lttzzlll

# classifier method
# dataSet: the training data set
# inx: the test sample
# labels: the corresponding labels about the data set
# k: the top k classes to be selected
def classify0(inX, dataSet, labels, k):
    sortedDistIndicies = euclideanMetric(dataSet, inX)
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]

lttzzlll

# classifier method
# dataSet: the training data set
# inx: the test sample
# labels: the corresponding labels about the data set
# k: the top k classes to be selected
def classify0(inX, dataSet, labels, k):
    sortedDistIndicies = euclideanMetric(dataSet, inX)
    classCount = {}
    for i in range(k):
        voteIlabel = labels[sortedDistIndicies[i]]

lttzzlll

'''
Created on Oct 12, 2010
Decision Tree Source Code for Machine Learning in Action Ch. 3
@author: Peter Harrington
'''
from math import log
import operator

# prepare data set
# create data set and corrsponding labels

lttzzlll

import pandas as pd

def run():
    data = pd.read_csv('Desktop_Win10Cortana_TRAIN_en-US_Live_2017-04_Desktop_Win10Cortana_Standard_en-us.hyp', sep='\t')

    wordCount = 0
    wordDict = {}
    for index, item in data.iterrows():
        wordList = item[8].split(' ')
        for word in wordList:

lttzzlll

'''
Python Training
https://microsoft.sharepoint.com/teams/stca/ipe/sr/_layouts/15/WopiFrame.aspx?sourcedoc={57bcddd2-341f-4151-84f7-f332fca4d07a}&action=edit&wd=target%28LearningCorner%2Eone%7CDF7F96A9-2186-462F-A0EC-8772881176AA%2FPerl%20and%20C%23%20Training%7C1C6AD0B9-765A-4DD5-A3C7-0822927FC9D1%2F%29
'''
import xml.etree.ElementTree as ET
from operator import itemgetter
import argparse

SRC_FILE_NAME = 'ITA_Blind_R2.xml'
DES_FILE_NAME = 'task1_output.txt'

lttzzlll

'''
Python Training
https://microsoft.sharepoint.com/teams/stca/ipe/sr/_layouts/15/WopiFrame.aspx?sourcedoc={57bcddd2-341f-4151-84f7-f332fca4d07a}&action=edit&wd=target%28LearningCorner%2Eone%7CDF7F96A9-2186-462F-A0EC-8772881176AA%2FPerl%20and%20C%23%20Training%7C1C6AD0B9-765A-4DD5-A3C7-0822927FC9D1%2F%29
'''
import pandas as pd
from operator import itemgetter
import argparse

SRC_FILE_NAME = 'Desktop_Merino_ThresholdCortana_Train_de-de_Li_1.hyp'
DES_FILE_NAME = 'task2_output.txt'

lttzzlll

'''
Python Training
'''
import argparse
import xml.etree.ElementTree as ET
from operator import itemgetter
import codecs

SRC_FILE_NAME = 'CortanaLiveData_ja-JP_2015_Audio_test.xml'
DES_FILE_NAME = 'task3_output.hyp'

lttzzlll

'''
Python Training
'''
import argparse
import codecs
import xml.etree.ElementTree as ET
import pandas as pd

INPUT_XML = 'CortanaLiveData_ja-JP_2015_Audio_test_Result.xml'
INPUT_HYP = 'task3_output.hyp'

lttzzlll

'''
Python Training
'''
import os
import codecs
import argparse
# import xml.etree.ElementTree as ET
from bs4 import BeautifulSoup

lttzzlll

'''
Python Training
'''
import os
import codecs
import argparse
# import xml.etree.ElementTree as ET
from bs4 import BeautifulSoup