{"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\n\ntrain = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/train.csv\")\ntest = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/test.csv\")\nweather_train = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/weather_train.csv\")\nweather_test = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/weather_test.csv\")\nbuilding_metadata = pd.read_csv(\"/kaggle/input/ashrae-energy-prediction/building_metadata.csv\")\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 1 Analyze Data"},{"metadata":{},"cell_type":"markdown","source":"# 1.1 Statistical Description"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"weather_train.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"building_metadata.describe()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"weather_train['precip_depth_1_hr']","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 1.2 Check for Missing Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in train.columns:\n    print(column, train[column].isna().sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in weather_train.columns:\n    print(column, weather_train[column].isna().sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in building_metadata.columns:\n    print(column, building_metadata[column].isna().sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in test.columns:\n    print(column, test[column].isna().sum())","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for column in weather_test.columns:\n    print(column, weather_test[column].isna().sum())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# 1.3 Impute Missing Data"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.impute import SimpleImputer\n\n\n# TODO: Check if mode is close to average/median\nimputer = SimpleImputer(strategy=\"most_frequent\")\n\n# impute missing data with most frequent occuring value\nimp_weather_train = pd.DataFrame(imputer.fit_transform(weather_train))\nimp_weather_test = pd.DataFrame(imputer.fit_transform(weather_test))\nimp_building_metadata = pd.DataFrame(imputer.fit_transform(building_metadata))\n\n# add columns back to variables\nimp_weather_train.columns = weather_train.columns\nimp_weather_test.columns = weather_test.columns\nimp_building_metadata.columns = building_metadata.columns\n","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}