/
fake_news_classifcation.py
142 lines (105 loc) · 5 KB
/
fake_news_classifcation.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
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Nov 19 14:17:24 2019
@author: sadrachpierre
"""
import pandas as pd
import numpy as np
import torch.nn as nn
from pytorch_pretrained_bert import BertTokenizer, BertModel
import torch
from torchnlp.datasets import imdb_dataset
from keras.preprocessing.sequence import pad_sequences
from sklearn.metrics import classification_report
pd.set_option('display.max_columns', None)
train_data, test_data = imdb_dataset(train=True, test=True)
df = pd.read_csv("fake.csv")
df = df[['text', 'type']]
print(len(df))
from collections import Counter
print(Counter(df['type'].values))
df = df[df['type'].isin(['fake', 'satire'])]
df.dropna(inplace = True)
df_fake = df[df['type'] == 'fake']
df_statire = df[df['type'] == 'satire']
df_statire = df_statire.sample(n=len(df_fake))
df = df_statire.append(df_fake)
df = df.sample(frac=1, random_state = 24).reset_index(drop=True)
print(Counter(df['type'].values))
train_data = df.head(19)
test_data = df.tail(19)
print(train_data)
train_data = [{'text': text, 'type': type_data } for text in list(train_data['text']) for type_data in list(train_data['type'])]
test_data = [{'text': text, 'type': type_data } for text in list(test_data['text']) for type_data in list(test_data['type'])]
train_texts, train_labels = list(zip(*map(lambda d: (d['text'], d['type']), train_data)))
test_texts, test_labels = list(zip(*map(lambda d: (d['text'], d['type']), test_data)))
tokenizer = BertTokenizer.from_pretrained('bert-base-uncased', do_lower_case=True)
train_tokens = list(map(lambda t: ['[CLS]'] + tokenizer.tokenize(t)[:511], train_texts))
test_tokens = list(map(lambda t: ['[CLS]'] + tokenizer.tokenize(t)[:511], test_texts))
train_tokens_ids = list(map(tokenizer.convert_tokens_to_ids, train_tokens))
test_tokens_ids = list(map(tokenizer.convert_tokens_to_ids, test_tokens))
train_tokens_ids = pad_sequences(train_tokens_ids, maxlen=512, truncating="post", padding="post", dtype="int")
test_tokens_ids = pad_sequences(test_tokens_ids, maxlen=512, truncating="post", padding="post", dtype="int")
train_y = np.array(train_labels) == 'fake'
test_y = np.array(test_labels) == 'fake'
#
#
class BertBinaryClassifier(nn.Module):
def __init__(self, dropout=0.1):
super(BertBinaryClassifier, self).__init__()
self.bert = BertModel.from_pretrained('bert-base-uncased')
self.dropout = nn.Dropout(dropout)
self.linear = nn.Linear(768, 1)
self.sigmoid = nn.Sigmoid()
def forward(self, tokens, masks=None):
_, pooled_output = self.bert(tokens, attention_mask=masks, output_all_encoded_layers=False)
dropout_output = self.dropout(pooled_output)
linear_output = self.linear(dropout_output)
proba = self.sigmoid(linear_output)
return proba
BATCH_SIZE = 1
EPOCHS = 1
train_masks = [[float(i > 0) for i in ii] for ii in train_tokens_ids]
test_masks = [[float(i > 0) for i in ii] for ii in test_tokens_ids]
train_masks_tensor = torch.tensor(train_masks)
test_masks_tensor = torch.tensor(test_masks)
train_tokens_tensor = torch.tensor(train_tokens_ids)
train_y_tensor = torch.tensor(train_y.reshape(-1, 1)).float()
test_tokens_tensor = torch.tensor(test_tokens_ids)
test_y_tensor = torch.tensor(test_y.reshape(-1, 1)).float()
train_dataset = torch.utils.data.TensorDataset(train_tokens_tensor, train_masks_tensor, train_y_tensor)
train_sampler = torch.utils.data.RandomSampler(train_dataset)
train_dataloader = torch.utils.data.DataLoader(train_dataset, sampler=train_sampler, batch_size=BATCH_SIZE)
test_dataset = torch.utils.data.TensorDataset(test_tokens_tensor, test_masks_tensor, test_y_tensor)
test_sampler = torch.utils.data.SequentialSampler(test_dataset)
test_dataloader = torch.utils.data.DataLoader(test_dataset, sampler=test_sampler, batch_size=BATCH_SIZE)
bert_clf = BertBinaryClassifier()
optimizer = torch.optim.Adam(bert_clf.parameters(), lr=3e-6)
for epoch_num in range(EPOCHS):
bert_clf.train()
train_loss = 0
for step_num, batch_data in enumerate(train_dataloader):
token_ids, masks, labels = tuple(t for t in batch_data)
probas = bert_clf(token_ids, masks)
loss_func = nn.BCELoss()
batch_loss = loss_func(probas, labels)
train_loss += batch_loss.item()
bert_clf.zero_grad()
batch_loss.backward()
optimizer.step()
print('Epoch: ', epoch_num + 1)
print("\r" + "{0}/{1} loss: {2} ".format(step_num, len(train_data) / BATCH_SIZE, train_loss / (step_num + 1)))
bert_clf.eval()
bert_predicted = []
all_logits = []
with torch.no_grad():
for step_num, batch_data in enumerate(test_dataloader):
token_ids, masks, labels = tuple(t for t in batch_data)
logits = bert_clf(token_ids, masks)
loss_func = nn.BCELoss()
loss = loss_func(logits, labels)
numpy_logits = logits.cpu().detach().numpy()
bert_predicted += list(numpy_logits[:, 0] > 0.5)
all_logits += list(numpy_logits[:, 0])
print(classification_report(test_y, bert_predicted))