Spaces:
Sleeping
Sleeping
Commit
·
7556992
1
Parent(s):
2b594bc
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,133 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import cv2
|
2 |
+
import time
|
3 |
+
import numpy as np
|
4 |
+
import pandas as pd
|
5 |
+
import gradio as gr
|
6 |
+
import tensorflow as tf
|
7 |
+
import matplotlib.pyplot as plt
|
8 |
+
from tensorflow.keras.datasets import imdb
|
9 |
+
from tensorflow.keras.callbacks import Callback
|
10 |
+
from tensorflow.keras.preprocessing.sequence import pad_sequences
|
11 |
+
from sklearn.model_selection import train_test_split
|
12 |
+
from tensorflow.keras.models import Sequential
|
13 |
+
from tensorflow.keras.layers import Dense, LSTM, Embedding
|
14 |
+
from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score
|
15 |
+
|
16 |
+
# Завантаження датасету з CSV-файлу
|
17 |
+
url = 'https://s3.amazonaws.com/amazon-reviews-pds/tsv/amazon_reviews_us_Books_v1_02.tsv.gz'
|
18 |
+
df = pd.read_csv(url, sep='\t', compression='gzip', error_bad_lines=False)
|
19 |
+
|
20 |
+
# Відображення перших 5 рядків датасету
|
21 |
+
print(df.head())
|
22 |
+
|
23 |
+
number_of_words = 10000
|
24 |
+
(X_train, y_train), (X_test, y_test) = imdb.load_data(num_words = number_of_words)
|
25 |
+
|
26 |
+
print(X_train.shape)
|
27 |
+
print(y_train.shape)
|
28 |
+
print(X_test.shape)
|
29 |
+
print(y_test.shape)
|
30 |
+
print(y_test[8])
|
31 |
+
|
32 |
+
%pprint
|
33 |
+
|
34 |
+
word_to_index = imdb.get_word_index()
|
35 |
+
word_to_index['great']
|
36 |
+
|
37 |
+
index_to_word = {index: word for (word, index) in word_to_index.items()}
|
38 |
+
|
39 |
+
print([index_to_word[i] for i in range(1, 51)])
|
40 |
+
|
41 |
+
print(X_train[123])
|
42 |
+
print(' '.join([index_to_word.get(i-3, '?') for i in X_train[123]]))
|
43 |
+
print(y_train[123])
|
44 |
+
|
45 |
+
words_per_review = 200
|
46 |
+
text = [2, 4, 5, 6]
|
47 |
+
X_train = pad_sequences(X_train, maxlen = words_per_review)
|
48 |
+
print(X_train.shape)
|
49 |
+
X_test = pad_sequences(X_test, maxlen = words_per_review)
|
50 |
+
print(X_test.shape)
|
51 |
+
print(X_train[123])
|
52 |
+
|
53 |
+
X_test, X_val, y_test, y_val = train_test_split(X_test, y_test, random_state = 11, test_size = 0.20)
|
54 |
+
|
55 |
+
print(X_test.shape)
|
56 |
+
print(X_val.shape)
|
57 |
+
|
58 |
+
rnn = Sequential()
|
59 |
+
rnn.add(Embedding(input_dim = number_of_words, output_dim = 128, input_length = words_per_review))
|
60 |
+
rnn.add(LSTM(units = 128, dropout = 0.2, recurrent_dropout = 0.2))
|
61 |
+
rnn.add(Dense(units = 1, activation = 'sigmoid'))
|
62 |
+
|
63 |
+
rnn.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
|
64 |
+
rnn.summary()
|
65 |
+
|
66 |
+
class TimingCallback(Callback):
|
67 |
+
def on_train_begin(self, logs={}):
|
68 |
+
self.start_time = time.time()
|
69 |
+
|
70 |
+
def on_train_end(self, logs={}):
|
71 |
+
elapsed_time = time.time() - self.start_time
|
72 |
+
print('Витрачений час на навчання: ', round(elapsed_time, 2), ' секунд')
|
73 |
+
|
74 |
+
history_rrn = rnn.fit(X_train, y_train, epochs = 10, batch_size = 32, validation_data = (X_test, y_test), callbacks=[TimingCallback()])
|
75 |
+
|
76 |
+
result = rnn.evaluate(X_test, y_test)
|
77 |
+
print(result)
|
78 |
+
|
79 |
+
def evaluate_model(model, history, X_test, Y_test):
|
80 |
+
loss, accuracy = model.evaluate(X_test, Y_test, verbose = 0)
|
81 |
+
print("Значення функції точності: ", accuracy)
|
82 |
+
|
83 |
+
# Обчислення тривалості навчання моделі (в епохах)
|
84 |
+
training_time = history.epoch[-1] + 1
|
85 |
+
print('Тривалість навчання: ', training_time, ' епох')
|
86 |
+
|
87 |
+
|
88 |
+
Y_pred = model.predict(X_test)
|
89 |
+
# Показує наскільки сильно відрізняються передбачення моделі від фактичних значень цільової змінної
|
90 |
+
print('Mean Absolute Error (MAE) - середня абсолютна помилка:', mean_absolute_error(Y_test, Y_pred))
|
91 |
+
# Показує середнє значення квадрата різниці між фактичними та передбаченими значеннями
|
92 |
+
print('Mean Squared Error (MSE) - середня квадратична помилка:', mean_squared_error(Y_test, Y_pred))
|
93 |
+
# Показує, наскільки добре модель відповідає даним
|
94 |
+
print('R-squared (R2) – коефіцієнт детермінації:' + str(r2_score(Y_test, Y_pred)))
|
95 |
+
|
96 |
+
#Побудова графіка
|
97 |
+
plt.plot(history.history['loss'], label='Training loss')
|
98 |
+
plt.title('Model loss')
|
99 |
+
plt.ylabel('Loss')
|
100 |
+
plt.xlabel('Epoch')
|
101 |
+
plt.legend()
|
102 |
+
plt.show()
|
103 |
+
|
104 |
+
evaluate_model(rnn, history_rrn, X_test, y_test)
|
105 |
+
|
106 |
+
|
107 |
+
# Створення функції для оцінки коментаря
|
108 |
+
def predict_comment_score(comment):
|
109 |
+
class_names = ["Negative", "Positive"]
|
110 |
+
words = comment.split()
|
111 |
+
print(len(words))
|
112 |
+
indexes = np.zeros(words_per_review).astype(int)
|
113 |
+
indexes[words_per_review -len(words) - 1] = 1
|
114 |
+
for i, word in enumerate(words):
|
115 |
+
indexes[words_per_review -len(words) + i] = word_to_index.get(word, 0) + 3
|
116 |
+
indexes = np.expand_dims(indexes, axis=0)
|
117 |
+
predictions = rnn.predict(indexes)
|
118 |
+
prediction = { }
|
119 |
+
prediction["Negative"] = float(np.round(1 - predictions[0], 3))
|
120 |
+
prediction["Positive"] = float(np.round(predictions[0], 3))
|
121 |
+
return prediction
|
122 |
+
|
123 |
+
demo = gr.Blocks()
|
124 |
+
|
125 |
+
# Створення інтерфейсу Gradio
|
126 |
+
with demo:
|
127 |
+
with gr.Tab("Predict comment score"):
|
128 |
+
image_input = gr.TextArea(label="Enter a comment")
|
129 |
+
output = gr.Label(label="Comment score")
|
130 |
+
image_button = gr.Button("Predict")
|
131 |
+
image_button.click(predict_comment_score, inputs=image_input, outputs=output)
|
132 |
+
|
133 |
+
demo.launch(debug=True)
|