{"cells":[{"cell_type":"markdown","metadata":{"_cell_guid":"cb2c9099-ae59-3832-f4a5-31665b7ead91"},"source":"Getting feet wet in understanding the data at hand ..."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"19703c8b-1b68-1289-890a-eb966ca386b4"},"outputs":[],"source":"\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 the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output."},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"0ea8a66e-aa0b-d038-8775-74b307ebafa9"},"outputs":[],"source":"def inspectDataFiles(anyDF):\n    anyDF.head()\n    anyDFHeader = anyDF.head(0) #Just grabbing the headers\n\n    l0Count = len(anyDFHeader.T.filter(like='L0_',axis = 0)) #axis = 0 by row\n    l1Count = len(anyDFHeader.T.filter(like='L1_',axis = 0)) \n    l2Count = len(anyDFHeader.T.filter(like='L2_',axis = 0))\n    l3Count = len(anyDFHeader.T.filter(like='L3_',axis = 0))\n\n    print(l0Count, l1Count, l2Count, l3Count)\n    return\n\n"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"b4af8e59-6d08-2259-11f1-97712968c94f"},"outputs":[],"source":"inspectDataFiles#Inspecting the Categorical data\n\ntrainCategoricalDF = pd.read_csv(\"../input/train_categorical.csv\", nrows = 10)\ninspectDataFiles(trainCategoricalDF)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"8cd199b5-2dc6-87a0-d28d-18bfade9eafc"},"outputs":[],"source":"#Inspecting the Numeric data\n\ntrainNumericDF = pd.read_csv(\"../input/train_numeric.csv\", nrows = 10)\ninspectDataFiles(trainNumericDF)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"c6fc3f98-6f51-d6f0-81d8-0517357cd7fe"},"outputs":[],"source":"#Inspecting the Date data\n\ntrainDateDF = pd.read_csv(\"../input/train_date.csv\", nrows = 10)\ninspectDataFiles(trainDateDF)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"2ecc6f12-ae31-ec29-7eea-b944ef88a0bf"},"outputs":[],"source":"trainCategoricalDF = pd.read_csv(\"../input/train_categorical.csv\", nrows = 10)\ninspectDataFiles(trainCategoricalDF)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"c6e1e6b4-b6b0-4200-ceb2-481474253db9"},"outputs":[],"source":"trainNumericDF = pd.read_csv(\"../input/train_numeric.csv\", nrows = 10)\ninspectDataFiles(trainNumericDF)"},{"cell_type":"code","execution_count":null,"metadata":{"_cell_guid":"702ef9f7-8b27-3db7-84d7-549af1c9da05"},"outputs":[],"source":"trainDateDF = pd.read_csv(\"../input/train_date.csv\", nrows = 10)\ninspectDataFiles(trainDateDF)"}],"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}