-
Notifications
You must be signed in to change notification settings - Fork 1
/
my_spacy.py
190 lines (148 loc) · 4.97 KB
/
my_spacy.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
import spacy
from spacy.lang.en import English
import pandas as pd
import numpy as np
import csv
import xlrd
from itertools import zip_longest
import re
import en_core_web_sm
from collections import Counter
# Load English tokenizer, tagger, parser, NER and word vectors
nlp = English()
#for multilanguage
#nlp=spacy.load("xx_ent_wiki_sm")
df=pd.read_csv("./csv_cleaned_Alfredo 2.csv")
df=df.drop_duplicates()
print(df)
# Create the pipeline 'sentencizer' component
sbd = nlp.create_pipe('sentencizer')
# Add the component to the pipeline
nlp.add_pipe(sbd)
num_sentences=[]
#per csv
text=df.text.tolist()
title=df.title.tolist()
#print(text)
size=len(title)
#print("8704",str(title[6647]))
#print("8706",str(title[13930]))
'''
for i in range(0,size):
# "nlp" Object is used to create documents with linguistic annotations.
doc = nlp(text[i])
# create list of sentence tokens
sents_list = []
for sent in doc.sents:
#print(sent.text)
sents_list.append(sent.text)
frasi=np.array(sents_list)
num_sentences.append(frasi.shape[0])
print(num_sentences)
print(len(num_sentences))
df['num_sentences_in_text']=pd.Series(num_sentences);
'''
#print(df)
'''
# print on csv with new col
with open('./num_sentences_in_text.csv', 'w', encoding="ISO-8859-1", newline='') as csv_num_sentences:
writer = csv.writer(csv_num_sentences)
rows = zip_longest(*[num_sentences], fillvalue = '')
writer.writerows(rows)
csv_num_sentences.close()
'''
'''
num_exclamation_mark_in_text = []
num_exclamation_mark_in_title = []
num_question_mark_in_text = []
num_question_mark_in_title = []
for i in range(0,size):
num_exclamation_mark_in_text.append(text[i].count('!'))
num_exclamation_mark_in_title.append(title[i].count('!'))
num_question_mark_in_text.append(text[i].count('?'))
num_question_mark_in_title.append(title[i].count('?'))
#print(num_exclamation_mark_in_text)
#print(num_question_mark_in_text)
with open('./num_marks.csv', 'w', encoding="ISO-8859-1", newline='') as csv_num_marks:
writer = csv.writer(csv_num_marks)
rows = zip_longest(*[num_exclamation_mark_in_text,num_exclamation_mark_in_title,num_question_mark_in_text,num_question_mark_in_title], fillvalue = '')
writer.writerows(rows)
csv_num_marks.close()
'''
'''
num_capital_words_in_text = []
num_capital_words_in_title = []
for i in range(0,size):
num_capital_words_in_text.append(len(re.findall(r'[A-Z]',text[i])))
num_capital_words_in_title.append(len(re.findall(r'[A-Z]',title[i])))
#print(num_capital_words)
with open('./num_capital_words.csv', 'w', encoding="ISO-8859-1", newline='') as csv_num_capital_words:
writer = csv.writer(csv_num_capital_words)
rows = zip_longest(*[num_capital_words_in_text,num_capital_words_in_title], fillvalue = '')
writer.writerows(rows)
csv_num_capital_words.close()
'''
'''
nlp = en_core_web_sm.load()
list_word_pos = []
list_adv = []
list_noun = []
list_propn = []
#list_I_we_me_us = []
list_adj = []
#list_no_not = []
list_punct = []
for i in range(0,size):
list_word_pos = []
docs=nlp(text[i])
for word in docs:
list_word_pos.append(word.pos_)
list_adv.append(list_word_pos.count("ADV"))
list_noun.append(list_word_pos.count("NOUN"))
list_propn.append(list_word_pos.count("PROPN"))
list_punct.append(list_word_pos.count("PUNCT"))
list_adj.append(list_word_pos.count("ADJ"))
#count_I_we_us=text[i].count(" I ")+text[i].count(" we ")+text[i].count(" WE ")+text[i].count(" We ")+text[i].count(" us ")+text[i].count(" US ")+text[i].count(" Us ")+text[i].count(" me ")+text[i].count(" ME ")+text[i].count(" Me ")
#list_I_we_me_us.append(count_I_we_us)
#count_no_not=text[i].count(" no ")+text[i].count(" NO ")+text[i].count(" No ")+text[i].count(" not ")+text[i].count(" NOT ")+text[i].count(" Not ")
#list_no_not.append(count_no_not)
print("List adv = ",list_adv)
print("List adj = ",list_adj)
print("List noun = ",list_noun)
#print("List I_we_me_us = ",list_I_we_me_us)
#print("List no_not = ",list_no_not)
print("List propn = ",list_propn)
print("List punct = ",list_punct)
with open('./pos_tagging.csv', 'w', encoding="ISO-8859-1", newline='') as csv_pos_tagging:
writer = csv.writer(csv_pos_tagging)
rows = zip_longest(*[list_adj,list_adv,list_noun,list_propn,list_punct], fillvalue = '')
writer.writerows(rows)
csv_pos_tagging.close()
'''
'''
total = 0
for i in list1:
total += len(i)
ave_size = float(total) / float(len(list1))
print(ave_size)
'''
list_lunghezze=[]
list_avg_lunghezze=[]
for i in range(0,len(text)):
token_list = []
my_doc = nlp(text[i])
total=0
for token in my_doc:
if not token.is_punct | token.is_space:
total += len(token.text)
token_list.append(token.text)
list_lunghezze.append(len(token_list))
list_avg_lunghezze.append(float(total) / float(len(token_list)))
#print(token_list)
#print(list_lunghezze)
#print(list_avg_lunghezze)
with open('./word.csv', 'w', encoding="ISO-8859-1", newline='') as csv_word:
writer = csv.writer(csv_word)
rows = zip_longest(*[list_lunghezze,list_avg_lunghezze], fillvalue = '')
writer.writerows(rows)
csv_word.close()