本文使用的数据类型是数值型,每一个样本6个特征表示,所用的数据如图所示:
图中A,B,C,D,E,F列表示六个特征,G表示样本标签。每一行数据即为一个样本的六个特征和标签。
实现RandomForest算法的代码如下:
from sklearn.ensemble import RandomForestClassifier
import csv
from sklearn.cross_validation import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.preprocessing import StandardScaler
data=[]
traffic_feature=[]
traffic_target=[]
csv_file = csv.reader(open('packSize_all.csv'))
for content in csv_file:
content=list(map(float,content))
if len(content)!=0:
data.append(content)
traffic_feature.append(content[0:6])
traffic_target.append(content[-1])
print('data=',data)
print('traffic_feature=',traffic_feature)
print('traffic_target=',traffic_target)
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=0.3,random_state=0)
# clf = RandomForestClassifier(criterion='entropy')
clf = RandomForestClassifier()
clf.fit(feature_train,target_train)
predict_results=clf.predict(feature_test)
print(accuracy_score(predict_results, target_test))
conf_mat = confusion_matrix(target_test, predict_results)
print(conf_mat)
print(classification_report(target_test, predict_results))
运行结果如图所示: