Machine Learning.py

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score

# 加载鸢尾花数据集
iris = load_iris()

# 将数据转化为 pandas DataFrame
X = pd.DataFrame(iris.data, columns=iris.feature_names)  # 特征数据
y = pd.Series(iris.target)  # 标签数据

# 显示前五行数据
print(X.head())

# 划分训练集和测试集（80% 训练集，20% 测试集）
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 标准化特征
scaler = StandardScaler() 
X_train = scaler.fit_transform(X_train)  #fit()：计算训练数据的均值和标准差transform()：用计算出的均值和标准差来转换数据
X_test = scaler.transform(X_test)  #未来数据计算不出来均值和标准差

# 创建 KNN 分类器o
knn = KNeighborsClassifier(n_neighbors=3)

# 训练模型
knn.fit(X_train, y_train)

# 预测测试集
y_pred = knn.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f'模型准确率: {accuracy:.2f}')