final

app.py

@@ -0,0 +1,152 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+import matplotlib.pyplot as plt
+import seaborn as sns
+from sklearn.cluster import KMeans
+from sklearn.preprocessing import StandardScaler, OneHotEncoder, LabelEncoder
+from sklearn.pipeline import Pipeline
+from sklearn.metrics import silhouette_score, davies_bouldin_score, calinski_harabasz_score
+
+st.title("Sales Trend Prediction using KMeans Clustering")
+
+def load_data():
+    return pd.read_csv("shopping_trends.csv")
+
+df = load_data()
+
+# Select relevant features for clustering
+features = ['Gender', 'Item Purchased', 'Previous Purchases', 'Frequency of Purchases', 'Purchase Amount (USD)']
+df_filtered = df[features].copy()
+
+# Convert Frequency of Purchases to string
+df_filtered['Frequency of Purchases'] = df_filtered['Frequency of Purchases'].astype(str)
+
+# One-hot encode categorical features
+categorical_features = ['Gender', 'Item Purchased', 'Frequency of Purchases']
+numerical_features = ['Previous Purchases', 'Purchase Amount (USD)']
+
+ohe = OneHotEncoder(drop='first', sparse_output=False)
+encoded_cats = ohe.fit_transform(df_filtered[categorical_features])
+categorical_df = pd.DataFrame(encoded_cats, columns=ohe.get_feature_names_out(categorical_features), index=df.index)
+
+df_processed = pd.concat([df_filtered[numerical_features], categorical_df], axis=1)
+
+# Standardizing the data
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(df_processed)
+
+# KMeans Clustering
+n_clusters = 3  # Set the number of clusters
+kmeans = KMeans(n_clusters=n_clusters, random_state=42)
+df['Cluster'] = kmeans.fit_predict(X_scaled)
+
+# Compute Clustering Metrics
+silhouette = silhouette_score(X_scaled, df['Cluster'])
+davies_bouldin = davies_bouldin_score(X_scaled, df['Cluster'])
+calinski_harabasz = calinski_harabasz_score(X_scaled, df['Cluster'])
+
+def predict_cluster(user_input):
+    """Predicts the cluster for a new user input."""
+    user_df = pd.DataFrame([user_input])
+    user_df['Frequency of Purchases'] = user_df['Frequency of Purchases'].astype(str)
+    user_cats = ohe.transform(user_df[categorical_features])
+    user_processed = pd.concat([user_df[numerical_features], pd.DataFrame(user_cats, columns=ohe.get_feature_names_out(categorical_features))], axis=1)
+    user_scaled = scaler.transform(user_processed)
+    return kmeans.predict(user_scaled)[0]
+
+# Create Tabs
+tab1, tab2, tab3 = st.tabs(["Dataset & Metrics", "Visualization", "Sales Trend Prediction"])
+
+with tab1:
+    st.subheader("Dataset Preview")
+    st.write(df.head())
+    
+    st.subheader("Clustering Metrics")
+    st.write(f"Number of Clusters: {n_clusters}")
+    st.write(f"Silhouette Score: {silhouette:.4f}")
+    st.write(f"Davies-Bouldin Score: {davies_bouldin:.4f}")
+    st.write(f"Calinski-Harabasz Score: {calinski_harabasz:.4f}")
+
+with tab2:
+    st.subheader("Data Visualizations")
+    
+    # Elbow Method Visualization
+    distortions = []
+    K_range = range(2, 11)
+    for k in K_range:
+        kmeans_tmp = KMeans(n_clusters=k, random_state=42)
+        kmeans_tmp.fit(X_scaled)
+        distortions.append(kmeans_tmp.inertia_)
+    
+    fig, ax = plt.subplots()
+    ax.plot(K_range, distortions, marker='o')
+    ax.set_xlabel('Number of Clusters')
+    ax.set_ylabel('Distortion')
+    ax.set_title('Elbow Method for Optimal K')
+    st.pyplot(fig)
+    
+    # Cluster Distribution Plot
+    fig, ax = plt.subplots()
+    sns.countplot(x=df['Cluster'], palette='viridis', ax=ax)
+    ax.set_xlabel('Cluster')
+    ax.set_ylabel('Count')
+    ax.set_title('Cluster Distribution')
+    st.pyplot(fig)
+    
+    # Visualizations for Item Purchased distribution
+    fig, ax = plt.subplots(figsize=(10, 5))
+    sns.countplot(y=df['Item Purchased'], order=df['Item Purchased'].value_counts().index, palette='viridis', ax=ax)
+    ax.set_title("Overall Item Purchase Distribution")
+    ax.set_xlabel("Count")
+    ax.set_ylabel("Item Purchased")
+    st.pyplot(fig)
+    
+    # Heatmap for Matrix Visualization
+    st.subheader("Feature Correlation Matrix")
+    label_encoders = {}
+    for col in categorical_features:
+        le = LabelEncoder()
+        df[col + '_Numeric'] = le.fit_transform(df[col])
+        label_encoders[col] = le
+    
+    correlation_matrix = df[['Gender_Numeric', 'Purchase Amount (USD)', 'Previous Purchases', 'Frequency of Purchases_Numeric']].corr()
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', ax=ax)
+    st.pyplot(fig)
+
+with tab3:
+    st.subheader("Enter Customer Details")
+    gender = st.selectbox("Gender", df['Gender'].unique())
+    item_purchased = st.selectbox("Item Purchased", df['Item Purchased'].unique())
+    previous_purchases = st.number_input("Previous Purchases", min_value=0, max_value=100, value=10)
+    frequency_of_purchases = st.selectbox("Frequency of Purchases", df['Frequency of Purchases'].unique().astype(str))
+    purchase_amount = st.number_input("Purchase Amount (USD)", min_value=1, max_value=500, value=50)
+
+    if st.button("Predict Sales Trend"):
+        user_input = {
+            'Gender': gender,
+            'Item Purchased': item_purchased,
+            'Previous Purchases': previous_purchases,
+            'Frequency of Purchases': frequency_of_purchases,
+            'Purchase Amount (USD)': purchase_amount
+        }
+        
+        predicted_cluster = predict_cluster(user_input)
+        st.write(f"Predicted Cluster: {predicted_cluster}")
+        
+        st.subheader(f"Sales Trend Analysis for Cluster {predicted_cluster}")
+        cluster_data = df[df['Cluster'] == predicted_cluster]
+        
+        # Visualization of top-selling items in the cluster
+        fig, ax = plt.subplots(figsize=(10, 5))
+        sns.countplot(y=cluster_data['Item Purchased'], order=cluster_data['Item Purchased'].value_counts().index, palette='viridis', ax=ax)
+        ax.set_title("Top Selling Items in This Cluster")
+        ax.set_xlabel("Count")
+        ax.set_ylabel("Item Purchased")
+        st.pyplot(fig)
+        
+        # Display average purchase amount trend
+        avg_purchase_amount = cluster_data.groupby('Item Purchased')['Purchase Amount (USD)'].mean()
+        st.write("### Average Purchase Amount for Items in This Cluster:")
+        st.write(avg_purchase_amount)

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+numpy
+matplotlib.pyplot
+seaborn
+scilkt-learn