{"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\n#importing the required packages \nimport pandas as pd \nimport numpy as np \nimport matplotlib.pyplot as plt \nimport seaborn as sns \n\n%matplotlib inline \n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"#Lets input the required datasets and explore them \n\nbuilding_metadata=pd.read_csv('../input/ashrae-energy-prediction/building_metadata.csv')\nweather_test = pd.read_csv('../input/ashrae-energy-prediction/weather_test.csv')\nweather_train = pd.read_csv('../input/ashrae-energy-prediction/weather_train.csv')\ntrain = pd.read_csv('../input/ashrae-energy-prediction/train.csv')\ntest = pd.read_csv('../input/ashrae-energy-prediction/test.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"building_metadata.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# We see that the above dataset consits of following columns \n\n#site id    : Primary key for this data set \n#building id : Foreign key to tie this data set to ...\n#primary_use : Use of the building \n#square_feet : Area of the building \n#floor_count: Number of floors on the building ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"building_metadata.dtypes\n\n#dtypes looks ok for all columns ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#checking for null values \nbuilding_metadata.isnull().sum()\n#We see some null valyes in year built and floor_count variable we need to check if we can fix this ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"building_metadata.info()\n\n#There to much missing values in floor count check if we can find this information in other dataset provided ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"building_metadata.describe()\n# We see that ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"bins_edges=np.arange(0,building_metadata['floor_count'].max()+2,2)\nplt.hist(building_metadata['floor_count'],bins=bins_edges);\nplt.xticks(bins_edges);","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(10,8))\nbins_edges=np.arange(building_metadata['year_built'].min(),building_metadata['year_built'].max()+5,5)\nplt.hist(building_metadata['year_built'],bins=bins_edges);\nplt.xticks(bins_edges,rotation=90);\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.c(building_metadata['primary_use']);","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}