Upload 3 files

components/image_render_analysis.py

@@ -0,0 +1,95 @@
+import streamlit as st
+import pandas as pd
+from typing import Dict, Any
+
+
+def render_analyzer_results(result: Dict[str, Any]) -> None:
+    """Render AdAnalysis results in Streamlit UI (table format)."""
+
+    # --- Headline ---
+    if "copywriting_breakdown" in result:
+        headline = result["copywriting_breakdown"].get("headline", "Ad Analysis Result")
+        st.header(f" {headline}")
+
+    # --- Visual Layout ---
+    if "visual_structure_layout" in result:
+        st.subheader(" Visual Structure Layout")
+        vsl = result["visual_structure_layout"]
+
+        table_data = [
+            ["Background", vsl.get("background_color")],
+            ["Psychological Association", vsl.get("psychological_association")],
+            ["Minimalism Level", vsl.get("minimalism_level")],
+            ["Flow Summary", vsl.get("hierarchy", {}).get("flow_summary")],
+            ["Key Elements Order", ", ".join(vsl.get("hierarchy", {}).get("key_elements_order", []))],
+        ]
+        df = pd.DataFrame(table_data, columns=["Property", "Value"])
+        st.table(df)
+
+
+    # --- Psychological Triggers ---
+    if "psychological_behavioral_triggers" in result:
+        st.subheader(" Psychological & Behavioral Triggers")
+        df = pd.DataFrame(result["psychological_behavioral_triggers"].items(), columns=["Trigger", "Description"])
+        st.table(df)
+
+    # --- Storytelling ---
+    if "story_creative_tells" in result:
+        st.subheader(" Storytelling Elements")
+        df = pd.DataFrame(result["story_creative_tells"].items(), columns=["Element", "Content"])
+        st.table(df)
+
+    # --- Strengths & Weaknesses ---
+    if "strengths" in result or "weaknesses" in result:
+        col1, col2 = st.columns(2)
+
+        with col1:
+            st.subheader("Strengths")
+            strengths = result.get("strengths", [])
+            if strengths:
+                df = pd.DataFrame(strengths)
+                df.rename(columns={"point": "Point", "why_it_matters": "Why It Matters"}, inplace=True)
+                st.table(df)
+            else:
+                st.info("No strengths found.")
+
+        with col2:
+            st.subheader("Weaknesses")
+            weaknesses = result.get("weaknesses", [])
+            if weaknesses:
+                df = pd.DataFrame(weaknesses)
+                df.rename(columns={"point": "Point", "why_it_matters": "Why It Matters"}, inplace=True)
+                st.table(df)
+            else:
+                st.info("No weaknesses found.")
+
+    # --- Risks ---
+    if "risks_in_arbitrage_context" in result:
+        st.subheader(" Risks in Arbitrage Context")
+        df = pd.DataFrame(result["risks_in_arbitrage_context"].items(), columns=["Risk", "Level"])
+        st.table(df)
+
+    # --- Optimization Next Steps ---
+    if "optimization_next_steps" in result:
+        st.subheader(" Optimization Next Steps")
+        opt = result["optimization_next_steps"]
+
+        if "creative_variants" in opt:
+            st.markdown("**Creative Variants**")
+            df = pd.DataFrame(opt["creative_variants"])
+            df.rename(
+                columns={
+                    "hypothesis": "Hypothesis",
+                    "change": "Change",
+                    "expected_effect": "Expected Effect",
+                    "metric_to_watch": "Metric to Watch",
+                },
+                inplace=True,
+            )
+            st.table(df)
+
+
+
+    with st.expander(" Raw JSON Result", expanded=False):
+        st.json(result)
+

components/render_analysis.py

@@ -1,5 +1,6 @@
 import json, pandas as pd, streamlit as st
 from typing import Dict, Any
+from helpers_function.helpers import _mean_effectiveness
 
 def _normalize_list(v):
     if v is None: return []
@@ -14,14 +15,6 @@ def _to_dataframe(items, columns_map):
     ordered_cols = [columns_map[k] for k in columns_map.keys() if columns_map[k] in df.columns]
     return df.reindex(columns=ordered_cols)
 
-def _mean_effectiveness(metrics):
-    if not metrics: return 0.0
-    scores = []
-    for m in metrics:
-        s = str(m.get("effectiveness_score", "0/10")).split("/")[0]
-        try: scores.append(int(s))
-        except Exception: pass
-    return round(sum(scores) / len(scores), 2) if scores else 0.0
 
 def _search_dataframe(df, query):
     if not query or df.empty: return df
@@ -130,11 +123,11 @@ def render_analyzer_results(analysis: Dict[str, Any]) -> None:
 
 
     with tabs[4]:
-        pretty = json.dumps(analysis, indent=2, ensure_ascii=False)
-        st.code(pretty, language="json")
+        res = json.dumps(analysis, indent=2, ensure_ascii=False)
+        st.code(res, language="json")
         st.download_button(
             "Download JSON",
-            data=pretty.encode("utf-8"),
+            data=res.encode("utf-8"),
             file_name="ad_analysis.json",
             mime="application/json",
             use_container_width=True