{"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)\npd.set_option('display.max_columns', None)\npd.set_option('display.max_rows', None)\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.preprocessing import LabelEncoder\nimport matplotlib.pyplot as plt\nimport seaborn as sns\nfrom sklearn.metrics import accuracy_score,confusion_matrix,precision_score,f1_score\nfrom sklearn import metrics\nfrom sklearn.calibration import CalibratedClassifierCV\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\nfrom sklearn.model_selection import train_test_split\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":{"trusted":true},"cell_type":"code","source":"train = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/train.csv')\ntest = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"list(train['ord_0'].unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"np.ceil(train['ord_0'].mean())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def summary(df):\n    summary = pd.DataFrame(df.dtypes, columns=['dtypes'])\n    summary = summary.reset_index()\n    summary['Name'] = summary['index']\n    summary = summary[['Name', 'dtypes']]\n    summary['Missing'] = df.isnull().sum().values    \n    summary['Uniques'] = df.nunique().values\n    summary['First Value'] = df.loc[0].values\n    summary['Second Value'] = df.loc[1].values\n    summary['Third Value'] = df.loc[2].values\n    return summary\n\n\nsummary(train)\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"set(train['bin_0'].isna())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"corr = train.corr()\nplt.figure(figsize=(10,10))\nax = sns.heatmap(corr,vmin=-1, vmax=1, center=0,cmap='coolwarm',square=True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Finding Missing Values**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def missing_value(df):\n    final = []\n    empty = {}\n    list_of_columns = list(df.columns)\n    for column in range(0,len(list_of_columns)):\n        data = set(df[list_of_columns[column]].isna())\n        empty.update({\n            list_of_columns[column]:data\n        })\n    final.append(empty)\n    return final","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"missing_value(train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Treating Null and Missing Values**"},{"metadata":{"trusted":true},"cell_type":"code","source":"train['bin_0'].mode()[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":" train['bin_0'].fillna(train['bin_0'].mode()[0], inplace = True)\ntest['bin_0'].fillna(test['bin_0'].mode()[0], inplace = True)\n\ntrain['bin_1'].fillna(train['bin_1'].mode()[0], inplace = True)\ntest['bin_1'].fillna(test['bin_1'].mode()[0], inplace = True)\n\ntrain['bin_2'].fillna(train['bin_2'].mode()[0],inplace = True)\ntest['bin_2'].fillna(test['bin_2'].mode()[0],inplace = True)\n\ntrain['bin_3'].fillna(train['bin_3'].mode()[0], inplace = True)\ntest['bin_3'].fillna(test['bin_3'].mode()[0], inplace = True)\n\ntrain['bin_4'].fillna(train['bin_4'].mode()[0], inplace = True)\ntest['bin_4'].fillna(test['bin_4'].mode()[0], inplace = True)\n\ntrain['nom_0'].fillna(train['nom_0'].mode()[0],inplace = True)\ntest['nom_0'].fillna(test['nom_0'].mode()[0],inplace = True)\n\ntrain['nom_1'].fillna(train['nom_1'].mode()[0],inplace = True)\ntest['nom_1'].fillna(test['nom_1'].mode()[0],inplace = True)\n\ntrain['nom_2'].fillna(train['nom_2'].mode()[0],inplace = True)\ntest['nom_2'].fillna(test['nom_2'].mode()[0],inplace = True)\n\ntrain['nom_3'].fillna(train['nom_3'].mode()[0],inplace = True)\ntest['nom_3'].fillna(test['nom_3'].mode()[0],inplace = True)\n\ntrain['nom_4'].fillna(train['nom_4'].mode()[0],inplace = True)\ntest['nom_4'].fillna(test['nom_4'].mode()[0],inplace = True)\n\ntrain['nom_5'].fillna(train['nom_5'].mode()[0],inplace = True)\ntest['nom_5'].fillna(test['nom_5'].mode()[0],inplace = True)\n\ntrain['nom_6'].fillna(train['nom_6'].mode()[0],inplace = True)\ntest['nom_6'].fillna(test['nom_6'].mode()[0],inplace = True)\n\ntrain['nom_7'].fillna(train['nom_7'].mode()[0],inplace = True)\ntest['nom_7'].fillna(test['nom_7'].mode()[0],inplace = True)\n\ntrain['nom_8'].fillna(train['nom_8'].mode()[0],inplace = True)\ntest['nom_8'].fillna(test['nom_8'].mode()[0],inplace = True)\n\ntrain['nom_9'].fillna(train['nom_9'].mode()[0],inplace = True)\ntest['nom_9'].fillna(test['nom_9'].mode()[0],inplace = True)\n\ntrain['ord_0'].fillna(np.ceil(train['ord_0'].mean()),inplace = True)\ntest['ord_0'].fillna(np.ceil(train['ord_0'].mean()),inplace = True)\n\ntrain['ord_1'].fillna(train['ord_1'].mode()[0],inplace = True)\ntest['ord_1'].fillna(test['ord_1'].mode()[0],inplace = True)\n\ntrain['ord_2'].fillna(train['ord_2'].mode()[0],inplace = True)\ntest['ord_2'].fillna(test['ord_2'].mode()[0],inplace = True)\n\ntrain['ord_3'].fillna(train['ord_3'].mode()[0],inplace = True)\ntest['ord_3'].fillna(test['ord_3'].mode()[0],inplace = True)\n\ntrain['ord_4'].fillna(train['ord_4'].mode()[0],inplace = True)\ntest['ord_4'].fillna(test['ord_4'].mode()[0],inplace = True)\n\ntrain['ord_5'].fillna(train['ord_5'].mode()[0],inplace = True)\ntest['ord_5'].fillna(test['ord_5'].mode()[0],inplace = True)\n\ntrain['day'].fillna(train['day'].mode()[0],inplace = True)\ntest['day'].fillna(test['day'].mode()[0],inplace = True)\n\ntrain['month'].fillna(train['month'].mode()[0],inplace = True)\ntest['month'].fillna(test['month'].mode()[0],inplace = True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Encoding the data**"},{"metadata":{"trusted":true},"cell_type":"code","source":"train['bin_3'] = train['bin_3'].apply(lambda x: 0 if x == 'F' else 1)\ntest['bin_3'] = test['bin_3'].apply(lambda x: 0 if x == 'F' else 1)\n\n# bin_4\ntrain['bin_4'] = train['bin_4'].apply(lambda x: 0 if x == 'N' else 1)\ntest['bin_4'] = test['bin_4'].apply(lambda x: 0 if x == 'N' else 1)\n\n# ord_1\ntrain.ord_1.replace(to_replace = ['Novice', 'Contributor','Expert', 'Master', 'Grandmaster'],\n                         value = [0, 1, 2, 3, 4], inplace = True)\ntest.ord_1.replace(to_replace = ['Novice', 'Contributor','Expert', 'Master', 'Grandmaster'],\n                         value = [0, 1, 2, 3, 4], inplace = True)\n\n# ord_2\ntrain.ord_2.replace(to_replace = ['Freezing', 'Cold', 'Warm', 'Hot','Boiling Hot', 'Lava Hot'],\n                         value = [0, 1, 2, 3, 4, 5], inplace = True)\ntest.ord_2.replace(to_replace = ['Freezing', 'Cold', 'Warm', 'Hot','Boiling Hot', 'Lava Hot'],\n                         value = [0, 1, 2, 3, 4, 5], inplace = True)\n\n# ord_3\ntrain.ord_3.replace(to_replace = ['a', 'b', 'c', 'd', 'e', 'f', 'g','h', 'i', 'j', 'k', 'l', 'm', 'n', 'o'],\n                         value = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], inplace = True)\ntest.ord_3.replace(to_replace = ['a', 'b', 'c', 'd', 'e', 'f', 'g','h', 'i', 'j', 'k', 'l', 'm', 'n', 'o'],\n                         value = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14], inplace = True)\n\n# ord_4\ntrain.ord_4.replace(to_replace = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I','J', 'K', 'L', 'M', 'N', 'O', \n                                     'P', 'Q', 'R','S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z'],\n                         value = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, \n                                  22, 23, 24, 25], inplace = True)\ntest.ord_4.replace(to_replace = ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I','J', 'K', 'L', 'M', 'N', 'O', \n                                     'P', 'Q', 'R','S', 'T', 'U', 'V', 'W', 'X', 'Y', 'Z'],\n                         value = [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, \n                                  22, 23, 24, 25], inplace = True)\n\nhigh_card = ['nom_0','nom_1','nom_2','nom_3','nom_4','nom_5', 'nom_6', 'nom_7', 'nom_8', 'nom_9','ord_5']\nfor col in high_card:\n    enc_nom = (train.groupby(col).size()) / len(train)\n    train[f'{col}'] = train[col].apply(lambda x: hash(str(x)) % 5000)\n    test[f'{col}'] = test[col].apply(lambda x: hash(str(x)) % 5000)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train['target']\nx = train.drop(['target','id','ord_3','ord_4'],axis = 1)\ntest = test.drop(['id','ord_3','ord_4'],axis = 1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"len(x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_test, y_train, y_test = train_test_split(x, y, test_size=0.33, random_state=42)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"clf = LogisticRegression(C=0.20, solver=\"lbfgs\", tol=0.020, max_iter=2020)\nclf.fit(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pred = clf.predict_proba(X_test)\npred","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred=clf.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"value = accuracy_score(y_test,y_pred)\nprint(value)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(8,8))\ndf_cm = pd.DataFrame(confusion_matrix(y_test, y_pred), range(2),range(2))\nsns.set(font_scale=1.4)#for label size\nsns.heatmap(df_cm, annot=True,annot_kws={\"size\": 16}, fmt='g')\nplt.xlabel('Predicted Class')\nplt.ylabel('Original Class')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"pres = precision_score(y_test, y_pred)\nprint(pres)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"f1 = f1_score(y_test, y_pred,average='micro')\nprint(f1*100)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_id = test.pop('id')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\nsubmission['id'] = test_id\nsubmission['target'] = clf.predict_proba(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv(\"submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**Caliberated Classifier**"},{"metadata":{"trusted":true},"cell_type":"code","source":"calibrate = CalibratedClassifierCV(clf,method='sigmoid',cv = 5)\ncalibrate.fit(X_train,y_train)\npred = calibrate.predict(test)\nprint(pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submi = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submi['id'] = test_id\nsubmi['target'] = calibrate.predict_proba(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submi.to_csv(\"submission_new.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.boxplot(column=['nom_0','nom_1','nom_2', 'nom_3' ,'nom_4'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"***XG Boost Classifier***"},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(list(test.columns)))\nprint(len(list(X_train.columns)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from xgboost import XGBClassifier\nxgb = XGBClassifier()\nxgb.fit(X_train, y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fianl = xgb.predict(test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"xgb_submi = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/sample_submission.csv')\nxgb_submi['id'] = test_id\nxgb_submi['target'] = xgb.predict_proba(test)\nxgb_submi.to_csv(\"xgb_submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"***RandomForestClassifier***"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier\n\n# Create the model with 100 trees\nrfc = RandomForestClassifier(n_estimators=100, \n                               bootstrap = True,\n                               max_features = 'sqrt')\n# Fit on training data\nrfc.fit(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"rfc_submi = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/sample_submission.csv')\nrfc_submi['id'] = test_id\nrfc_submi['target'] = xgb.predict_proba(test)\nrfc_submi.to_csv(\"rfc_submission.csv\", index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}