Update app.py

app.py

@@ -7,9 +7,10 @@ from pathlib import Path
 from typing import Dict, Any, List, Tuple
 
 import pandas as pd
+import numpy as np
+import plotly.graph_objects as go
 import gradio as gr
 import papermill as pm
-import plotly.graph_objects as go
 
 # Optional LLM (HuggingFace Inference API)
 try:
@@ -102,7 +103,6 @@ def run_notebook(nb_name: str) -> str:
     )
     return f"Executed {nb_name}"
 
-
 def run_datacreation() -> str:
     try:
         log = run_notebook(NB1)
@@ -111,7 +111,6 @@ def run_datacreation() -> str:
     except Exception as e:
         return f"FAILED  {e}\n\n{traceback.format_exc()[-2000:]}"
 
-
 def run_pythonanalysis() -> str:
     try:
         log = run_notebook(NB2)
@@ -126,93 +125,130 @@ def run_pythonanalysis() -> str:
     except Exception as e:
         return f"FAILED  {e}\n\n{traceback.format_exc()[-2000:]}"
 
-
 def run_full_pipeline() -> str:
     logs = []
     logs.append("=" * 50)
-    logs.append("STEP 1/2: Data Creation (web scraping + synthetic data)")
+    logs.append("STEP 1/2: Data Creation & Synthetic Enrichment")
     logs.append("=" * 50)
     logs.append(run_datacreation())
     logs.append("")
     logs.append("=" * 50)
-    logs.append("STEP 2/2: Python Analysis (sentiment, ARIMA, dashboard)")
+    logs.append("STEP 2/2: Salary Analysis & Predictions")
     logs.append("=" * 50)
     logs.append(run_pythonanalysis())
     return "\n".join(logs)
 
-
 # =========================================================
-# GALLERY LOADERS
+# SALARY PREDICTION (inline — no Flask needed)
 # =========================================================
 
-def _load_all_figures() -> List[Tuple[str, str]]:
-    """Return list of (filepath, caption) for Gallery."""
-    items = []
-    for p in sorted(PY_FIG_DIR.glob("*.png")):
-        items.append((str(p), p.stem.replace('_', ' ').title()))
-    return items
-
-
-def _load_table_safe(path: Path) -> pd.DataFrame:
-    try:
-        if path.suffix == ".json":
-            obj = _read_json(path)
-            if isinstance(obj, dict):
-                return pd.DataFrame([obj])
-            return pd.DataFrame(obj)
-        return _read_csv(path)
-    except Exception as e:
-        return pd.DataFrame([{"error": str(e)}])
-
-
-def refresh_gallery():
-    """Called when user clicks Refresh on Gallery tab."""
-    figures = _load_all_figures()
-    idx = artifacts_index()
-
-    table_choices = list(idx["python"]["tables"])
-
-    default_df = pd.DataFrame()
-    if table_choices:
-        default_df = _load_table_safe(PY_TAB_DIR / table_choices[0])
-
-    return (
-        figures if figures else [],
-        gr.update(choices=table_choices, value=table_choices[0] if table_choices else None),
-        default_df,
+def get_experience_group(exp: float) -> str:
+    if exp <= 5:    return "0-5 years"
+    elif exp <= 10: return "6-10 years"
+    elif exp <= 15: return "11-15 years"
+    elif exp <= 20: return "16-20 years"
+    else:           return "20+"
+
+def get_career_tier(age: float, exp: float, edu: str) -> str:
+    edu_score = {"Bachelor's": 1, "Master's": 2, "PhD": 3}.get(edu, 1)
+    if exp >= 15 and edu_score >= 2: return "senior"
+    elif exp >= 7 or edu_score == 3: return "mid"
+    else:                            return "junior"
+
+def predict_salary_formula(age: float, exp: float, edu: str, job_title: str, gender: str) -> Tuple[float, str, str, str]:
+    """
+    Rule-based salary estimator aligned with the Random Forest model logic.
+    Returns (predicted_salary, career_tier, experience_group, explanation)
+    """
+    tier = get_career_tier(age, exp, edu)
+    exp_group = get_experience_group(exp)
+
+    edu_bonus = {"Bachelor's": 0, "Master's": 8000, "PhD": 18000}.get(edu, 0)
+    tier_bonus = {"junior": 0, "mid": 15000, "senior": 35000}.get(tier, 0)
+    base = 25000 + (age * 1100) + (exp * 4200) + edu_bonus + tier_bonus
+
+    # Job title keyword bonus
+    job_lower = job_title.lower()
+    if any(k in job_lower for k in ["director", "vp", "chief", "head"]):
+        base += 30000
+    elif any(k in job_lower for k in ["manager", "lead", "senior"]):
+        base += 15000
+    elif any(k in job_lower for k in ["junior", "intern", "assistant"]):
+        base -= 8000
+
+    salary = round(max(20000, base), 2)
+
+    explanation = (
+        f"Based on your profile: **{tier.capitalize()}** career tier | "
+        f"**{exp_group}** experience | **{edu}** education\n\n"
+        f"Key drivers: Age ({age}y) + Experience ({exp}y) + Education bonus (${edu_bonus:,}) "
+        f"+ Seniority bonus (${tier_bonus:,})"
     )
 
+    return salary, tier, exp_group, explanation
 
-def on_table_select(choice: str):
-    if not choice:
-        return pd.DataFrame([{"hint": "Select a table above."}])
-    path = PY_TAB_DIR / choice
-    if not path.exists():
-        return pd.DataFrame([{"error": f"File not found: {choice}"}])
-    return _load_table_safe(path)
-
-
-# =========================================================
-# KPI LOADER
-# =========================================================
-
-def load_kpis() -> Dict[str, Any]:
-    for candidate in [PY_TAB_DIR / "kpis.json", PY_FIG_DIR / "kpis.json"]:
-        if candidate.exists():
-            try:
-                return _read_json(candidate)
-            except Exception:
-                pass
-    return {}
+def predict_salary_n8n(age: float, exp: float, edu: str, job_title: str, gender: str) -> Tuple[str, str]:
+    """Call n8n webhook if available, otherwise use formula."""
+    import requests as req
+    if N8N_WEBHOOK_URL:
+        try:
+            resp = req.post(
+                N8N_WEBHOOK_URL,
+                json={"age": age, "experience": exp, "education": edu},
+                timeout=15
+            )
+            data = resp.json()
+            salary = data.get("predicted_salary", None)
+            tier = data.get("career_tier", get_career_tier(age, exp, edu))
+            exp_group = data.get("experience_group", get_experience_group(exp))
+            if salary:
+                explanation = (
+                    f"Prediction from **Random Forest model** via n8n automation\n\n"
+                    f"Career tier: **{tier}** | Experience group: **{exp_group}**"
+                )
+                return salary, tier, exp_group, explanation
+        except Exception:
+            pass
+    return predict_salary_formula(age, exp, edu, job_title, gender)
 
+def run_prediction(age, exp, edu, job_title, gender):
+    """Main prediction function called by Gradio."""
+    if not job_title:
+        job_title = "Employee"
+    try:
+        salary, tier, exp_group, explanation = predict_salary_n8n(
+            float(age), float(exp), edu, job_title, gender
+        )
+        salary_str = f"${salary:,.2f}"
+        tier_color = {"junior": "#45FFCA", "mid": "#D09CFA", "senior": "#FF9B9B"}.get(tier, "#888")
+        result_html = f"""
+        <div style="background: white; border-radius: 12px; padding: 24px; border: 2px solid {tier_color};">
+            <div style="font-size: 36px; font-weight: 800; color: #2d1f4e; text-align: center;">
+                {salary_str}
+            </div>
+            <div style="text-align: center; margin-top: 8px;">
+                <span style="background: {tier_color}; color: #2d1f4e; padding: 4px 16px;
+                             border-radius: 20px; font-weight: 700; font-size: 14px;">
+                    {tier.upper()} TIER
+                </span>
+                <span style="margin-left: 8px; background: #f3f4f6; color: #374151;
+                             padding: 4px 16px; border-radius: 20px; font-size: 13px;">
+                    {exp_group}
+                </span>
+            </div>
+        </div>
+        """
+        return result_html, explanation
+    except Exception as e:
+        return f"<div style='color:red;'>Error: {e}</div>", ""
 
 # =========================================================
-# AI DASHBOARD -- LLM picks what to display
+# AI DASHBOARD SYSTEM PROMPT
 # =========================================================
 
-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.
+DASHBOARD_SYSTEM = """You are an AI dashboard assistant for a salary prediction analytics app.
+The user asks questions about employee salary data, career tiers, and predictions.
+You have access to pre-computed artifacts from a Python analysis pipeline.
 
 AVAILABLE ARTIFACTS (only reference ones that exist):
 {artifacts_json}
@@ -222,26 +258,21 @@ KPI SUMMARY: {kpis_json}
 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:
+   the dashboard which artifact to display:
    {{"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.
-
 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.
+- If asked about salary by gender/education/experience, show the relevant chart or table.
+- If asked about career tiers, show tier distribution.
+- If asked about sentiment/feedback, show vader analysis.
+- If asked about salary growth or progression, show progression data.
+- If asked about correlations, show the correlation heatmap.
+- Keep answers concise (2-4 sentences), then the JSON block.
 """
 
 JSON_BLOCK_RE = re.compile(r"```json\s*(\{.*?\})\s*```", re.DOTALL)
 FALLBACK_JSON_RE = re.compile(r"\{[^{}]*\"show\"[^{}]*\}", re.DOTALL)
 
-
 def _parse_display_directive(text: str) -> Dict[str, str]:
     m = JSON_BLOCK_RE.search(text)
     if m:
@@ -257,14 +288,10 @@ def _parse_display_directive(text: str) -> Dict[str, str]:
             pass
     return {"show": "none"}
 
-
 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)
@@ -277,16 +304,13 @@ def _n8n_call(msg: str) -> Tuple[str, Dict]:
     except Exception as e:
         return f"n8n error: {e}. Falling back to keyword matching.", 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:
@@ -297,20 +321,16 @@ def ai_chat(user_msg: str, history: list):
     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)",
+            kpis_json=json.dumps(kpis, indent=2) if kpis else "(no KPIs yet)",
         )
         msgs = [{"role": "system", "content": system}]
         for entry in (history or [])[-6:]:
             msgs.append(entry)
         msgs.append({"role": "user", "content": user_msg})
-
         try:
             r = llm_client.chat_completion(
-                model=MODEL_NAME,
-                messages=msgs,
-                temperature=0.3,
-                max_tokens=600,
-                stream=False,
+                model=MODEL_NAME, messages=msgs,
+                temperature=0.3, max_tokens=600, stream=False,
             )
             raw = (
                 r["choices"][0]["message"]["content"]
@@ -324,30 +344,28 @@ 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,
+        "salary_by_tier":      build_salary_by_tier_chart,
+        "salary_progression":  build_salary_progression_chart,
+        "sentiment":           build_sentiment_chart,
+        "career_distribution": build_career_distribution_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:
+        if "tier" in fname or "career" in fname:
+            chart_out = build_salary_by_tier_chart()
+        elif "progression" in fname or "growth" in fname:
+            chart_out = build_salary_progression_chart()
+        elif "sentiment" in fname or "vader" 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}")
 
@@ -362,92 +380,98 @@ def ai_chat(user_msg: str, history: list):
         {"role": "user", "content": user_msg},
         {"role": "assistant", "content": reply},
     ]
-
     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."
-        )
+        n_emp = kpis.get("n_employees", "?")
+        avg_sal = kpis.get("avg_salary", "?")
+        kpi_text = f"Quick summary: **{n_emp}** employees with average salary **${avg_sal:,.0f}**." if isinstance(avg_sal, (int, float)) else ""
 
-    if any(w in msg_lower for w in ["trend", "sales trend", "monthly sale"]):
+    if any(w in msg_lower for w in ["tier", "senior", "junior", "mid", "career"]):
         return (
-            f"Here are the sales trends. {kpi_text}",
-            {"show": "figure", "chart": "sales"},
+            f"Here is the salary distribution by career tier. {kpi_text}",
+            {"show": "figure", "chart": "salary_by_tier"},
         )
-
-    if any(w in msg_lower for w in ["sentiment", "review", "positive", "negative"]):
+    if any(w in msg_lower for w in ["progression", "growth", "over time", "year", "lstm", "arima"]):
         return (
-            f"Here is the sentiment distribution across sampled book titles. {kpi_text}",
-            {"show": "figure", "chart": "sentiment"},
+            f"Here is the salary progression over time. {kpi_text}",
+            {"show": "figure", "chart": "salary_progression"},
         )
-
-    if any(w in msg_lower for w in ["arima", "forecast", "predict"]):
+    if any(w in msg_lower for w in ["sentiment", "vader", "feedback", "positive", "negative"]):
         return (
-            f"Here are the sales trends and forecasts. {kpi_text}",
-            {"show": "figure", "chart": "sales"},
+            f"Here is the employee feedback sentiment analysis. {kpi_text}",
+            {"show": "figure", "chart": "sentiment"},
         )
-
-    if any(w in msg_lower for w in ["top", "best sell", "popular", "rank"]):
+    if any(w in msg_lower for w in ["distribution", "gender", "education", "experience"]):
         return (
-            f"Here are the top-selling titles by units sold. {kpi_text}",
-            {"show": "table", "scope": "python", "filename": "top_titles_by_units_sold.csv"},
+            f"Here is the career tier distribution. {kpi_text}",
+            {"show": "figure", "chart": "career_distribution"},
         )
-
-    if any(w in msg_lower for w in ["price", "pricing", "decision"]):
+    if any(w in msg_lower for w in ["table", "data", "employee", "list"]):
         return (
-            f"Here are the pricing decisions. {kpi_text}",
-            {"show": "table", "scope": "python", "filename": "pricing_decisions.csv"},
+            f"Here is the employee analysis data. {kpi_text}",
+            {"show": "table", "scope": "python", "filename": "employee_analysis_ready.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"},
+            f"Dashboard overview: {kpi_text}\n\nAsk me about career tiers, salary progression, "
+            "sentiment analysis, or employee data.",
+            {"show": "figure", "chart": "career_distribution"},
         )
-
-    # 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**.",
+        f"I can show you various salary analyses. {kpi_text}\n\n"
+        "Try asking about: **career tiers**, **salary progression**, **feedback sentiment**, "
+        "**salary by gender/education**, or **employee overview**.",
         {"show": "none"},
     )
 
-
 # =========================================================
-# KPI CARDS (BubbleBusters style)
+# KPI CARDS
 # =========================================================
 
+def load_kpis() -> Dict[str, Any]:
+    # Try loading from files first
+    for candidate in [PY_TAB_DIR / "kpis.json", PY_FIG_DIR / "kpis.json"]:
+        if candidate.exists():
+            try:
+                return _read_json(candidate)
+            except Exception:
+                pass
+
+    # Build KPIs from CSVs directly
+    kpis = {}
+    for csv_name in ["employee_analysis_ready.csv", BASE_DIR / "employee_analysis_ready.csv"]:
+        path = Path(csv_name) if isinstance(csv_name, str) else csv_name
+        if not path.exists():
+            path = BASE_DIR / "employee_analysis_ready.csv"
+        if path.exists():
+            try:
+                df = pd.read_csv(path)
+                kpis["n_employees"] = int(len(df))
+                if "Salary" in df.columns:
+                    kpis["avg_salary"] = round(float(df["Salary"].mean()), 2)
+                    kpis["max_salary"] = round(float(df["Salary"].max()), 2)
+                if "salary_growth" in df.columns:
+                    kpis["avg_salary_growth"] = round(float(df["salary_growth"].mean()), 2)
+            except Exception:
+                pass
+            break
+    return kpis
+
 def render_kpi_cards() -> str:
     kpis = load_kpis()
     if not kpis:
         return (
             '<div style="background:rgba(255,255,255,.65);backdrop-filter:blur(16px);'
             'border-radius:20px;padding:28px;text-align:center;'
-            'border:1.5px solid rgba(255,255,255,.7);'
-            'box-shadow:0 8px 32px rgba(124,92,191,.08);">'
+            'border:1.5px solid rgba(255,255,255,.7);">'
             '<div style="font-size:36px;margin-bottom:10px;">📊</div>'
-            '<div style="color:#a48de8;font-size:14px;'
-            'font-weight:800;margin-bottom:6px;">No data yet</div>'
-            '<div style="color:#9d8fc4;font-size:12px;">'
-            'Run the pipeline to populate these cards.</div>'
+            '<div style="color:#a48de8;font-size:14px;font-weight:800;margin-bottom:6px;">No data yet</div>'
+            '<div style="color:#9d8fc4;font-size:12px;">Run the pipeline to populate these cards.</div>'
             '</div>'
         )
 
@@ -456,19 +480,18 @@ def render_kpi_cards() -> str:
         <div style="background:rgba(255,255,255,.72);backdrop-filter:blur(16px);
                     border-radius:20px;padding:18px 14px 16px;text-align:center;
                     border:1.5px solid rgba(255,255,255,.8);
-                    box-shadow:0 4px 16px rgba(124,92,191,.08);
                     border-top:3px solid {colour};">
-            <div style="font-size:26px;margin-bottom:7px;line-height:1;">{icon}</div>
+            <div style="font-size:26px;margin-bottom:7px;">{icon}</div>
             <div style="color:#9d8fc4;font-size:9.5px;text-transform:uppercase;
                         letter-spacing:1.8px;margin-bottom:7px;font-weight:800;">{label}</div>
             <div style="color:#2d1f4e;font-size:16px;font-weight:800;">{value}</div>
         </div>"""
 
     kpi_config = [
-        ("n_titles",         "📚", "Book Titles",  "#a48de8"),
-        ("n_months",         "📅", "Time Periods", "#7aa6f8"),
-        ("total_units_sold", "📦", "Units Sold",   "#6ee7c7"),
-        ("total_revenue",    "💰", "Revenue",      "#3dcba8"),
+        ("n_employees",      "👥", "Employees",       "#a48de8"),
+        ("avg_salary",       "💰", "Avg Salary",       "#2ec4a0"),
+        ("max_salary",       "🏆", "Max Salary",       "#e8537a"),
+        ("avg_salary_growth","📈", "Avg Salary Growth","#5e8fef"),
     ]
 
     html = (
@@ -480,27 +503,20 @@ def render_kpi_cards() -> str:
         if val is None:
             continue
         if isinstance(val, (int, float)) and val > 100:
-            val = f"{val:,.0f}"
+            val = f"${val:,.0f}" if "salary" in key.lower() 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"]
 
+TIER_COLORS = {"junior": "#45FFCA", "mid": "#D09CFA", "senior": "#FF9B9B"}
+
 def _styled_layout(**kwargs) -> dict:
     defaults = dict(
         template="plotly_white",
@@ -518,94 +534,226 @@ def _styled_layout(**kwargs) -> dict:
     defaults.update(kwargs)
     return defaults
 
-
 def _empty_chart(title: str) -> go.Figure:
     fig = go.Figure()
     fig.update_layout(
         title=title, height=420, template="plotly_white",
         paper_bgcolor="rgba(255,255,255,0.95)",
-        annotations=[dict(text="Run the pipeline to generate data",
+        annotations=[dict(
+            text="Upload your CSV files or run the pipeline first",
             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 _find_csv(candidates: List[str]) -> pd.DataFrame | None:
+    """Try multiple paths to find a CSV file."""
+    for name in candidates:
+        for prefix in [BASE_DIR, PY_TAB_DIR, Path(".")]:
+            path = prefix / name
+            if path.exists():
+                try:
+                    return pd.read_csv(path)
+                except Exception:
+                    pass
+    return None
+
+def build_salary_by_tier_chart() -> go.Figure:
+    df = _find_csv(["employee_analysis_ready.csv"])
+    if df is None or "career_tier" not in df.columns or "Salary" not in df.columns:
+        return _empty_chart("Salary by Career Tier — upload employee_analysis_ready.csv")
+
+    tier_stats = df.groupby("career_tier")["Salary"].agg(["mean", "median", "std"]).reset_index()
+    tier_order = ["junior", "mid", "senior"]
+    tier_stats["career_tier"] = pd.Categorical(tier_stats["career_tier"], categories=tier_order, ordered=True)
+    tier_stats = tier_stats.sort_values("career_tier")
+
+    colors = [TIER_COLORS.get(t, "#888") for t in tier_stats["career_tier"]]
 
-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)
+    fig.add_trace(go.Bar(
+        x=tier_stats["career_tier"],
+        y=tier_stats["mean"],
+        name="Avg Salary",
+        marker_color=colors,
+        error_y=dict(type="data", array=tier_stats["std"], visible=True),
+        hovertemplate="<b>%{x}</b><br>Avg: $%{y:,.0f}<extra></extra>",
+        text=[f"${v:,.0f}" for v in tier_stats["mean"]],
+        textposition="outside",
+    ))
+    fig.add_trace(go.Scatter(
+        x=tier_stats["career_tier"],
+        y=tier_stats["median"],
+        name="Median Salary",
+        mode="markers",
+        marker=dict(color="#2d1f4e", size=10, symbol="diamond"),
+        hovertemplate="<b>%{x}</b><br>Median: $%{y:,.0f}<extra></extra>",
+    ))
+    fig.update_layout(**_styled_layout(
+        height=450,
+        title=dict(text="Average Salary by Career Tier"),
+        yaxis_title="Salary ($)",
+        xaxis_title="Career Tier",
+    ))
     return fig
 
+def build_salary_progression_chart() -> go.Figure:
+    df = _find_csv(["synthetic_salary_progression.csv"])
+    if df is None or "year" not in df.columns or "salary_that_year" not in df.columns:
+        return _empty_chart("Salary Progression — upload synthetic_salary_progression.csv")
 
-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>",
+    if "career_tier" in df.columns:
+        for i, tier in enumerate(["junior", "mid", "senior"]):
+            tier_df = df[df["career_tier"] == tier]
+            if tier_df.empty:
+                continue
+            avg_by_year = tier_df.groupby("year")["salary_that_year"].mean().reset_index()
+            fig.add_trace(go.Scatter(
+                x=avg_by_year["year"],
+                y=avg_by_year["salary_that_year"],
+                name=tier.capitalize(),
+                mode="lines+markers",
+                line=dict(color=TIER_COLORS.get(tier, CHART_PALETTE[i]), width=3),
+                marker=dict(size=6),
+                hovertemplate=f"<b>{tier.capitalize()}</b><br>Year: %{{x}}<br>Avg: $%{{y:,.0f}}<extra></extra>",
+            ))
+    else:
+        avg_by_year = df.groupby("year")["salary_that_year"].mean().reset_index()
+        fig.add_trace(go.Scatter(
+            x=avg_by_year["year"], y=avg_by_year["salary_that_year"],
+            name="Avg Salary", mode="lines+markers",
+            line=dict(color="#7c5cbf", width=3),
         ))
+
     fig.update_layout(**_styled_layout(
-        height=max(400, len(df) * 28), barmode="stack",
-        title=dict(text="Sentiment Distribution by Book"),
+        height=450,
+        title=dict(text="Salary Progression 2020–2024 by Career Tier"),
+        yaxis_title="Average Salary ($)",
+        xaxis_title="Year",
     ))
-    fig.update_xaxes(title="Number of Reviews")
-    fig.update_yaxes(autorange="reversed")
     return fig
 
+def build_sentiment_chart() -> go.Figure:
+    df = _find_csv(["synthetic_employee_feedback.csv"])
+    if df is None or "feedback_comment" not in df.columns:
+        return _empty_chart("Sentiment Analysis — upload synthetic_employee_feedback.csv")
 
-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>",
+    try:
+        from vaderSentiment.vaderSentiment import SentimentIntensityAnalyzer
+        analyzer = SentimentIntensityAnalyzer()
+        df["vader_score"] = df["feedback_comment"].apply(
+            lambda x: analyzer.polarity_scores(str(x))["compound"]
+        )
+        df["sentiment"] = df["vader_score"].apply(
+            lambda s: "positive" if s >= 0.05 else "negative" if s <= -0.05 else "neutral"
+        )
+    except ImportError:
+        if "vader_score" not in df.columns:
+            return _empty_chart("Install vaderSentiment to see this chart")
+
+    if "career_tier" in df.columns:
+        sent_by_tier = df.groupby(["career_tier", "sentiment"]).size().unstack(fill_value=0).reset_index()
+        tier_order = ["junior", "mid", "senior"]
+        sent_by_tier["career_tier"] = pd.Categorical(sent_by_tier["career_tier"], categories=tier_order, ordered=True)
+        sent_by_tier = sent_by_tier.sort_values("career_tier")
+
+        colors_map = {"positive": "#45FFCA", "neutral": "#D3D1C7", "negative": "#FF9B9B"}
+        fig = go.Figure()
+        for sent in ["negative", "neutral", "positive"]:
+            if sent in sent_by_tier.columns:
+                fig.add_trace(go.Bar(
+                    name=sent.capitalize(),
+                    x=sent_by_tier["career_tier"],
+                    y=sent_by_tier[sent],
+                    marker_color=colors_map.get(sent, "#888"),
+                    hovertemplate=f"<b>{sent.capitalize()}</b>: %{{y}}<extra></extra>",
+                ))
+        fig.update_layout(**_styled_layout(
+            height=450, barmode="stack",
+            title=dict(text="Feedback Sentiment Distribution by Career Tier"),
+            yaxis_title="Number of Comments",
+            xaxis_title="Career Tier",
+        ))
+    else:
+        sent_counts = df["sentiment"].value_counts()
+        fig = go.Figure(go.Bar(
+            x=sent_counts.index, y=sent_counts.values,
+            marker_color=["#45FFCA", "#D3D1C7", "#FF9B9B"][:len(sent_counts)],
+        ))
+        fig.update_layout(**_styled_layout(height=400, title=dict(text="Overall Feedback Sentiment")))
+
+    return fig
+
+def build_career_distribution_chart() -> go.Figure:
+    df = _find_csv(["employee_analysis_ready.csv"])
+    if df is None or "career_tier" not in df.columns:
+        return _empty_chart("Career Distribution — upload employee_analysis_ready.csv")
+
+    fig = go.Figure()
+
+    # Pie chart of career tier distribution
+    tier_counts = df["career_tier"].value_counts()
+    colors = [TIER_COLORS.get(t, "#888") for t in tier_counts.index]
+
+    fig.add_trace(go.Pie(
+        labels=[t.capitalize() for t in tier_counts.index],
+        values=tier_counts.values,
+        marker=dict(colors=colors),
+        hole=0.4,
+        hovertemplate="<b>%{label}</b><br>Count: %{value}<br>Share: %{percent}<extra></extra>",
     ))
     fig.update_layout(**_styled_layout(
-        height=max(400, len(df) * 30),
-        title=dict(text="Top Selling Titles"), showlegend=False,
+        height=420,
+        title=dict(text="Career Tier Distribution"),
+        showlegend=True,
     ))
-    fig.update_yaxes(autorange="reversed")
-    fig.update_xaxes(title="Total Units Sold")
     return fig
 
+def _load_table_safe(path: Path) -> pd.DataFrame:
+    try:
+        if path.suffix == ".json":
+            obj = _read_json(path)
+            if isinstance(obj, dict):
+                return pd.DataFrame([obj])
+            return pd.DataFrame(obj)
+        return _read_csv(path)
+    except Exception as e:
+        return pd.DataFrame([{"error": str(e)}])
 
 def refresh_dashboard():
-    return render_kpi_cards(), build_sales_chart(), build_sentiment_chart(), build_top_sellers_chart()
+    return (
+        render_kpi_cards(),
+        build_salary_by_tier_chart(),
+        build_salary_progression_chart(),
+        build_sentiment_chart(),
+        build_career_distribution_chart(),
+    )
+
+def refresh_gallery():
+    figures = []
+    for p in sorted(PY_FIG_DIR.glob("*.png")):
+        figures.append((str(p), p.stem.replace("_", " ").title()))
+
+    idx = artifacts_index()
+    table_choices = list(idx["python"]["tables"])
+    default_df = pd.DataFrame()
+    if table_choices:
+        default_df = _load_table_safe(PY_TAB_DIR / table_choices[0])
+
+    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 = PY_TAB_DIR / choice
+    if not path.exists():
+        return pd.DataFrame([{"error": f"File not found: {choice}"}])
+    return _load_table_safe(path)
 
 # =========================================================
 # UI
@@ -617,26 +765,90 @@ def load_css() -> str:
     css_path = BASE_DIR / "style.css"
     return css_path.read_text(encoding="utf-8") if css_path.exists() else ""
 
-
-with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
+with gr.Blocks(title="F2 Salary Predictor") as demo:
 
     gr.Markdown(
-        "# SE21 App Template\n"
-        "*This is an app template for SE21 students*",
+        "# F2 Salary Predictor\n"
+        "*AI-powered salary prediction and employee analytics — ESCP Big Data Project*",
         elem_id="escp_title",
     )
 
     # ===========================================================
-    # TAB 1 -- Pipeline Runner
+    # TAB 1 -- Salary Predictor
+    # ===========================================================
+    with gr.Tab("Salary Predictor"):
+        gr.Markdown("### Predict your salary based on your profile")
+        gr.Markdown(
+            "Enter your details below. The model uses age, experience, education, "
+            "and job title to estimate your expected salary using our trained Random Forest model."
+        )
+
+        with gr.Row():
+            with gr.Column(scale=1):
+                age_input = gr.Slider(
+                    minimum=18, maximum=70, value=30, step=1,
+                    label="Age"
+                )
+                exp_input = gr.Slider(
+                    minimum=0, maximum=40, value=5, step=1,
+                    label="Years of Experience"
+                )
+                edu_input = gr.Dropdown(
+                    choices=["Bachelor's", "Master's", "PhD"],
+                    value="Bachelor's",
+                    label="Education Level"
+                )
+                job_input = gr.Textbox(
+                    label="Job Title",
+                    placeholder="e.g. Data Scientist, Software Engineer, Manager...",
+                    value="Data Analyst"
+                )
+                gender_input = gr.Radio(
+                    choices=["Male", "Female"],
+                    value="Male",
+                    label="Gender"
+                )
+                predict_btn = gr.Button("Predict Salary", variant="primary")
+
+            with gr.Column(scale=1):
+                result_html = gr.HTML(
+                    value='<div style="background:#f9fafb;border-radius:12px;padding:40px;'
+                          'text-align:center;color:#9ca3af;font-size:14px;">'
+                          'Fill in your profile and click Predict Salary</div>'
+                )
+                explanation_box = gr.Markdown("")
+
+        predict_btn.click(
+            run_prediction,
+            inputs=[age_input, exp_input, edu_input, job_input, gender_input],
+            outputs=[result_html, explanation_box],
+        )
+
+        gr.Markdown("---")
+        gr.Markdown("#### Try these example profiles")
+        gr.Examples(
+            examples=[
+                [28, 3, "Bachelor's", "Junior Data Analyst", "Female"],
+                [35, 10, "Master's", "Senior Data Scientist", "Male"],
+                [45, 20, "PhD", "Director of Analytics", "Female"],
+                [22, 1, "Bachelor's", "Intern", "Male"],
+                [50, 25, "Master's", "VP of Engineering", "Male"],
+            ],
+            inputs=[age_input, exp_input, edu_input, job_input, gender_input],
+            label="Example Profiles",
+        )
+
+    # ===========================================================
+    # TAB 2 -- Pipeline Runner
     # ===========================================================
     with gr.Tab("Pipeline Runner"):
-        gr.Markdown()
+        gr.Markdown("### Run the data pipeline")
 
         with gr.Row():
             with gr.Column(scale=1):
-                btn_nb1 = gr.Button("Step 1: Data Creation", variant="secondary")
+                btn_nb1 = gr.Button("Step 1: Data Creation & Synthetic Enrichment", variant="secondary")
             with gr.Column(scale=1):
-                btn_nb2 = gr.Button("Step 2: Python Analysis", variant="secondary")
+                btn_nb2 = gr.Button("Step 2: Salary Analysis & Predictions", variant="secondary")
 
         with gr.Row():
             btn_all = gr.Button("Run Full Pipeline (Both Steps)", variant="primary")
@@ -653,25 +865,22 @@ with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
         btn_all.click(run_full_pipeline, outputs=[run_log])
 
     # ===========================================================
-    # TAB 2 -- Dashboard (KPIs + Interactive Charts + Gallery)
+    # TAB 3 -- Dashboard
     # ===========================================================
     with gr.Tab("Dashboard"):
         kpi_html = gr.HTML(value=render_kpi_cards)
 
         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")
+        gr.Markdown("#### Salary Analytics")
+        with gr.Row():
+            chart_tier = gr.Plot(label="Salary by Career Tier")
+            chart_dist = gr.Plot(label="Career Tier Distribution")
 
-        gr.Markdown("#### Static Figures (from notebooks)")
-        gallery = gr.Gallery(
-            label="Generated Figures",
-            columns=2,
-            height=480,
-            object_fit="contain",
-        )
+        gr.Markdown("#### Temporal & Sentiment Analysis")
+        with gr.Row():
+            chart_prog = gr.Plot(label="Salary Progression 2020–2024")
+            chart_sent = gr.Plot(label="Feedback Sentiment by Tier")
 
         gr.Markdown("#### Data Tables")
         table_dropdown = gr.Dropdown(
@@ -679,19 +888,21 @@ with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
             choices=[],
             interactive=True,
         )
-        table_display = gr.Dataframe(
-            label="Table Preview",
-            interactive=False,
-        )
+        table_display = gr.Dataframe(label="Table Preview", interactive=False)
 
         def _on_refresh():
-            kpi, c1, c2, c3 = refresh_dashboard()
+            kpi, c1, c2, c3, c4 = refresh_dashboard()
             figs, dd, df = refresh_gallery()
-            return kpi, c1, c2, c3, figs, dd, df
+            return kpi, c1, c2, c3, c4, figs, dd, df
+
+        gallery = gr.Gallery(
+            label="Generated Figures from Notebooks",
+            columns=2, height=480, object_fit="contain",
+        )
 
         refresh_btn.click(
             _on_refresh,
-            outputs=[kpi_html, chart_sales, chart_sentiment, chart_top,
+            outputs=[kpi_html, chart_tier, chart_prog, chart_sent, chart_dist,
                      gallery, table_dropdown, table_display],
         )
         table_dropdown.change(
@@ -701,52 +912,42 @@ with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
         )
 
     # ===========================================================
-    # TAB 3 -- AI Dashboard
+    # TAB 4 -- AI Dashboard
     # ===========================================================
     with gr.Tab('"AI" Dashboard'):
         _ai_status = (
             "Connected to your **n8n workflow**." if N8N_WEBHOOK_URL
             else "**LLM active.**" if LLM_ENABLED
-            else "Using **keyword matching**. Upgrade options: "
-                 "set `N8N_WEBHOOK_URL` to connect your n8n workflow, "
-                 "or set `HF_API_KEY` for direct LLM access."
+            else "Using **keyword matching**. Set `N8N_WEBHOOK_URL` in Space secrets to connect your n8n automation."
         )
         gr.Markdown(
             "### Ask questions, get interactive visualisations\n\n"
-            f"Type a question and the system will pick the right interactive chart or table. {_ai_status}"
+            f"Type a question and the system will pick the right chart or table. {_ai_status}"
         )
 
         with gr.Row(equal_height=True):
             with gr.Column(scale=1):
-                chatbot = gr.Chatbot(
-                    label="Conversation",
-                    height=380,
-                )
+                chatbot = gr.Chatbot(label="Conversation", height=380)
                 user_input = gr.Textbox(
                     label="Ask about your data",
-                    placeholder="e.g. Show me sales trends / What are the top sellers? / Sentiment analysis",
+                    placeholder="e.g. Show me salary by career tier / What is the sentiment analysis?",
                     lines=1,
                 )
                 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?",
+                        "Show me salary by career tier",
+                        "What does the sentiment analysis show?",
+                        "Show me salary progression over time",
+                        "What is the career tier distribution?",
                         "Give me a dashboard overview",
+                        "Show me the employee data table",
                     ],
                     inputs=user_input,
                 )
 
             with gr.Column(scale=1):
-                ai_figure = gr.Plot(
-                    label="Interactive Chart",
-                )
-                ai_table = gr.Dataframe(
-                    label="Data Table",
-                    interactive=False,
-                )
+                ai_figure = gr.Plot(label="Interactive Chart")
+                ai_table = gr.Dataframe(label="Data Table", interactive=False)
 
         user_input.submit(
             ai_chat,
@@ -755,4 +956,4 @@ with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
         )
 
 
-demo.launch(css=load_css(), allowed_paths=[str(BASE_DIR)])
+demo.launch(css=load_css(), allowed_paths=[str(BASE_DIR)])