示例#1
0
def compute_features():

    t = open("./package/training_set_3.csv", 'w')
    c = csv.writer(t)
    c.writerow(["serial no"])

    i = 1
    while i < 10:
        c.writerow([i])
        i = i + 1

    t.close()

    #two files 1_chat and 2_chat are created
    #first feature to extract ////"""average words per line""""
    average_word(
        "./package/test_final.txt", 3
    )  #creates a text file named number_word_1 which contains number of word in each line.
    #print "average_word_feature extracted"

    #second feature """word length per line"''
    word_length(
        "./package/test_final.txt", 3
    )  #creates a text file named word_length_1 which contains number of word in each line.
    #print "word_length_feature extracted"

    #third feature ""uppercase_lowrcase ratio""""
    ratio(
        "./package/test_final.txt", 3
    )  #creates a text file named word_length_1 which contains number of word in each line.
    #print "ratio_feature extracted"

    #fourth feature ""time_chat , time to give that particular reply"""

    #sixth feature """smiley count """every 10 line feature usage
    smiley_count("./package/test_final.txt", 3)
    #print "smiley count extracted"

    #fifth feature """stopwaord usagee in a line""""every 10 line feature
    stopword_usage("./package/test_final.txt", 3)
    #print "stopword feature extracted"

    #seventh feature """punchuation usage""""
    punctuation("./package/test_final.txt", 3)
    #print "punctuation_feature extracted"

    #eighth feature """message length ""
    msg_length("./package/test_final.txt", 3)
    #print "msg_length_feature extracted"

    #ninth feature """acronym count """
    acro_line("./package/test_final.txt", 3)
示例#2
0
def compute_features():

    t = open("./package/training_set_3.csv", "w")
    c = csv.writer(t)
    c.writerow(["serial no"])

    i = 1
    while i < 10:
        c.writerow([i])
        i = i + 1

    t.close()

    # two files 1_chat and 2_chat are created
    # first feature to extract ////"""average words per line""""
    average_word(
        "./package/test_final.txt", 3
    )  # creates a text file named number_word_1 which contains number of word in each line.
    # print "average_word_feature extracted"

    # second feature """word length per line"''
    word_length(
        "./package/test_final.txt", 3
    )  # creates a text file named word_length_1 which contains number of word in each line.
    # print "word_length_feature extracted"

    # third feature ""uppercase_lowrcase ratio""""
    ratio(
        "./package/test_final.txt", 3
    )  # creates a text file named word_length_1 which contains number of word in each line.
    # print "ratio_feature extracted"

    # fourth feature ""time_chat , time to give that particular reply"""

    # sixth feature """smiley count """every 10 line feature usage
    smiley_count("./package/test_final.txt", 3)
    # print "smiley count extracted"

    # fifth feature """stopwaord usagee in a line""""every 10 line feature
    stopword_usage("./package/test_final.txt", 3)
    # print "stopword feature extracted"

    # seventh feature """punchuation usage""""
    punctuation("./package/test_final.txt", 3)
    # print "punctuation_feature extracted"

    # eighth feature """message length ""
    msg_length("./package/test_final.txt", 3)
    # print "msg_length_feature extracted"

    # ninth feature """acronym count """
    acro_line("./package/test_final.txt", 3)
示例#3
0
	

	#fifth feature ""stopwaord usagee in a line""every 10 line feature
	stopword_usage('./chats_process/'+str(first)+'_'+str(second)+'/'+first+'.txt',str(first),str(second),1)
	stopword_usage('./chats_process/'+str(first)+'_'+str(second)+'/'+second+'.txt',str(first),str(second),2)
	#print "stopword feature extracted"
	
	
	#sixth feature""punchuation usage""
	punctuation('./chats_process/'+str(first)+'_'+str(second)+'/'+first+'.txt',str(first),str(second),1)
	punctuation('./chats_process/'+str(first)+'_'+str(second)+'/'+second+'.txt',str(first),str(second),2)
	#print "punctuation_feature extracted"

	
	#seventh feature ""message length ""
	msg_length('./chats_process/'+str(first)+'_'+str(second)+'/'+first+'.txt',str(first),str(second),1)
	msg_length('./chats_process/'+str(first)+'_'+str(second)+'/'+second+'.txt',str(first),str(second),2)
	#print "msg_length_feature extracted"
	
	
	#eighth feature ""acronym count "
	acro_line('./chats_process/'+str(first)+'_'+str(second)+'/'+first+'.txt',str(first),str(second),1)
	acro_line('./chats_process/'+str(first)+'_'+str(second)+'/'+second+'.txt',str(first),str(second),2)
	#print "acro_line extracted"

	
	#ninth feature ""elongation of vowel count""
	elongation_vowel('./chats_process/'+str(first)+'_'+str(second)+'/'+first+'.txt',str(first),str(second),1)
	elongation_vowel('./chats_process/'+str(first)+'_'+str(second)+'/'+second+'.txt',str(first),str(second),2)
	#print "elongation of vowel count"
示例#4
0
print "smiley count extracted"


#fifth feature """stopwaord usagee in a line""""every 10 line feature
stopword_usage("./package/1_chat.txt",1)
stopword_usage("./package/2_chat.txt",2)
print "stopword feature extracted"

#seventh feature """punchuation usage""""
punctuation("./package/1_chat.txt",1)
punctuation("./package/2_chat.txt",2)
print "punctuation_feature extracted"


#eighth feature """message length ""
msg_length("./package/1_chat.txt",1)
msg_length("./package/2_chat.txt",2)
print "msg_length_feature extracted"

#ninth feature """acronym count """
acro_line("./package/1_chat.txt",1)
acro_line("./package/2_chat.txt",2)
print "acro_line extracted"


#tenth feature """elongation of vowel count"""
elongation_vowel("./package/1_chat.txt",1)
elongation_vowel("./package/2_chat.txt",2)
print "elongation of vowel count"

#eleventh feature """suspension count """