divide letters for text analysis

azureml_divideletters.py

# The script MUST contain a function named azureml_main
# which is the entry point for this module.
#
# The entry point function can contain up to two input arguments:
#   Param<dataframe1>: a pandas.DataFrame
#   Param<dataframe2>: a pandas.DataFrame
# coding: UTF-8
def azureml_main(dataframe1 = None, dataframe2 = None):
    import numpy as np
    from pandas import Series, DataFrame
    import pandas as pd
    from sklearn.feature_extraction.text import CountVectorizer
    
    dy, dx = dataframe1.shape
    data = [0] * dy
    namedata = dataframe1["name1"]

    for y in range(0,dy):
        line = namedata[y]
        output_line = '';
        x = 0
        xe = len(line);
        while x < xe:
            if ord(line[x]) >= 128:
                output_line = output_line + hex(ord(line[x])) + hex(ord(line[x+1])) + hex(ord(line[x+2])) + ' '
                x = x + 2
            else:
                output_line = output_line + hex(ord(line[x])) + ' '
            x = x + 1
        data[y] = output_line
    dataframe1["name_tx"] = Series(data)

    # Return value must be of a sequence of pandas.DataFrame
    return dataframe1,