|
from sklearn.cluster import KMeans |
|
from sklearn.metrics import silhouette_score |
|
from sklearn.preprocessing import StandardScaler |
|
import streamlit as st |
|
import matplotlib.pyplot as plt |
|
import seaborn as sns |
|
import pandas as pd |
|
from sklearn.decomposition import PCA |
|
|
|
def summarize_cluster_characteristics(clustered_data, labels, cluster_number): |
|
cluster_data = clustered_data[labels == cluster_number] |
|
summary = cluster_data.mean().to_dict() |
|
return summary |
|
|
|
def perform_clustering(df, n_clusters): |
|
df = df.dropna() |
|
|
|
scaler = StandardScaler() |
|
df_value_scaled = scaler.fit_transform(df) |
|
|
|
|
|
model = KMeans(n_clusters=n_clusters, random_state=42) |
|
model.fit(df_value_scaled) |
|
labels = model.predict(df_value_scaled) |
|
score = silhouette_score(df_value_scaled, labels) |
|
|
|
df['Cluster'] = labels |
|
return df, score, df_value_scaled, labels, model |
|
|
|
def plot_clusters(df_value_scaled, labels, new_data_point=None): |
|
pca = PCA(n_components=2) |
|
components = pca.fit_transform(df_value_scaled) |
|
df_components = pd.DataFrame(data=components, columns=['PC1', 'PC2']) |
|
df_components['Cluster'] = labels |
|
|
|
plt.figure(figsize=(10, 6)) |
|
sns.scatterplot(x='PC1', y='PC2', hue='Cluster', data=df_components, palette='viridis', s=100, alpha=0.7) |
|
|
|
|
|
if new_data_point is not None: |
|
plt.scatter(new_data_point[:, 0], new_data_point[:, 1], color='red', marker='o', s=100, label='New Data Point') |
|
|
|
plt.title('Cluster Visualization') |
|
plt.xlabel('Principal Component 1') |
|
plt.ylabel('Principal Component 2') |
|
plt.legend(title='Cluster') |
|
st.pyplot(plt) |
|
|