import numpy as np
import matplotlib.pyplot as plt
from sklearn import datasets
from sklearn.model_selection import train_test_split
from sklearn.naive_bayes import GaussianNB
from sklearn.metrics import accuracy_score, classification_report
from sklearn.decomposition import PCA

# 加載數(shù)據(jù)
iris = datasets.load_iris()
X = iris.data
y = iris.target

# 劃分訓練集和測試集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)

# 創(chuàng)建并訓練模型
gnb = GaussianNB()
gnb.fit(X_train, y_train)

# 預測
y_pred = gnb.predict(X_test)

# 評估模型
accuracy = accuracy_score(y_test, y_pred)
print(f"準確率: {accuracy:.2f}")

print("\n分類報告:")
print(classification_report(y_test, y_pred, target_names=iris.target_names))

# 可視化
# 使用PCA降維到2D
pca = PCA(n_compnotallow=2)
X_pca = pca.fit_transform(X)

# 繪制散點圖
plt.figure(figsize=(10, 8))
colors = ['red', 'green', 'blue']
for i, c in zip(range(3), colors):
    plt.scatter(X_pca[y == i, 0], X_pca[y == i, 1], c=c, label=iris.target_names[i])

plt.title('鳶尾花數(shù)據(jù)集的PCA可視化')
plt.xlabel('第一主成分')
plt.ylabel('第二主成分')
plt.legend()
plt.show()

# 繪制決策邊界
x_min, x_max = X_pca[:, 0].min() - 0.5, X_pca[:, 0].max() + 0.5
y_min, y_max = X_pca[:, 1].min() - 0.5, X_pca[:, 1].max() + 0.5
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),
                     np.arange(y_min, y_max, 0.02))
Z = gnb.predict(pca.inverse_transform(np.c_[xx.ravel(), yy.ravel()]))
Z = Z.reshape(xx.shape)

plt.figure(figsize=(10, 8))
plt.contourf(xx, yy, Z, alpha=0.8, cmap=plt.cm.RdYlBu)
plt.scatter(X_pca[:, 0], X_pca[:, 1], c=y, cmap=plt.cm.RdYlBu, edgecolor='black')
plt.title('樸素貝葉斯分類器的決策邊界')
plt.xlabel('第一主成分')
plt.ylabel('第二主成分')
plt.show()