Update src/streamlit_app.py

src/streamlit_app.py

@@ -10,6 +10,8 @@ import streamlit as st
 import matplotlib.pyplot as plt
 import seaborn as sns
 import joblib
+import zipfile
+import io
 
 # ML imports
 from sklearn.model_selection import train_test_split
@@ -29,37 +31,36 @@ import shap
 # -------------------------
 st.set_page_config(page_title="Steel Authority of India Limited (MODEX)", layout="wide")
 
-# Base ephemeral paths (no Hugging Face data mount)
+# Base directory and persistent logs
 BASE_DIR = "./"
-
 LOG_DIR = os.path.join(BASE_DIR, "logs")
-DATA_DIR = os.path.join(LOG_DIR, "data_ephemeral")
-os.makedirs(DATA_DIR, exist_ok=True)
 os.makedirs(LOG_DIR, exist_ok=True)
 
-# Timestamped log file
-timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
-LOG_PATH = os.path.join(LOG_DIR, f"run_{timestamp}.log")
+# Timestamped run subfolder
+run_id = datetime.now().strftime("%Y%m%d_%H%M%S")
+RUN_DIR = os.path.join(LOG_DIR, f"run_{run_id}")
+os.makedirs(RUN_DIR, exist_ok=True)
+
+# File paths for this run
+CSV_PATH = os.path.join(RUN_DIR, "flatfile_universe_advanced.csv")
+META_PATH = os.path.join(RUN_DIR, "feature_metadata_advanced.json")
+ENSEMBLE_ARTIFACT = os.path.join(RUN_DIR, "ensemble_models.joblib")
+LOG_PATH = os.path.join(RUN_DIR, "run.log")
 
 def log(msg: str):
-    """Log message with timestamp to /logs/ for ephemeral HF runs."""
     with open(LOG_PATH, "a", encoding="utf-8") as f:
-        f.write(f"[{datetime.now().strftime('%Y-%m-%d %H:%M:%S')}] {msg}\n")
+        f.write(f"[{datetime.now():%Y-%m-%d %H:%M:%S}] {msg}\n")
     print(msg)
 
-log(" Streamlit session started.")
-log(f"Python PID={os.getpid()} | Time={datetime.now().isoformat()}")
-log(f"Data Dir = {DATA_DIR} | Log Dir = {LOG_DIR}")
-CSV_PATH = os.path.join(DATA_DIR, "flatfile_universe_advanced.csv")
-META_PATH = os.path.join(DATA_DIR, "feature_metadata_advanced.json")
-ENSEMBLE_ARTIFACT = os.path.join(DATA_DIR, "ensemble_models.joblib")
+log(f" Streamlit session started | run_id={run_id}")
+log(f"Run directory: {RUN_DIR}")
 
 
 # Confirm storage mount
 if os.path.exists("/data"):
-    st.sidebar.success(f" Using persistent storage: {DATA_DIR}")
+    st.sidebar.success(f" Using persistent storage | Run directory: {RUN_DIR}")
 else:
-    st.sidebar.warning(f" Using ephemeral storage: {DATA_DIR}. Data will be lost on rebuild.")
+    st.sidebar.warning(f" Using ephemeral storage | Run directory: {RUN_DIR}. Data will be lost on rebuild.")
 
 
 # -------------------------
@@ -85,7 +86,7 @@ def generate_advanced_flatfile(
         variance_overrides: dict mapping feature name or substring → stddev multiplier
     """
     np.random.seed(random_seed)
-    os.makedirs(DATA_DIR, exist_ok=True)
+    os.makedirs(RUN_DIR, exist_ok=True)
     if variance_overrides is None:
         variance_overrides = {}
 
@@ -771,7 +772,7 @@ with tabs[4]:
                 st.pyplot(fig)
                 
                 # Save trained stack artifacts
-                stack_artifact = os.path.join(DATA_DIR, f"stacked_{use_case.replace(' ', '_')}.joblib")
+                stack_artifact = os.path.join(RUN_DIR, f"stacked_{use_case.replace(' ', '_')}.joblib")
                 to_save = {
                     "base_models": {bm["family"]: bm["model"] for bm in base_models if bm["family"] in selected},
                     "meta": meta,
@@ -904,10 +905,52 @@ in metallurgical AI modeling. Click any title to open the official paper.
 # -------------------------
 st.markdown("---")
 st.markdown("**Notes:** This dataset is synthetic and for demo/prototyping. Real plant integration requires NDA, data on-boarding, sensor mapping, and plant safety checks before any control actions.")
+
+# -----  Download tab
+tabs.append("Download Saved Runs")
+with tabs[-1]:
+    st.subheader("Reproducibility & Run Exports")
+
+    run_folders = sorted(
+        [f for f in os.listdir(LOG_DIR) if f.startswith("run_")],
+        reverse=True
+    )
+
+    if not run_folders:
+        st.info("No completed runs found yet.")
+    else:
+        selected_run = st.selectbox("Select run folder", run_folders, index=0)
+        selected_path = os.path.join(LOG_DIR, selected_run)
+
+        # Show contained files
+        files = [
+            f for f in os.listdir(selected_path)
+            if os.path.isfile(os.path.join(selected_path, f))
+        ]
+        st.write(f"Files in `{selected_run}`:")
+        st.write(", ".join(files))
+
+        # Zip the folder in-memory for download
+        zip_buffer = io.BytesIO()
+        with zipfile.ZipFile(zip_buffer, "w", zipfile.ZIP_DEFLATED) as zipf:
+            for root, _, filenames in os.walk(selected_path):
+                for fname in filenames:
+                    file_path = os.path.join(root, fname)
+                    zipf.write(file_path, arcname=os.path.relpath(file_path, selected_path))
+        zip_buffer.seek(0)
+
+        st.download_button(
+            label=f"Download full run ({selected_run}.zip)",
+            data=zip_buffer,
+            file_name=f"{selected_run}.zip",
+            mime="application/zip"
+        )
+
+
 # -----  Logs tab
 tabs.append("View Logs")
 with tabs[-1]:
-    st.subheader("📜 Session & Model Logs")
+    st.subheader(" Session & Model Logs")
     st.markdown("Each run creates a timestamped log file in `/logs/` inside this Space. Use this panel to review run progress and debug output.")
 
     log_files = sorted(
@@ -923,4 +966,4 @@ with tabs[-1]:
         with open(path, "r", encoding="utf-8") as f:
             content = f.read()
         st.text_area("Log Output", content, height=400)
-        st.download_button("⬇️ Download Log", content, file_name=latest)
+        st.download_button(" Download Log", content, file_name=latest)