analysis.py 文件源码

def normalize_columns_separately(data_obj, column_headers):
    final_columns = []
    # print column_headers
    columns = data_obj.get_data(column_headers).transpose().tolist()
    for column in columns:
        temp_column = []
        max_num = max(column)
        min_num = min(column)
        for number in column:
            number -= min_num
            number *= 1 / (max_num - min_num)
            temp_column.append(number)
        final_columns.append(temp_column)
    # print "Normalized matrix"
    # print np.matrix(final_columns).transpose()
    print "\n\n"
    return np.matrix(final_columns).transpose()


# Takes in a list of column headers and the Data object and returns a matrix with each entry normalized so that the
# minimum value (of all the data in this set of columns)
# is mapped to zero and its maximum value is mapped to 1.