InventoryDemandPre.py 文件源码

def find_missing_products():
    train = pd.read_csv('/Users/srinath/playground/data-science/BimboInventoryDemand/train.csv')
    train_ids = train['Producto_ID'].unique()
    test = pd.read_csv('/Users/srinath/playground/data-science/BimboInventoryDemand/test.csv')
    test_ids = test['Producto_ID'].unique()

    missing_ids = pd.Index(test_ids).difference(pd.Index(train_ids))
    print "missing ID count ", len(missing_ids)

    missing_ids_df =  pd.DataFrame(missing_ids, columns=["Producto_ID"])
    missing_ids_df.to_csv('missing_ids.csv', index=False)

    entries_with_missing = pd.merge(test, missing_ids_df, on='Producto_ID')

    print "Mising entries=", entries_with_missing.shape[0], "percentage=", entries_with_missing.shape[0]*100/test.shape[0]

    print "full entries count", test.shape[0]