{"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_type":"markdown","source":"# Loading in the dataset"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"df_train = pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/train.csv\")\ndf_test = pd.read_csv(\"/kaggle/input/cat-in-the-dat-ii/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Checking for missing value on the training dataset\ndf_train.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Checking for missing value on the test dataset\ndf_test.isna().sum()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"* We happen to have a lot of missing data for both training and testing.\n* For the sake of simplicity I will just replace them with NA.\n* Later, however, we will need to impute the missing variables."},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.info()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#  Since we have both integers/floats and strings I will fill integers with np.nan and strings with \"NA\"\nobject\nobject_type = np.dtype(\"O\")\ndf_train = df_train.apply(lambda x: x.fillna(\"NA\") if x.dtype == object_type\n                                       else x.fillna(-1))\ndf_test = df_test.apply(lambda x: x.fillna(\"NA\") if x.dtype == object_type\n                                       else x.fillna(-1))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Encoding Features\n\nNow that we have dealt with missing values I will move on to encode the features"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.preprocessing import LabelEncoder","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# For simplicity sake I will encode all categorical variables the same way but this is not the way we will do it for our actual submission\ncategorical_columns = df_train.select_dtypes(\"object\")\n\nfor col in categorical_columns:\n    encoder = LabelEncoder()\n    encoded = encoder.fit_transform(df_train[col])\n    df_train[col] = encoded\n    \n# Same for the test\n    \ncategorical_columns = df_test.select_dtypes(\"object\")\n\nfor col in categorical_columns:\n    encoder = LabelEncoder()\n    encoded = encoder.fit_transform(df_test[col])\n    df_test[col] = encoded","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_train.head()","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 = df_train.drop([\"id\",\"target\"],axis=1)\ny = df_train.target\nX_train, X_test, y_train, y_test = train_test_split(X,y) # Splitting the data to train and test to see how we are doing","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.ensemble import RandomForestClassifier # Importing our model of choice","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Notice I'm not using cross validation here but it will be neccesary when we want to make a good submission\nrf = RandomForestClassifier(n_jobs=-1)\nrf.fit(X_train,y_train)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = rf.predict(X_test)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.metrics import classification_report","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(classification_report(preds,y_test)) # We are not doing well here as we lack precision on target class 1","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"preds = rf.predict(df_test.drop(\"id\",axis=1))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Making a submission\n\nWe want ids from y_test and the predictions but to make sure lets check the sample submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = pd.read_csv('/kaggle/input/cat-in-the-dat-ii/sample_submission.csv')\nsample.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({\n    \"id\" : df_test.id,\n    \"target\" : preds\n})\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"We can then submit the prediction after committing the kernel by selecting it from the output files."},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv(\"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}