完全汇总，十大机器学习算法！！

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_california_housing
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# 加载加州房价数据集
housing = fetch_california_housing()
X = pd.DataFrame(housing.data, columns=housing.feature_names)
y = housing.target

# 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)

# 训练线性回归模型
lr = LinearRegression()
lr.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = lr.predict(X_test)

# 计算均方误差
mse = mean_squared_error(y_test, y_pred)
print("Mean Squared Error:", mse)

# 绘制预测值与真实值的散点图
plt.figure(figsize=(10, 6))
plt.scatter(y_test, y_pred, alpha=0.5)
plt.xlabel("True Values")
plt.ylabel("Predictions")
plt.title("True Values vs Predictions")
plt.show()

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.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix
from matplotlib.colors import ListedColormap

# 加载鸢尾花数据集
iris = load_iris()
X = iris.data[:, :2]  # 只选择前两个特征用于可视化
y = iris.target

# 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)

# 训练逻辑回归模型
lr = LogisticRegression()
lr.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = lr.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 绘制决策边界
x_min, x_max = X[:, 0].min() - 0.5, X[:, 0].max() + 0.5
y_min, y_max = X[:, 1].min() - 0.5, X[:, 1].max() + 0.5
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.01),
                     np.arange(y_min, y_max, 0.01))
Z = lr.predict(np.c_[xx.ravel(), yy.ravel()])
Z = Z.reshape(xx.shape)

# 绘制结果
plt.figure(figsize=(10, 6))
plt.contourf(xx, yy, Z, alpha=0.8, cmap=ListedColormap(('red', 'green', 'blue')))
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=ListedColormap(('red', 'green', 'blue')), edgecolors='k')
plt.xlabel('Sepal Length')
plt.ylabel('Sepal Width')
plt.title('Logistic Regression Decision Boundary')
plt.show()

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.tree import DecisionTreeClassifier, plot_tree
from sklearn.metrics import accuracy_score

# 加载鸢尾花数据集
iris = load_iris()
X = iris.data
y = iris.target

# 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)

# 构建决策树模型
dt = DecisionTreeClassifier()
dt.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = dt.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 绘制决策树
plt.figure(figsize=(12, 8))
plot_tree(dt, filled=True, feature_names=iris.feature_names, class_names=iris.target_names)
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score, confusion_matrix

# 加载手写数字数据集
digits = load_digits()
X = digits.data
y = digits.target

# 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)

# 构建K近邻模型
knn = KNeighborsClassifier(n_neighbors=5)
knn.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = knn.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 绘制混淆矩阵
conf_matrix = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
plt.imshow(conf_matrix, cmap='Blues')
plt.colorbar()
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
plt.title('Confusion Matrix')
plt.show()

# 随机选择一些样本并展示预测结果
plt.figure(figsize=(10, 8))
for i in range(10):
    idx = np.random.randint(0, len(X_test))
    image = X_test[idx].reshape(8, 8)
    plt.subplot(2, 5, i+1)
    plt.imshow(image, cmap='binary')
    plt.title(f'Predicted: {y_pred[idx]}, Actual: {y_test[idx]}')
    plt.axis('off')
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score, confusion_matrix

# 加载手写数字数据集
digits = load_digits()
X = digits.data
y = digits.target

# 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)

# 构建支持向量机模型
svm = SVC(kernel='rbf', gamma='scale')
svm.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = svm.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 绘制混淆矩阵
conf_matrix = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
plt.imshow(conf_matrix, cmap='Blues')
plt.colorbar()
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
plt.title('Confusion Matrix')
plt.show()

# 随机选择一些样本并展示预测结果
plt.figure(figsize=(10, 8))
for i in range(10):
    idx = np.random.randint(0, len(X_test))
    image = X_test[idx].reshape(8, 8)
    plt.subplot(2, 5, i+1)
    plt.imshow(image, cmap='binary')
    plt.title(f'Predicted: {y_pred[idx]}, Actual: {y_test[idx]}')
    plt.axis('off')
plt.show()

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.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score, confusion_matrix
import seaborn as sns

# 加载鸢尾花数据集
iris = load_iris()
X = iris.data
y = iris.target

# 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)

# 构建朴素贝叶斯模型
nb = GaussianNB()
nb.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = nb.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 绘制混淆矩阵
conf_matrix = confusion_matrix(y_test, y_pred)
plt.figure(figsize=(8, 6))
sns.heatmap(conf_matrix, annot=True, cmap='Blues', fmt='d')
plt.xlabel('Predicted Label')
plt.ylabel('True Label')
plt.title('Confusion Matrix')
plt.show()

# 绘制特征的概率密度估计图
plt.figure(figsize=(10, 8))
for i in range(4):
    plt.subplot(2, 2, i+1)
    sns.histplot(X_train[:, i], kde=True, color='skyblue', label='Train', alpha=0.6)
    sns.histplot(X_test[:, i], kde=True, color='salmon', label='Test', alpha=0.6)
    plt.title(f'Feature {i+1} Distribution')
    plt.xlabel('Feature Value')
    plt.ylabel('Density')
    plt.legend()
plt.tight_layout()
plt.show()

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.preprocessing import StandardScaler

# 加载鸢尾花数据集
iris = load_iris()
X = iris.data
y = iris.target

# 特征标准化
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# 使用PCA进行降维
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)

# 构建K均值聚类模型
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(X_scaled)

# 获取聚类中心和预测类别
cluster_centers = kmeans.cluster_centers_
y_pred = kmeans.labels_

# 可视化聚类结果
plt.figure(figsize=(10, 8))

# 绘制原始数据的散点图
plt.subplot(2, 1, 1)
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', s=50, alpha=0.8)
plt.title('Original Data')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')

# 绘制聚类结果的散点图
plt.subplot(2, 1, 2)
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y_pred, cmap='viridis', s=50, alpha=0.8)
plt.scatter(cluster_centers[:, 0], cluster_centers[:, 1], c='red', marker='x', s=200, label='Cluster Centers')
plt.title('K-Means Clustering')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.legend()

plt.tight_layout()
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.decomposition import PCA

# 加载手写数字识别数据集
digits = load_digits()
X = digits.data
y = digits.target

# 构建PCA模型并拟合数据
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X)

# 可视化降维后的数据
plt.figure(figsize=(10, 8))
scatter = plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap='viridis', s=20, alpha=0.7)
plt.colorbar(scatter)
plt.title('2D PCA Visualization of MNIST Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score
from matplotlib.colors import ListedColormap

# 加载鸢尾花数据集
iris = load_iris()
X = iris.data[:, [2, 3]]  # 取特征的后两个维度
y = iris.target

# 划分训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 构建随机森林模型
rf_clf = RandomForestClassifier(n_estimators=100, random_state=42)
rf_clf.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = rf_clf.predict(X_test)

# 计算模型准确率
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 可视化决策边界
def plot_decision_regions(X, y, classifier, test_idx=None, resolution=0.02):
    markers = ('s', 'x', 'o', '^', 'v')
    colors = ('red', 'blue', 'lightgreen', 'gray', 'cyan')
    cmap = ListedColormap(colors[:len(np.unique(y))])

    x1_min, x1_max = X[:, 0].min() - 1, X[:, 0].max() + 1
    x2_min, x2_max = X[:, 1].min() - 1, X[:, 1].max() + 1
    xx1, xx2 = np.meshgrid(np.arange(x1_min, x1_max, resolution), np.arange(x2_min, x2_max, resolution))
    Z = classifier.predict(np.array([xx1.ravel(), xx2.ravel()]).T)
    Z = Z.reshape(xx1.shape)
    plt.contourf(xx1, xx2, Z, alpha=0.4, cmap=cmap)
    plt.xlim(xx1.min(), xx1.max())
    plt.ylim(xx2.min(), xx2.max())

    for idx, cl in enumerate(np.unique(y)):
        plt.scatter(x=X[y == cl, 0], y=X[y == cl, 1], alpha=0.8, c=[cmap(idx)], marker=markers[idx], label=cl, edgecolor='black')

    if test_idx:
        X_test, y_test = X[test_idx, :], y[test_idx]
        plt.scatter(X_test[:, 0], X_test[:, 1], c='', edgecolor='black', alpha=1.0, linewidth=1, marker='o', s=100, label='Test Set')

plot_decision_regions(X_train, y_train, classifier=rf_clf)
plt.title('Random Forest Classifier - Decision Boundary (Training Set)')
plt.xlabel('Petal Length (cm)')
plt.ylabel('Petal Width (cm)')
plt.legend(loc='upper left')
plt.show()

import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import load_digits
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import accuracy_score

# 加载手写数字识别数据集
digits = load_digits()
X = digits.data
y = digits.target

# 数据标准化
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

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

# 构建神经网络模型
mlp = MLPClassifier(hidden_layer_sizes=(100, 50), activation='relu', solver='adam', max_iter=500, random_state=42)

# 训练模型
history = mlp.fit(X_train, y_train)

# 预测并计算准确率
y_pred = mlp.predict(X_test)
accuracy = accuracy_score(y_test, y_pred)
print("Accuracy:", accuracy)

# 绘制训练过程中的损失曲线
plt.figure(figsize=(10, 6))
plt.plot(history.loss_curve_)
plt.title('Training Loss Curve')
plt.xlabel('Epochs')
plt.ylabel('Loss')
plt.grid(True)
plt.show()