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
| import pandas as pd
import numpy as np
from sklearn.feature_extraction.text import CountVectorizer,TfidfVectorizer
from sklearn.linear_model import LogisticRegression
import warnings
warnings.filterwarnings("ignore")
# Read the dataset
df_train = pd.read_csv('../data/train.csv')
df_valid = pd.read_csv('../data/test.csv')
df_test = pd.read_csv('../data/testB.csv')
df_train = df_train.fillna('')
df_valid.fillna('')
df_test = df_test.fillna('')
# Features
df_train['text'] = df_train.apply(lambda x:' '.join(x.drop('uuid').astype(str)),axis=1)
df_valid['text'] = df_valid.apply(lambda x:' '.join(x.drop('uuid').astype(str)),axis=1)
df_test['text'] = df_test.apply(lambda x:' '.join(x.drop('uuid').astype(str)),axis=1)
# df_train['text']
vector = TfidfVectorizer().fit(df_train['text'].tolist())
vocab = vector.vocabulary_
train_vector = vector.transform(df_train['text'])
valid_vector = vector.transform(df_valid['text'])
test_vector = vector.transform(df_test['text'])
df_trainv = pd.DataFrame(train_vector.toarray(),columns=vocab)
df_validv = pd.DataFrame(valid_vector.toarray(),columns=vocab)
df_testv = pd.DataFrame(test_vector.toarray(),columns=vocab)
df_train.describe()
# lightGBM model
import lightgbm as lgb
data = lgb.Dataset(df_trainv,df_train['label'])
# data_val = lgb.Dataset(df_validv,df_valid['label'])
params = {
'boosting_type': 'gbdt',
'objective': 'binary',
'metric': 'binary_logloss',
'num_leaves': 31,
'learning_rate': 0.05,
'feature_fraction': 0.9,
'bagging_fraction': 0.8,
'bagging_freq': 5,
'verbose': 0
}
model = lgb.train(params, data)
y_pred = model.predict(test_vector)
y_pred = np.where(y_pred>=0.5,1,0)
df_test['label'] = y_pred
df_test['Keywords'] = df_test['title'].fillna('')
df_test[['uuid', 'Keywords', 'label']].to_csv('../data/task1_lightGBM.csv', index=None)
|
