{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"import 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 sn\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_data = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/train.csv',index_col = 'id')\ntest_data = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/test.csv', index_col = 'id')\nprint(train_data.shape,test_data.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"study_train_data = pd.DataFrame({'columns':train_data.columns})\nstudy_train_data['datatypes'] = train_data.dtypes.values\nstudy_train_data['missing'] = train_data.isnull().sum().values\nstudy_train_data['unique'] = train_data.nunique().values\n\nprint(study_train_data)\n\n                                ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"number = test_data.isnull().sum().values\n\nmissing_values_df = pd.DataFrame({'coloumns': test_data.columns,\n                                   'missing_value': number })\n\nfig, ax = plt.subplots(figsize=(17, 6))\ng = sn.barplot(x='coloumns',y = 'missing_value' ,data = missing_values_df,palette ='spring')\n\n#for p in g.patches:\n    #g.annotate(format(p.get_height(), '.2f'), (p.get_x() + p.get_width() / 2., p.get_height()), ha = 'center', va = 'center', xytext = (0, 10), textcoords = 'offset points')\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"info_test = pd.DataFrame({'columns': test_data.columns})\ninfo_test['datatype'] = test_data.dtypes.values\ninfo_test['missing_values'] = test_data.isnull().sum().values\ninfo_test['unique_values'] = test_data.nunique().values\n\nprint(info_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig ,ax = plt.subplots(figsize=(15,7))\nsn.barplot(x = 'columns',y = 'missing_values',ax=ax,data =info_test,palette = 'spring')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_cols_missing_values = [col for col in train_data.columns if train_data[col].isnull().any()]\ntest_cols_missing_values = [cols for cols in test_data.columns if test_data[cols].isnull().any()]\n\nfrom sklearn.impute import SimpleImputer\nimpu = SimpleImputer(strategy='most_frequent')\ntrain_data[train_cols_missing_values] = impu.fit_transform(train_data[train_cols_missing_values])\ntest_data[test_cols_missing_values] = impu.fit_transform(test_data[test_cols_missing_values])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, ax = plt.subplots(figsize = (5,7))\ng = sn.countplot(x='target',ax = ax,data = train_data,palette ='spring')\nfor p in g.patches:\n    g.annotate(format(p.get_height(), '.2f'), (p.get_x() + p.get_width() / 2., p.get_height()), ha = 'center', va = 'center', xytext = (0, 10), textcoords = 'offset points')\n\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"x_train = train_data.iloc[:, :-1]\ny_train = train_data.iloc[:, -1]\nx_test = test_data.iloc[:, ]\n\nfrom sklearn.preprocessing import LabelEncoder\nimput = LabelEncoder()\ncategorical_columns = [col for col in x_train.columns if x_train[col].dtype == 'object']\ncate_col = [cols for cols in x_test.columns if x_test[cols].dtype == 'object']\nfor i in categorical_columns:\n    x_train[i] = imput.fit_transform(x_train[i])\nfor j in cate_col:\n    x_test[j] = imput.fit_transform(x_test[j])\nprint(x_train)\nprint(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import StandardScaler\nscale = StandardScaler()\nx_train = scale.fit_transform(x_train)\nx_test = scale.fit_transform(x_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from xgboost import XGBClassifier\nclassifer = XGBClassifier(booster = 'gbtree',eta = 0.1,max_depth = 10,objective = 'binary:logistic',eval_metric='auc',random_state = 2020)\nclassifer.fit(x_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = classifer.predict_proba(x_test)[:, 1]\nprint(y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/sample_submission.csv')\nsub_id = submission_df['id']\nsubmission = pd.DataFrame({'id':sub_id})\nsubmission['target'] = y_pred\nsubmission.to_csv(\"submission5.csv\",index = False)","execution_count":null,"outputs":[]}],"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":4}