NLP/nlptopython.py at main · omjadhav18/NLP · GitHub

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
# import spacy

# nlp = spacy.load("en_core_web_sm")

# doc=nlp("Apple is looking for buying uk startup for $1 billion")

# for token in doc:
#     print(token.text)


#SPECIAL CASE TOKENIZATION

# import spacy
# from spacy.symbols import ORTH

# nlp=spacy.load("en_core_web_sm")

# doc=nlp("gimme that")


# special_case=[{ORTH:"gim"},{ORTH:"me"}]

# nlp.tokenizer.add_special_case("gimme",special_case)

# for token in nlp("gimme that"):
#     print(token.text)


#POS (parts of speech) tagging in NLP;

# import spacy
# from spacy import displacy
# nlp=spacy.load("en_core_web_sm")
# doc=nlp("Python is a programming language. Current year is 2025 . Dollar Symbol is $")

# #print(doc)

# # for token in doc:
# #     print(token)

# for token in doc:
#     print(token,"--->",token.pos_)

# for token in doc:
#     print(token,"--->",token.pos)  #Now this will give the numbers because it gives the numbers

# displacy.serve(doc,style="dep")   # this shows us the visualization part.


#Spacy stopwords removal.

#stopwords ----> these are the words that are often used in the sentence and create confusion to understand context of the document.  ex: a an i me , my , myself, he , him,


# import spacy
# from spacy.lang.en.stop_words import STOP_WORDS

# #print(STOP_WORDS)
# #print("in" in STOP_WORDS)  #first way to check.

# nlp=spacy.load("en_core_web_sm")
# # print(nlp.vocab["in"].is_stop)  #second way to check.


# doc=nlp("Python is a programming language. I am learning Natural Language Processing")

# for token in doc:
#     if(nlp.vocab[token.text].is_stop):
#         print(token.text)


# for token in doc:
#     if not nlp.vocab[token.text].is_stop:
#         print(token.text)


#Named Entity Recongnition:


# import spacy
# from spacy import displacy

# nlp=spacy.load("en_core_web_sm")

# doc=nlp("Apple is looking at buying U.K startup for $1 billion")

# for token in doc:
#     print(token.text,'-->', token.pos_)

# # displacy.serve(doc,style="ent")

# for entity in doc.ents:
#     print(entity.text)
#     # if entity.label_ == "ORG":
#     #     print(entity.text)


#Lemmatization  -- goal is to reduce different forms of words to common forms.
# ex: am, are, is -> be
# car,cars,car's -> car