Spaces:
Sleeping
Sleeping
Download src/streamlit_app.py from EnYa32/AppUserClustering: direct link, hf CLI and curl.
- Browser
- Download file 5.21 kB
-
https://huggingface.co/spaces/EnYa32/AppUserClustering/resolve/main/src/streamlit_app.py
- Command line
-
hf download hf://spaces/EnYa32/AppUserClustering/src/streamlit_app.py
-
curl -L -o streamlit_app.py https://huggingface.co/spaces/EnYa32/AppUserClustering/resolve/main/src/streamlit_app.py
5.21 kB
| import streamlit as st | |
| import pandas as pd | |
| import numpy as np | |
| import joblib | |
| import matplotlib.pyplot as plt | |
| from sklearn.decomposition import PCA | |
| st.set_page_config(page_title="KMeans User Segmentation", layout="centered") | |
| st.title("π₯ KMeans User Segmentation") | |
| st.write("Upload a CSV or enter values manually to assign users into **KMeans clusters**.") | |
| # ----------------------------- | |
| # Load artifacts | |
| # ----------------------------- | |
| def load_artifacts(): | |
| model = joblib.load("src/kmeans_user_segmentation.pkl") | |
| scaler = joblib.load("src/scaler.pkl") | |
| return model, scaler | |
| model, scaler = load_artifacts() | |
| st.success("Model + scaler loaded successfully β ") | |
| # ----------------------------- | |
| # Feature columns used in training | |
| # ----------------------------- | |
| FEATURES = [ | |
| "Average Screen Time", | |
| "Average Spent on App (INR)", | |
| "Ratings", | |
| "Last Visited Minutes", | |
| "New Password Request", | |
| ] | |
| # ----------------------------- | |
| # Sidebar options | |
| # ----------------------------- | |
| st.sidebar.header("βοΈ Options") | |
| input_mode = st.sidebar.radio("Input method", ["Upload CSV", "Manual Input"]) | |
| show_pca = st.sidebar.checkbox("Show PCA 2D plot (based on input data)", value=True) | |
| # ----------------------------- | |
| # Helper: validate + prepare | |
| # ----------------------------- | |
| def prepare_features(df: pd.DataFrame) -> pd.DataFrame: | |
| missing = [c for c in FEATURES if c not in df.columns] | |
| if missing: | |
| raise ValueError(f"Missing columns: {missing}") | |
| X = df[FEATURES].copy() | |
| # Make sure numeric | |
| for c in FEATURES: | |
| X[c] = pd.to_numeric(X[c], errors="coerce") | |
| if X.isna().any().any(): | |
| bad_cols = X.columns[X.isna().any()].tolist() | |
| raise ValueError(f"Non-numeric or missing values found in: {bad_cols}. Please clean your CSV.") | |
| return X | |
| # ----------------------------- | |
| # Input: CSV | |
| # ----------------------------- | |
| df = None | |
| if input_mode == "Upload CSV": | |
| uploaded = st.file_uploader("Upload CSV", type=["csv"]) | |
| if uploaded is None: | |
| st.info("Upload a CSV to start.") | |
| else: | |
| df = pd.read_csv(uploaded) | |
| st.subheader("π Data Preview") | |
| st.dataframe(df.head()) | |
| # ----------------------------- | |
| # Input: Manual | |
| # ----------------------------- | |
| else: | |
| st.info("Manual input is best for quick testing. For real segmentation, use CSV upload.") | |
| n = st.slider("Number of users (rows)", 1, 20, 5) | |
| rows = [] | |
| for i in range(n): | |
| st.markdown(f"### User {i+1}") | |
| c1, c2 = st.columns(2) | |
| screen_time = c1.number_input("Average Screen Time", min_value=0.0, value=10.0, key=f"st_{i}") | |
| spent = c2.number_input("Average Spent on App (INR)", min_value=0.0, value=100.0, key=f"sp_{i}") | |
| c3, c4 = st.columns(2) | |
| ratings = c3.number_input("Ratings", min_value=0.0, value=7.0, key=f"ra_{i}") | |
| last_visit = c4.number_input("Last Visited Minutes", min_value=0.0, value=1000.0, key=f"lv_{i}") | |
| pwd_req = st.number_input("New Password Request", min_value=0.0, value=1.0, key=f"pw_{i}") | |
| rows.append([screen_time, spent, ratings, last_visit, pwd_req]) | |
| df = pd.DataFrame(rows, columns=FEATURES) | |
| st.subheader("π Manual Data") | |
| st.dataframe(df) | |
| # ----------------------------- | |
| # Predict | |
| # ----------------------------- | |
| if df is not None and len(df) > 0: | |
| try: | |
| X = prepare_features(df) | |
| X_scaled = scaler.transform(X) | |
| clusters = model.predict(X_scaled) | |
| out = df.copy() | |
| out["cluster"] = clusters | |
| st.subheader("β Cluster Results") | |
| st.dataframe(out.head(20)) | |
| st.subheader("π Cluster Distribution") | |
| st.write(out["cluster"].value_counts().sort_index()) | |
| # Cluster profile (means) | |
| st.subheader("π Cluster Profile (mean values)") | |
| profile = out.groupby("cluster")[FEATURES].mean(numeric_only=True).round(2) | |
| st.dataframe(profile) | |
| # Simple bar chart for profile | |
| st.subheader("π Average Feature Values per Cluster") | |
| fig, ax = plt.subplots(figsize=(9, 4)) | |
| profile.plot(kind="bar", ax=ax) | |
| ax.set_xlabel("Cluster") | |
| ax.set_ylabel("Mean value") | |
| ax.legend(loc="best") | |
| st.pyplot(fig) | |
| # PCA plot (optional) | |
| if show_pca and len(out) >= 3: | |
| pca = PCA(n_components=2, random_state=42) | |
| X_pca = pca.fit_transform(X_scaled) | |
| st.subheader("π§ PCA 2D Projection (Input Data)") | |
| fig2, ax2 = plt.subplots(figsize=(6, 5)) | |
| sc = ax2.scatter(X_pca[:, 0], X_pca[:, 1], c=clusters) | |
| ax2.set_title("KMeans Clusters (PCA Projection)") | |
| ax2.set_xlabel("PC1") | |
| ax2.set_ylabel("PC2") | |
| st.pyplot(fig2) | |
| # Download results | |
| st.subheader("β¬οΈ Download") | |
| csv = out.to_csv(index=False).encode("utf-8") | |
| st.download_button("Download results CSV", csv, file_name="clustered_users.csv", mime="text/csv") | |
| st.info("Tip: Clustering is unsupervised β clusters are groups with similar behavior patterns, not 'correct/incorrect' labels.") | |
| except Exception as e: | |
| st.error(str(e)) | |
| st.stop() |