Create app.py

app.py

@@ -0,0 +1,100 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.preprocessing import StandardScaler, MinMaxScaler
+from sklearn.decomposition import PCA
+from sklearn.cluster import KMeans, AgglomerativeClustering, DBSCAN
+from sklearn.metrics import silhouette_score
+import joblib
+import matplotlib.pyplot as plt
+
+# Function to load and process data (including PCA)
+def process_data(file, scaler_option):
+    df = pd.read_csv(file)
+    features = ['RI4', 'RI5', 'RI7', 'RI9']
+    df_selected = df[features].fillna(df.mean())
+    
+    # Apply chosen scaler
+    if scaler_option == 'StandardScaler':
+        scaler = StandardScaler()
+    elif scaler_option == 'MinMaxScaler':
+        scaler = MinMaxScaler()
+
+    scaled_data = scaler.fit_transform(df_selected)
+    
+    # PCA Transformation (2 components for visualization)
+    pca = PCA(n_components=2)
+    pca_data = pca.fit_transform(scaled_data)
+    
+    return pca_data
+
+# Set up the Streamlit page
+st.title("Clustering Analysis with K-means, Hierarchical, and DBSCAN Models")
+
+# Upload the detectors report CSV file
+data_file = st.file_uploader("Upload the detectors report file (.csv)", type="csv")
+
+# Upload the models
+kmeans_model = st.file_uploader("Upload the K-means model (.sav)", type="sav")
+hierarchical_model = st.file_uploader("Upload the Hierarchical Clustering model (.sav)", type="sav")
+dbscan_model = st.file_uploader("Upload the DBSCAN model (.sav)", type="sav")
+
+# Parameter selection for K-means, Hierarchical Clustering, and DBSCAN
+if data_file is not None:
+    st.sidebar.header("Adjust Clustering Parameters")
+
+    # Scaler selection
+    scaler_option = st.sidebar.selectbox("Choose Scaler", ("StandardScaler", "MinMaxScaler"))
+
+    # K-means parameters
+    kmeans_clusters = st.sidebar.slider("K-means: Number of Clusters", min_value=2, max_value=10, value=3)
+    
+    # Hierarchical Clustering parameters
+    hierarchical_clusters = st.sidebar.slider("Hierarchical: Number of Clusters", min_value=2, max_value=10, value=3)
+    linkage = st.sidebar.selectbox("Hierarchical: Linkage Method", ["ward", "complete", "average", "single"])
+    
+    # DBSCAN parameters
+    dbscan_eps = st.sidebar.number_input("DBSCAN: Epsilon", min_value=0.1, max_value=10.0, value=0.5, step=0.1)
+    dbscan_min_samples = st.sidebar.slider("DBSCAN: Minimum Samples", min_value=1, max_value=20, value=5)
+    
+    # Load and process the data
+    pca_data = process_data(data_file, scaler_option)
+
+    # Prepare the plot
+    fig, ax = plt.subplots(1, 3, figsize=(15, 5))
+    ax = ax.flatten()
+
+    # K-means Clustering
+    if kmeans_model is not None:
+        kmeans = joblib.load(kmeans_model)
+        kmeans.set_params(n_clusters=kmeans_clusters)
+        kmeans_labels = kmeans.fit_predict(pca_data)
+        ax[0].scatter(pca_data[:, 0], pca_data[:, 1], c=kmeans_labels, cmap='viridis')
+        ax[0].set_title(f"K-means Clustering (n_clusters={kmeans_clusters})")
+    else:
+        ax[0].set_title("K-means Model Missing")
+    
+    # Hierarchical Clustering
+    if hierarchical_model is not None:
+        hierarchical = joblib.load(hierarchical_model)
+        hierarchical.set_params(n_clusters=hierarchical_clusters, linkage=linkage)
+        hierarchical_labels = hierarchical.fit_predict(pca_data)
+        ax[1].scatter(pca_data[:, 0], pca_data[:, 1], c=hierarchical_labels, cmap='viridis')
+        ax[1].set_title(f"Hierarchical Clustering (n_clusters={hierarchical_clusters}, linkage={linkage})")
+    else:
+        ax[1].set_title("Hierarchical Model Missing")
+    
+    # DBSCAN Clustering
+    if dbscan_model is not None:
+        dbscan = joblib.load(dbscan_model)
+        dbscan.set_params(eps=dbscan_eps, min_samples=dbscan_min_samples)
+        dbscan_labels = dbscan.fit_predict(pca_data)
+        ax[2].scatter(pca_data[:, 0], pca_data[:, 1], c=dbscan_labels, cmap='viridis')
+        ax[2].set_title(f"DBSCAN Clustering (eps={dbscan_eps}, min_samples={dbscan_min_samples})")
+    else:
+        ax[2].set_title("DBSCAN Model Missing")
+
+    # Display the plots
+    st.pyplot(fig)
+else:
+    st.info("Please upload the detectors report file to proceed.")