modified code and added dataset

.gitignore

@@ -0,0 +1,2 @@
+.env
+venv/

app.py

@@ -0,0 +1,87 @@
+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
+from sklearn.decomposition import PCA
+
+# Load dataset
+st.title("Customer Segmentation App")
+
+# File uploader
+dataset_file = st.file_uploader("Upload your CSV file", type=["csv"])
+
+if dataset_file is not None:
+    df = pd.read_csv(dataset_file)
+    st.write("### Preview of Uploaded Data:")
+    st.dataframe(df.head())
+    
+    # Drop rows with missing values in the entire dataset
+    df.dropna(inplace=True)
+    
+    # Select features for clustering
+    st.write("### Select Features for Clustering")
+    selected_features = st.multiselect("Choose features", df.columns.tolist(), default=df.columns.tolist())
+    
+    if selected_features:
+        data = df[selected_features]
+        
+        # Identify categorical and numerical features
+        categorical_cols = data.select_dtypes(include=['object']).columns.tolist()
+        numerical_cols = data.select_dtypes(include=['number']).columns.tolist()
+        
+        # Encode categorical features
+        if categorical_cols:
+            encoder = OneHotEncoder(drop='first', sparse_output=False, handle_unknown='ignore')
+            encoded_cats = encoder.fit_transform(data[categorical_cols])
+            encoded_cats_df = pd.DataFrame(encoded_cats, columns=encoder.get_feature_names_out(categorical_cols))
+            data = pd.concat([data[numerical_cols].reset_index(drop=True), encoded_cats_df], axis=1)
+        
+        # Standardize data
+        scaler = StandardScaler()
+        scaled_data = scaler.fit_transform(data)
+        
+        # Ensure no NaN values exist after transformations
+        if np.isnan(scaled_data).any():
+            st.error("Data contains NaN values even after preprocessing. Please check your dataset.")
+        else:
+            # Determine number of clusters using Elbow Method
+            st.write("### Elbow Method for Optimal K")
+            distortions = []
+            K_range = range(1, 11)
+            for k in K_range:
+                kmeans = KMeans(n_clusters=k, random_state=42, n_init=10)
+                kmeans.fit(scaled_data)
+                distortions.append(kmeans.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')
+            st.pyplot(fig)
+            
+            # Choose number of clusters
+            k = st.slider("Select Number of Clusters", min_value=2, max_value=10, value=3)
+            
+            # Apply K-Means
+            kmeans = KMeans(n_clusters=k, random_state=42, n_init=10)
+            df['Cluster'] = kmeans.fit_predict(scaled_data)
+            
+            st.write("### Clustered Data")
+            st.dataframe(df.head())
+            
+            # PCA for visualization
+            pca = PCA(n_components=2)
+            pca_result = pca.fit_transform(scaled_data)
+            df['PCA1'] = pca_result[:, 0]
+            df['PCA2'] = pca_result[:, 1]
+            
+            # Scatter plot of clusters
+            st.write("### Cluster Visualization (PCA)")
+            fig, ax = plt.subplots()
+            sns.scatterplot(x='PCA1', y='PCA2', hue='Cluster', palette='viridis', data=df, ax=ax)
+            ax.set_title("Customer Segmentation (PCA Visualization)")
+            st.pyplot(fig)

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+pandas
+numpy
+matplotlib
+seaborn
+scikit-learn