{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.10.12","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"gpu","dataSources":[{"sourceId":84896,"databundleVersionId":10305135,"sourceType":"competition"},{"sourceId":9178166,"sourceType":"datasetVersion","datasetId":5547076}],"dockerImageVersionId":30823,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":true}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"# Welcome to my notebook!\n\n## https://www.youtube.com/watch?v=PQXHJbX1BN8\n\n### Please click the link above to see the associated video tutorial \n\n### Part 2 notebook: https://www.kaggle.com/code/curtiscoding1/s4e12-beyond-the-baseline-part-2","metadata":{}},{"cell_type":"markdown","source":"![image.png](attachment:b116ac34-6cae-4152-9a6e-8a4bc4de0cdf.png)","metadata":{},"attachments":{"b116ac34-6cae-4152-9a6e-8a4bc4de0cdf.png":{"image/png":"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"}}},{"cell_type":"markdown","source":"# Imports","metadata":{}},{"cell_type":"code","source":"# Imports\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport lightgbm as lgb\nimport xgboost as xgb\nimport catboost as cb\nfrom sklearn.metrics import *\nfrom sklearn.model_selection import *\nfrom matplotlib import pyplot as plt\nimport seaborn as sns\nimport optuna \nfrom sklearn.pipeline import Pipeline\nfrom sklearn.impute import SimpleImputer\nfrom sklearn.compose import ColumnTransformer\nfrom sklearn.model_selection import cross_val_score\n\n# Finding File Paths\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:04:36.89747Z","iopub.execute_input":"2024-12-31T20:04:36.897887Z","iopub.status.idle":"2024-12-31T20:04:38.762839Z","shell.execute_reply.started":"2024-12-31T20:04:36.89786Z","shell.execute_reply":"2024-12-31T20:04:38.762093Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Setup","metadata":{}},{"cell_type":"code","source":"# Reading Train and Test\ntrain = pd.read_csv('/kaggle/input/playground-series-s4e12/train.csv')\ntest = pd.read_csv('/kaggle/input/playground-series-s4e12/test.csv')\n\n# Dropping ID column\ntrain.drop('id', axis = 1, inplace = True)\ntest.drop('id', axis = 1, inplace = True)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:04:58.445533Z","iopub.execute_input":"2024-12-31T20:04:58.446391Z","iopub.status.idle":"2024-12-31T20:05:04.574396Z","shell.execute_reply.started":"2024-12-31T20:04:58.446356Z","shell.execute_reply":"2024-12-31T20:05:04.573522Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Preliminary Data Analysis","metadata":{}},{"cell_type":"code","source":"# Train dataframe basic info\ntrain.info()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:05:48.296144Z","iopub.execute_input":"2024-12-31T20:05:48.296454Z","iopub.status.idle":"2024-12-31T20:05:48.831781Z","shell.execute_reply.started":"2024-12-31T20:05:48.29643Z","shell.execute_reply":"2024-12-31T20:05:48.830792Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# More Train dataframe basic info\ntrain.describe()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:05:57.992728Z","iopub.execute_input":"2024-12-31T20:05:57.993065Z","iopub.status.idle":"2024-12-31T20:05:58.548894Z","shell.execute_reply.started":"2024-12-31T20:05:57.993038Z","shell.execute_reply":"2024-12-31T20:05:58.547918Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Train dataframe preview\ntrain.head()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:06:06.511939Z","iopub.execute_input":"2024-12-31T20:06:06.512255Z","iopub.status.idle":"2024-12-31T20:06:06.531317Z","shell.execute_reply.started":"2024-12-31T20:06:06.512233Z","shell.execute_reply":"2024-12-31T20:06:06.530331Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Cat(egorical) and Cont(inuous) columns identification\ncats = test.select_dtypes(include=[\"object_\"]).columns.tolist()\nconts = [col for col in test.columns if col not in cats]","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:06:32.280821Z","iopub.execute_input":"2024-12-31T20:06:32.281173Z","iopub.status.idle":"2024-12-31T20:06:32.384871Z","shell.execute_reply.started":"2024-12-31T20:06:32.281144Z","shell.execute_reply":"2024-12-31T20:06:32.383996Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# EDA","metadata":{}},{"cell_type":"code","source":"# Aggregate by mean Premium Amount for each Credit Score\ngrouped = train.groupby('Credit Score')['Premium Amount'].mean().reset_index()\n\n# Plot\nplt.figure(figsize=(10, 6))\nsns.lineplot(data=grouped, x='Credit Score', y='Premium Amount', marker='o')\nplt.title('Average Premium Amount for Credit Scores')\nplt.xlabel('Credit Score')\nplt.ylabel('Average Premium Amount')\nplt.grid(True, linestyle='--', alpha=0.6)\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:06:48.569912Z","iopub.execute_input":"2024-12-31T20:06:48.570218Z","iopub.status.idle":"2024-12-31T20:06:49.021462Z","shell.execute_reply.started":"2024-12-31T20:06:48.570196Z","shell.execute_reply":"2024-12-31T20:06:49.020588Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Annual Income Histogram\ntrain['Annual Income'].hist()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:07:09.771697Z","iopub.execute_input":"2024-12-31T20:07:09.772044Z","iopub.status.idle":"2024-12-31T20:07:09.986462Z","shell.execute_reply.started":"2024-12-31T20:07:09.772014Z","shell.execute_reply":"2024-12-31T20:07:09.985438Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Premium Amount Histogram\ntrain['Premium Amount'].hist()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:07:24.470198Z","iopub.execute_input":"2024-12-31T20:07:24.470524Z","iopub.status.idle":"2024-12-31T20:07:24.664808Z","shell.execute_reply.started":"2024-12-31T20:07:24.470491Z","shell.execute_reply":"2024-12-31T20:07:24.663796Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Feature Engineering","metadata":{}},{"cell_type":"code","source":"# Creating Feature Engineering Function\ndef feature_eng(df):\n    # Date Features\n    df['date'] = df['Policy Start Date'].apply(lambda x: x.split(' ')[0])\n    df['date'] = pd.to_datetime(df['date'])\n    df['year'] = df['date'].dt.year \n    df['month'] = df['date'].dt.month\n    df['day'] = df['date'].dt.day \n    df.drop('Policy Start Date', axis = 1, inplace = True)\n    df.drop('date', axis = 1, inplace = True)\n\n    \n    # Log Annual Income\n    df['Log Annual Income'] = np.log(df['Annual Income']) # big improvement to score\n\n    # Credit Score over 512\n    df['Credit_Score_Over_512'] = (df['Credit Score'] > 512).astype('object')\n\n# Apply Function to both Dataframes\nfeature_eng(train)\nfeature_eng(test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:00.499787Z","iopub.execute_input":"2024-12-31T20:10:00.500211Z","iopub.status.idle":"2024-12-31T20:10:02.374124Z","shell.execute_reply.started":"2024-12-31T20:10:00.500168Z","shell.execute_reply":"2024-12-31T20:10:02.373109Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Pre Processing","metadata":{}},{"cell_type":"code","source":"# Creating Pre Processing Function\ndef pp(df):\n    for col in cats:\n        df[col] = df[col].fillna('Other')\n        df[col] = df[col].astype('category')\n    \n    for col in conts:\n        mean = df[col].mean()\n        df[col] = df[col].fillna(mean)\n        df[col] = df[col].astype('float32')\n\n# Re-defining Cats & Conts due to new columns\ncats = test.select_dtypes(include=[\"object_\"]).columns.tolist()\nconts = [col for col in test.columns if col not in cats]\n\n# Applying function to both dataframes\npp(train)\npp(test)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:02.375337Z","iopub.execute_input":"2024-12-31T20:10:02.375614Z","iopub.status.idle":"2024-12-31T20:10:05.119685Z","shell.execute_reply.started":"2024-12-31T20:10:02.375592Z","shell.execute_reply":"2024-12-31T20:10:05.118921Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Create X (train dataframe minus dependent variable)\nX = train.copy()\nX.drop('Premium Amount', axis = 1, inplace = True)\n\n\n# Create y (dependent variable from train dataframe)\ny = train.copy()\ny = y['Premium Amount']\ny = np.log(y)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:05.12133Z","iopub.execute_input":"2024-12-31T20:10:05.121696Z","iopub.status.idle":"2024-12-31T20:10:05.255319Z","shell.execute_reply.started":"2024-12-31T20:10:05.121662Z","shell.execute_reply":"2024-12-31T20:10:05.254629Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Modeling","metadata":{}},{"cell_type":"code","source":"# Creating LGBM\nlgbm = lgb.LGBMRegressor(n_estimators = 200, random_seed=42, verbose = -1, device = 'gpu')\n\n# Fit \nlgbm.fit(X, y)\n\n# Predict\npreds = lgbm.predict(test)\npreds = np.exp(preds)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:19.049851Z","iopub.execute_input":"2024-12-31T20:10:19.050151Z","iopub.status.idle":"2024-12-31T20:10:27.875328Z","shell.execute_reply.started":"2024-12-31T20:10:19.050128Z","shell.execute_reply":"2024-12-31T20:10:27.874566Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Feature Importances\nlgb.plot_importance(lgbm, max_num_features=20, importance_type='split') \nplt.title(\"Feature Importances\")\nplt.show()","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:32.729418Z","iopub.execute_input":"2024-12-31T20:10:32.729809Z","iopub.status.idle":"2024-12-31T20:10:33.078297Z","shell.execute_reply.started":"2024-12-31T20:10:32.729779Z","shell.execute_reply":"2024-12-31T20:10:33.077387Z"}},"outputs":[],"execution_count":null},{"cell_type":"markdown","source":"# Submission","metadata":{}},{"cell_type":"code","source":"# Reading submission File\nsub = pd.read_csv('/kaggle/input/playground-series-s4e12/sample_submission.csv')","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:45.504643Z","iopub.execute_input":"2024-12-31T20:10:45.504949Z","iopub.status.idle":"2024-12-31T20:10:45.658015Z","shell.execute_reply.started":"2024-12-31T20:10:45.504928Z","shell.execute_reply":"2024-12-31T20:10:45.657298Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Entering my predictions\nsub['Premium Amount'] = preds","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:46.030678Z","iopub.execute_input":"2024-12-31T20:10:46.031027Z","iopub.status.idle":"2024-12-31T20:10:46.036269Z","shell.execute_reply.started":"2024-12-31T20:10:46.030996Z","shell.execute_reply":"2024-12-31T20:10:46.035324Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Writing File\nsub.to_csv('submission.csv', index = False)","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:46.495131Z","iopub.execute_input":"2024-12-31T20:10:46.495423Z","iopub.status.idle":"2024-12-31T20:10:47.808283Z","shell.execute_reply.started":"2024-12-31T20:10:46.495402Z","shell.execute_reply":"2024-12-31T20:10:47.807199Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# Viewing Submission\nsub","metadata":{"trusted":true,"execution":{"iopub.status.busy":"2024-12-31T20:10:47.809652Z","iopub.execute_input":"2024-12-31T20:10:47.809978Z","iopub.status.idle":"2024-12-31T20:10:47.819693Z","shell.execute_reply.started":"2024-12-31T20:10:47.809943Z","shell.execute_reply":"2024-12-31T20:10:47.818795Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}