This repository was archived by the owner on Sep 12, 2018. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathrel_post_01.py
More file actions
89 lines (59 loc) · 2.28 KB
/
rel_post_01.py
File metadata and controls
89 lines (59 loc) · 2.28 KB
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
# This code is supporting material for the book
# Building Machine Learning Systems with Python
# by Willi Richert and Luis Pedro Coelho
# published by PACKT Publishing
#
# It is made available under the MIT License
import os
import sys
import scipy as sp
from sklearn.feature_extraction.text import CountVectorizer
DIR = r"../data/toy"
posts = [open(os.path.join(DIR, f)).read() for f in os.listdir(DIR)]
new_post = "imaging databases"
import nltk.stem
english_stemmer = nltk.stem.SnowballStemmer('english')
class StemmedCountVectorizer(CountVectorizer):
def build_analyzer(self):
analyzer = super(StemmedCountVectorizer, self).build_analyzer()
return lambda doc: (english_stemmer.stem(w) for w in analyzer(doc))
# vectorizer = CountVectorizer(min_df=1, stop_words='english',
# preprocessor=stemmer)
vectorizer = StemmedCountVectorizer(min_df=1, stop_words='english')
from sklearn.feature_extraction.text import TfidfVectorizer
class StemmedTfidfVectorizer(TfidfVectorizer):
def build_analyzer(self):
analyzer = super(StemmedTfidfVectorizer, self).build_analyzer()
return lambda doc: (english_stemmer.stem(w) for w in analyzer(doc))
vectorizer = StemmedTfidfVectorizer(
min_df=1, stop_words='english', charset_error='ignore')
print(vectorizer)
X_train = vectorizer.fit_transform(posts)
num_samples, num_features = X_train.shape
print("#samples: %d, #features: %d" % (num_samples, num_features))
new_post_vec = vectorizer.transform([new_post])
print(new_post_vec, type(new_post_vec))
print(new_post_vec.toarray())
print(vectorizer.get_feature_names())
def dist_raw(v1, v2):
delta = v1 - v2
return sp.linalg.norm(delta.toarray())
def dist_norm(v1, v2):
v1_normalized = v1 / sp.linalg.norm(v1.toarray())
v2_normalized = v2 / sp.linalg.norm(v2.toarray())
delta = v1_normalized - v2_normalized
return sp.linalg.norm(delta.toarray())
dist = dist_norm
best_dist = sys.maxsize
best_i = None
for i in range(0, num_samples):
post = posts[i]
if post == new_post:
continue
post_vec = X_train.getrow(i)
d = dist(post_vec, new_post_vec)
print("=== Post %i with dist=%.2f: %s" % (i, d, post))
if d < best_dist:
best_dist = d
best_i = i
print("Best post is %i with dist=%.2f" % (best_i, best_dist))