# 导入所需的库
import sklearn
import pandas as pd
from sklearn import datasets

# 从sklearn中加载鸢尾花数据集
iris_clf = datasets.load_iris()
print(iris_clf.target_names)
print(iris_clf.feature_names)

# 将数据集分为训练集和测试集
X, y = datasets.load_iris( return_X_y = True)
from sklearn.model_selection import train_test_split

# 60 %训练数据集和40 %测试数据集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.40)

# 从sklearn模块中导入随机森林分类器
from sklearn.ensemble import RandomForestClassifier

# 创建数据帧
data = pd.DataFrame({'sepallength': iris_clf.data[:, 0],
'sepalwidth': iris_clf.data[:, 1],
'petallength': iris_clf.data[:, 2],
'petalwidth': iris_clf.data[:, 3],
'species': iris_clf.target})

# 创建一个随机森林分类器
RForest_clf = RandomForestClassifier(n_estimators = 100)

# 使用fit()函数在训练数据集上训练模型
RForest_clf.fit(X_train, y_train)

# 从测试数据集中进行预测
y_pred = RForest_clf.predict(X_test)

# 导入计算精度所需的度量标准库
from sklearn import metrics
print('\n'"Accuracy of our Random Forst Classifier is: ",
metrics.accuracy_score(y_test, y_pred)*100)

['setosa' 'versicolor' 'virginica']
['sepal length (cm)', 'sepal width (cm)', 'petal length (cm)', 'petal width (cm)']

Accuracy of our Random Forst Classifier is: 95.0

# 预测花的类型
RForest_clf.predict([[5, 4, 3, 1]])

array([1])

# 预测花的类型
RForest_clf.predict([[5, 4, 5, 2]])

array([2])