机器学习任务1

import pandas as pd

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split, cross_val_score

from sklearn.ensemble import RandomForestClassifier

from sklearn.metrics import classification_report

import numpy as np

 

local_iris_df = pd.read_csv('iris.data')

print("从本地读取的数据：")

print(local_iris_df.head())

 

iris = load_iris()

X = iris.data

y = iris.target

 

 

rf_classifier = RandomForestClassifier(n_estimators=100, random_state=42)

 

 

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

 

 

print(f"交叉验证的准确度: {np.mean(cv_scores):.4f} ± {np.std(cv_scores):.4f}")

 

 

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

 

 

rf_classifier.fit(X_train, y_train)

 

 

y_pred = rf_classifier.predict(X_test)

 

 

print("\n分类报告：")

print(classification_report(y_test, y_pred, target_names=iris.target_names))