Add app.py, backend, and model for HF Space

app.py

@@ -1,4 +1,148 @@
+import os
+import joblib
+import pandas as pd
 import streamlit as st
 
-st.title("✅ HF Space App Test")
-st.write("Hello! This Space is working.")
+NONE = None
+# from backend.train_model import train_model
+
+# Get the current directory of the Streamlit script
+# BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+#
+# # Build the absolute path to the model
+# # BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+# MODEL_PATH = os.path.join(BASE_DIR, "..", "models", "best_model.pkl")
+# REPORTS_DIR = os.path.join(BASE_DIR, "..", "reports")
+# PLOTS_DIR = os.path.join(REPORTS_DIR, "plots")
+MODEL_DIR = "backend/models"
+MODEL_FILE = "my_model.pkl"
+MODEL_PATH = os.path.join(MODEL_DIR, MODEL_FILE)
+
+REPORTS_DIR = "backend/reports"
+PLOTS_DIR = os.path.join(REPORTS_DIR, "plots")
+
+
+BACKEND_URL = os.getenv("BACKEND_URL", "http://backend:5000")
+
+st.set_page_config(page_title="Diabetes Prediction Dashboard", layout="wide")
+st.title("🩺 Diabetes Prediction Dashboard")
+
+# ---------- Sidebar ----------
+st.sidebar.header("Navigation")
+page = st.sidebar.radio("Go to", ["Predict", "Batch Predict", "Reports & Plots"])
+
+# ---------- Load best model ----------
+
+@st.cache_resource
+def load_model(path):
+    if os.path.exists(path):
+        model = joblib.load(path)
+        st.sidebar.success("✅ Best model loaded")
+        return model
+    else:
+        st.sidebar.error("❌ Best model not found. Run backend/train_model.py first.")
+        return None
+
+model = load_model(MODEL_PATH)
+
+# ---------- Features ----------
+FEATURES = [
+    "Pregnancies", "Glucose", "BloodPressure", "SkinThickness",
+    "Insulin", "BMI", "DiabetesPedigreeFunction", "Age"
+]
+
+def predict_df(df: pd.DataFrame):
+    """Run model prediction on a DataFrame"""
+    if model is None:
+        st.error("Model not loaded")
+        return None
+    missing = [c for c in FEATURES if c not in df.columns]
+    if missing:
+        st.error(f"Missing columns: {missing}")
+        return None
+    return model.predict(df[FEATURES])
+
+# ---------- Pages ----------
+if page == "Predict":
+    st.subheader("🔹 Single Prediction")
+
+    cols = st.columns(4)
+    values = {}
+    ranges = {
+        "Pregnancies": (0, 20, 1), "Glucose": (0, 220, 120),
+        "BloodPressure": (0, 150, 70), "SkinThickness": (0, 100, 20),
+        "Insulin": (0, 900, 80), "BMI": (0.0, 70.0, 25.0),
+        "DiabetesPedigreeFunction": (0.0, 3.0, 0.5), "Age": (0, 120, 30)
+    }
+
+    for i, f in enumerate(FEATURES):
+        with cols[i % 4]:
+            lo, hi, default = ranges[f]
+            if isinstance(default, float):
+                values[f] = st.number_input(f, lo, hi, float(default))
+            else:
+                values[f] = st.number_input(f, int(lo), int(hi), int(default))
+
+    if st.button("Predict"):
+        row = pd.DataFrame([values])
+        pred = predict_df(row)
+        if pred is not None:
+            st.success("✅ Diabetic" if int(pred[0]) == 1 else "🟢 Not Diabetic")
+
+elif page == "Batch Predict":
+    st.subheader("📂 Batch Prediction (Upload CSV)")
+    st.caption("CSV must include columns: " + ", ".join(FEATURES))
+
+    file = st.file_uploader("Upload CSV", type=["csv"])
+    if file is not None:
+        df = pd.read_csv(file)
+        st.write("Preview of uploaded data:")
+        st.dataframe(df.head())
+
+        preds = predict_df(df)
+        if preds is not None:
+            out = df.copy()
+            out["Prediction"] = preds
+            st.success(f"Predicted {len(out)} rows")
+            st.dataframe(out.head())
+
+            st.download_button(
+                "⬇️ Download predictions",
+                data=out.to_csv(index=False).encode('utf-8'),
+                file_name="predictions.csv",
+                mime="text/csv"
+            )
+
+elif page == "Reports & Plots":
+    st.subheader("📊 Model Comparison & Diagnostics")
+
+    # Table report
+    # cmp_path = os.path.join(REPORTS_DIR, "model_comparison.csv")
+    # if os.path.exists(cmp_path):
+    #     cmp_df = pd.read_csv(cmp_path)
+    #     st.dataframe(cmp_df)
+    # else:
+    #     st.warning("⚠️ model_comparison.csv not found. Run training.")
+
+    # Plots grid
+    plot_files = [
+        ("Accuracy (bar)", "model_accuracy.png"),
+        ("F1 (bar)", "model_f1.png"),
+        ("Confusion Matrix (best)", "confusion_matrix.png"),
+        ("ROC (best)", "roc_curve.png"),
+        ("Variance (before/after)", "variance_comparison.png"),
+        ("LR Loss vs Iterations", "logreg_loss_curves.png"),
+        ("LR Accuracy vs Iterations", "logreg_accuracy_curves.png"),
+    ]
+
+    rows = st.columns(2)
+    i = 0
+    for title, fname in plot_files:
+        p = os.path.join(PLOTS_DIR, fname)
+        if os.path.exists(p):
+            with rows[i % 2]:
+                st.markdown(f"**{title}**")
+                st.image(p, use_container_width=True)
+            i += 1
+        else:
+            st.info(f"{fname} not available yet.")