1

app.py

@@ -0,0 +1,93 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from sklearn.cluster import KMeans
+import matplotlib.pyplot as plt
+
+# App Title
+st.title("Unsupervised Learning: K-Means Clustering")
+
+# Sidebar Section: Tab for downloading a sample dataset
+st.sidebar.subheader("Sample Dataset")
+st.sidebar.write("Download a sample dataset to test the app. This sample contains two numerical features for demonstration purposes.")
+sample_data = {
+    "Feature1": [1.0, 1.5, 3.0, 5.0, 3.5, 4.5, 3.5],
+    "Feature2": [1.0, 2.0, 4.0, 7.0, 5.0, 5.0, 4.5],
+}
+sample_df = pd.DataFrame(sample_data)
+sample_csv = sample_df.to_csv(index=False)
+st.sidebar.download_button(
+    label="Download Sample CSV",
+    data=sample_csv,
+    file_name="sample_data.csv",
+    mime="text/csv"
+)
+
+# Main Section: Upload dataset
+st.header("Step 1: Upload Your Dataset")
+st.write("Upload a CSV file containing your data. Ensure it includes numerical features for clustering.")
+uploaded_file = st.file_uploader("Upload your dataset (CSV format)", type="csv")
+if uploaded_file:
+    data = pd.read_csv(uploaded_file)
+    st.write("Preview of the uploaded data:")
+    st.dataframe(data)
+
+    # Step 2: Select features for clustering
+    st.subheader("Step 2: Feature Selection")
+    st.write("Select the numerical features you want to use for clustering.")
+    selected_features = st.multiselect(
+        "Select features for clustering:", data.columns.tolist()
+    )
+
+    if selected_features:
+        X = data[selected_features]
+
+        # Step 3: Configure clustering parameters
+        st.subheader("Step 3: Clustering Configuration")
+        st.write("Choose the number of clusters you want to create using the slider below.")
+        n_clusters = st.slider("Select the number of clusters:", min_value=2, max_value=10, value=3)
+
+        # Apply K-Means Clustering
+        model = KMeans(n_clusters=n_clusters, random_state=42)
+        cluster_labels = model.fit_predict(X)
+
+        # Step 4: Add cluster labels to the dataset
+        data['Cluster'] = cluster_labels
+        st.write("Clustered Data:")
+        st.dataframe(data)
+
+        # Step 5: Visualize the clusters
+        st.subheader("Step 5: Cluster Visualization")
+        st.write("Visualize the clustering results. Select at least two features for plotting.")
+        if len(selected_features) >= 2:
+            fig, ax = plt.subplots()
+            scatter = ax.scatter(
+                X[selected_features[0]],
+                X[selected_features[1]],
+                c=cluster_labels,
+                cmap="viridis",
+                s=50
+            )
+            ax.set_xlabel(selected_features[0])
+            ax.set_ylabel(selected_features[1])
+            ax.set_title("K-Means Clustering")
+            legend = ax.legend(*scatter.legend_elements(), title="Clusters")
+            ax.add_artist(legend)
+            st.pyplot(fig)
+        else:
+            st.warning("Select at least 2 features for visualization.")
+
+        # Step 6: Download the clustered data
+        st.subheader("Step 6: Download Clustered Data")
+        st.write("Download the dataset with the cluster labels added.")
+        csv = data.to_csv(index=False)
+        st.download_button(
+            label="Download CSV",
+            data=csv,
+            file_name="clustered_data.csv",
+            mime="text/csv"
+        )
+    else:
+        st.warning("Please select features for clustering.")
+else:
+    st.info("Awaiting file upload. Use the sample dataset in the sidebar if you don’t have a file.")

requirements.txt

@@ -0,0 +1,4 @@
+streamlit
+pandas
+scikit-learn
+matplotlib