Update app.py

app.py

@@ -207,35 +207,67 @@ def load_kpis() -> Dict[str, Any]:
 
 
 # =========================================================
-# AI DASHBOARD -- LLM picks what to display
+# DATA LOADER FOR YOUR DATASET
 # =========================================================
 
-DASHBOARD_SYSTEM = """You are an AI dashboard assistant for a book-sales analytics app.
-The user asks questions or requests about their data. You have access to pre-computed
-artifacts from a Python analysis pipeline.
+def load_main_dataset() -> pd.DataFrame:
+    for candidate in [
+        BASE_DIR / "final_dataset.csv",
+        BASE_DIR / "datareal.csv",
+    ]:
+        if candidate.exists():
+            try:
+                if candidate.name == "datareal.csv":
+                    return pd.read_csv(candidate, sep=";")
+                return pd.read_csv(candidate)
+            except Exception:
+                pass
+    return pd.DataFrame()
 
-AVAILABLE ARTIFACTS (only reference ones that exist):
-{artifacts_json}
 
-KPI SUMMARY: {kpis_json}
+def load_kpis() -> Dict[str, Any]:
+    df = load_main_dataset()
+    if df.empty:
+        return {}
+
+    kpis = {
+        "n_rows": len(df),
+        "n_countries": df["COUNTRY"].nunique() if "COUNTRY" in df.columns else None,
+        "avg_job_satisfaction": round(df["AVG_JOB_SATISFACTION"].mean(), 2)
+            if "AVG_JOB_SATISFACTION" in df.columns else None,
+        "avg_income": round(df["MEAN_NET_INCOME"].mean(), 2)
+            if "MEAN_NET_INCOME" in df.columns else None,
+        "avg_work_life_balance": round(df["WORK_LIFE_BALANCE"].mean(), 2)
+            if "WORK_LIFE_BALANCE" in df.columns else None,
+        "avg_stress_level": round(df["STRESS_LEVEL"].mean(), 2)
+            if "STRESS_LEVEL" in df.columns else None,
+        "avg_weekly_hours": round(df["AVG_WEEKLY_WORKING_HOURS"].mean(), 2)
+            if "AVG_WEEKLY_WORKING_HOURS" in df.columns else None,
+    }
+
+    return {k: v for k, v in kpis.items() if v is not None}
 
-YOUR JOB:
-1. Answer the user's question conversationally using the KPIs and your knowledge of the artifacts.
-2. At the END of your response, output a JSON block (fenced with ```json ... ```) that tells
-   the dashboard which artifact to display. The JSON must have this shape:
-   {{"show": "figure"|"table"|"none", "scope": "python", "filename": "..."}}
 
-   - Use "show": "figure" to display a chart image.
-   - Use "show": "table" to display a CSV/JSON table.
-   - Use "show": "none" if no artifact is relevant.
+# =========================================================
+# AI DASHBOARD -- adapted to your dataset
+# =========================================================
 
-RULES:
-- If the user asks about sales trends or forecasting by title, show sales_trends or arima figures.
-- If the user asks about sentiment, show sentiment figure or sentiment_counts table.
-- If the user asks about forecast accuracy or ARIMA, show arima figures.
-- If the user asks about top sellers, show top_titles_by_units_sold.csv.
-- If the user asks a general data question, pick the most relevant artifact.
-- Keep your answer concise (2-4 sentences), then the JSON block.
+DASHBOARD_SYSTEM = """You are an AI dashboard assistant for a country-level job satisfaction analytics app.
+The dataset contains variables such as COUNTRY, AVG_JOB_SATISFACTION, WORK_LIFE_BALANCE,
+STRESS_LEVEL, MEAN_NET_INCOME, and AVG_WEEKLY_WORKING_HOURS.
+
+Your job:
+1. Answer the user's question briefly and clearly.
+2. At the end, output a JSON block inside ```json ... ``` with:
+{"show": "figure"|"table"|"none", "scope": "python", "filename": "..."}
+
+Use these filenames:
+- "job_satisfaction_by_country" for country ranking chart
+- "correlation_heatmap" for correlation chart
+- "income_vs_satisfaction" for scatter chart
+- "top_countries_table" for top countries table
+- "bottom_countries_table" for bottom countries table
+- "full_dataset_table" for full dataset preview
 """
 
 JSON_BLOCK_RE = re.compile(r"```json\s*(\{.*?\})\s*```", re.DOTALL)
@@ -259,34 +291,73 @@ def _parse_display_directive(text: str) -> Dict[str, str]:
 
 
 def _clean_response(text: str) -> str:
-    """Strip the JSON directive block from the displayed response."""
     return JSON_BLOCK_RE.sub("", text).strip()
 
 
-def _n8n_call(msg: str) -> Tuple[str, Dict]:
-    """Call the student's n8n webhook and return (reply, directive)."""
-    import requests as req
-    try:
-        resp = req.post(N8N_WEBHOOK_URL, json={"question": msg}, timeout=20)
-        data = resp.json()
-        answer = data.get("answer", "No response from n8n workflow.")
-        chart = data.get("chart", "none")
-        if chart and chart != "none":
-            return answer, {"show": "figure", "chart": chart}
-        return answer, {"show": "none"}
-    except Exception as e:
-        return f"n8n error: {e}. Falling back to keyword matching.", None
+def _keyword_fallback(msg: str, idx: Dict, kpis: Dict) -> Tuple[str, Dict]:
+    msg_lower = msg.lower()
+
+    if not kpis:
+        return (
+            "No dataset found yet. Please run the pipeline first.",
+            {"show": "none"},
+        )
+
+    summary = (
+        f"The dataset contains **{kpis.get('n_rows', '?')}** rows and "
+        f"**{kpis.get('n_countries', '?')}** countries. "
+        f"Average job satisfaction is **{kpis.get('avg_job_satisfaction', '?')}**."
+    )
+
+    if any(w in msg_lower for w in ["country", "countries", "ranking", "top countries", "bottom countries"]):
+        return (
+            f"Here is the country-level job satisfaction ranking. {summary}",
+            {"show": "figure", "filename": "job_satisfaction_by_country"},
+        )
+
+    if any(w in msg_lower for w in ["correlation", "heatmap", "relationship"]):
+        return (
+            f"Here is the correlation overview for the numeric variables. {summary}",
+            {"show": "figure", "filename": "correlation_heatmap"},
+        )
+
+    if any(w in msg_lower for w in ["income", "salary", "net income"]):
+        return (
+            f"Here is the relationship between income and job satisfaction. {summary}",
+            {"show": "figure", "filename": "income_vs_satisfaction"},
+        )
+
+    if any(w in msg_lower for w in ["top", "best", "highest"]):
+        return (
+            f"Here are the top countries by job satisfaction. {summary}",
+            {"show": "table", "scope": "python", "filename": "top_countries_table"},
+        )
+
+    if any(w in msg_lower for w in ["bottom", "lowest", "worst"]):
+        return (
+            f"Here are the bottom countries by job satisfaction. {summary}",
+            {"show": "table", "scope": "python", "filename": "bottom_countries_table"},
+        )
+
+    if any(w in msg_lower for w in ["overview", "summary", "dataset", "data", "kpi"]):
+        return (
+            f"Here is an overview of the dataset. {summary}",
+            {"show": "table", "scope": "python", "filename": "full_dataset_table"},
+        )
+
+    return (
+        f"{summary} Ask about country rankings, correlations, income effects, or top/bottom countries.",
+        {"show": "none"},
+    )
 
 
 def ai_chat(user_msg: str, history: list):
-    """Chat function for the AI Dashboard tab."""
     if not user_msg or not user_msg.strip():
         return history, "", None, None
 
     idx = artifacts_index()
     kpis = load_kpis()
 
-    # Priority: n8n webhook > HF LLM > keyword fallback
     if N8N_WEBHOOK_URL:
         reply, directive = _n8n_call(user_msg)
         if directive is None:
@@ -295,10 +366,7 @@ def ai_chat(user_msg: str, history: list):
     elif not LLM_ENABLED:
         reply, directive = _keyword_fallback(user_msg, idx, kpis)
     else:
-        system = DASHBOARD_SYSTEM.format(
-            artifacts_json=json.dumps(idx, indent=2),
-            kpis_json=json.dumps(kpis, indent=2) if kpis else "(no KPIs yet, run the pipeline first)",
-        )
+        system = DASHBOARD_SYSTEM
         msgs = [{"role": "system", "content": system}]
         for entry in (history or [])[-6:]:
             msgs.append(entry)
@@ -324,39 +392,26 @@ def ai_chat(user_msg: str, history: list):
             reply_fb, directive = _keyword_fallback(user_msg, idx, kpis)
             reply += "\n\n" + reply_fb
 
-    # Resolve artifacts — build interactive Plotly charts when possible
     chart_out = None
     tab_out = None
     show = directive.get("show", "none")
     fname = directive.get("filename", "")
-    chart_name = directive.get("chart", "")
-
-    # Interactive chart builders keyed by name
-    chart_builders = {
-        "sales": build_sales_chart,
-        "sentiment": build_sentiment_chart,
-        "top_sellers": build_top_sellers_chart,
-    }
 
-    if chart_name and chart_name in chart_builders:
-        chart_out = chart_builders[chart_name]()
-    elif show == "figure" and fname:
-        # Fallback: try to match filename to a chart builder
-        if "sales_trend" in fname:
-            chart_out = build_sales_chart()
-        elif "sentiment" in fname:
-            chart_out = build_sentiment_chart()
-        elif "arima" in fname or "forecast" in fname:
-            chart_out = build_sales_chart()  # closest interactive equivalent
-        else:
-            chart_out = _empty_chart(f"No interactive chart for {fname}")
-
-    if show == "table" and fname:
-        fp = PY_TAB_DIR / fname
-        if fp.exists():
-            tab_out = _load_table_safe(fp)
-        else:
-            reply += f"\n\n*(Could not find table: {fname})*"
+    if show == "figure":
+        if fname == "job_satisfaction_by_country":
+            chart_out = build_job_satisfaction_chart()
+        elif fname == "correlation_heatmap":
+            chart_out = build_correlation_chart()
+        elif fname == "income_vs_satisfaction":
+            chart_out = build_income_chart()
+
+    if show == "table":
+        if fname == "top_countries_table":
+            tab_out = get_top_countries_table()
+        elif fname == "bottom_countries_table":
+            tab_out = get_bottom_countries_table()
+        elif fname == "full_dataset_table":
+            tab_out = get_dataset_preview()
 
     new_history = (history or []) + [
         {"role": "user", "content": user_msg},
@@ -366,73 +421,8 @@ def ai_chat(user_msg: str, history: list):
     return new_history, "", chart_out, tab_out
 
 
-def _keyword_fallback(msg: str, idx: Dict, kpis: Dict) -> Tuple[str, Dict]:
-    """Simple keyword matcher when LLM is unavailable."""
-    msg_lower = msg.lower()
-
-    if not idx["python"]["figures"] and not idx["python"]["tables"]:
-        return (
-            "No artifacts found yet. Please run the pipeline first (Tab 1), "
-            "then come back here to explore the results.",
-            {"show": "none"},
-        )
-
-    kpi_text = ""
-    if kpis:
-        total = kpis.get("total_units_sold", 0)
-        kpi_text = (
-            f"Quick summary: **{kpis.get('n_titles', '?')}** book titles across "
-            f"**{kpis.get('n_months', '?')}** months, with **{total:,.0f}** total units sold."
-        )
-
-    if any(w in msg_lower for w in ["trend", "sales trend", "monthly sale"]):
-        return (
-            f"Here are the sales trends. {kpi_text}",
-            {"show": "figure", "chart": "sales"},
-        )
-
-    if any(w in msg_lower for w in ["sentiment", "review", "positive", "negative"]):
-        return (
-            f"Here is the sentiment distribution across sampled book titles. {kpi_text}",
-            {"show": "figure", "chart": "sentiment"},
-        )
-
-    if any(w in msg_lower for w in ["arima", "forecast", "predict"]):
-        return (
-            f"Here are the sales trends and forecasts. {kpi_text}",
-            {"show": "figure", "chart": "sales"},
-        )
-
-    if any(w in msg_lower for w in ["top", "best sell", "popular", "rank"]):
-        return (
-            f"Here are the top-selling titles by units sold. {kpi_text}",
-            {"show": "table", "scope": "python", "filename": "top_titles_by_units_sold.csv"},
-        )
-
-    if any(w in msg_lower for w in ["price", "pricing", "decision"]):
-        return (
-            f"Here are the pricing decisions. {kpi_text}",
-            {"show": "table", "scope": "python", "filename": "pricing_decisions.csv"},
-        )
-
-    if any(w in msg_lower for w in ["dashboard", "overview", "summary", "kpi"]):
-        return (
-            f"Dashboard overview: {kpi_text}\n\nAsk me about sales trends, sentiment, forecasts, "
-            "pricing, or top sellers to see specific visualizations.",
-            {"show": "table", "scope": "python", "filename": "df_dashboard.csv"},
-        )
-
-    # Default
-    return (
-        f"I can show you various analyses. {kpi_text}\n\n"
-        "Try asking about: **sales trends**, **sentiment**, **ARIMA forecasts**, "
-        "**pricing decisions**, **top sellers**, or **dashboard overview**.",
-        {"show": "none"},
-    )
-
-
 # =========================================================
-# KPI CARDS (BubbleBusters style)
+# KPI CARDS
 # =========================================================
 
 def render_kpi_cards() -> str:
@@ -465,10 +455,13 @@ def render_kpi_cards() -> str:
         </div>"""
 
     kpi_config = [
-        ("n_titles",         "📚", "Book Titles",  "#a48de8"),
-        ("n_months",         "📅", "Time Periods", "#7aa6f8"),
-        ("total_units_sold", "📦", "Units Sold",   "#6ee7c7"),
-        ("total_revenue",    "💰", "Revenue",      "#3dcba8"),
+        ("n_rows", "📄", "Rows", "#a48de8"),
+        ("n_countries", "🌍", "Countries", "#7aa6f8"),
+        ("avg_job_satisfaction", "😊", "Avg Job Satisfaction", "#6ee7c7"),
+        ("avg_income", "💰", "Avg Net Income", "#3dcba8"),
+        ("avg_work_life_balance", "⚖️", "Work-Life Balance", "#f4b942"),
+        ("avg_stress_level", "🔥", "Stress Level", "#ff6b6b"),
+        ("avg_weekly_hours", "⏱️", "Weekly Hours", "#8fa8f8"),
     ]
 
     html = (
@@ -479,28 +472,21 @@ def render_kpi_cards() -> str:
         val = kpis.get(key)
         if val is None:
             continue
-        if isinstance(val, (int, float)) and val > 100:
-            val = f"{val:,.0f}"
+        if isinstance(val, (int, float)):
+            val = f"{val:,.2f}" if abs(val) < 1000 else f"{val:,.0f}"
         html += card(icon, label, str(val), colour)
-    # Extra KPIs not in config
-    known = {k for k, *_ in kpi_config}
-    for key, val in kpis.items():
-        if key not in known:
-            label = key.replace("_", " ").title()
-            if isinstance(val, (int, float)) and val > 100:
-                val = f"{val:,.0f}"
-            html += card("📈", label, str(val), "#8fa8f8")
     html += "</div>"
     return html
 
 
 # =========================================================
-# INTERACTIVE PLOTLY CHARTS (BubbleBusters style)
+# INTERACTIVE PLOTLY CHARTS
 # =========================================================
 
 CHART_PALETTE = ["#7c5cbf", "#2ec4a0", "#e8537a", "#e8a230", "#5e8fef",
                  "#c45ea8", "#3dbacc", "#a0522d", "#6aaa3a", "#d46060"]
 
+
 def _styled_layout(**kwargs) -> dict:
     defaults = dict(
         template="plotly_white",
@@ -508,11 +494,6 @@ def _styled_layout(**kwargs) -> dict:
         plot_bgcolor="rgba(255,255,255,0.98)",
         font=dict(family="system-ui, sans-serif", color="#2d1f4e", size=12),
         margin=dict(l=60, r=20, t=70, b=70),
-        legend=dict(
-            orientation="h", yanchor="bottom", y=1.02, xanchor="right", x=1,
-            bgcolor="rgba(255,255,255,0.92)",
-            bordercolor="rgba(124,92,191,0.35)", borderwidth=1,
-        ),
         title=dict(font=dict(size=15, color="#4b2d8a")),
     )
     defaults.update(kwargs)
@@ -522,90 +503,181 @@ def _styled_layout(**kwargs) -> dict:
 def _empty_chart(title: str) -> go.Figure:
     fig = go.Figure()
     fig.update_layout(
-        title=title, height=420, template="plotly_white",
+        title=title,
+        height=420,
+        template="plotly_white",
         paper_bgcolor="rgba(255,255,255,0.95)",
-        annotations=[dict(text="Run the pipeline to generate data",
-            x=0.5, y=0.5, xref="paper", yref="paper", showarrow=False,
-            font=dict(size=14, color="rgba(124,92,191,0.5)"))],
+        annotations=[dict(
+            text="Run the pipeline to generate data",
+            x=0.5, y=0.5, xref="paper", yref="paper",
+            showarrow=False,
+            font=dict(size=14, color="rgba(124,92,191,0.5)")
+        )],
     )
     return fig
 
 
-def build_sales_chart() -> go.Figure:
-    path = PY_TAB_DIR / "df_dashboard.csv"
-    if not path.exists():
-        return _empty_chart("Sales Trends — run the pipeline first")
-    df = pd.read_csv(path)
-    date_col = next((c for c in df.columns if "month" in c.lower() or "date" in c.lower()), None)
-    val_cols = [c for c in df.columns if c != date_col and df[c].dtype in ("float64", "int64")]
-    if not date_col or not val_cols:
-        return _empty_chart("Could not auto-detect columns in df_dashboard.csv")
-    df[date_col] = pd.to_datetime(df[date_col], errors="coerce")
-    fig = go.Figure()
-    for i, col in enumerate(val_cols):
-        fig.add_trace(go.Scatter(
-            x=df[date_col], y=df[col], name=col.replace("_", " ").title(),
-            mode="lines+markers", line=dict(color=CHART_PALETTE[i % len(CHART_PALETTE)], width=2),
-            marker=dict(size=4),
-            hovertemplate=f"<b>{col.replace('_',' ').title()}</b><br>%{{x|%b %Y}}: %{{y:,.0f}}<extra></extra>",
-        ))
-    fig.update_layout(**_styled_layout(height=450, hovermode="x unified",
-                                        title=dict(text="Monthly Overview")))
-    fig.update_xaxes(gridcolor="rgba(124,92,191,0.15)", showgrid=True)
-    fig.update_yaxes(gridcolor="rgba(124,92,191,0.15)", showgrid=True)
-    return fig
+def build_job_satisfaction_chart() -> go.Figure:
+    df = load_main_dataset()
+    if df.empty or "COUNTRY" not in df.columns or "AVG_JOB_SATISFACTION" not in df.columns:
+        return _empty_chart("Job Satisfaction by Country — run the pipeline first")
 
+    plot_df = df[["COUNTRY", "AVG_JOB_SATISFACTION"]].sort_values(
+        "AVG_JOB_SATISFACTION", ascending=False
+    ).head(20)
+
+    fig = go.Figure(go.Bar(
+        x=plot_df["AVG_JOB_SATISFACTION"],
+        y=plot_df["COUNTRY"],
+        orientation="h",
+        marker=dict(color=plot_df["AVG_JOB_SATISFACTION"], colorscale="Viridis"),
+        hovertemplate="<b>%{y}</b><br>Job Satisfaction: %{x:.2f}<extra></extra>",
+    ))
 
-def build_sentiment_chart() -> go.Figure:
-    path = PY_TAB_DIR / "sentiment_counts_sampled.csv"
-    if not path.exists():
-        return _empty_chart("Sentiment Distribution — run the pipeline first")
-    df = pd.read_csv(path)
-    title_col = df.columns[0]
-    sent_cols = [c for c in ["negative", "neutral", "positive"] if c in df.columns]
-    if not sent_cols:
-        return _empty_chart("No sentiment columns found in CSV")
-    colors = {"negative": "#e8537a", "neutral": "#5e8fef", "positive": "#2ec4a0"}
-    fig = go.Figure()
-    for col in sent_cols:
-        fig.add_trace(go.Bar(
-            name=col.title(), y=df[title_col], x=df[col],
-            orientation="h", marker_color=colors.get(col, "#888"),
-            hovertemplate=f"<b>{col.title()}</b>: %{{x}}<extra></extra>",
-        ))
     fig.update_layout(**_styled_layout(
-        height=max(400, len(df) * 28), barmode="stack",
-        title=dict(text="Sentiment Distribution by Book"),
+        height=max(450, len(plot_df) * 28),
+        title=dict(text="Top Countries by Job Satisfaction"),
+        showlegend=False,
     ))
-    fig.update_xaxes(title="Number of Reviews")
     fig.update_yaxes(autorange="reversed")
+    fig.update_xaxes(title="Average Job Satisfaction")
     return fig
 
 
-def build_top_sellers_chart() -> go.Figure:
-    path = PY_TAB_DIR / "top_titles_by_units_sold.csv"
-    if not path.exists():
-        return _empty_chart("Top Sellers — run the pipeline first")
-    df = pd.read_csv(path).head(15)
-    title_col = next((c for c in df.columns if "title" in c.lower()), df.columns[0])
-    val_col = next((c for c in df.columns if "unit" in c.lower() or "sold" in c.lower()), df.columns[-1])
-    fig = go.Figure(go.Bar(
-        y=df[title_col], x=df[val_col], orientation="h",
-        marker=dict(color=df[val_col], colorscale=[[0, "#c5b4f0"], [1, "#7c5cbf"]]),
-        hovertemplate="<b>%{y}</b><br>Units: %{x:,.0f}<extra></extra>",
+def build_income_chart() -> go.Figure:
+    df = load_main_dataset()
+    needed = {"MEAN_NET_INCOME", "AVG_JOB_SATISFACTION", "COUNTRY"}
+    if df.empty or not needed.issubset(df.columns):
+        return _empty_chart("Income vs Job Satisfaction — run the pipeline first")
+
+    fig = go.Figure(go.Scatter(
+        x=df["MEAN_NET_INCOME"],
+        y=df["AVG_JOB_SATISFACTION"],
+        mode="markers+text",
+        text=df["COUNTRY"],
+        textposition="top center",
+        marker=dict(
+            size=10,
+            color=df["AVG_JOB_SATISFACTION"],
+            colorscale="Viridis",
+            showscale=True,
+        ),
+        hovertemplate="<b>%{text}</b><br>Income: %{x:,.0f}<br>Job Satisfaction: %{y:.2f}<extra></extra>",
     ))
+
     fig.update_layout(**_styled_layout(
-        height=max(400, len(df) * 30),
-        title=dict(text="Top Selling Titles"), showlegend=False,
+        height=500,
+        title=dict(text="Income vs Job Satisfaction"),
+    ))
+    fig.update_xaxes(title="Mean Net Income")
+    fig.update_yaxes(title="Average Job Satisfaction")
+    return fig
+
+
+def build_correlation_chart() -> go.Figure:
+    df = load_main_dataset()
+    if df.empty:
+        return _empty_chart("Correlation Heatmap — run the pipeline first")
+
+    num_df = df.select_dtypes(include=["number"])
+    if num_df.empty:
+        return _empty_chart("No numeric columns found")
+
+    corr = num_df.corr(numeric_only=True)
+
+    fig = go.Figure(data=go.Heatmap(
+        z=corr.values,
+        x=corr.columns,
+        y=corr.columns,
+        colorscale="RdBu",
+        zmin=-1,
+        zmax=1,
+        hovertemplate="X: %{x}<br>Y: %{y}<br>Corr: %{z:.2f}<extra></extra>",
+    ))
+
+    fig.update_layout(**_styled_layout(
+        height=600,
+        title=dict(text="Correlation Heatmap"),
     ))
-    fig.update_yaxes(autorange="reversed")
-    fig.update_xaxes(title="Total Units Sold")
     return fig
 
 
+def get_top_countries_table() -> pd.DataFrame:
+    df = load_main_dataset()
+    if df.empty or "COUNTRY" not in df.columns or "AVG_JOB_SATISFACTION" not in df.columns:
+        return pd.DataFrame([{"info": "No data available"}])
+    return df[["COUNTRY", "AVG_JOB_SATISFACTION"]].sort_values(
+        "AVG_JOB_SATISFACTION", ascending=False
+    ).head(10)
+
+
+def get_bottom_countries_table() -> pd.DataFrame:
+    df = load_main_dataset()
+    if df.empty or "COUNTRY" not in df.columns or "AVG_JOB_SATISFACTION" not in df.columns:
+        return pd.DataFrame([{"info": "No data available"}])
+    return df[["COUNTRY", "AVG_JOB_SATISFACTION"]].sort_values(
+        "AVG_JOB_SATISFACTION", ascending=True
+    ).head(10)
+
+
+def get_dataset_preview() -> pd.DataFrame:
+    df = load_main_dataset()
+    if df.empty:
+        return pd.DataFrame([{"info": "No data available"}])
+    return df.head(20)
+
+
 def refresh_dashboard():
-    return render_kpi_cards(), build_sales_chart(), build_sentiment_chart(), build_top_sellers_chart()
+    return (
+        render_kpi_cards(),
+        build_job_satisfaction_chart(),
+        build_correlation_chart(),
+        build_income_chart(),
+    )
+
+
+# =========================================================
+# GALLERY / TABLE REFRESH
+# =========================================================
+
+def refresh_gallery():
+    figures = _load_all_figures()
+
+    table_choices = []
+    if (BASE_DIR / "final_dataset.csv").exists():
+        table_choices.append("final_dataset.csv")
+    if (BASE_DIR / "datareal.csv").exists():
+        table_choices.append("datareal.csv")
+
+    default_df = pd.DataFrame()
+    if table_choices:
+        first_path = BASE_DIR / table_choices[0]
+        if first_path.name == "datareal.csv":
+            default_df = pd.read_csv(first_path, sep=";", nrows=MAX_PREVIEW_ROWS)
+        else:
+            default_df = pd.read_csv(first_path, nrows=MAX_PREVIEW_ROWS)
 
+    return (
+        figures if figures else [],
+        gr.update(choices=table_choices, value=table_choices[0] if table_choices else None),
+        default_df,
+    )
+
+
+def on_table_select(choice: str):
+    if not choice:
+        return pd.DataFrame([{"hint": "Select a table above."}])
+
+    path = BASE_DIR / choice
+    if not path.exists():
+        return pd.DataFrame([{"error": f"File not found: {choice}"}])
+
+    try:
+        if path.name == "datareal.csv":
+            return pd.read_csv(path, sep=";", nrows=MAX_PREVIEW_ROWS)
+        return pd.read_csv(path, nrows=MAX_PREVIEW_ROWS)
+    except Exception as e:
+        return pd.DataFrame([{"error": str(e)}])
 
 # =========================================================
 # UI
@@ -661,9 +733,9 @@ with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
         refresh_btn = gr.Button("Refresh Dashboard", variant="primary")
 
         gr.Markdown("#### Interactive Charts")
-        chart_sales = gr.Plot(label="Monthly Overview")
-        chart_sentiment = gr.Plot(label="Sentiment Distribution")
-        chart_top = gr.Plot(label="Top Sellers")
+        chart_sales = gr.Plot(label="Job Satisfaction by Country")
+        chart_sentiment = gr.Plot(label="Correlation Heatmap")
+        chart_top = gr.Plot(label="Income vs Job Satisfaction")
 
         gr.Markdown("#### Static Figures (from notebooks)")
         gallery = gr.Gallery(
@@ -729,12 +801,12 @@ with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
                 )
                 gr.Examples(
                     examples=[
-                        "Show me the sales trends",
-                        "What does the sentiment look like?",
-                        "Which titles sell the most?",
-                        "Show the ARIMA forecasts",
-                        "What are the pricing decisions?",
-                        "Give me a dashboard overview",
+                        "Show me the top countries by job satisfaction",
+                        "Show me the correlation heatmap",
+                        "How does income relate to job satisfaction?",
+                        "Which countries have the lowest job satisfaction?",
+                        "Give me a dataset overview",
+                        "Show me the top 10 countries",
                     ],
                     inputs=user_input,
                 )