Python训练营-Day18

 
import pandas as pd
import pandas as pd    
import numpy as np     
import matplotlib.pyplot as plt    
import seaborn as sns   
import warnings
warnings.filterwarnings("ignore")
 
 
plt.rcParams['font.sans-serif'] = ['SimHei']  
plt.rcParams['axes.unicode_minus'] = False    
data = pd.read_csv('heart.csv')    
from sklearn.preprocessing import StandardScaler
# 数据标准化
scaler = StandardScaler()
 
 
from sklearn.model_selection import train_test_split
X = data.drop(['target'], axis=1)  
y = data['target'] # 标签
# # 按照8:2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)  # 80%训练集，20%测试集
import numpy as np
import pandas as pd
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
from sklearn.decomposition import PCA
from sklearn.metrics import silhouette_score, calinski_harabasz_score, davies_bouldin_score
import matplotlib.pyplot as plt
import seaborn as sns
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)
 
# 评估不同 k 值下的指标
k_range = range(2, 11)  # 测试 k 从 2 到 10
inertia_values = []
silhouette_scores = []
ch_scores = []
db_scores = []
 
for k in k_range:
    kmeans = KMeans(n_clusters=k, random_state=42)
    kmeans_labels = kmeans.fit_predict(X_scaled)
    inertia_values.append(kmeans.inertia_)  # 惯性（肘部法则）
    silhouette = silhouette_score(X_scaled, kmeans_labels)  # 轮廓系数
    silhouette_scores.append(silhouette)
    ch = calinski_harabasz_score(X_scaled, kmeans_labels)  # CH 指数
    ch_scores.append(ch)
    db = davies_bouldin_score(X_scaled, kmeans_labels)  # DB 指数
    db_scores.append(db)
    print(f"k={k}, 惯性: {kmeans.inertia_:.2f}, 轮廓系数: {silhouette:.3f}, CH 指数: {ch:.2f}, DB 指数: {db:.3f}")
 
# 提示用户选择 k 值
selected_k = 3 # 这里选择3后面好分析，也可以根据图选择最佳的k值
 
# 使用选择的 k 值进行 KMeans 聚类
kmeans = KMeans(n_clusters=selected_k, random_state=42)
kmeans_labels = kmeans.fit_predict(X_scaled)
X['KMeans_Cluster'] = kmeans_labels
 
# 使用 PCA 降维到 2D 进行可视化
pca = PCA(n_components=2)
X_pca = pca.fit_transform(X_scaled)
 
# KMeans 聚类结果可视化
plt.figure(figsize=(6, 5))
sns.scatterplot(x=X_pca[:, 0], y=X_pca[:, 1], hue=kmeans_labels, palette='viridis')
plt.title(f'KMeans Clustering with k={selected_k} (PCA Visualization)')
plt.xlabel('PCA Component 1')
plt.ylabel('PCA Component 2')
plt.show()
 
# 打印 KMeans 聚类标签的前几行
print(f"KMeans Cluster labels (k={selected_k}) added to X:")
print(X[['KMeans_Cluster']].value_counts())
X.columns
x1= X.drop('KMeans_Cluster',axis=1) # 删除聚类标签列
y1 = X['KMeans_Cluster']
# 构建随机森林，用shap重要性来筛选重要性
import shap
import numpy as np
from sklearn.ensemble import RandomForestClassifier  # 随机森林分类器
model = RandomForestClassifier(n_estimators=100, random_state=42)  # 随机森林模型
model.fit(x1, y1)  # 训练模型,此时无需在意准确率 直接全部数据用来训练了
shap.initjs()
# 初始化 SHAP 解释器
explainer = shap.TreeExplainer(model)
shap_values = explainer.shap_values(x1) # 这个计算耗时
shap_values.shape # 第一维是样本数，第二维是特征数，第三维是类别数
# --- 1. SHAP 特征重要性条形图 (Summary Plot - Bar) ---
print("--- 1. SHAP 特征重要性条形图 ---")
shap.summary_plot(shap_values[:, :, 0], x1, plot_type="bar",show=False)  #  这里的show=False表示不直接显示图形,这样可以继续用plt来修改元素，不然就直接输出了
plt.title("SHAP Feature Importance (Bar Plot)")
plt.show()
# 此时判断一下这几个特征是离散型还是连续型
import pandas as pd
selected_features = ['age', 'thalach','slope']
 
for feature in selected_features:
    unique_count = X[feature].nunique() # 唯一值指的是在某一列或某个特征中，不重复出现的值
    # 连续型变量通常有很多唯一值，而离散型变量的唯一值较少
    print(f'{feature} 的唯一值数量: {unique_count}')
    if unique_count < 10:  # 这里 10 是一个经验阈值，可以根据实际情况调整
        print(f'{feature} 可能是离散型变量')
    else:
        print(f'{feature} 可能是连续型变量')
# X["Purpose_debt consolidation"].value_counts() # 统计每个唯一值的出现次数
import matplotlib.pyplot as plt
 
# 总样本中的前四个重要性的特征分布图
fig, axes = plt.subplots(2, 2, figsize=(12, 8))
axes = axes.flatten()
 
for i, feature in enumerate(selected_features):
    axes[i].hist(X[feature], bins=20)
    axes[i].set_title(f'Histogram of {feature}')
    axes[i].set_xlabel(feature)
    axes[i].set_ylabel('Frequency')
 
plt.tight_layout()
plt.show()
# 绘制出每个簇对应的这四个特征的分布图
X[['KMeans_Cluster']].value_counts()
# 分别筛选出每个簇的数据
X_cluster0 = X[X['KMeans_Cluster'] == 0]
X_cluster1 = X[X['KMeans_Cluster'] == 1]
X_cluster2 = X[X['KMeans_Cluster'] == 2]
# 先绘制簇0的分布图
 
import matplotlib.pyplot as plt
 
# 总样本中的前四个重要性的特征分布图
fig, axes = plt.subplots(2, 2, figsize=(12, 8))
axes = axes.flatten()
 
for i, feature in enumerate(selected_features):
    axes[i].hist(X_cluster0[feature], bins=20)
    axes[i].set_title(f'Histogram of {feature}')
    axes[i].set_xlabel(feature)
    axes[i].set_ylabel('Frequency')
 
plt.tight_layout()
plt.show()
# 先绘制簇1的分布图
 
import matplotlib.pyplot as plt
 
# 总样本中的前四个重要性的特征分布图
fig, axes = plt.subplots(2, 2, figsize=(12, 8))
axes = axes.flatten()
 
for i, feature in enumerate(selected_features):
    axes[i].hist(X_cluster1[feature], bins=20)
    axes[i].set_title(f'Histogram of {feature}')
    axes[i].set_xlabel(feature)
    axes[i].set_ylabel('Frequency')
 
plt.tight_layout()
plt.show()
# 先绘制簇2的分布图
 
import matplotlib.pyplot as plt
 
# 总样本中的前四个重要性的特征分布图
fig, axes = plt.subplots(2, 2, figsize=(12, 8))
axes = axes.flatten()
 
for i, feature in enumerate(selected_features):
    axes[i].hist(X_cluster2[feature], bins=20)
    axes[i].set_title(f'Histogram of {feature}')
    axes[i].set_xlabel(feature)
    axes[i].set_ylabel('Frequency')
 
plt.tight_layout()
plt.show()

@浙大疏锦行