/
preprocessing.py
32 lines (21 loc) · 962 Bytes
/
preprocessing.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
__author__ = 'diego'
from load import load_data
import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.cross_validation import train_test_split
#dicas: np.concatenate, np.random.shuffle
def prepare_data():
X = load_data()
features = X[:, 5:43]
city_encoder = LabelEncoder()
city_group_encoder = LabelEncoder()
type_encoder = LabelEncoder()
raw_city = city_encoder.fit_transform(X[:, 2:3].flatten())
raw_city_group = city_group_encoder.fit_transform(X[:, 3:4].flatten())
raw_type = type_encoder.fit_transform(X[:, 4:5].flatten())
features =np.concatenate((np.array([raw_type]).T, features), axis=1)
features =np.concatenate((np.array([raw_city_group]).T, features ), axis=1)
features =np.concatenate(( np.array([raw_city]).T, features), axis=1)
return train_test_split(features, X[:, 42:43].flatten(), test_size=0.33, random_state=42)
if __name__ == '__main__':
prepare_data()