{"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)\n\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":{"_cell_guid":"","_uuid":"","trusted":true},"cell_type":"code","source":"sample_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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.shape","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":"test.isnull().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data = train.append(test,sort = False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.drop(['id','target'], axis = 1, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for col in list(data.columns):\n    print(col, data[col].unique())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"categorical_features = [col for c, col in enumerate(data.columns) \\\n                        if not ( np.issubdtype(data.dtypes[c], np.number )  )  ]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"categorical_features","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.drop(['id','target'], axis = 1, inplace = True)\ntest.drop(['id'], axis = 1, inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for col in list(train.drop(['target'], axis = 1).columns):\n    train[col].fillna(train[col].mode()[0], inplace = True)\n    test[col].fillna(test[col].mode()[0], inplace = True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"encoder = LabelEncoder()\nfor col in categorical_features:\n    train[col] = encoder.fit_transform(train[col])\n    test[col] = encoder.fit_transform(test[col])","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":"test.isnull().sum()","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.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train,X_val,y_train,y_val = train_test_split(train.drop(['id','target'], axis = 1), train['target'], test_size = 0.5, random_state = 42, shuffle = True, stratify = train['target'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_val.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_val.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.linear_model import LogisticRegression\nfrom sklearn import svm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"LRC = LogisticRegression(max_iter = 500)\nSVMC = svm.SVC()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"LRC.fit(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"LRC.score(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"LRC.score(X_val,y_val)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions = LRC.predict(test.drop(['id'],axis = 1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predictions","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['target'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train.shape","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train['target'].value_counts(normalize = True)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"**As we can see that our training data has 81.2% of target value as 0, the model that we build should give us the accuracy of more than 81.2%. Which means that if we simply predict the target value as 0 (without even looking at the other features or doing any thing ), we will be correct 81% of times**"},{"metadata":{},"cell_type":"markdown","source":"**Let us see what would be the public score with a simple Logistic regression model without any data engineering on the given set**"},{"metadata":{"trusted":true},"cell_type":"code","source":"test['target'] = LRC.predict_proba(test.drop(['id','target'],axis = 1))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test.columns","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test['target']","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit = test[['id','target']]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit.to_csv(\"../working/submit.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":1}