ensemble_method_func.py 文件源码

def _df_initial_fixer(df, word, sample=60000):
    '''
    function:
    - ramdomly select rows (image) "sample" times from the df dataframe
    and delete features that are not used in ensemble method modeling

    input:
        df = dataframe. output of 1_feature_engineering_func. [pd.dataframe]
        word = name of topic ig "cat" [str]
        sample = number of sample you want to extract from df [int]

    output:
    new data frame!

    '''
    print "total number of images for df_{}: {}".format(word, len(df))
    random_index = np.random.choice(list(df.index), sample, replace=False)
    df = df.loc[list(random_index)]
    df_test = df.drop(['drawing','key_id','timestamp','recognized','X','Y','time',\
                        'X_per_stroke','Y_per_stroke','time_per_stroke',\
                        'total_time_of_stroke','dp_per_stroke','dp_percent_per_stroke',\
                        'direction'], axis=1)
    return df_test