Python实现孤立森林（IForest）+SVR的组合预测模型

只讨论性能，不考虑关联性，降噪数据未填补。

1.引入数据集

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.metrics import explained_variance_score
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
import pandas as pd
import numpy as np
import time

from sklearn import metrics

import csv

data=[]
traffic_feature=[]
traffic_target=[]
csv_file = csv.reader(open('turang.csv'))
for content in csv_file:
    content=list(map(float,content))
    if len(content)!=0:
        data.append(content)
        traffic_feature.append(content[0:4])
        traffic_target.append(content[-1])

data=np.array(data)

traffic_feature=np.array(traffic_feature)
traffic_target=np.array(traffic_target)

df=pd.DataFrame(data=data,columns = ['土壤温度','空气湿度','空气温度','光照强度','土壤水分'])
df

	土壤温度	空气湿度	空气温度	光照强度	土壤水分
0	37.77	27.00	39.90	68150.99	9.88
1	37.80	28.83	40.03	63989.96	9.85
2	37.82	26.82	40.20	63039.88	9.78
3	37.96	24.33	39.90	62988.95	9.77
4	37.77	24.03	39.60	59670.04	9.80
...	...	...	...	...	...
3078	28.57	91.17	17.23	861.47	28.30
3079	28.52	90.90	17.17	861.55	28.30
3080	28.50	89.80	17.15	861.76	28.28
3081	28.49	86.70	17.27	861.98	28.27
3082	28.46	84.50	17.43	860.32	28.28

3083 rows × 5 columns

2.标准化

scaler = StandardScaler() # 标准化转换
scaler.fit(traffic_feature)  # 训练标准化对象
traffic_feature= scaler.transform(traffic_feature)   # 转换数据集
feature_train,feature_test,target_train, target_test = train_test_split(traffic_feature,traffic_target,test_size=0.1,random_state=10)

3.SVR

from sklearn.svm import SVR
import matplotlib.pyplot as plt  
start1=time.time()
model_svr = SVR(C=1,epsilon=0.1,gamma=10)
model_svr.fit(feature_train,target_train)
predict_results1=model_svr.predict(feature_test)
end1=time.time()

SVRRESULT=predict_results1

plt.plot(target_test)#测试数组
plt.plot(predict_results1)#测试数组
plt.legend(['True','SVR'])
fig = plt.gcf()
fig.set_size_inches(18.5, 10.5)
plt.title("SVR")  # 标题
plt.show()
print("EVS:",explained_variance_score(target_test,predict_results1))
print("R2:",metrics.r2_score(target_test,predict_results1))
print("Time:",end1-start1)

EVS: 0.6563954626493961
R2: 0.6536622059850858
Time: 0.3603041172027588

4.引入IForest降噪

from sklearn.ensemble import IsolationForest

model_isof = IsolationForest()
outlier_label = model_isof.fit_predict(df)
# 将array 类型的标签数据转成 DataFrame
outlier_pd = pd.DataFrame(outlier_label, columns=['outlier_label'])
# 将标签数据与原来的数据合并
data_merge = pd.concat((df, outlier_pd), axis=1)
normal_source = data_merge[data_merge['outlier_label']==1]
normal_source

 5.测试效果

IF_traffic_feature=normal_source.values[:,[0,1,2,3]]
IF_traffic_target=normal_source.values[:,[4]]
scaler.fit(IF_traffic_feature)  # 训练标准化对象
IF_traffic_feature= scaler.transform(IF_traffic_feature)   # 转换数据集
feature_train,feature_test,target_train, target_test = train_test_split(IF_traffic_feature,IF_traffic_target,test_size=0.1,random_state=10)
from sklearn.svm import SVR
import matplotlib.pyplot as plt  
start1=time.time()
model_svr = SVR(C=1,epsilon=0.1,gamma=10)
model_svr.fit(feature_train,target_train)
predict_results1=model_svr.predict(feature_test)
end1=time.time()


plt.plot(target_test)#测试数组
plt.plot(predict_results1)#测试数组
plt.legend(['True','SVR'])
fig = plt.gcf()
fig.set_size_inches(18.5, 10.5)
plt.title("SVR")  # 标题
plt.show()
print("EVS:",explained_variance_score(target_test,predict_results1))
print("R2:",metrics.r2_score(target_test,predict_results1))
print("Time:",end1-start1)

EVS: 0.5487895968648998
R2: 0.5255880566754088
Time: 0.2094569206237793

效果不怎么样...可能是数据集或者未数据填补的原因。