changes

app.py

@@ -0,0 +1,103 @@
+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 AgglomerativeClustering
+from sklearn.metrics import confusion_matrix
+
+# Load dataset
+@st.cache_data
+def load_data():
+    file_path = "car_price_dataset.csv"  # Ensure this file is in the same directory
+    return pd.read_csv(file_path)
+
+df = load_data()
+
+# Streamlit App Title
+st.title("🚗 Car Price Clustering & Evaluation")
+
+# Creating Tabs
+tab1, tab2, tab3 = st.tabs(["📊 Dataset Overview", "📈 Visual Matrix", "⚙️ User Input for Clustering"])
+
+# --- TAB 1: Dataset Overview ---
+with tab1:
+    st.write("## Dataset Overview")
+    st.write(df.head())
+    st.write(df.describe())
+
+# --- TAB 2: Visualization Matrix ---
+with tab2:
+    st.write("## Data Visualization")
+
+    # Select numerical features
+    numerical_df = df.select_dtypes(include=[np.number])
+
+    # Correlation Heatmap
+    st.write("### Correlation Heatmap")
+    fig, ax = plt.subplots(figsize=(8, 5))
+    sns.heatmap(numerical_df.corr(), annot=True, cmap="coolwarm", fmt=".2f")
+    st.pyplot(fig)
+
+    # Confusion Matrix
+    st.write("### Confusion Matrix")
+    selected_features = ["Engine_Size", "Mileage", "Price"]
+    if all(f in numerical_df.columns for f in selected_features):
+        X = df[selected_features].dropna().values
+        n_clusters = 3  # Default cluster count
+
+        # Apply Hierarchical Clustering
+        hc = AgglomerativeClustering(n_clusters=n_clusters, linkage='ward')
+        labels = hc.fit_predict(X)
+
+        # Generate dummy "true labels" (for demonstration)
+        true_labels = np.random.randint(0, n_clusters, len(labels))
+
+        cm = confusion_matrix(true_labels, labels)
+        fig, ax = plt.subplots(figsize=(5, 4))
+        sns.heatmap(cm, annot=True, cmap="Blues", fmt="d")
+        plt.xlabel("Predicted")
+        plt.ylabel("Actual")
+        st.pyplot(fig)
+    else:
+        st.warning("Not enough numerical data for clustering.")
+
+    # Scatter Plot
+    st.write("### Scatter Plot")
+    scatter_x = st.selectbox("Select X-axis", numerical_df.columns, index=0)
+    scatter_y = st.selectbox("Select Y-axis", numerical_df.columns, index=1)
+
+    fig, ax = plt.subplots(figsize=(6, 4))
+    sns.scatterplot(x=df[scatter_x], y=df[scatter_y], alpha=0.7)
+    plt.xlabel(scatter_x)
+    plt.ylabel(scatter_y)
+    st.pyplot(fig)
+
+# --- TAB 3: User Input & Clustering ---
+with tab3:
+    st.write("## Perform Clustering")
+
+    numerical_features = numerical_df.columns.tolist()
+    selected_features = st.multiselect("Select features for clustering", numerical_features, default=["Engine_Size", "Mileage", "Price"])
+
+    if len(selected_features) < 2:
+        st.warning("Please select at least two numerical features.")
+    else:
+        X = df[selected_features].dropna().values  # Prepare data
+
+        # Choose Number of Clusters (With + / - Buttons)
+        n_clusters = st.number_input("Select Number of Clusters", min_value=2, max_value=10, value=3, step=1)
+
+        # Predict Button
+        if st.button("Predict Clusters"):
+            # Apply Hierarchical Clustering
+            hc = AgglomerativeClustering(n_clusters=n_clusters, linkage='ward')
+            labels = hc.fit_predict(X)
+
+            # Display results
+            df["Cluster"] = labels
+            st.write("### Clustered Data")
+            st.write(df[selected_features + ["Cluster"]].head(10))
+
+            st.success("Clustering Complete! 🎉")
+ 

requirements.txt

@@ -0,0 +1,6 @@
+streamlit
+panda
+numpy
+matplotlib
+scipy
+scikit-learn