{"cells":[{"metadata":{"_uuid":"50e2ca4b8c7c3e424dd82e0f6b737f5e1875bba9"},"cell_type":"markdown","source":"## Simple Decision Tree just for a Sample Submission"},{"metadata":{"_uuid":"9b7815ebaece8e789b90ce907f5ae7d4963c7e77"},"cell_type":"markdown","source":"### Abstract"},{"metadata":{"_uuid":"21cffe085540624923e89f63062dec75cae40c33"},"cell_type":"markdown","source":"The only purpose is to make a sample submission. I prefer not to make it with a dummy file, instead, I have modeled very simple decision tree by using only train.csv and test.csv."},{"metadata":{"_uuid":"34510d9db44448ca4f11e79cf2791d207ae52de9"},"cell_type":"markdown","source":"### Importing Libraries"},{"metadata":{"trusted":true,"_uuid":"04f85c10816cda41d95043445899338173946eb3"},"cell_type":"code","source":"import pandas as pd\nimport numpy as np\nfrom sklearn.tree import DecisionTreeRegressor\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split  ","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d52b260a1657682e7a2c6aa0448158928e1ae3ee"},"cell_type":"markdown","source":"### Loading and Displaying Datasets"},{"metadata":{"trusted":true,"_uuid":"bc5cf3e87aea761f5f11acfa6fc7c7d5b8aeb973"},"cell_type":"code","source":"df_train = pd.read_csv(\"../input/train.csv\")\ndf_test = pd.read_csv(\"../input/test.csv\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"78384e7a0bac920444c6a9ed21f6caabe554b5f1"},"cell_type":"code","source":"df_train.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false,"_uuid":"1da7e050c13649ffa5101b85d609de04cca83102"},"cell_type":"code","source":"df_test.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false,"_uuid":"7b24cda9e0bceb52bb6a97fdae4a380c4b553150"},"cell_type":"code","source":"print(\"length of train dataset:\", len(df_train))\nprint(\"length of test dataset:\", len(df_test))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"e9cb05162743478c038c262c64d5fafd6b833e29"},"cell_type":"markdown","source":"### Creating Numpy Arrays from Datasets"},{"metadata":{"trusted":false,"_uuid":"d86c94ec927d71a82913009f59288b47085ce032"},"cell_type":"code","source":"y = df_train[\"target\"].values\nX = df_train[[\"card_id\", \"feature_1\", \"feature_2\", \"feature_3\"]].values\nXsub = df_test[[\"card_id\", \"feature_1\", \"feature_2\", \"feature_3\"]].values\n\nprint(\"input features for train set:\\n\",X)\nprint(\"--------------------\")\nprint(\"input features for test set:\\n\",Xsub)\nprint(\"--------------------\")\nprint(\"output:\\n\",y)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"7fff9f1b9f2919e22fe574def605bd7724d7942d"},"cell_type":"markdown","source":"### Create Very Simple Decisin Tree"},{"metadata":{"trusted":false,"_uuid":"a59cf331eea2e6e62104b00bf2642974dc995a31"},"cell_type":"code","source":"model = DecisionTreeRegressor(max_depth=5)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b7848adaf153457c54ceda785b7ecb24c6dda84f"},"cell_type":"markdown","source":"### Train the Model"},{"metadata":{"trusted":false,"_uuid":"221a5380ff9bae28dd90d7d80268b76812821f3a"},"cell_type":"code","source":"model.fit(X[:,1:], y)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d4f218f7aad415bf890af372e0f325f3964d9b91"},"cell_type":"markdown","source":"### Make Predictions"},{"metadata":{"trusted":false,"_uuid":"403426d1f65ef88c4d552712e1d629a1f1b90eb5"},"cell_type":"code","source":"y_pred = model.predict(Xsub[:,1:])","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"b99fdf179a62ac7621b3db3dacb76f7e71da642b"},"cell_type":"markdown","source":"### Create Result Numpy Array"},{"metadata":{"trusted":false,"_uuid":"a9f0a59cdd338916c82b2a365f83fd4ea0ecc898"},"cell_type":"code","source":"y_pred = y_pred.reshape(len(y_pred),1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false,"_uuid":"204d42418da669ef40fa72765048cf5aebd8b8a2"},"cell_type":"code","source":"resultarray = np.append(Xsub, y_pred, axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false,"_uuid":"eb7fed35fbbdf0c5141555563332be63c533233a"},"cell_type":"code","source":"print(resultarray)","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"5499475ad35cf948b053443e023473ee68eea335"},"cell_type":"markdown","source":"### Create a Dataframe for Submission"},{"metadata":{"trusted":false,"_uuid":"cf2ca3ab3c6af25e411a8a847696a25b7446a7ac"},"cell_type":"code","source":"resultdf = pd.DataFrame(resultarray, columns=[\"card_id\", \"f1\", \"f2\", \"f3\", \"target\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false,"_uuid":"0bd2886262ee34214fa9d75150eec504c5ddb14d"},"cell_type":"code","source":"resultdf = resultdf.drop(['f1', 'f2', 'f3'], axis=1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false,"_uuid":"5275319560feb4487ddb30efd4ebaf9a11f2f091"},"cell_type":"code","source":"resultdf.head()","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"4adab9c5c6c0c68325a2d9e7f8314e9db5c50882"},"cell_type":"markdown","source":"### Create Submission csv File"},{"metadata":{"trusted":false,"_uuid":"a4008daec065c45f861b1e87ecad758d803b50ff"},"cell_type":"code","source":"resultdf.to_csv(\"submission.csv\", sep=',', index=False)","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}