Enhanced Visualisation Changes

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 import numpy as np
 import datetime as dt
 from sklearn.cluster import KMeans
+from sklearn.decomposition import PCA
 import matplotlib.pyplot as plt
 import seaborn as sns
 import plotly.express as px
@@ -130,6 +131,30 @@ fig_cluster = px.scatter_3d(
 )
 st.plotly_chart(fig_cluster)
 
+#Enhanced RFM Analysis
+st.header("📊 Enhanced RFM Analysis")
+
+# Interactive RFM Heatmap
+heatmap_data = rfm[["Recency", "Frequency", "Monetary", "Cluster"]].groupby("Cluster").mean()
+fig, ax = plt.subplots(figsize=(10, 6))
+sns.heatmap(heatmap_data, annot=True, fmt=".1f", cmap="coolwarm", cbar=True, ax=ax)
+ax.set_title("Average RFM Values per Cluster", fontsize=16)
+st.pyplot(fig)
+
+# Animated RFM Scatter
+st.subheader("📈 Animated RFM Scatter Plot")
+fig_rfm_animated = px.scatter_3d(
+    rfm,
+    x="Recency",
+    y="Frequency",
+    z="Monetary",
+    color="Cluster",
+    animation_frame="Cluster",  # Add animation based on clusters
+    title="RFM Clusters Over Time",
+    size="Monetary",
+)
+st.plotly_chart(fig_rfm_animated)
+
 # Product Recommendation
 st.header("🎯 Product Recommendations")
 
@@ -173,6 +198,27 @@ if st.button("Recommend for Cluster"):
     except KeyError:
         st.warning("The selected product is not in the vocabulary for this cluster.")
 
+# PCA to visualize Word2Vec embeddings
+st.subheader("📊 Word2Vec Embedding Visualization")
+vectors = model.wv[model.wv.key_to_index.keys()]  # Product vectors
+pca = PCA(n_components=2)
+pca_result = pca.fit_transform(vectors)
+
+# Create DataFrame for visualization
+embedding_df = pd.DataFrame(pca_result, columns=["PCA1", "PCA2"])
+embedding_df["Product"] = model.wv.key_to_index.keys()
+
+# Interactive Plot
+fig_embed = px.scatter(
+    embedding_df,
+    x="PCA1",
+    y="PCA2",
+    hover_data=["Product"],
+    title="Word2Vec Product Embeddings",
+    template="plotly_dark",
+)
+st.plotly_chart(fig_embed)
+
 # Export Data
 st.header("📤 Export Processed Data")
 if st.button("Export RFM Data"):