{"cells":[{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"16a95dd0-4143-6f12-4219-983389bcd896"},"outputs":[],"source":"import pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn import linear_model\n\ntrain_data = pd.read_csv(\"../input/train.csv\")\ntest_data  = pd.read_csv(\"../input/test.csv\")\n\n"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0000f444-d956-545c-7ec5-5c5b52febcf6"},"outputs":[],"source":"# Partition the data into train and cross-validation\n\nprint(\"Partitioning training data into cross-validation and training...\")\n\ncross_validation_data = train_data.sample(frac = 0.2)\ntrain_data_x_cv = train_data.drop(cross_validation_data.index)\n\nprint(\"Length of original training set \"+str(len(train_data)))\nprint(\"Length of cross-validation set \"+str(len(cross_validation_data)))\nprint(\"Length of final training set \"+str(len(train_data_x_cv)))\n\n"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0127a79e-c622-24ad-1285-10836584a372"},"outputs":[],"source":"print(train_data.columns)\nprint(test_data.columns)\nx_variables = list(train_data.columns)\nx_variables.remove('label')\ny_variable = 'label'"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"e6a323c5-bf01-6e26-30c9-4387236e9036"},"outputs":[],"source":"test = pd.DataFrame(test)\ntest.columns = ['count']\ntest.sort(['count'],ascending = [1],inplace = True)\nprint(len(test[test['count']==0]))\nprint(len(test))"}],"metadata":{"_change_revision":0,"_is_fork":false,"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.0"}},"nbformat":4,"nbformat_minor":0}