-
Notifications
You must be signed in to change notification settings - Fork 0
/
zoom_app_reviews_star_calculation.py
249 lines (164 loc) · 6.04 KB
/
zoom_app_reviews_star_calculation.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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
# -*- coding: utf-8 -*-
"""Zoom_App_Reviews_Star_Calculation.ipynb
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1ZxENbcGa6UffcAc4LqehvMmcGxT7JDOP
# Libraries
"""
import numpy as np
import pandas as pd
"""# Dataset"""
from google.colab import drive
drive.mount('/content/drive')
dataset = pd.read_csv('/content/drive/MyDrive/SQA/Project Works/Datasets/Zoom_Reviews.csv', delimiter = ',', nrows=751)
dataset.shape
dataset.head()
from sklearn.utils import shuffle
df = shuffle(dataset)
df.head()
"""# Data Processing"""
X_data = []
Y_data = []
for i in range(2,len(df)):
try:
X_data.append(df['Reveiws'].iloc[i])
Y_data.append(df['Rating'].iloc[i])
except Exception as e:
print(e)
pass
X_data
Y_data
import re
import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords
from nltk.stem.porter import PorterStemmer
ps = PorterStemmer()
all_stopwords = stopwords.words('english')
all_stopwords.remove('not')
corpus=[]
for i in range(0, len(X_data)):
review = re.sub('[^a-zA-Z]', ' ', str(X_data[i]))
review = review.lower()
review = review.split()
review = [ps.stem(word) for word in review if not word in set(all_stopwords)]
review = ' '.join(review)
corpus.append(review)
corpus
len(corpus)
import pickle
pickle_out = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/X_Zoom.pickle", "wb")
pickle.dump(X_data, pickle_out, protocol=4) # protocol=4 is used for new version of pickle which can serialize more than 4GB data
pickle_out.close()
pickle_out = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Y_Zoom.pickle", "wb")
pickle.dump(Y_data, pickle_out, protocol=4) # protocol=4 is used for new version of pickle which can serialize more than 4GB data
pickle_out.close()
import pickle
pickle_in = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/X_Zoom.pickle", "rb")
X = pickle.load(pickle_in)
pickle_in = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Y_Zoom.pickle", "rb")
Y = pickle.load(pickle_in)
len(X)
len(Y)
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.preprocessing.text import Tokenizer
tokens_model = Tokenizer(num_words = 64)
tokens_model.fit_on_texts(X)
seq = tokens_model.texts_to_sequences(X)
word_index = tokens_model.word_index
print(tokens_model.word_index)
len(word_index)
print(seq)
max_length = 47
from tensorflow.keras.preprocessing.sequence import pad_sequences
import numpy as np
X = pad_sequences(seq, maxlen=max_length)
Y = np.asarray(Y)
X.shape
Y.shape
Y = Y - 1
Y
"""# Performance Analysis (Model #1)"""
model = tf.keras.models.load_model('/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Models/model-v3-10-performance-0.62-2.03.hdf5')
records = model.evaluate(X, Y)
predictions = model.predict(X) # predict output for all test data
scores = tf.nn.softmax(predictions)
Y_pred = []
for score in scores:
Y_pred.append(np.argmax(score))
Y_pred = np.array(Y_pred) # predicted labels
Y_pred
Y_pred = Y_pred + 1
Y_pred
print('Average Star Rating: ', sum(Y_pred)/len(Y_pred))
print('Actual Average Star Rating: ', sum(Y+1)/len(Y))
"""# Performance Analysis (Model #2)"""
model = tf.keras.models.load_model('/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Model_2/model-15-performance-0.43-1.33.h5')
records = model.evaluate(X, Y)
predictions = model.predict(X) # predict output for all test data
scores = tf.nn.softmax(predictions)
Y_pred = []
for score in scores:
Y_pred.append(np.argmax(score))
Y_pred = np.array(Y_pred) # predicted labels
Y_pred = Y_pred + 1
print('Average Star Rating: ', sum(Y_pred)/len(Y_pred))
"""# Performance Analysis (Model #3)"""
import pickle
pickle_in = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/X_Zoom.pickle", "rb")
X = pickle.load(pickle_in)
pickle_in = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Y_Zoom.pickle", "rb")
Y = pickle.load(pickle_in)
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.preprocessing.text import Tokenizer
tokens_model = Tokenizer(num_words = 64)
tokens_model.fit_on_texts(X)
seq = tokens_model.texts_to_sequences(X)
word_index = tokens_model.word_index
max_length = 36
from tensorflow.keras.preprocessing.sequence import pad_sequences
import numpy as np
X = pad_sequences(seq, maxlen=max_length)
Y = np.asarray(Y)
Y = Y - 1
model = tf.keras.models.load_model('/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Model_3/model-15-performance-0.71-0.82.h5')
records = model.evaluate(X, Y)
predictions = model.predict(X) # predict output for all test data
scores = tf.nn.softmax(predictions)
Y_pred = []
for score in scores:
Y_pred.append(np.argmax(score))
Y_pred = np.array(Y_pred) # predicted labels
Y_pred = Y_pred + 1
print('Average Star Rating: ', sum(Y_pred)/len(Y_pred))
"""# Performance Analysis (Model #4)"""
import pickle
pickle_in = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/X_Zoom.pickle", "rb")
X = pickle.load(pickle_in)
pickle_in = open("/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Y_Zoom.pickle", "rb")
Y = pickle.load(pickle_in)
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.preprocessing.text import Tokenizer
tokens_model = Tokenizer(num_words = 64)
tokens_model.fit_on_texts(X)
seq = tokens_model.texts_to_sequences(X)
word_index = tokens_model.word_index
max_length = 48
from tensorflow.keras.preprocessing.sequence import pad_sequences
import numpy as np
X = pad_sequences(seq, maxlen=max_length)
Y = np.asarray(Y)
Y = Y - 1
model = tf.keras.models.load_model('/content/drive/MyDrive/SQA/Project Works/Datasets/Pickle Data/Model_4/model-v2-04-performance-0.54-1.16.hdf5')
records = model.evaluate(X, Y)
predictions = model.predict(X) # predict output for all test data
scores = tf.nn.softmax(predictions)
Y_pred = []
for score in scores:
Y_pred.append(np.argmax(score))
Y_pred = np.array(Y_pred) # predicted labels
Y_pred = Y_pred + 1
print('Average Star Rating: ', sum(Y_pred)/len(Y_pred))