add ability to group by question text (#2)

- add ability to group by question text (443384fa02a3fa8384ecd9404799d4ba76d6cd74)

app.py

@@ -37,14 +37,16 @@ df = get_data()
 # Streamlit UI
 st.title("🌍 CGD Survey Explorer (Live DB)")
 
-# Multiselect filters (defaults = empty, shows all if none selected)
+st.sidebar.header("🔎 Filter Questions")
+
+# Multiselect filters with default = show all
 country_options = sorted(df["country"].dropna().unique())
 year_options = sorted(df["year"].dropna().unique())
 
 selected_countries = st.sidebar.multiselect("Select Country/Countries", country_options)
 selected_years = st.sidebar.multiselect("Select Year(s)", year_options)
-
 keyword = st.sidebar.text_input("Keyword Search", "")
+group_by_question = st.sidebar.checkbox("Group by Question Text")
 
 # Apply filters
 filtered = df[
@@ -53,21 +55,44 @@ filtered = df[
     (df["question_text"].str.contains(keyword, case=False, na=False))
 ]
 
-# Generate dynamic subheading
-heading_parts = []
-if selected_countries:
-    heading_parts.append("Countries: " + ", ".join(selected_countries))
-if selected_years:
-    heading_parts.append("Years: " + ", ".join(map(str, selected_years)))
-if heading_parts:
-    st.markdown("### Results for " + " | ".join(heading_parts))
+# Output
+if group_by_question:
+    st.subheader("📊 Grouped by Question Text")
+
+    grouped = (
+        filtered.groupby("question_text")
+        .agg({
+            "country": lambda x: sorted(set(x)),
+            "year": lambda x: sorted(set(x)),
+            "answer_text": lambda x: list(x)[:3]  # preview up to 3 answers
+        })
+        .reset_index()
+        .rename(columns={
+            "country": "Countries",
+            "year": "Years",
+            "answer_text": "Sample Answers"
+        })
+    )
+
+    st.dataframe(grouped)
+
+    if grouped.empty:
+        st.info("No questions found with current filters.")
+
 else:
-    st.markdown("### Results for All Countries and Years")
+    # Context-aware heading
+    heading_parts = []
+    if selected_countries:
+        heading_parts.append("Countries: " + ", ".join(selected_countries))
+    if selected_years:
+        heading_parts.append("Years: " + ", ".join(map(str, selected_years)))
+    if heading_parts:
+        st.markdown("### Results for " + " | ".join(heading_parts))
+    else:
+        st.markdown("### Results for All Countries and Years")
 
-# Display results including answer_text
-st.dataframe(filtered[["country", "year", "question_text", "answer_text"]])
+    st.dataframe(filtered[["country", "year", "question_text", "answer_text"]])
 
-# Empty result message
-if filtered.empty:
-    st.info("No matching questions found.")
+    if filtered.empty:
+        st.info("No matching questions found.")