python 12实验

1.导入数据。
2.清洗数据，将缺失值或“NAN”替换为“无”，并将文本数据转换为数值型数据。
3.使用聚类算法（如KMeans）对数据进行聚类，并计算样本到簇中心的平均距离以确定最佳的簇数量。
4.对数据进行PCA降维，以便在三维空间中可视化聚类结果。
5.使用Matplotlib绘制三维散点图。

pip install mlxtend

import pandas as pd
import numpy as np
from sklearn import preprocessing
from mlxtend.preprocessing import TransactionEncoder
import re
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
inputfile_1= "./生枣仁主治病症.xlsx"
df = pd.read_excel(inputfile_1)
df['方名'] = df['方名'].str.strip()
df.head()

数据清洗：将缺失值或'NAN'替换为'无

cols = ['药1', '药2', '药3', '药4']
df[cols] = df[cols].fillna('无')
df.drop_duplicates(inplace=True)
df.head()

 

from sklearn.preprocessing import LabelEncoder
from sklearn.decomposition import PCA
from sklearn.preprocessing import LabelEncoder
label_encoder = LabelEncoder()
# 文本数据转换为数值型数据
for col in ['药1', '药2', '药3', '药4']:
    df[col] = label_encoder.fit_transform(df[col])
from sklearn.metrics import pairwise_distances_argmin_min
distances = []
K = range(2, 10)
for k in K:
    kmeans = KMeans(n_clusters=k, random_state=42).fit(df.drop(columns=['方名']))
    labels = kmeans.labels_
    cluster_centers = kmeans.cluster_centers_
    
    # 计算样本到簇中心的平均距离
    distances_to_centers = pairwise_distances_argmin_min(df.drop(columns=['方名']), cluster_centers)[1]
    avg_distance = distances_to_centers.mean()
    distances.append(avg_distance)

# 找到最佳的簇数量（基于样本到簇中心的平均距离）
optimal_k = distances.index(min(distances)) + 2  # 因为K的范围是从2开始的
print(f"Optimal number of clusters: {optimal_k}")

kmeans = KMeans(n_clusters=optimal_k, random_state=42)
clusters = kmeans.fit_predict(df.drop(columns=['方名']))
df['Cluster'] = clusters

pca = PCA(n_components=3)
X_pca = pca.fit_transform(df.drop(columns=['方名', '方名']))

fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
for i in range(optimal_k):
    ax.scatter(X_pca[df['Cluster'] == i, 0], X_pca[df['Cluster'] == i, 1], X_pca[df['Cluster'] == i, 2], label=f'Cluster {i}')
ax.set_xlabel('PCA Feature 1')
ax.set_ylabel('PCA Feature 2')
ax.set_zlabel('PCA Feature 3')
ax.legend()
plt.title('3D Scatter Plot of Clusters')
plt.show()

# 绘制簇数量与平均距离的折线图
plt.figure()
plt.plot(K, distances, 'bx-')
plt.xlabel('Number of Clusters (K)')
plt.ylabel('Average Distance to Cluster Centers')
plt.title('Average Distance to Cluster Centers vs. Number of Clusters')
plt.xticks(K)
plt.show()