每日总结45

import pandas as pd

df = pd.read_csv('iris.csv')

print(df.head())

 

from sklearn.datasets import load_iris

iris = load_iris()

X, y = iris.data, iris.target

print(X.shape, y.shape)

 

from sklearn.model_selection import cross_val_score

from sklearn.ensemble import RandomForestClassifier

 

# 初始化随机森林分类器

rf_classifier = RandomForestClassifier(n_estimators=100)

 

# 进行五折交叉验证

scores = cross_val_score(rf_classifier, X, y, cv=5)

print("Cross-validation scores:", scores)

 

from sklearn.model_selection import train_test_split

from sklearn.metrics import classification_report

 

# 划分训练集和测试集

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

 

# 训练模型

rf_classifier.fit(X_train, y_train)

 

# 预测测试集

y_pred = rf_classifier.predict(X_test)

 

# 输出模型性能报告

print(classification_report(y_test, y_pred))