机器学习十大算法

机器学习十大算法的 Python 代码示例，我们将使用常见的scikit-learn库来实现，数据集使用鸢尾花数据集。

1. 决策树算法（Decision Tree）

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
from sklearn.metrics import accuracy_score

# 加载数据集
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=0.3, random_state=42)

# 创建决策树分类器
clf = DecisionTreeClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"决策树准确率: {accuracy}")

2. 朴素贝叶斯算法（Naive Bayes）

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

# 加载数据集
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=0.3, random_state=42)

# 创建朴素贝叶斯分类器
clf = GaussianNB()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"朴素贝叶斯准确率: {accuracy}")

3. 支持向量机（Support Vector Machine，SVM）

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from sklearn.metrics import accuracy_score

# 加载数据集
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=0.3, random_state=42)

# 创建 SVM 分类器
clf = SVC()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"SVM 准确率: {accuracy}")

4. K 近邻算法（K – Nearest Neighbor，KNN）

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import accuracy_score

# 加载数据集
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=0.3, random_state=42)

# 创建 KNN 分类器
clf = KNeighborsClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"KNN 准确率: {accuracy}")

5. 逻辑回归（Logistic Regression）

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

# 加载数据集
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=0.3, random_state=42)

# 创建逻辑回归分类器
clf = LogisticRegression(max_iter=1000)
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"逻辑回归准确率: {accuracy}")

6. 随机森林算法（Random Forest）

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

# 加载数据集
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=0.3, random_state=42)

# 创建随机森林分类器
clf = RandomForestClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"随机森林准确率: {accuracy}")

7. 梯度提升树（Gradient Boosting Decision Tree，GBDT）

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.metrics import accuracy_score

# 加载数据集
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=0.3, random_state=42)

# 创建 GBDT 分类器
clf = GradientBoostingClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"GBDT 准确率: {accuracy}")

8. K – 均值聚类算法（K – Means Clustering）

from sklearn.datasets import load_iris
from sklearn.cluster import KMeans
import matplotlib.pyplot as plt

# 加载数据集
iris = load_iris()
X = iris.data

# 创建 KMeans 聚类器
kmeans = KMeans(n_clusters=3, random_state=42)
kmeans.fit(X)

# 获取聚类标签
labels = kmeans.labels_

# 可视化聚类结果（取前两个特征）
plt.scatter(X[:, 0], X[:, 1], c=labels, cmap='viridis')
centers = kmeans.cluster_centers_
plt.scatter(centers[:, 0], centers[:, 1], c='red', marker='X', s=200)
plt.title('K - Means Clustering')
plt.xlabel('Sepal length')
plt.ylabel('Sepal width')
plt.show()

9. 主成分分析（Principal Component Analysis，PCA）

from sklearn.datasets import load_iris
from sklearn.decomposition import PCA
import matplotlib.pyplot as plt

# 加载数据集
iris = load_iris()
X = iris.data

# 创建 PCA 对象，降维到 2 维
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X)

# 可视化降维后的数据
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=iris.target, cmap='viridis')
plt.title('PCA of Iris Dataset')
plt.xlabel('Principal Component 1')
plt.ylabel('Principal Component 2')
plt.show()

10. AdaBoost 算法（Adaptive Boosting）

from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from sklearn.ensemble import AdaBoostClassifier
from sklearn.metrics import accuracy_score

# 加载数据集
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=0.3, random_state=42)

# 创建 AdaBoost 分类器
clf = AdaBoostClassifier()
clf.fit(X_train, y_train)

# 预测
y_pred = clf.predict(X_test)

# 计算准确率
accuracy = accuracy_score(y_test, y_pred)
print(f"AdaBoost 准确率: {accuracy}")

这些代码示例展示了如何使用scikit-learn库实现机器学习十大算法，并在鸢尾花数据集上进行简单的训练和测试。你可以根据实际需求调整参数和使用其他数据集。