jHOQIAAABANarKazrWnT457rpzcpxWl1UAAAAAADuMqgwdAQAAAIAdV/WGjm1NcftlZ3W/kcy7w03RlE0KAAAA7DpuX9J7w38+k80E+ECqM3RcNzvGn9IYk/5tXvcbybw7vJBNDAAAAOxKrvhtxN/f2zvDr5/NZgJ8IFUZOrbec2PMWh8xdNKcEjeS6RwmxMBsegAAAACgelRl6Nj2bHri9KgY9cUBxQoAAAAAYIdRlaFj/bHDk3/bon19sQwAAAAA7DiqMnSsPXVMXHDk7LjuX5uiI6sDAAAAAHYM1Xl69d1T4/oVES03Nsbxnzoqji45THb3agAAAACoQlUZOkbfumg4vqGH4ZBsYgAAAACgmlRl6Fh3+uS4686ZPQznuXs1AAAAAFSh6jzSEQAAAADYYVVl6Nixqinmz53Xw9AS7dn0AAAAAED1qMrQsX3+1Dj7q2f1MPwsWrLpAQAAAIDqUZWhY+3gi+LWH9/WbbjhygnxlZNqkynq4ys/+OvkXwAAAACg2lRl6Fhz+MAYfNKQbsPQL54Xl900My4f2hI/n788mxoAAAAAqCY73o1k+gyIoz4V0fGLedHUkdUBAAAAAFVjxwsdoz1aV2UPAQAAAICqU5WhY9m7Vz8wI66+eFR8656Ims8PiYE12RMAAAAAgKpRlaFj2btX/+2EuP7u5ohjLowbJg2P9JYysKsa8bPeG/7unmwmAAAAAO9DVYaO5e5efeuPZ8YDDy2NxTPHxWCJI7u4jo0Rc1t7Z3jxzWwmAAAAAO9DVYaO5e5ePfikhhhwoHOqAQAAAKCaVfeNZDZ2RNuKLa/v2Byt67NxAAAAAEBVqtrQsWPxTXH2kGPjpOGNW1zXcWQM+8Nj44xvz47WjdmEAAAAAEBVqc7Qcc3MGDtqcszvaIgR35yy+ZqOP5oc555UE813XBTn39CcTQwAAAAAVJOqDB1b7r0xHlw/IC6ePjOuGjNy8zUdhzXGJTfNjMuHJtNc/x/RlE0PAAAAAFSPqgwd259Lj2IcHoOPL5a76DMgjvpU8nd9cyxfU6wCAAAAAKpHVYaOtYc1JP/OjtnzO4oVW9rYGsufSv72bYijDi1WAQAAAADVoypDx/oRF8WIvq1x8982xvgfzogHO+9effdNMf7/GRmXPphMc8HnYmA2PQAAAABQParzRjIHDo8rZkyMEbUtMWvqhDi/8+7VF0+OWY9EDP76bXHr+enRkAAAAABAtanO0DFRc/SouOrXS2Px/TM33736J7Nj7pJFcetFQ6KuTzYhAAAAAFBVqjZ07FRzRMPmu1cPqo+6mmwEAAAAAFCVqit03NgRrYtnRtPKrNxFezTdMzOa3bEaAAAAAKpa9YSO65vj+lEnxLAzx8Xstqyui45Y/otxccafnhBn39iclAAAAACAalQloWN73HtpY1y9IKLhSxNjZH1W3UVdnDx2YjQe2R7zv9cY37qnPasHAAAAAKpJdYSOK2bGdXd3RM2Xp8Yd/zgqGg7M6rdS90ej4vKfTo0RfTti1s0zozWrBwAAAACqR1WEju1PLorm5O9XTj85erxPzIHDo/FLyd9HlkeLc6wBAAAAoOpURejYsT47VXqP4p+e1PRJ/22NdmdYAwAAAEDVqYrQsa6+oXCEY1NzS7Giko0t0fS75O/hJ0R9XbEKAAAAAKge1XFNx+M/FxceGdH0DxfGpAdao2NjVr+1jtZ48IoL48rFEfX/z8nRkFUDAAAAANWjOkLHPg1x7uUXRkPflrj9b0+O4z9zVBz9qRLDcSfH+be2RM2gCXHVOSJHAAAAAKhG1RE6JmoGjYu7Zs+Iy8cMj4Yja7PaLdVG/fHD49yrZ8bc6edFQ493nAEAAAAAtoeqCR0LDh0Yjd+cGnfNXhTLnlq+1bAo7rlzalzy+YaoLdxIBgAAAACoRtUVOgIAAAAAOzyhIwAAAACQK6EjAAAAAJAroSMAAAAAkCuhIwBADi77dcTR1/fe8M6mbEYAALADEDoCAORk7Ru9NwAAwI5E6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCMB2dcujvTfcujibCQAAAB8qoSMA29WvWyPG/2fvDBN/nc0EAACAD5XQEQAAAADIldARAAAAAMiV0BEAAAAAyJXQEQAAAADIldARAAAAAMiV0BEAAAAAyJXQEQAAAADIldARAAAAAMiV0BEAAAAAyJXQEWAXM+1fHo7Lruy9AQAAAISOALuYFctfimtvXNIrw7//8ulsLgAAAOzKhI47scdeiDj6+t4bFievDwAAAABbEzru5Na+0XsDAAAAAJQidAQAAAAAciV0BAAAAAByJXQEAHrFb56NeHBl7w1rXstmBAAAVB2hIwDQa77wi94bXn8rmwkAEFf8tncHtp/0Jq63L+m94YkXsxlBzoSOAAAAsINrWx/xT/N7b2D7+vt7e2/oeDubCeRM6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAAAAAORK6AgAAAAA5EroCAAAAADkSugIAADATudXLRG3L+m94bnXshkBUJLQEQAAgJ3S39/bewMAlQkdAQAAAIBcCR23sHDaWXHO6K7Dpfe1ZWMjVt83Kc757v2xOisXrL0/Lk2n3boeAAAAAHZRQset9B81JW6Zdtu7w+Wn1mVjSmmOa8dPi9XDJsQt3zkl+me1AAAAALArEzq+qy1Wr8webpO2mPXdybEwDRxHN2R1AAAAAIDQcSuHHVbpyMbNFk4bF3fG6Lhc4AgAAAAAXQgd39UWK1siFv6g9PUct5Re+/HalaPjcqdUAwAAAEA3Qsd3NcTYLa7leMtVoyOmj+sePLZMizsfiDjxzA8eOG7c+HYsXPBQvP7aa1lNV6+8/HIsWvBwVupuVeuzsezJx7NSd888vSJ71Dtef/317FHv2LChI3vUVVvbC/HYo01ZaefxzjvvFLaHV19tz2q6am9/pTA+nW5nk67PdL2Wkm4H6ed+4403spquXnrxxXi0aVFW6u73K5+JluXLslJ3zUsWx6vtpZd5b3vyieZCO97ZrG1ri8ceKb9O0r5pRctTWWnnkW5HxTa6Mavpas1zq+Px5iVZqXe8s2lT9ujD89aGDcU2un59VrPzWPbE49H67O+zUndNCx+Ol9ety0o7j5VJG21ZXr6NNi95LJ5fsyYrdfX229m+TZl9hHR5LUrGl1PYt0mW+/aw5rnn4vGli7NSd8ufWhbPJt8p5TzStDD5Tlqblbp6M/kOS5fLho7S+zbr1/fuPtXixY8m8yjdRte99FI8smhBVuru2d+vjKeefCIrdZf2a8+tXpWVutrUuW+znb5nm5LPtW7dS1mpq/XJNpq+t7feeiur6eqF59fEkscezUrdpd9jlfa1Fyf7Nun34fbQnGzHz695Lit1tTFpo73pjTd697ug0jJP9/fS/b6dzcvJNty0sHwbTb+nKv0m3FGlfVaxjW7Iarp64YXny7bfPLzey/s1r7xcev9h48aNxX6zzG/CHdmKZN9i5TNPZ6XuHk1+P6xdW7rf7Oh4s7Bc3nzzzayGHYXQsZyDT4nLv3FKrJ7+q1iYVRXUj46xo46KhT+YFLNK71dus9132z0+fsQnYq+amqymq3367hMf/8QnslJ3Bxx4YHz0o4dlpe4+cvDB2aPeUe5956VPnz2yR13tt99+MeBjH89KO4/ddtutsD3U1Oyd1XS1zz7J9pCMT6fb2QwY8LHYb9/9slJXe+yxR+Fz77nnnllNV/327RcDPl5+ezjoIx+JurqPZqXu+h9+eOy9d+ll3ts+euhhccABB2alnce+++0bhw8ov07Svunggw/JSjuPvffZO2ujpb9aa/ffPw49tHePj98evUOfPfoU2+hee2U1O49DDj00DjzwoKzU3cc+fkTyXd03K+08DkraaF1d+TZ6WP/Do7a2Nit11adPcXvYq8z20Ldf32T8J7NSd4V9m6Rv3B5q96+NQw87PCt1V3fIIXHgQR/JSt19LNk36dtv36zUVdo+0uXSJ/lOK2WvvXp3n+rwwwdUXCcDPnZEVuruwIMOikM+emhW6u6ww/rH/vsfkJW62m334r5uzXb6ni2sk779slJX6X5sYZ0k22wp+yXbeP9kuZVzcNJGPvKR8vvahyf7Nv32Lb099LZ0nexXu39W6mr3Mp83L3vt2bvfBZWWebpODqrQRndU+yTbcPp9U05Pvwl3VGmfVWyj5X4T1pZtv3ko12fmJV2vpeye9Zt7771PVrPzqDvkoxXbcNpn71v2N+GeheVS7jch1Uvo+D4cduplcfmoiDvHf7DgMd0RS3fqyzWcdAf04IPLX2OyX7Jju/8BpXfyUmlH3Jv2LLPjnJdyXyJpB7wz7lCkYWK6PZT7gtsz2YlLx++MoeNByZfP3vuU/mLdffc+hc+dho+lpCFtpS+v9IsrDXvKOeDAg7ZbWJIGjtvrB0lvSttopf/pkfZNldbJjqqnNpr+8E1/vPem7dE/9NRGd2Q9tdH0B25NL/8PuO2hpzaaBm/lwtbO77KK+zZ173/fpjf11EbTYG3f/Ur/GEp9JNlnK/c/sdJ9mnS5lNu36e32k+43VfoerbRO0u/RSusk/R7t26/0j+dU+rl7+8d7OZXaaLo80veW/sAvZZ99+hb+x2U5tbX7F4LJctJ9m/R/GG8PaRvtW6GN9qZywXpeKi3zntrojirdhj9IG91R9dxG9yk7Lg+9/Vu3XL/Y0/fojixtv5XaaOE34fv8HqV6CR0rWP3cMxH1h0ep/2/U/9TLYuyw5XHn+Gldj4QEAAAAgF2c0LHT2vvj2i2v35iUp05fHv2H/GHZazeeOHpKnFmfPG+04BEAAAAAOgkdt/Dc9HHv3rn6nPHT4rBv3BaXn1r+UPaIuhjxnQlxYqTB4we/xiMAAAAA7AyEjp3SG8dseffqZBh7XDYuk55Sfct3tr5rdeddry+LEeUvYQYAAFShO5/oveGXy7OZAMAuSOgIAADssn7SHDHmV70zXDE3mwkA7IKEjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjkDVe+mNiAn/1XvDPS3ZjAAAAIBcCB2BHcKPmnpvAAAAAPIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAAAAByJXQEAAAAAHIldAQAAAAAciV0BAAA3vWvTREnT++9Yf1b2YwAgJ2a0BEAAOjisRd6bwAAdg1CRwAAAAAgV0JHAAAAACBXQkcAAAAAIFdCRwAAAAAgV0JHAAAAACBXQkcAAAAAIFdCRwAAAAAgV0JHAAAAACBXQkcAAN6zmct6b/j177OZAACwwxI6AgDwnk2eF/HVu3tnuOPxbCYAAOywhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAAABAroSOAAAAAECuhI4AAAAAQK6EjgAAUMEzr0Rc8l+9N8xtzWYEALATEToCAEAP/rWp9wYAgJ2R0BEAAAAAyJXQEQAAAADIldARAAAAAMiV0BEAAAAAyJXQEQAAAADIldARAAAAAMiV0LGLtpj13bPinNHZ8N37Y3U2JrX6vknd6mLt/XFpiWkBAAAAYFcldHxXGjiOizuPmBC3TLstGabEmTEtLp3WnI0vpTmuHT8tVg9LnvOdU6J/VgsAAAAAuzKhY6clv4o7W06JsaMbsoq6GHHh6Oj/wIyYtTar6iINKSfHwjRwfPc5AAAAAIDQMbNw4f0Rw/44TszKBQf3j8Nieaxck5W3sHDauLgzRsflAkcAAAAA6ELoWNAWq1dG9O9fl5U71cUR9RHPPdeWlYsWTjsrrl05Oi53SjUAAAAAdLPbpkT2eBdWvJ7j/CFT4vJTtwweu9anN5K5dPrywpgTv3FbjD2u8PB9Sxf9a6++Gn379Ys+ffpktZu9/fbb8cYb62O//Wqzmq46Ojpi48aN0bdv36ymq4d+/0Z8Z25N7L576Ww5fW46brfddstqNkvf2zvvvFPyfaXS8bv9Zl7stvblrKar9Lmp9zPvVDr+pzeeFgfsX5PVbPbWW2/FhuSz99t336ym6AfzI/5rZT7zLvW5O2b8Kmr6VF4uH2Tev/zpn8er7e2xT7I+99hjj6x2s8L2sH597LvffoXn//kd2YhMcd6bktf/4O/tzbZXYp/fzM3GbNv28F6WyylDD4+LL/jDwuPUa6+9GjV71cSee+2V1WyWPrd17evxd/+1X1bT1Xud99beSdf3kqURK1qzmq4qrbMel0syblPy3w8mnRTHHXNQVrtZuj53T55bU9N1O/9pc8Sti3vYVpN5b6w07wrvbf0vZsc+8VbhcbnlUnHeiXR8uXnfddupSf/0Zuy7b+l19uabbxbe3z777FMon/vLiDWvFR4WbNu80/fd8zp5561k2rtnFx6netwe3tmYvGry3zYul2OOPjD+6btDCo/Tcetffz32qy3dZ2/Y0BFvv/V2/NXd/bKarnp6b5WXS7I9bEy2t5bfx55LH8/qNvug7aRz3l/72z+Izw37WFZblD739ddeK/ld9ptnIy6f+8HnnX7mkuMf+E2889K6sstlmz53Mk3aDku548b/Hnsm/XHN3ntnNV0V++x9kj57z0L5sl9HPJzdVa6neW/a9E4yftN7Wi5v/+JXsWdWrLw9FMeXn3f397Zvvz3jjptOLTzuSNroO8n722ef0vsXryfb+Z577hln/Hv3PjtV6b1t67b4xqoXY98FDxceb6nUctnSts77zM9/Ms4bdUw2pmjDhg2FfYx+yba8tWdeifi7X73/eacqrZPdH26Kt1e29rhc3u+8/2niCfHpow8p+fy3334r3nwj6bOT/YtO/9qU9OXLio97mnf6PZr2mZU+99bv7fWf/Sr2TZrNtm0P733fJt2nSr36anvsvfc+he11a+n7SvvsdH/yS3ftHq8Xvxbfta3barnl0vm53379zdjrvv/Kajcrbg/pcytvq6VsOe/PnnBIXPa/BhXKndI+ec+99oy9kn2rrb2d9Dt/8dN3Cs/tqZ2UUph3Mk25fnPTkicinlze43J5P/NOx//Pixpi2H//ZFbT1RtvvFF43b236LN/1RJx7YLi40rzThXXSfl5l3pvb//qgdgz2efZcp2Usk3zTp+71fh0Wy7+Jnwj+U1Yer8q/U2YtsP0N8TF9yeL/8VsROa97ttsaevPvenOX8XuW0yWfpdtSrapctvDe1ku/Q/tFzf8cGg2pvjcdFvu/O2ztbeSPvvzP+9TeVtNvN918tryZ2Pfxx7bpuWytW2Z99lf+lR8+a8+k9Vslr52mhFs/Ztw8QsR30y6kg8673R7SPudrcf3+e1D8c7za9/T9rC1SuNv/9GfJb/3itvi3tlvgK2ln7tm7+Q34Z6lfxOm20PaZ5f7bFSpZMNg0wubZk4atelb976QlTt1rV9178RNX51036YF6d+zJ26a2Vaoft+SHdtN83/7m03JDlFW09VLL72YjJ+blbpb+czTm5qXLM5K3S1d/Oim3698Jit1l8573UsvZaWu2l95pTA++ZLLarpa1frspsceWZSVunuieemmp1e0ZKXuHn5o/qa2tq2Xd9H69a8X5v3mm29kNV09v+a5TYsWPJyVulv+1LJNTz35RFbqrmnhw5vWPLc6K3WVfGkX5p10aFlNVy+uXbvpofm/zUrdPZN85sebl2Sl7hY/9sim1md/n5W6Sjr4wrxffnldVtNVWp+OTzrcrKar9HUXP/pIVuqueemSTc88vSIrdZd+rvTzlZIuj3Te6fIp5bnVqzY9smhBVuouXR/peiln4YKHNr3w/Jqs1FW6HaTzTreLUtYm21G6PZWzomX5picfb85K3aXbcbo9l/JuG20v3UbT9pOOLydtf0uSdljO0sWPVWyjv5s3t9APlNLeXmyjb721IavpavWq1k2PNpVvo08+8fimFcufykrdLUjb6Avl2uj6wryTHeCspqu0jS58+HdZqbuWZFtYVqGNPrJoYWGbKmXDhmIbfe21V7Oarl58sXIb7anfXJK00Wd/vzIrdZW2vXTeL68r3UZfefnlwvi0LZdSbKNNWam7nvrNh343b9PataW/eF5/vbONvpnVdJX2eYuSvq+cp5Y9uWl5MpRT7Defy0pdvfnmm4V5Jz/es5qu1ra1bXo4ee/lpG308eSzl/PYI01l2+jGjW8X5v3KKy9nNV2tW1e5jabrulIbbV66eNPKCv1moY2+WLqNJjvOhXlv2FCpjS7MSt0tS9poS4U2uvDh8v3mG290ttH1WU1XL7zw/KYFldpoMt8nnyjfb6bvO33/pfTUb6bLK11u5fTcRivs22RtNF3vpXT2mxX3bSq10ceTNppsr+VU6jdfT9pHOu+0vZRS3Ld5KCt1l7bPtJ2W07RwQdl9m576zbRfqdRG032HSvs26TIr12927tuk/WMpPfWbhTaarPNyHu9h3ybd1l4s02+myyOdd7k2mi7Ppgr7NsueTNto+X2bdH0+v6bcvk3lfrMtbaM97Ns8UWHfJv3+L9dG387aaNoeSump30zb39Ilj2Wl7tJxv1/5dFbqLn3tsr8/kn4jHZ/2I6X01G+m+3vpsilnwUO/KyzbUtJ1kc677L5N0t9WaqPptpBuE+Wk+8nPrS7XRjcU5p1+b5SSbsOV+s1CG03aQjlpG+qpjZb7/ZF+v6bjy7XRnvrNtO945ukKvwnTfZtkP6GU17LfHxvK/P4otNEK+zY99Zvp78m07y2lI2ujad9dSvo7tlK/+fSKtI1W2LdJlllrmX2b9DsqnXf6e7yUl7M2Wu43YeH3R4V+M/2OTb9ryynu25T+TZh+t6fzLttG09+ElfZteug3098P6T5KKWnbTOf9RvI7hB2LIx0zhVOmY+ubwjTHtaMnR2RHNRaOdJx3UuG06igc9Rhx5lWXxYiDs8nfh/T/XKX/J6Dc/0lIOviSR72l/v/t3Q9slPd9x/FPR9STUu2qRHFVjDuimqaKkyx13E4g1IE8EtSkoNWZl6049RKSaSWeVEKjxEMKEC2CLgtUKnHUhj91cNpRNw6y12QxrgWakFGL41SlbkUwilVzIJm1mqehnRTU/X7P85x9d767585+HD/Pw/slGd899+Dnee75/Xu+z+/3e2y0365T/C5H6btaC7ttv7s7H5jt/lHBz/22bT+3f3/u2y7eayaz7VLfi9+2S30v8912qe9lPtu27Of2s1LbLrZvC7ltq2RaNdu2PXKWLCn+vVgLsm2fc+J399fve5nftv3S6jWzkvleiu2b2bb9bGG27ZdeipcPlv1eFm7bC3dO/LZtP7fmklYz2y62b0Fsu9j3spjbtkqdE7NhfWD+f6lzYi3Ito3SadWUXddMWi3y+cJu2y+tli4f/Hq2zW/bfumlcA+NjFLfy/y37Zdeymnb2L9deN/s35/7tueeR8vZdqnvZb7bdr+XuZ2TUtu27Of2s1LbLrZvC7ltq3RanV/5ML9tlz4nfm2bcsqHuW877m0b+38L79v8tl06vZRzTop97rdt+7k1l7T6YWy72PeymNu2Sp4T87ftaKdS5aa1ENu23LQ6t/JhIbeN8CLo6MkOKE7P03hlQNu3XVRTZ6vzgJn8dZxA5eA6tXmfAwAAAAAAABAPksmovrdZDWOdeul45qExk+rr6JRa7i8aUGxo3aum2gHtb+3UsLcMAAAAAAAAuN4RdJxWp7bOdi3telKPtD5sfgo9WCZflTY8264G2cDjLvVd8RYDAAAAAAAA1zGGVwMAAAAAAAAIFD0dAQAAAAAAAASKoCMAAAAAAACAQBF0BAAAAAAAABAo5nREoFLHd2l7qlmHW+u8JXEyqv2t3Vr+4g5tuMVblHG2U4+8MOC9kRqeOqK2O703UXVlQNu3XVRTZ2vRJ7gPdz6snmq/By5FQ7G0a49x/6D3xmpsj0X6Lnju8tKxalv1/LPrVO29ja4SeTfDSe+dUksM0nORvDsrLRvVMTjekuWQd15T3tvo598CaTk/32aLeh4uWg/Z72G3hr13cSmXXZPqe+5J9Yx5b4045NNinLq367z3zojVuSzNPXapqVTdFGmz07IVizZyCflpOo7HOyvfZotrHs5rT8S5XLZy24wrYlxO4cNA0BGByCmY4lbZ5FQyBQpd54Lv/Znl+e+jJucCdp3aZl3s5TYio17plky75tzvH7lbbdPH517oXorsMZc+d6njA7p07zrvfHvrKsJBC7+8myWTDiKdnn3ybsngXOSUUQ5FvSzOVkFadrlllaJ6sVsyLeeXw1Evl/OYY99vyt3p8+ad+6UxDdQMm3pnqal33DrGCyZfF4FH71hjfTHvltPjTfEOMmZz2hLjcblhWyGnrDqllXFMz/nlcNzL5bx07AaZby1wTQiUh+HVmD/bQB60FwWm4G30lsWGaTB1uL2fDr/YWqABYT7vGTAXvFtmKtg7zcVC43n1/GTUWxAlphFsLvTsXdnDT63zluVKHe9wA1Gde9VU6y2MKr+0e4v5LOcitk5NLSuUGvrFTM+pCPE7d9XTAUerShuaTBoYu6hL3pJo8cu7WWw6GDfHHun07Jd3J5Ua917GgH85ZL+PmAQcK0nLntTxbg3XtqopkhdDPmn57M81rHVqmi6bo10uz2LbENnnzdRDTaZ+Gh6OYpvCX8N0wNFyz6XGU/E4lyUMd+7Wpca4B6YmNZ7XyzHWnLbEdRpwNIZ/0qlUY3MsA+ipkVNKZdepcS6XrwyoZ3CFmrbMpOPqe7eYtpZZfnzSWwJUhqAjfNm7G4+0Puz97FLf2QFtt7+veCuYBvLhyN75sHeaM8dmfjpHnbs79rerShuePVK898SVX+j02AqtrM/9fGl1SBvN9s5c1vFuPz6qvufs70wlUucG4EpcqFbfu0OHI9Kgcs7l9PF2atg0CJ3f3ufRTrv5/NJytM6dL9+07JN3p3nBqS33a7m3JIx8y+Ey8q61dKnf9xEOfnnXLy27QbfVaojExc8866FZRtXTdV4NTeHM60Gl5ajyP/548a2HY8W/HnZ4waknHljmLYim8tLyCi3/pPcy4kqnZa8Twqq749HGKjctZ2QCVQ9EtIeyb5syXvzz7q2qzmk/Valh1QqlUgQdMTcEHVGSLZTc7tRHdNj5adb4CzPzWUSbrVDdIVnusZmLuurumaG25bh80XwX+QWzuSBeemv4eojZCtUbCpA53qbU7llz7cSFbRw5d5y9Yz384jL1TA/Xm6tJDQ+dD2GjMoC0PIv5m+b7qm65P3xB2cDSsrlIeM5+b1k9lUMomHLY7XEy/EJ2ozqcjccg8u6llJtPL+VfJHqfh0fweTfMvRwDSct33u/0uNg/ffHrBlmjcLE/t+Mf1ZBJDw0N0buYrzgvm7L9pRAHzEsrMy/b+su50RXtG4BlpeUrKdMOPq+ebTPl8P6z3mcR45+WbR1rOyFMzgrWRU/l9VKkezmW0aasvrdZDWOdeinTbjL/pyei5XJ59dD7SuXdCLPtquuhFzoWBkFHlOD1lngquydYndrKHN4VdpkLsyeyeo/Y3jPxGyLuchsE7Tm9RxpaYzBEuhCnMZA7NMAOhXi+yJDxcg132jnksof1hUNwadkG4TKNZfuwCtPQDNmxWkGlZed8Lm8P+TxwQZXDbu+xTIPaDtNV15PhCzwGknfdoeQpc3xDDTPH3NY4oP3PDYSqwRx8PeTeGAln0CaotGx7fpr8Pr7bK6vci+Nw52NrLsfv3hiJ5FD5svOyDXB49Y7z0KBo9nItLy+bY3WCG1Gf9qHMtGzPd6bOsT/m3NsbX5ELPJaTlqcDrD/XquljblfD4O7I9ZarvF6yN0ai28uxvDalbUO1a6lpV7hllRukjF5ZVUbeveVuraw1abkjq71ke2fP42YoQNARxTkV6DqtimDjrxyZnjDFG/tx4l6ER/GO3JzYHqiBDq10L4rcu9zZFXU4BJeW3WGcbmN5i9RhLwTD1jssmLRs7/Q65zPsDytYqHLYu2BKdb0ZrvMbZN7Nv4h4wDSqxzrVE6IL3sDrobNvOjdGQllvB5WWr9hhYB3SlkxZZXulmAvBkAWUZ6n0+J3jdG+MRHJajLLzsr2Yz5zLL2jIXtCH/VwW4J+X3QCyDZBHMaiaY655+U5T57as0HBPxM5vBfVSfjDHmW82bPWsj0rrJTdIGZXpTPKV2aZ0htJnB5T3anmPKaui1pO1rLzr3dhT58yQ8+EvOHlXy6ujVxchFAg6AvPxyWWm8J3dBT116X2pdpmWeu8RYc6FnzfM5LqaHNw2OtpN43lAQxEdDlWce6dXY1kNKntxP2byrnMXO67zjV0vqlRdaILOW6pjXyYPDw9IjV8I3Y2RINleKcqbEqGh1ZRVIQsoz4u9wM0M94v9U5yzeT1uxk5pOK9dFXnODYFMHePVO+YcpzLDjyM5DBfTitQvznRLsRbWaYeCNOnM15kbUDZt5C2mrBrsjul8vNmdENx6yAlGV4d9RAHCiqAjfBQIODjzGMbD7Kddune8yuY0Ms5r/LL33hN475WADM96ylqMnyxY4KLFCQZXwgYcvQu/sA/dm3dajpj5peXsnjWZH3coTbUzh1HYerMuTDkc2psjAeTdgg/zcu7wh++hBsHl3SjM/TfftBz1cq2M47cBR+fJ6zF4mE4Q9XCElMzLzoPr8uodZ0jjCudcRy+4PLe8bNvHkewt5ZuWq7TctCEuXcodSh3aetZH2fVSkQdqRk3pNmXcrpXmkHe9KQaifp6xeAg6orhb1qmp0RTEL2T3+hl1Hi4RB5mhdtOTAhup4x05Ewf7c4dO5HxHzrwXYZv3r0obmtZJg7tz5tIZ7twdzx5dzoMG8uYjMRWmnaC+EqmRU7PmeQmjYNKyydt5PS3c9BG2oZrXWVoOqhw26X9/9rxSXn4I3c2RgPLurEnfzUVDX4edtylcE90Hk3c9Z38ewvyaJZC07Ob/VFdHTu+ScJZVeco8fttbtTrkD7cqSzl5Ob9cyuTTCA7VDDQvh125edm2h7ODG077OOw3Rgooq14qUDZ560TtwUiVpGWnnRzZodVWOW3KAtd6US2ryq2HjmdPgWA+3zZ7hAFQiY/8wfBeAwU5T2ybnjx2ndrsE9u2ndLKF2dPhO2sq/bo3LE1DQLbky1TsNpeTnZuqILH4Kxb+LjdJ4FlGh/mOwrhvH8OpwfFTMXS8JSdk+RJnV5VYBJ+Z12VOBZT4T5X5P+Ggrt/042k2lY933RR24scU6G0m5v2czWEbQLpStJywXOX931Z9jsL65DyStJyibw7I9zpuZJyuGDezUsfVujS8LRK8m6p82Yayq1ZFw6NIa2bgqyHhlaHN8965p2Wrbz8H+p6N0/p4y9QDk+zPeJKlWFh5JeX8/KoFdZ8Wo6K6mGjrLopvHzz8qx8GsU0nFFmvTSrbRLRHstlpmUnDRRL31Ey67zNblPmXusZYW4j+/DLu7mfRzgdIzQIOqJyEW8k+YlNBVqWUhfsMVTsAjamSMsxFvNyeBbybnxdb2k5H3k51sjLMUZajjHalECQGF4NAAAAAAAAIFAEHQEAAAAAAAAEiqAjAAAAAAAAgEAxpyMAAAAAAACAQNHTEQAAAAAAAECgCDoCAAAAAAAACBRBRwAAAAAAAACBIugIAAAAAAAAIFAEHQEAAAAAAAAEiqAjAAAAAAAAgEARdAQAAAAAAAAQqI/8wfBeAwAAYLFcS2ti9B1NTLlvk7feo7plCfdNiE2dG9Lo5CdUt7pWSW8ZAAAAQNARAABgkaXPdWlby071/95b4EmubterHZtVd6O3YDFdndJUWkokk0os8ZYZI99aoYcObNbR99pV7y0DAAAAGF4NAACwmC73qq3ZBhxr1bzrgI6+PaTBngPa8VCd0qd266GtvZr0Vl1MI9+5R5//syfVm7cztV85ole//9eq9d4DAAAAFkFHAACARTT6+l6dvJrQpgO9ev6ra1X/6SrV3LVWm/65W688UqP0YLsOnvFWDqHkbau0kqHVAAAAyLNkp+G9BgAAwIdqUie+t0+D43+np/5lrWpybgffoJo//p2+131aV+se0N/cfbM0NaLXXv6hfjr1Ka2qzQrzjb+tfd/v1YUb7tCfVufOAzl5pltHf/S2Tpwe1cQNn9Id1R/zPslybVKjb76hrjcHdPr0kC5c+bhuXl6l5A3ux1NnuvSd7hM6d/kDXbv2O42lZ7Y/0b9XB/um9KmVK3IDj5dH1dd7RG/+dEinL6T1ieW36uacXZtQ/7cPqNcey82TOvnG9/WGWffC1U/o1j+5WYn8W+M++wgAAIBwYU5HAACARTOiPZ9p1iEVmRPxcrce/2K7Tj7WrXNPm0/z32ec2a3b/vag1uwZ0isPVrnLrk2of/tmtb0+5r731Jr/e8z83+n438VetX3lyVnzSUpJbXjpbb14X5UmX39Mq5854S03srZfaE7H9Jm9emhzh0avegusG+v1zL916dHbM1v2jv3Tdaq7PJqzbqJxt97qaFZNZu7IMvYRAAAA4cLwagAAgBia6t+rba+PqfbBvXrr7HmdG+7VjsaExg60aM+pdGYt9f+rDebVa+sPh/TL35j1fvMrDf5wpzZ9dae2/oUbzKv68l698jX7apV29L6jM/84Kzw649qoDn2zQ6Naqx097+jce+d1pmen1tgg47PdmvBWm3ZZWrnvhLvtn7n7mB7cqYOnK9tHAAAAhAtBRwAAgNiZ0un+XqW1Xlue3qha27kwWadN/2R7I6b12sl33NXM6//+H/t7herqqtynUi9JqObzLdqxa+NMT8NEUsmPOi/00ZvM61JP0/7lf6jjolT/9E5tussdcJ28q0Vb/75GevdHOnnBWTTjq7v0TGONu+2bzD5+4wnVmP2auDzlfl7uPgIAACBUCDoCAADEzph+NWh+VU3pnc692vdt7+cNL9h4YcJ7InaV7vlz22uxW4+vXa+2HWadA906+csJpa85K1RscmxUto9i/W017gJP7Z1rzb+j+u3v3PdF3VSV9yTs4PcRAAAAC4+gIwAAwKJJ6OPLvJfZft2lQ6czPf3mJm3nSJwc0msvdejl6Z9ejbgfT6vddFDH9rSoPjGh/h+Ydb7Vrseb1uqu+9vVf9lbKQCJj+U+4KYSH9Y+AgAAIDgEHQEAABZNlWo+a39PanJ6NPGoDj27U3seXquvPfMjnTSL1nw2t9dgvvT/ZuY/zKhS7Urz68bNOmrnQHwv7+dAs1nDsySpugd36uh//sqZK/HMz07o6La1Slzo1p5jo95K5Uve4u5r/j5Njuc+0KYiAe8jAAAAFh5BRwAAgEVTpTUb1pvfvdr38pCm7HDhRJ0ePXhEX789rdOnbL/E9dq42gsRLvF6C753XhPTQ4vNeoPd3uuMGt2xuka62qXek9k9JtOauOAOrM6YeOug+sa9N+bvJ2+qUX3jKmeI8+T/5Qcz/SU+e4fWmN8//kHvzD5em9CJt+zTrzfqntvcRZUIeh8BAACw8D7yB8N7DQAAgA/btQl1b1mv7YNpJT5Zr/u+tEpVvx9SX/+IJu0QaSPRuFPH9rWo9sYp9W9dpbZ/Tyv5uY36q9U1Sr/bpddOuYHFNXuG9MqDXoDy929r29on1Hc1qfq/bNbKZdLEqW71vZvWfftOaP+Xq5T+9UF9beNujSip2vs26r7PJM3/G9WPj50w267V1t639fXb3T83+fpjWv3MCSU/Xaea5l069pj7BOuRb63QQwc26+h79iE1Vtos22iWjSm5ukWbPpfQxGCX+n6dVu22Xr31D3XOWuZ/as9nmnXosW6dezrradiXu/X4F9sl71gq2UcAAACEBz0dAQAAFtOSGjV3nNCr31ivmvSI+g536NCxEU0l1+rR7/bq6LZ66f3favIDu3JS9z3fq+cfqlP63V4deumg+hOP6dUXWpw/leOm9Xqx94AeXS2NHDuol826feO12vD0Ae34khuYTNy+Wa/07tWjjQlN9He58z7+4ITSt23UM0e6coJ5VV96Qls/l9TUhVGN/pe3sKCE6r/ZZY5nrRIj9m/a7Sa15uluHX08E3AsXyX7CAAAgPCgpyMAAECYpNNK35BQYon33khfTStxY96DWK6Z9ZS7XlF23Q/Muj7PcklPmb+YnPsDXwopuO/zsBD7CAAAgOARdAQAAAAAAAAQKIZXAwAAAAAAAAgUQUcAAAAAAAAAgSLoCAAAAAAAACBQBB0BAAAAAAAABIqgIwAAAAAAAIBAEXQEAAAAAAAAECiCjgAAAAAAAAACRdARAAAAAAAAQKAIOgIAAAAAAAAIFEFHAAAAAAAAAIEi6AgAAAAAAAAgUAQdAQAAAAAAAASKoCMAAAAAAACAQBF0BAAAAAAAABAogo4AAAAAAAAAAkXQEQAAAAAAAECgCDoCAAAAAAAACBRBRwAAAAAAAACBIugIAAAAAAAAIFAEHQEAAAAAAAAEiqAjAAAAAAAAgEARdAQAAAAAAAAQKIKOAAAAAAAAAAJF0BEAAAAAAABAgKT/B/wB5EqnR4MNAAAAAElFTkSuQmCC"}}},{"cell_type":"code","source":"\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"valid_y","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:46:55.246553Z","iopub.execute_input":"2023-12-10T00:46:55.246943Z","iopub.status.idle":"2023-12-10T00:46:55.471038Z","shell.execute_reply.started":"2023-12-10T00:46:55.246909Z","shell.execute_reply":"2023-12-10T00:46:55.470096Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"grouped_df = valid_y.groupby(['correct']).size().reset_index(name='Count')\n\n# Display the result\nprint(grouped_df)\n\n","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:47:37.78746Z","iopub.execute_input":"2023-12-10T00:47:37.78787Z","iopub.status.idle":"2023-12-10T00:47:37.79904Z","shell.execute_reply.started":"2023-12-10T00:47:37.787834Z","shell.execute_reply":"2023-12-10T00:47:37.797994Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"grouped_df = train_y.groupby(['correct']).size().reset_index(name='Count')\n\n# Display the result\nprint(grouped_df)\n\n","metadata":{"execution":{"iopub.status.busy":"2023-12-10T00:48:27.081111Z","iopub.execute_input":"2023-12-10T00:48:27.081474Z","iopub.status.idle":"2023-12-10T00:48:27.091577Z","shell.execute_reply.started":"2023-12-10T00:48:27.081442Z","shell.execute_reply":"2023-12-10T00:48:27.090516Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# PUT TRUE LABELS INTO DATAFRAME WITH 18 COLUMNS\ntrue = oof.copy()\nfor k in range(18):\n # GET TRUE LABELS\n tmp = train_label.loc[train_label.q == k+1].set_index('session').loc[ALL_USERS]\n true[k] = tmp.correct.values","metadata":{"execution":{"iopub.status.busy":"2023-10-30T04:02:52.481946Z","iopub.execute_input":"2023-10-30T04:02:52.482845Z","iopub.status.idle":"2023-10-30T04:02:52.569701Z","shell.execute_reply.started":"2023-10-30T04:02:52.482805Z","shell.execute_reply":"2023-10-30T04:02:52.568871Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# FIND BEST THRESHOLD TO CONVERT PROBS INTO 1s AND 0s\nscores = []; thresholds = []\nbest_score = 0; best_threshold = 0\n\nfor threshold in np.arange(0.4,0.81,0.01):\n print(f'{threshold:.02f}, ',end='')\n preds = (oof.values.reshape((-1))>threshold).astype('int')\n m = f1_score(true.values.reshape((-1)), preds, average='macro') \n scores.append(m)\n thresholds.append(threshold)\n if m>best_score:\n best_score = m\n best_threshold = threshold","metadata":{"execution":{"iopub.status.busy":"2023-10-30T04:11:40.900879Z","iopub.execute_input":"2023-10-30T04:11:40.901282Z","iopub.status.idle":"2023-10-30T04:11:47.417191Z","shell.execute_reply.started":"2023-10-30T04:11:40.901248Z","shell.execute_reply":"2023-10-30T04:11:47.416041Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\n# PLOT THRESHOLD VS. F1_SCORE\nplt.figure(figsize=(20,5))\nplt.plot(thresholds,scores,'-o',color='blue')\nplt.scatter([best_threshold], [best_score], color='blue', s=300, alpha=1)\nplt.xlabel('Threshold',size=14)\nplt.ylabel('Validation F1 Score',size=14)\nplt.title(f'Threshold vs. F1_Score with Best F1_Score = {best_score:.3f} at Best Threshold = {best_threshold:.3}',size=18)\nplt.show()","metadata":{"execution":{"iopub.status.busy":"2023-10-30T04:11:47.419166Z","iopub.execute_input":"2023-10-30T04:11:47.419867Z","iopub.status.idle":"2023-10-30T04:11:47.760463Z","shell.execute_reply.started":"2023-10-30T04:11:47.419822Z","shell.execute_reply":"2023-10-30T04:11:47.75953Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print('When using optimal threshold...')\nfor k in range(18):\n \n # COMPUTE F1 SCORE PER QUESTION\n m = f1_score(true[k].values, (oof[k].values>best_threshold).astype('int'), average='macro')\n print(f'Q{k}: F1 =',m)\n \n# COMPUTE F1 SCORE OVERALL\nm = f1_score(true.values.reshape((-1)), (oof.values.reshape((-1))>best_threshold).astype('int'), average='macro')\nprint('==> Overall F1 =',m)","metadata":{"execution":{"iopub.status.busy":"2023-10-30T04:11:51.487748Z","iopub.execute_input":"2023-10-30T04:11:51.488669Z","iopub.status.idle":"2023-10-30T04:11:51.816179Z","shell.execute_reply.started":"2023-10-30T04:11:51.488632Z","shell.execute_reply":"2023-10-30T04:11:51.815105Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import jo_wilder\nenv = jo_wilder.make_env()\niter_test = env.iter_test()","metadata":{"execution":{"iopub.status.busy":"2023-02-08T11:43:58.636667Z","iopub.execute_input":"2023-02-08T11:43:58.637082Z","iopub.status.idle":"2023-02-08T11:43:58.659081Z","shell.execute_reply.started":"2023-02-08T11:43:58.637049Z","shell.execute_reply":"2023-02-08T11:43:58.658053Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"limits = {'0-4':(1,4), '5-12':(4,14), '13-22':(14,19)}\n\nfor (sample_submission, test) in iter_test:\n \n dummies = pd.get_dummies(test['event_name'])\n test = pd.concat([test, dummies], axis=1)\n df = feature_engineer(test)\n grp = test.level_group.values[0]\n a,b = limits[grp]\n for t in range(a,b):\n clf = models[f'{grp}_{t}']\n p = clf.predict_proba(df[FEATURES].astype('float32'))[:,1]\n mask = sample_submission.session_id.str.contains(f'q{t}')\n sample_submission.loc[mask,'correct'] = int(p.item()>best_threshold)\n \n env.predict(sample_submission)","metadata":{"execution":{"iopub.status.busy":"2023-02-08T11:43:58.945999Z","iopub.execute_input":"2023-02-08T11:43:58.946341Z","iopub.status.idle":"2023-02-08T11:43:59.43599Z","shell.execute_reply.started":"2023-02-08T11:43:58.946312Z","shell.execute_reply":"2023-02-08T11:43:59.435065Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submit = pd.read_csv('submission.csv')","metadata":{"execution":{"iopub.status.busy":"2023-02-08T11:59:53.258512Z","iopub.execute_input":"2023-02-08T11:59:53.258864Z","iopub.status.idle":"2023-02-08T11:59:53.266328Z","shell.execute_reply.started":"2023-02-08T11:59:53.258835Z","shell.execute_reply":"2023-02-08T11:59:53.265313Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"submit #my daily submission is over 5...so couldn't see the result yet;","metadata":{"execution":{"iopub.status.busy":"2023-02-08T12:13:04.256688Z","iopub.execute_input":"2023-02-08T12:13:04.257083Z","iopub.status.idle":"2023-02-08T12:13:04.269268Z","shell.execute_reply.started":"2023-02-08T12:13:04.25705Z","shell.execute_reply":"2023-02-08T12:13:04.268238Z"},"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"","metadata":{}}]}