客户细分：聚类算法实现的全面指南

            pip install scikit-learn numpy pandas matplotlib
            

              
                Copy
              
            
          

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

# Load your customer data into a Pandas DataFrame
data = pd.read_csv('customer_data.csv')

# Select the features you want to use for clustering
features = ['Purchase Frequency', 'Average Order Value', 'Customer Age']
X = data[features]

# Handle missing values (if any)
X = X.fillna(X.mean())

# Scale the features using StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Determine the optimal number of clusters using the Elbow Method
wcss = []
for i in range(1, 11):
 kmeans = KMeans(n_clusters=i, init='k-means++', max_iter=300, n_init=10, random_state=0)
 kmeans.fit(X_scaled)
 wcss.append(kmeans.inertia_)

plt.plot(range(1, 11), wcss)
plt.title('Elbow Method')
plt.xlabel('Number of clusters')
plt.ylabel('WCSS')
plt.show()

# Based on the Elbow Method, choose the optimal number of clusters
k = 3

# Apply K-Means clustering
kmeans = KMeans(n_clusters=k, init='k-means++', max_iter=300, n_init=10, random_state=0)
y_kmeans = kmeans.fit_predict(X_scaled)

# Add the cluster labels to the original DataFrame
data['Cluster'] = y_kmeans

# Analyze the clusters
cluster_analysis = data.groupby('Cluster').mean()
print(cluster_analysis)

# Visualize the clusters (for 2D or 3D data)
if len(features) == 2:
 plt.scatter(X_scaled[y_kmeans == 0, 0], X_scaled[y_kmeans == 0, 1], s=100, c='red', label='Cluster 1')
 plt.scatter(X_scaled[y_kmeans == 1, 0], X_scaled[y_kmeans == 1, 1], s=100, c='blue', label='Cluster 2')
 plt.scatter(X_scaled[y_kmeans == 2, 0], X_scaled[y_kmeans == 2, 1], s=100, c='green', label='Cluster 3')
 plt.scatter(kmeans.cluster_centers_[:, 0], kmeans.cluster_centers_[:, 1], s=300, c='yellow', label='Centroids')
 plt.title('Clusters of customers')
 plt.xlabel(features[0])
 plt.ylabel(features[1])
 plt.legend()
 plt.show()

            

              
                Copy
              
            
          

            import pandas as pd
import numpy as np
from sklearn.cluster import AgglomerativeClustering
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
from scipy.cluster.hierarchy import dendrogram, linkage

# Load your customer data into a Pandas DataFrame
data = pd.read_csv('customer_data.csv')

# Select the features you want to use for clustering
features = ['Purchase Frequency', 'Average Order Value', 'Customer Age']
X = data[features]

# Handle missing values (if any)
X = X.fillna(X.mean())

# Scale the features using StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Determine the linkage method (e.g., 'ward', 'complete', 'average', 'single')
linkage_method = 'ward'

# Create the linkage matrix
linked = linkage(X_scaled, method=linkage_method)

# Plot the dendrogram to help determine the number of clusters
plt.figure(figsize=(10, 7))
dendrogram(linked, orientation='top', distance_sort='ascending', show_leaf_counts=True)
plt.title('Hierarchical Clustering Dendrogram')
plt.xlabel('Sample Index')
plt.ylabel('Cluster Distance')
plt.show()

# Based on the dendrogram, choose the number of clusters
n_clusters = 3

# Apply Hierarchical Clustering
cluster = AgglomerativeClustering(n_clusters=n_clusters, linkage=linkage_method)
y_hc = cluster.fit_predict(X_scaled)

# Add the cluster labels to the original DataFrame
data['Cluster'] = y_hc

# Analyze the clusters
cluster_analysis = data.groupby('Cluster').mean()
print(cluster_analysis)

            

              
                Copy
              
            
          

            import pandas as pd
import numpy as np
from sklearn.cluster import DBSCAN
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt

# Load your customer data into a Pandas DataFrame
data = pd.read_csv('customer_data.csv')

# Select the features you want to use for clustering
features = ['Purchase Frequency', 'Average Order Value', 'Customer Age']
X = data[features]

# Handle missing values (if any)
X = X.fillna(X.mean())

# Scale the features using StandardScaler
scaler = StandardScaler()
X_scaled = scaler.fit_transform(X)

# Determine the optimal values for epsilon (eps) and min_samples
# This often requires experimentation and domain knowledge
eps = 0.5
min_samples = 5

# Apply DBSCAN clustering
dbscan = DBSCAN(eps=eps, min_samples=min_samples)
y_dbscan = dbscan.fit_predict(X_scaled)

# Add the cluster labels to the original DataFrame
data['Cluster'] = y_dbscan

# Analyze the clusters
cluster_analysis = data.groupby('Cluster').mean()
print(cluster_analysis)

# Visualize the clusters (for 2D data)
if len(features) == 2:
 plt.scatter(X_scaled[y_dbscan == 0, 0], X_scaled[y_dbscan == 0, 1], s=100, c='red', label='Cluster 1')
 plt.scatter(X_scaled[y_dbscan == 1, 0], X_scaled[y_dbscan == 1, 1], s=100, c='blue', label='Cluster 2')
 plt.scatter(X_scaled[y_dbscan == -1, 0], X_scaled[y_dbscan == -1, 1], s=100, c='gray', label='Outliers (Noise)')
 plt.title('Clusters of customers (DBSCAN)')
 plt.xlabel(features[0])
 plt.ylabel(features[1])
 plt.legend()
 plt.show()

            

              
                Copy
              
            
          

            from sklearn.metrics import silhouette_score, davies_bouldin_score, calinski_harabasz_score

# Assuming you have the cluster labels (y_kmeans, y_hc, or y_dbscan) and the scaled data (X_scaled)

# Calculate the Silhouette Score
silhouette = silhouette_score(X_scaled, y_kmeans)
print(f"Silhouette Score: {silhouette}")

# Calculate the Davies-Bouldin Index
db_index = davies_bouldin_score(X_scaled, y_kmeans)
print(f"Davies-Bouldin Index: {db_index}")

# Calculate the Calinski-Harabasz Index
ch_index = calinski_harabasz_score(X_scaled, y_kmeans)
print(f"Calinski-Harabasz Index: {ch_index}")

            

              
                Copy