forked from h2oai/driverlessai-recipes
-
Notifications
You must be signed in to change notification settings - Fork 0
/
text_similarity_transformers.py
147 lines (118 loc) · 4.75 KB
/
text_similarity_transformers.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
"""Row-by-row similarity between two text columns based on common N-grams, Jaccard similarity, Dice similarity and edit distance."""
from h2oaicore.transformer_utils import CustomTransformer
import datatable as dt
import numpy as np
_global_modules_needed_by_name = ['nltk==3.4.3']
import nltk
class CountCommonNGramsTransformer(CustomTransformer):
def __init__(self, ngrams, **kwargs):
super().__init__(**kwargs)
self.ngrams = ngrams
@staticmethod
def get_default_properties():
return dict(col_type="text", min_cols=2, max_cols=2, relative_importance=1)
@staticmethod
def get_parameter_choices():
return {"ngrams": [1, 2, 3]}
@property
def display_name(self):
return "CountCommon%dGrams" % self.ngrams
def fit_transform(self, X: dt.Frame, y: np.array = None):
return self.transform(X)
def transform(self, X: dt.Frame):
output = []
X = X.to_pandas()
text1_arr = X.iloc[:, 0].values
text2_arr = X.iloc[:, 1].values
for ind, text1 in enumerate(text1_arr):
try:
text1 = set(nltk.ngrams(str(text1).lower().split(), self.ngrams))
text2 = text2_arr[ind]
text2 = set(nltk.ngrams(str(text2).lower().split(), self.ngrams))
output.append(len(text1.intersection(text2)))
except:
output.append(-1)
return np.array(output)
class JaccardSimilarityTransformer(CustomTransformer):
"""Jaccard similarity measure on n-grams"""
def __init__(self, ngrams, **kwargs):
super().__init__(**kwargs)
self.ngrams = ngrams
@staticmethod
def get_default_properties():
return dict(col_type="text", min_cols=2, max_cols=2, relative_importance=1)
@staticmethod
def get_parameter_choices():
return {"ngrams": [1, 2, 3]}
@property
def display_name(self):
return "JaccardSimilarity_%dGrams" % self.ngrams
def fit_transform(self, X: dt.Frame, y: np.array = None):
return self.transform(X)
def transform(self, X: dt.Frame):
output = []
X = X.to_pandas()
text1_arr = X.iloc[:, 0].values
text2_arr = X.iloc[:, 1].values
for ind, text1 in enumerate(text1_arr):
try:
text1 = set(nltk.ngrams(str(text1).lower().split(), self.ngrams))
text2 = text2_arr[ind]
text2 = set(nltk.ngrams(str(text2).lower().split(), self.ngrams))
output.append(len(text1.intersection(text2)) / len(text1.union(text2)))
except:
output.append(-1)
return np.array(output)
class DiceSimilarityTransformer(CustomTransformer):
"""Dice similarity measure on n-grams"""
def __init__(self, ngrams, **kwargs):
super().__init__(**kwargs)
self.ngrams = ngrams
@staticmethod
def get_default_properties():
return dict(col_type="text", min_cols=2, max_cols=2, relative_importance=1)
@staticmethod
def get_parameter_choices():
return {"ngrams": [1, 2, 3]}
@property
def display_name(self):
return "DiceSimilarity_%dGrams" % self.ngrams
def fit_transform(self, X: dt.Frame, y: np.array = None):
return self.transform(X)
def transform(self, X: dt.Frame):
output = []
X = X.to_pandas()
text1_arr = X.iloc[:, 0].values
text2_arr = X.iloc[:, 1].values
for ind, text1 in enumerate(text1_arr):
try:
text1 = set(nltk.ngrams(str(text1).lower().split(), self.ngrams))
text2 = text2_arr[ind]
text2 = set(nltk.ngrams(str(text2).lower().split(), self.ngrams))
output.append((2 * len(text1.intersection(text2))) / (len(text1) + len(text2)))
except:
output.append(-1)
return np.array(output)
class EditDistanceTransformer(CustomTransformer):
_modules_needed_by_name = ['editdistance==0.5.3']
@staticmethod
def get_default_properties():
return dict(col_type="text", min_cols=2, max_cols=2, relative_importance=1)
def fit_transform(self, X: dt.Frame, y: np.array = None):
return self.transform(X)
def transform(self, X: dt.Frame):
import editdistance
output = []
X = X.to_pandas()
text1_arr = X.iloc[:, 0].values
text2_arr = X.iloc[:, 1].values
for ind, text1 in enumerate(text1_arr):
try:
text1 = str(text1).lower().split()
text2 = text2_arr[ind]
text2 = str(text2).lower().split()
edit_distance = editdistance.eval(text1, text2)
output.append(edit_distance)
except:
output.append(-1)
return np.array(output)