Update app.py

app.py

@@ -1,5 +1,52 @@
-# --- MotherDuck Connection ---
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+import duckdb
+import os
+
+# --- Set page layout ---
+st.set_page_config(layout="wide", page_title="Sentiment Analysis")
+
+# --- CSS for Flag Toggle ---
+st.markdown("""
+    <style>
+    .flag-container { display: flex; justify-content: center; gap: 10px; }
+    .flag { cursor: pointer; width: 40px; height: 30px; }
+    </style>
+""", unsafe_allow_html=True)
+
+# --- State & Language ---
+flag_selection = st.radio("", ["🇬🇧", "🇧🇬"], horizontal=True, label_visibility="collapsed")
+LANG = "English" if flag_selection == "🇬🇧" else "Български"
+
+T = {
+    "English": {
+        "title": "📊 Sentiment Analysis Dashboard",
+        "select_entities": "Select Entities",
+        "select_domains": "Select Domains",
+        "score_type": "Select Score Type",
+        "group_by_domain": "Group by Domain",
+        "all_scores": "Show All Score Types",
+        "no_data": "No data matches the selected filters.",
+        "avg_over_time": "Average {} Over Time",
+        "scores_over_time": "Sentiment Scores Over Time",
+        "select_entities_prompt": "Please select at least one entity."
+    },
+    "Български": {
+        "title": "📊 Табло за анализ на настроенията",
+        "select_entities": "Изберете обекти",
+        "select_domains": "Изберете източници",
+        "score_type": "Изберете тип оценка",
+        "group_by_domain": "Групирай по сайт",
+        "all_scores": "Покажи всички типове оценки",
+        "no_data": "Няма данни за избраните филтри.",
+        "avg_over_time": "Средна стойност на {} във времето",
+        "scores_over_time": "Оценки на настроенията във времето",
+        "select_entities_prompt": "Моля, изберете поне един обект."
+    }
+}
 
+# --- MotherDuck Connection ---
 @st.cache_resource
 def get_connection():
     try:
@@ -11,17 +58,20 @@ def get_connection():
 
 con = get_connection()
 
-# --- Cached Metadata for Filters ---
+# --- Metadata for Filters ---
 @st.cache_data(ttl=600)
 def get_filter_options():
-    # Fast counts via DuckDB
-    entities = con.sql("SELECT entity, COUNT(*) as c FROM sentiment_analysis GROUP BY 1 ORDER BY c DESC").df()
-    domains = con.sql("SELECT domain, COUNT(*) as c FROM sentiment_analysis GROUP BY 1 ORDER BY c DESC").df()
+    # Trim and count for cleaner lookups
+    entities = con.sql("SELECT trim(entity) as entity, COUNT(*) as c FROM sentiment_analysis GROUP BY 1 ORDER BY c DESC").df()
+    domains = con.sql("SELECT trim(domain) as domain, COUNT(*) as c FROM sentiment_analysis GROUP BY 1 ORDER BY c DESC").df()
     return entities, domains
+
+df_entities, df_domains = get_filter_options()
+
+# --- Sidebar ---
 st.title(T[LANG]["title"])
 
 with st.sidebar:
-    # Create lookup dictionaries to avoid filtering dataframes in the lambda (prevents crashes)
     entity_lookup = dict(zip(df_entities['entity'], df_entities['c']))
     domain_lookup = dict(zip(df_domains['domain'], df_domains['c']))
 
@@ -38,32 +88,59 @@ with st.sidebar:
     )
 
     score_type = st.selectbox(T[LANG]["score_type"], ["entity_score", "title_score", "overall_score"])
+    group_by_domain = st.checkbox(T[LANG]["group_by_domain"])
+    all_scores = st.checkbox(T[LANG]["all_scores"])
+    
+    timeframes = {"All": 9999, "Last 7 Days": 7, "Last 30 Days": 30, "Last Year": 365}
+    time_choice = st.selectbox("Timeframe", list(timeframes.keys()))
+
+# --- Logic: Stop if no selection ---
+if not selected_entities:
     st.info(T[LANG]["select_entities_prompt"])
     st.stop()
 
-# Dynamic SQL construction
+# --- Dynamic Granularity Logic (Targeting ~50 points) ---
+days = timeframes[time_choice]
+if days <= 50:
+    bucket = "1 day"
+elif days <= 365:
+    bucket = "1 week"
+else:
+    bucket = "1 month"
+
+# --- Query Building ---
 where_clause = f"WHERE entity IN ({str(selected_entities)[1:-1]})"
 if selected_domains:
     where_clause += f" AND domain IN ({str(selected_domains)[1:-1]})"
 if time_choice != "All":
-    where_clause += f" AND created_at >= (epoch(now()) - {timeframes[time_choice] * 86400})"
-
+    where_clause += f" AND created_at >= (epoch(now()) - {days * 86400})"
 
 if all_scores:
-
     sql_query = f"""
     SELECT 
-        time_bucket(interval '1 day', created_at) as date,
+        time_bucket(interval '{bucket}', created_at) as date,
         entity,
         domain,
         score_name as score_type,
+        AVG(score_value) as score
+    FROM (
+        UNPIVOT sentiment_analysis 
+        ON entity_score, title_score, overall_score
+        INTO NAME score_name VALUE score_value
+    )
+    {where_clause}
+    GROUP BY ALL
+    """
 else:
     sql_query = f"""
     SELECT 
-        time_bucket(interval '1 day', created_at) as date,
+        time_bucket(interval '{bucket}', created_at) as date,
         entity,
         domain,
         AVG({score_type}) as score
+    FROM sentiment_analysis
+    {where_clause}
+    GROUP BY ALL
     """
 
 # --- Execution & Plotting ---
@@ -76,31 +153,34 @@ except Exception as e:
 if filtered_df.empty:
     st.warning(T[LANG]["no_data"])
 else:
-    # Build dynamic labels for the legend
+    # Build legend labels
     color_col = "entity"
     if group_by_domain:
         filtered_df["label"] = filtered_df["entity"] + " | " + filtered_df["domain"]
         color_col = "label"
     
     if all_scores:
-        current_label = filtered_df["label"] if group_by_domain else filtered_df["entity"]
-        filtered_df["label"] = current_label + " | " + filtered_df["score_type"]
+        current_base = filtered_df["label"] if group_by_domain else filtered_df["entity"]
+        filtered_df["label"] = current_base + " | " + filtered_df["score_type"]
         color_col = "label"
 
+    # Plot
     fig = px.line(
         filtered_df.sort_values("date"),
         x="date", y="score", color=color_col,
-        title=T[LANG]["scores_over_time"] if all_scores else T[LANG]["avg_over_time"].format(score_type.replace('_', ' ').title()),
-        labels={"score": "Sentiment Score", "date": "Date", "label": "Entity/Source"}
+        title=f"{T[LANG]['scores_over_time']} (Grouped by {bucket})",
+        labels={"score": "Score", "date": "Date"}
     )
 
-    # Styling
+    # Layout styling
     fig.update_layout(
         yaxis=dict(range=[-10, 10], gridcolor="lightgrey"),
         plot_bgcolor="white",
         legend=dict(orientation="h", y=-0.2, x=0.5, xanchor="center")
     )
     
-    # Static horizontal reference lines
+    # Reference lines
     for val in [-5, 0, 5]:
-        fig.add_hline(y=val, line_width=2 if val==0 else 1, line_dash="dash", line_color="black")
+        fig.add_hline(y=val, line_width=2 if val==0 else 1, line_dash="dash", line_color="black")
+
+    st.plotly_chart(fig, use_container_width=True)