{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.preprocessing import Imputer\nfrom sklearn import preprocessing\nfrom sklearn import linear_model\nfrom sklearn.metrics import roc_auc_score\nimport category_encoders as ce\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn.model_selection import StratifiedKFold\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"","_uuid":"","trusted":true},"cell_type":"code","source":"import pandas as pd\nsample_submission = pd.read_csv(\"../input/cat-in-the-dat-ii/sample_submission.csv\")\ntest = pd.read_csv(\"../input/cat-in-the-dat-ii/test.csv\")\ntrain = pd.read_csv(\"../input/cat-in-the-dat-ii/train.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x=\"bin_0\", data=train)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x=\"bin_1\", data=train)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x=\"bin_2\", data=train)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x=\"bin_3\", data=train)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(x=\"bin_4\", data=train)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_0\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_1\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_2\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_3\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_4\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_5\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_6\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_7\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_8\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"chart=sns.countplot(x=\"nom_9\", data=train)\n\n# chart.set_xticklabels(rotation=45)\nplt.gcf().set_size_inches(16, 8)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# train['nom_3'].value_counts()\nfor i in ['nom_0' ,'nom_1','nom_2','nom_3','nom_4','nom_5','nom_6','nom_7', 'nom_8','nom_9']:\n    print(train[i].value_counts())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**lot's of categories in nom_ data ..**"},{"metadata":{"trusted":true},"cell_type":"code","source":"# train['nom_3'].value_counts()\nfor i in ['ord_0' ,'ord_1','ord_2','ord_3','ord_4','ord_5']:\n    print(train[i].value_counts())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"categorical_variables=['bin_3','bin_4' ,'nom_0','nom_1','nom_2','nom_3' ,'nom_4','nom_5','nom_6','nom_7',\n                       'nom_8','nom_9','ord_1','ord_2','ord_3','ord_4' ,'ord_5']\n\n# new_train = pd.get_dummies(data=train, columns=categorical_variables)\ncontinous_variables =['bin_0', 'bin_1', 'bin_2','ord_0','day','month']\ncols = [col for col in train.columns if col!='target']\nbin_cols = ['bin_0','bin_1','bin_2','bin_3','bin_4']\nord_cols = ['ord_0','ord_1','ord_2','ord_3','ord_4','ord_5']\nnom_cols = ['nom_0','nom_1','nom_2','nom_3','nom_4','nom_5','nom_6','nom_7','nom_8','nom_9']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.sort_index(inplace=True)\ntrain_y = train['target']; test_id = test['id']\ntrain.drop(['target', 'id'], axis=1, inplace=True)\ntest.drop('id', axis=1, inplace=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"categorical_features = train.columns.tolist();  smoothing=0.20\nfinal_df = pd.DataFrame([])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for tr_idx, f_idx in StratifiedKFold(n_splits=5, random_state=2600, shuffle=True).split(train, train_y):\n    ce_target_encoder = ce.TargetEncoder(cols = categorical_features, smoothing=smoothing)\n    ce_target_encoder.fit(train.iloc[tr_idx, :], train_y.iloc[tr_idx])\n    final_df = final_df.append(ce_target_encoder.transform(train.iloc[f_idx, :]), ignore_index=False)\nce_target_encoder = ce.TargetEncoder(cols = categorical_features, smoothing=smoothing)\nce_target_encoder.fit(train, train_y)\ntrain = final_df.sort_index()\ntest = ce_target_encoder.transform(test)\nglm =LogisticRegression( random_state=2, solver='lbfgs', max_iter=20600, fit_intercept=True, penalty='l2', verbose=0)\nglm.fit(train, train_y)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pd.DataFrame({'id': test_id, 'target': glm.predict_proba(test)[:,1]}).to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"references :- https://www.kaggle.com/kaggleurroad/categorical\nalso https://www.kaggle.com/abhishek for his amazing youTube Channel"}],"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":4,"nbformat_minor":1}