使用XGBoost做了一个快速训练模板，方便日后使用。

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
import pandas as pd
from xgboost import XGBClassifier
from sklearn.model_selection import train_test_split

from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.metrics import f1_score


dataset = pd.read_csv(r'totalDataSet.csv',)
accountDataSet = pd.read_csv(r'accountFeature.csv',)
#依靠addr合并dataset
dataset = pd.merge(dataset,accountDataSet,on='addr')

X=dataset.iloc[:,1:92]
Y=dataset.iloc[:,92]

X_train,X_test,y_train,y_test=train_test_split(X,Y,test_size=0.33,random_state=7)

model=XGBClassifier()
eval_set=[(X_test,y_test)]
model.fit(X_train,y_train,
         early_stopping_rounds=10,
         eval_metric='logloss',
         eval_set=eval_set,
         verbose=True,
         )

y_pred=model.predict(X_test)

#四舍五入
predictions=[round(value) for value in y_pred]

accuracyScore=accuracy_score(y_test,predictions)
print('accuracy: %.2f%%' % (accuracyScore*100))

precisionScore=precision_score(y_test,predictions)
print('precision: %.2f%%' % (precisionScore*100))

recallScore = recall_score(y_test,predictions)
print('recall: %.2f%%' % (recallScore*100))

f1Score = f1_score(y_test,predictions)
print('f1Score: %.2f%%' % (f1Score*100))