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
| import pandas as pd
import idsw.hdfs as ih
hdfs = ih.client()
reader = hdfs.open('/user/bf_ssglf_user01/idsw//jiangmanhua/dataset/dimension-jmh_train.csv', 'rb')
df = pd.read_csv(reader)
df.head()
X=df.iloc[:,2:42]
X.iloc[0:5]
Y=df.iloc[:,1]
Y.iloc[0:5]
from sklearn.model_selection import train_test_split
import numpy as np
X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.25)
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import cross_val_score
clf = DecisionTreeClassifier(random_state=0)
scores = cross_val_score(clf, X, Y, cv=10)
print("Accuracy: %0.2f (+/- %0.2f)" % (scores.mean(), scores.std() * 2))
from sklearn.ensemble import RandomForestClassifier
model = RandomForestClassifier(n_estimators = 10, criterion="gini")
model = model.fit(Xd_train, y_train)
y_predicted = model.predict(Xd_test)
accuracy = np.mean(y_predicted == y_test) * 100
print ("y_test\n",y_test)
print ("y_predicted\n",y_predicted)
print ("accuracy:",accuracy)
reader2 = hdfs.open('/user/bf_ssglf_user01/idsw//jiangmanhua/dataset/dimension-jmh_202202_0203.csv', 'rb')
testdf = pd.read_csv(reader2)
testdf.head()
testX=testdf.iloc[:,1:41]
testY = model.predict(testX)
testY
testdf.iloc[:,0]
out=pd.merge(testdf.iloc[:,0].to_frame(), pd.DataFrame(testY,columns=list('A')), left_index=True, right_index=True)
out.head()
with hdfs.open('/user/bf_ssglf_user01/idsw//jiangmanhua/dataset/dimension-jmh_train_result.csv', 'wb') as ff:
out.to_csv(ff,index=0,header=0)
pd.read_csv(hdfs.open('/user/bf_ssglf_user01/idsw//jiangmanhua/dataset/dimension-jmh_train_result.csv', 'rb'),header=None).head()
hdfs.tail('/user/bf_ssglf_user01/idsw/jiangmanhua/dataset/dimension-jmh_train_result.csv')
|
