Update app.py

app.py

@@ -1,6 +1,5 @@
 # app.py — Streamlit radar charts from MongoDB (scores 0–1)
 import os
-import json
 from datetime import date
 from typing import Dict, List
 
@@ -52,24 +51,13 @@ def safe_mean(vals):
     vals = [v for v in vals if v is not None]
     return float(np.mean(vals)) if vals else 0.0
 
-
 def to_frame(records: List[dict]) -> pd.DataFrame:
-    if not records:
-        return pd.DataFrame()
-    df = pd.DataFrame(records)
-    # Expand skills into columns in SKILLS order
-    skill_df = pd.json_normalize(df.get("skills", {})).reindex(columns=SKILLS)
-    for k in SKILLS:
-        if k not in skill_df:
-            skill_df[k] = 0.0
-    df = pd.concat([df.drop(columns=["skills"], errors="ignore"), skill_df], axis=1)
-    return df
-
+    # Records are returned already flattened with skill columns
+    return pd.DataFrame(records) if records else pd.DataFrame()
 
 def aggregate_groups_row(row: pd.Series) -> Dict[str, float]:
     return {g: safe_mean([float(row.get(s, 0.0)) for s in members]) for g, members in SKILL_GROUPS.items()}
 
-
 def summarize(records: List[dict], level: str = "student") -> pd.DataFrame:
     """Average per label over SKILLS; level in {student, student+source}."""
     df = to_frame(records)
@@ -79,8 +67,11 @@ def summarize(records: List[dict], level: str = "student") -> pd.DataFrame:
         df["label"] = df["student"].astype(str) + " — " + df["source"].astype(str)
     else:
         df["label"] = df["student"].astype(str)
-    return df.groupby("label")[SKILLS].mean().reset_index()
-
+    # ensure missing skill columns exist (safety)
+    for k in SKILLS:
+        if k not in df:
+            df[k] = 0.0
+    return df.groupby("label", dropna=False)[SKILLS].mean(numeric_only=True).reset_index()
 
 def plot_radar(df: pd.DataFrame, grouped: bool, title: str):
     if df.empty:
@@ -123,10 +114,8 @@ def plot_radar(df: pd.DataFrame, grouped: bool, title: str):
     )
     return fig
 
-
 # ------------------- Mongo Access (secrets-only) -------------------
 def _get_secret(name: str) -> str | None:
-    # Prefer Streamlit secrets, fallback to env vars
     try:
         val = st.secrets.get(name)
         if val is not None:
@@ -135,7 +124,6 @@ def _get_secret(name: str) -> str | None:
         pass
     return os.getenv(name)
 
-
 def _build_uri(db_name: str | None) -> str | None:
     user = _get_secret("MONGO_USER")
     pw = _get_secret("MONGO_PASS")
@@ -145,19 +133,15 @@ def _build_uri(db_name: str | None) -> str | None:
     user_q = quote_plus(user)
     pw_q = quote_plus(pw)
     db_path = f"/{db_name}" if db_name else ""
-    # TLS flags help on some hosts; SRV requires dnspython (present on Streamlit Cloud)
     return (
         f"mongodb+srv://{user_q}:{pw_q}@{cluster}{db_path}"
         f"?retryWrites=true&w=majority&tls=true&tlsAllowInvalidCertificates=true"
     )
 
-
 @st.cache_resource(show_spinner=False)
 def _client(uri: str):
-    # Use a cached client resource (not cache_data) for connections
     return MongoClient(uri, serverSelectionTimeoutMS=10000)
 
-
 @st.cache_data(show_spinner=False)
 def mongo_distinct(uri: str, db: str, coll: str, field: str) -> List[str]:
     if not uri:
@@ -169,7 +153,6 @@ def mongo_distinct(uri: str, db: str, coll: str, field: str) -> List[str]:
     except Exception:
         return []
 
-
 @st.cache_data(show_spinner=False)
 def mongo_records(
     uri: str,
@@ -180,6 +163,7 @@ def mongo_records(
     start: str | None,
     end: str | None,
 ) -> List[dict]:
+    """Return FLAT rows: student, source, date, and one column per skill (0–1 floats)."""
     if not uri:
         return []
     q = {}
@@ -196,25 +180,33 @@ def mongo_records(
     try:
         c = _client(uri)
         proj = {"_id": 0, "student": 1, "source": 1, "date": 1, "skills": 1}
-        out = list(c[db][coll].find(q, proj))
-        # normalize scores to floats; default 0.0
-        for r in out:
-            r.setdefault("skills", {})
-            r["skills"] = {k: float(r["skills"].get(k, 0.0)) for k in SKILLS}
-        return out
+        docs = list(c[db][coll].find(q, proj))
+        rows = []
+        for d in docs:
+            base = {
+                "student": str(d.get("student", "")),
+                "source": str(d.get("source", "")),
+                "date": str(d.get("date", "")),
+            }
+            sd = d.get("skills") or {}
+            for k in SKILLS:
+                try:
+                    base[k] = float(sd.get(k, 0.0))
+                except Exception:
+                    base[k] = 0.0
+            rows.append(base)
+        return rows
     except Exception:
         return []
 
-
 # ------------------- UI -------------------
-st.title("📊 Student Skill Radar")
+st.title("📊 Student Skill Radar — MongoDB (secrets-based)")
 
 with st.sidebar:
     st.subheader("MongoDB Settings")
     db_name = st.text_input("Database name", value="student_skills")
     coll_name = st.text_input("Collection name", value="responses_IFE_2025")
 
-    # Build from MONGO_USER / MONGO_PASS / MONGO_CLUSTER only
     mongo_uri = _build_uri(db_name)
 
     if not mongo_uri:
@@ -261,9 +253,11 @@ with right:
     if df.empty:
         st.info("No data. Adjust filters or check Mongo connection.")
     else:
-        st.dataframe(df, use_container_width=True, height=450)
+        # Removed the table per your request
         csv = df.to_csv(index=False).encode("utf-8")
         st.download_button("Download CSV", data=csv, file_name="skill_scores.csv", mime="text/csv")
+        st.caption(f"{len(df)} line(s) aggregated.")
+
 
 
 # # app.py