-
Notifications
You must be signed in to change notification settings - Fork 1
/
mytraining.py
33 lines (29 loc) · 1.28 KB
/
mytraining.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
import pandas as pd
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn import preprocessing
import pickle
def data_split(data, ratio):
np.random.seed(42)
shuffled = np.random.permutation(len(data))
test_set_size = int(len(data) * ratio)
test_indices = shuffled[:test_set_size]
train_indices = shuffled[test_set_size:]
return data.iloc[train_indices], data.iloc[test_indices]
if __name__ == "__main__":
df=pd.read_csv('tested_personTable(1)(1).csv').dropna()
train, test = data_split(df, 0.2)
X_train=train[['fever','head_ache','sore_throat','age_60_and_above','cough','shortness_of_breath','test_indication','gender']].to_numpy()
X_test=test[['fever','head_ache','sore_throat','age_60_and_above','cough','shortness_of_breath','test_indication','gender']].to_numpy()
Y_train=train[['corona_result']].to_numpy().reshape(46571,)
Y_test=test[['corona_result']].to_numpy().reshape(11642,)
lab_enc = preprocessing.LabelEncoder()
Y_train = lab_enc.fit_transform(Y_train)
clf=LogisticRegression()
clf.fit(X_train,Y_train)
inputfeatures=[1,0,0,0,1,0,1,1]
infProb=clf.predict_proba([inputfeatures])[0][1]
print(infProb)
outfile = open('models.pkl', 'wb')
pickle.dump(clf, outfile)
outfile.close()