Upload 11 files

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 background_top.png filter=lfs diff=lfs merge=lfs -text
+background_top[[:space:]](1).png filter=lfs diff=lfs merge=lfs -text

Dockerfile (1)

@@ -0,0 +1,26 @@
+FROM python:3.10-slim
+
+ENV DEBIAN_FRONTEND=noninteractive
+ENV PYTHONDONTWRITEBYTECODE=1
+ENV PYTHONUNBUFFERED=1
+
+ENV GRADIO_SERVER_NAME=0.0.0.0
+ENV GRADIO_SERVER_PORT=7860
+
+WORKDIR /app
+COPY . /app
+
+# Python deps (from requirements.txt)
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Notebook execution deps
+RUN pip install --no-cache-dir notebook ipykernel papermill
+
+# Pre-install packages the notebooks use via !pip install
+RUN pip install --no-cache-dir textblob faker vaderSentiment transformers
+
+RUN python -m ipykernel install --user --name python3 --display-name "Python 3"
+
+EXPOSE 7860
+
+CMD ["python", "app.py"]

README (1).md

@@ -0,0 +1,11 @@
+---
+title: SE21 App Template
+emoji: 📊
+colorFrom: blue
+colorTo: purple
+sdk: docker
+pinned: false
+short_description: AI-enhanced analytics dashboard template for SE21 students
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app (1).py

@@ -0,0 +1,754 @@
+import os
+import re
+import json
+import time
+import traceback
+from pathlib import Path
+from typing import Dict, Any, List, Tuple
+ 
+import pandas as pd
+import gradio as gr
+import papermill as pm
+import plotly.graph_objects as go
+ 
+# Optional LLM (HuggingFace Inference API)
+try:
+    from huggingface_hub import InferenceClient
+except Exception:
+    InferenceClient = None
+ 
+# =========================================================
+# CONFIG
+# =========================================================
+ 
+BASE_DIR = Path(__file__).resolve().parent
+ 
+NB1 = os.environ.get("NB1", "datacreation.ipynb").strip()
+NB2 = os.environ.get("NB2", "pythonanalysis.ipynb").strip()
+ 
+RUNS_DIR = BASE_DIR / "runs"
+ART_DIR = BASE_DIR / "artifacts"
+PY_FIG_DIR = ART_DIR / "py" / "figures"
+PY_TAB_DIR = ART_DIR / "py" / "tables"
+ 
+PAPERMILL_TIMEOUT = int(os.environ.get("PAPERMILL_TIMEOUT", "1800"))
+MAX_PREVIEW_ROWS = int(os.environ.get("MAX_FILE_PREVIEW_ROWS", "50"))
+MAX_LOG_CHARS = int(os.environ.get("MAX_LOG_CHARS", "8000"))
+ 
+HF_API_KEY = os.environ.get("HF_API_KEY", "").strip()
+MODEL_NAME = os.environ.get("MODEL_NAME", "deepseek-ai/DeepSeek-R1").strip()
+HF_PROVIDER = os.environ.get("HF_PROVIDER", "novita").strip()
+N8N_WEBHOOK_URL = os.environ.get("N8N_WEBHOOK_URL", "").strip()
+ 
+LLM_ENABLED = bool(HF_API_KEY) and InferenceClient is not None
+llm_client = (
+    InferenceClient(provider=HF_PROVIDER, api_key=HF_API_KEY)
+    if LLM_ENABLED
+    else None
+)
+ 
+# =========================================================
+# HELPERS
+# =========================================================
+ 
+def ensure_dirs():
+    for p in [RUNS_DIR, ART_DIR, PY_FIG_DIR, PY_TAB_DIR]:
+        p.mkdir(parents=True, exist_ok=True)
+ 
+def stamp():
+    return time.strftime("%Y%m%d-%H%M%S")
+ 
+def tail(text: str, n: int = MAX_LOG_CHARS) -> str:
+    return (text or "")[-n:]
+ 
+def _ls(dir_path: Path, exts: Tuple[str, ...]) -> List[str]:
+    if not dir_path.is_dir():
+        return []
+    return sorted(p.name for p in dir_path.iterdir() if p.is_file() and p.suffix.lower() in exts)
+ 
+def _read_csv(path: Path) -> pd.DataFrame:
+    return pd.read_csv(path, nrows=MAX_PREVIEW_ROWS)
+ 
+def _read_json(path: Path):
+    with path.open(encoding="utf-8") as f:
+        return json.load(f)
+ 
+def artifacts_index() -> Dict[str, Any]:
+    return {
+        "python": {
+            "figures": _ls(PY_FIG_DIR, (".png", ".jpg", ".jpeg")),
+            "tables": _ls(PY_TAB_DIR, (".csv", ".json")),
+        },
+    }
+ 
+# =========================================================
+# PIPELINE RUNNERS
+# =========================================================
+ 
+def run_notebook(nb_name: str) -> str:
+    ensure_dirs()
+    nb_in = BASE_DIR / nb_name
+    if not nb_in.exists():
+        return f"ERROR: {nb_name} not found."
+    nb_out = RUNS_DIR / f"run_{stamp()}_{nb_name}"
+    pm.execute_notebook(
+        input_path=str(nb_in),
+        output_path=str(nb_out),
+        cwd=str(BASE_DIR),
+        log_output=True,
+        progress_bar=False,
+        request_save_on_cell_execute=True,
+        execution_timeout=PAPERMILL_TIMEOUT,
+    )
+    return f"Executed {nb_name}"
+ 
+ 
+def run_datacreation() -> str:
+    try:
+        log = run_notebook(NB1)
+        csvs = [f.name for f in BASE_DIR.glob("*.csv")]
+        return f"OK  {log}\n\nCSVs now in /app:\n" + "\n".join(f"  - {c}" for c in sorted(csvs))
+    except Exception as e:
+        return f"FAILED  {e}\n\n{traceback.format_exc()[-2000:]}"
+ 
+ 
+def run_pythonanalysis() -> str:
+    try:
+        log = run_notebook(NB2)
+        idx = artifacts_index()
+        figs = idx["python"]["figures"]
+        tabs = idx["python"]["tables"]
+        return (
+            f"OK  {log}\n\n"
+            f"Figures: {', '.join(figs) or '(none)'}\n"
+            f"Tables:  {', '.join(tabs) or '(none)'}"
+        )
+    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("=" * 50)
+    logs.append(run_datacreation())
+    logs.append("")
+    logs.append("=" * 50)
+    logs.append("STEP 2/2: Python Analysis (sentiment, ARIMA, dashboard)")
+    logs.append("=" * 50)
+    logs.append(run_pythonanalysis())
+    return "\n".join(logs)
+ 
+ 
+# =========================================================
+# GALLERY LOADERS
+# =========================================================
+ 
+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 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 {}
+ 
+ 
+# =========================================================
+# AI DASHBOARD -- LLM picks what to display
+# =========================================================
+ 
+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.
+ 
+AVAILABLE ARTIFACTS (only reference ones that exist):
+{artifacts_json}
+ 
+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:
+   {{"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.
+"""
+ 
+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:
+        try:
+            return json.loads(m.group(1))
+        except json.JSONDecodeError:
+            pass
+    m = FALLBACK_JSON_RE.search(text)
+    if m:
+        try:
+            return json.loads(m.group(0))
+        except json.JSONDecodeError:
+            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)
+        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 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:
+            reply_fb, directive = _keyword_fallback(user_msg, idx, kpis)
+            reply += "\n\n" + reply_fb
+    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)",
+        )
+        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,
+            )
+            raw = (
+                r["choices"][0]["message"]["content"]
+                if isinstance(r, dict)
+                else r.choices[0].message.content
+            )
+            directive = _parse_display_directive(raw)
+            reply = _clean_response(raw)
+        except Exception as e:
+            reply = f"LLM error: {e}. Falling back to keyword matching."
+            reply_fb, directive = _keyword_fallback(user_msg, idx, kpis)
+            reply += "\n\n" + reply_fb
+ 
+    # Resolve artifacts
+    chart_out = None
+    tab_out = None
+    show = directive.get("show", "none")
+    fname = directive.get("filename", "")
+    chart_name = directive.get("chart", "")
+ 
+    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:
+        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()
+        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})*"
+ 
+    # FIX Gradio 6: history format is list of dicts with role/content
+    new_history = (history or []) + [
+        {"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."
+        )
+ 
+    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. {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. {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.",
+            {"show": "table", "scope": "python", "filename": "df_dashboard.csv"},
+        )
+ 
+    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
+# =========================================================
+ 
+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);">'
+            '<div style="font-size:36px;margin-bottom:10px;">&#128202;</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>'
+        )
+ 
+    def card(icon, label, value, colour):
+        return f"""
+        <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="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",         "&#128218;", "Book Titles",  "#a48de8"),
+        ("n_months",         "&#128197;", "Time Periods", "#7aa6f8"),
+        ("total_units_sold", "&#128230;", "Units Sold",   "#6ee7c7"),
+        ("total_revenue",    "&#128176;", "Revenue",      "#3dcba8"),
+    ]
+ 
+    html = (
+        '<div style="display:grid;grid-template-columns:repeat(auto-fit,minmax(140px,1fr));'
+        'gap:12px;margin-bottom:24px;">'
+    )
+    for key, icon, label, colour in kpi_config:
+        val = kpis.get(key)
+        if val is None:
+            continue
+        if isinstance(val, (int, float)) and val > 100:
+            val = f"{val:,.0f}"
+        html += card(icon, label, str(val), colour)
+ 
+    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("&#128200;", label, str(val), "#8fa8f8")
+    html += "</div>"
+    return html
+ 
+ 
+# =========================================================
+# 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",
+        paper_bgcolor="rgba(255,255,255,0.95)",
+        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)
+    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",
+            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_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"),
+    ))
+    fig.update_xaxes(title="Number of Reviews")
+    fig.update_yaxes(autorange="reversed")
+    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>",
+    ))
+    fig.update_layout(**_styled_layout(
+        height=max(400, len(df) * 30),
+        title=dict(text="Top Selling Titles"), showlegend=False,
+    ))
+    fig.update_yaxes(autorange="reversed")
+    fig.update_xaxes(title="Total Units Sold")
+    return fig
+ 
+ 
+def refresh_dashboard():
+    return render_kpi_cards(), build_sales_chart(), build_sentiment_chart(), build_top_sellers_chart()
+ 
+ 
+# =========================================================
+# UI
+# =========================================================
+ 
+ensure_dirs()
+ 
+ 
+def load_css() -> str:
+    css_path = BASE_DIR / "style.css"
+    return css_path.read_text(encoding="utf-8") if css_path.exists() else ""
+ 
+css_content = load_css()
+
+with gr.Blocks(title="AIBDM 2026 Workshop App") as demo:
+    gr.HTML(f"<style>{css_content}</style>")
+
+    gr.Markdown(
+        "# SE21 App Template\n"
+        "*This is an app template for SE21 students*",
+        elem_id="escp_title",
+    )
+ 
+    # ===========================================================
+    # TAB 1 -- Pipeline Runner
+    # ===========================================================
+    with gr.Tab("Pipeline Runner"):
+        with gr.Row():
+            with gr.Column(scale=1):
+                btn_nb1 = gr.Button("Step 1: Data Creation", variant="secondary")
+            with gr.Column(scale=1):
+                btn_nb2 = gr.Button("Step 2: Python Analysis", variant="secondary")
+ 
+        with gr.Row():
+            btn_all = gr.Button("Run Full Pipeline (Both Steps)", variant="primary")
+ 
+        run_log = gr.Textbox(
+            label="Execution Log",
+            lines=18,
+            max_lines=30,
+            interactive=False,
+        )
+ 
+        btn_nb1.click(run_datacreation, outputs=[run_log])
+        btn_nb2.click(run_pythonanalysis, outputs=[run_log])
+        btn_all.click(run_full_pipeline, outputs=[run_log])
+ 
+    # ===========================================================
+    # TAB 2 -- Dashboard
+    # ===========================================================
+    with gr.Tab("Dashboard"):
+        kpi_html = gr.HTML(value=render_kpi_cards())   # FIX: call function directly for initial load
+ 
+        refresh_btn = gr.Button("Refresh Dashboard", variant="primary")
+ 
+        gr.Markdown("#### Interactive Charts")
+        chart_sales = gr.Plot(label="Monthly Overview", value=build_sales_chart())           # FIX: initial load
+        chart_sentiment = gr.Plot(label="Sentiment Distribution", value=build_sentiment_chart())  # FIX: initial load
+        chart_top = gr.Plot(label="Top Sellers", value=build_top_sellers_chart())            # FIX: initial load
+ 
+        gr.Markdown("#### Static Figures (from notebooks)")
+        gallery = gr.Gallery(
+            label="Generated Figures",
+            columns=2,
+            height=480,
+            object_fit="contain",
+            value=_load_all_figures(),   # FIX: initial load
+        )
+ 
+        gr.Markdown("#### Data Tables")
+ 
+        # FIX: load initial table choices
+        _initial_idx = artifacts_index()
+        _initial_table_choices = list(_initial_idx["python"]["tables"])
+        _initial_df = pd.DataFrame()
+        if _initial_table_choices:
+            _initial_df = _load_table_safe(PY_TAB_DIR / _initial_table_choices[0])
+ 
+        table_dropdown = gr.Dropdown(
+            label="Select a table to view",
+            choices=_initial_table_choices,
+            value=_initial_table_choices[0] if _initial_table_choices else None,
+            interactive=True,
+        )
+        table_display = gr.Dataframe(
+            label="Table Preview",
+            interactive=False,
+            value=_initial_df if not _initial_df.empty else None,
+        )
+ 
+        def _on_refresh():
+            kpi, c1, c2, c3 = refresh_dashboard()
+            figs, dd, df = refresh_gallery()
+            return kpi, c1, c2, c3, figs, dd, df
+ 
+        refresh_btn.click(
+            _on_refresh,
+            outputs=[kpi_html, chart_sales, chart_sentiment, chart_top,
+                     gallery, table_dropdown, table_display],
+        )
+        table_dropdown.change(
+            on_table_select,
+            inputs=[table_dropdown],
+            outputs=[table_display],
+        )
+ 
+    # ===========================================================
+    # TAB 3 -- 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**. Set `N8N_WEBHOOK_URL` or `HF_API_KEY` to upgrade."
+        )
+        gr.Markdown(
+            "### Ask questions, get interactive visualisations\n\n"
+            f"{_ai_status}"
+        )        
+        with gr.Row(equal_height=True):
+            with gr.Column(scale=1):
+                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?",
+                    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?",
+                        "Give me a dashboard overview",
+                    ],
+                    inputs=user_input,
+                )
+ 
+            with gr.Column(scale=1):
+                ai_figure = gr.Plot(label="Interactive Chart")
+                ai_table = gr.Dataframe(label="Data Table", interactive=False)
+ 
+        user_input.submit(
+            ai_chat,
+            inputs=[user_input, chatbot],
+            outputs=[chatbot, user_input, ai_figure, ai_table],
+        )
+ 
+demo.launch(allowed_paths=[str(BASE_DIR)])

datacreation.ipynb

@@ -0,0 +1,1203 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4ba6aba8"
+      },
+      "source": [
+        "# 🤖 **Data Collection, Creation, Storage, and Processing**\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "jpASMyIQMaAq"
+      },
+      "source": [
+        "## **1.** 📦 Install required packages"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 25,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "f48c8f8c",
+        "outputId": "2c9eb68f-0716-425f-9eea-12094df9d3ee"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: beautifulsoup4 in /usr/local/lib/python3.12/dist-packages (4.13.5)\n",
+            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (2.2.2)\n",
+            "Requirement already satisfied: matplotlib in /usr/local/lib/python3.12/dist-packages (3.10.0)\n",
+            "Requirement already satisfied: seaborn in /usr/local/lib/python3.12/dist-packages (0.13.2)\n",
+            "Requirement already satisfied: numpy in /usr/local/lib/python3.12/dist-packages (2.0.2)\n",
+            "Requirement already satisfied: textblob in /usr/local/lib/python3.12/dist-packages (0.19.0)\n",
+            "Requirement already satisfied: soupsieve>1.2 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4) (2.8.3)\n",
+            "Requirement already satisfied: typing-extensions>=4.0.0 in /usr/local/lib/python3.12/dist-packages (from beautifulsoup4) (4.15.0)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas) (2.9.0.post0)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.2)\n",
+            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas) (2025.3)\n",
+            "Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.3.3)\n",
+            "Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (0.12.1)\n",
+            "Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (4.61.1)\n",
+            "Requirement already satisfied: kiwisolver>=1.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (1.4.9)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (26.0)\n",
+            "Requirement already satisfied: pillow>=8 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (11.3.0)\n",
+            "Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.12/dist-packages (from matplotlib) (3.3.2)\n",
+            "Requirement already satisfied: nltk>=3.9 in /usr/local/lib/python3.12/dist-packages (from textblob) (3.9.1)\n",
+            "Requirement already satisfied: click in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (8.3.1)\n",
+            "Requirement already satisfied: joblib in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (1.5.3)\n",
+            "Requirement already satisfied: regex>=2021.8.3 in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (2025.11.3)\n",
+            "Requirement already satisfied: tqdm in /usr/local/lib/python3.12/dist-packages (from nltk>=3.9->textblob) (4.67.3)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas) (1.17.0)\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install beautifulsoup4 pandas matplotlib seaborn numpy textblob"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "lquNYCbfL9IM"
+      },
+      "source": [
+        "## **2.** ⛏ Web-scrape all book titles, prices, and ratings from books.toscrape.com"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "0IWuNpxxYDJF"
+      },
+      "source": [
+        "### *a. Initial setup*\n",
+        "Define the base url of the website you will scrape as well as how and what you will scrape"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 26,
+      "metadata": {
+        "id": "91d52125"
+      },
+      "outputs": [],
+      "source": [
+        "import requests\n",
+        "from bs4 import BeautifulSoup\n",
+        "import pandas as pd\n",
+        "import time\n",
+        "\n",
+        "base_url = \"https://books.toscrape.com/catalogue/page-{}.html\"\n",
+        "headers = {\"User-Agent\": \"Mozilla/5.0\"}\n",
+        "\n",
+        "titles, prices, ratings = [], [], []"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "oCdTsin2Yfp3"
+      },
+      "source": [
+        "### *b. Fill titles, prices, and ratings from the web pages*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 23,
+      "metadata": {
+        "id": "xqO5Y3dnYhxt"
+      },
+      "outputs": [],
+      "source": [
+        "# Loop through all 50 pages\n",
+        "for page in range(1, 51):\n",
+        "    url = base_url.format(page)\n",
+        "    response = requests.get(url, headers=headers)\n",
+        "    soup = BeautifulSoup(response.content, \"html.parser\")\n",
+        "    books = soup.find_all(\"article\", class_=\"product_pod\")\n",
+        "\n",
+        "    for book in books:\n",
+        "        titles.append(book.h3.a[\"title\"])\n",
+        "        prices.append(float(book.find(\"p\", class_=\"price_color\").text[1:]))\n",
+        "        ratings.append(book.p.get(\"class\")[1])\n",
+        "\n",
+        "    time.sleep(0.5)  # polite scraping delay"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "T0TOeRC4Yrnn"
+      },
+      "source": [
+        "### *c. ✋🏻🛑⛔️ Create a dataframe df_books that contains the now complete \"title\", \"price\", and \"rating\" objects*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 24,
+      "metadata": {
+        "id": "l5FkkNhUYTHh"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "df_books = pd.DataFrame({\n",
+        "    \"title\": titles,\n",
+        "    \"price\": prices,\n",
+        "    \"rating\": ratings\n",
+        "})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "duI5dv3CZYvF"
+      },
+      "source": [
+        "### *d. Save web-scraped dataframe either as a CSV or Excel file*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 27,
+      "metadata": {
+        "id": "lC1U_YHtZifh"
+      },
+      "outputs": [],
+      "source": [
+        "# 💾 Save to CSV\n",
+        "df_books.to_csv(\"books_data.csv\", index=False)\n",
+        "\n",
+        "# 💾 Or save to Excel\n",
+        "# df_books.to_excel(\"books_data.xlsx\", index=False)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "qMjRKMBQZlJi"
+      },
+      "source": [
+        "### *e. ✋🏻🛑⛔️ View first fiew lines*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 28,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "O_wIvTxYZqCK",
+        "outputId": "86d3f20b-fa44-4fc1-b6aa-306f15780c30"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "                                   title  price rating\n",
+              "0                   A Light in the Attic  51.77  Three\n",
+              "1                     Tipping the Velvet  53.74    One\n",
+              "2                             Soumission  50.10    One\n",
+              "3                          Sharp Objects  47.82   Four\n",
+              "4  Sapiens: A Brief History of Humankind  54.23   Five"
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-b206477a-b8f4-448c-be41-650117cff31c\" class=\"colab-df-container\">\n",
+              "    <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>title</th>\n",
+              "      <th>price</th>\n",
+              "      <th>rating</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>A Light in the Attic</td>\n",
+              "      <td>51.77</td>\n",
+              "      <td>Three</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>Tipping the Velvet</td>\n",
+              "      <td>53.74</td>\n",
+              "      <td>One</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>Soumission</td>\n",
+              "      <td>50.10</td>\n",
+              "      <td>One</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>Sharp Objects</td>\n",
+              "      <td>47.82</td>\n",
+              "      <td>Four</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>Sapiens: A Brief History of Humankind</td>\n",
+              "      <td>54.23</td>\n",
+              "      <td>Five</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b206477a-b8f4-448c-be41-650117cff31c')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-b206477a-b8f4-448c-be41-650117cff31c button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-b206477a-b8f4-448c-be41-650117cff31c');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df_books",
+              "summary": "{\n  \"name\": \"df_books\",\n  \"rows\": 1500,\n  \"fields\": [\n    {\n      \"column\": \"title\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 999,\n        \"samples\": [\n          \"The Grownup\",\n          \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n          \"Ayumi's Violin\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"price\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 14.477392573574008,\n        \"min\": 10.0,\n        \"max\": 59.99,\n        \"num_unique_values\": 903,\n        \"samples\": [\n          19.73,\n          55.65,\n          46.31\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rating\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"One\",\n          \"Two\",\n          \"Four\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 28
+        }
+      ],
+      "source": [
+        "df_books.head()"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "p-1Pr2szaqLk"
+      },
+      "source": [
+        "## **3.** 🧩 Create a meaningful connection between real & synthetic datasets"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "SIaJUGIpaH4V"
+      },
+      "source": [
+        "### *a. Initial setup*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 29,
+      "metadata": {
+        "id": "-gPXGcRPuV_9"
+      },
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import random\n",
+        "from datetime import datetime\n",
+        "import warnings\n",
+        "\n",
+        "warnings.filterwarnings(\"ignore\")\n",
+        "random.seed(2025)\n",
+        "np.random.seed(2025)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "pY4yCoIuaQqp"
+      },
+      "source": [
+        "### *b. Generate popularity scores based on rating (with some randomness) with a generate_popularity_score function*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 30,
+      "metadata": {
+        "id": "mnd5hdAbaNjz"
+      },
+      "outputs": [],
+      "source": [
+        "def generate_popularity_score(rating):\n",
+        "    base = {\"One\": 2, \"Two\": 3, \"Three\": 3, \"Four\": 4, \"Five\": 4}.get(rating, 3)\n",
+        "    trend_factor = random.choices([-1, 0, 1], weights=[1, 3, 2])[0]\n",
+        "    return int(np.clip(base + trend_factor, 1, 5))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "n4-TaNTFgPak"
+      },
+      "source": [
+        "### *c. ✋🏻🛑⛔️ Run the function to create a \"popularity_score\" column from \"rating\"*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 31,
+      "metadata": {
+        "id": "V-G3OCUCgR07"
+      },
+      "outputs": [],
+      "source": [
+        "df_books[\"popularity_score\"] = df_books[\"rating\"].apply(generate_popularity_score)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HnngRNTgacYt"
+      },
+      "source": [
+        "### *d. Decide on the sentiment_label based on the popularity score with a get_sentiment function*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 32,
+      "metadata": {
+        "id": "kUtWmr8maZLZ"
+      },
+      "outputs": [],
+      "source": [
+        "def get_sentiment(popularity_score):\n",
+        "    if popularity_score <= 2:\n",
+        "        return \"negative\"\n",
+        "    elif popularity_score == 3:\n",
+        "        return \"neutral\"\n",
+        "    else:\n",
+        "        return \"positive\""
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "HF9F9HIzgT7Z"
+      },
+      "source": [
+        "### *e. ✋🏻🛑⛔️ Run the function to create a \"sentiment_label\" column from \"popularity_score\"*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 33,
+      "metadata": {
+        "id": "tafQj8_7gYCG"
+      },
+      "outputs": [],
+      "source": [
+        "df_books[\"sentiment_label\"] = df_books[\"popularity_score\"].apply(get_sentiment)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "T8AdKkmASq9a"
+      },
+      "source": [
+        "## **4.** 📈 Generate synthetic book sales data of 18 months"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "OhXbdGD5fH0c"
+      },
+      "source": [
+        "### *a. Create a generate_sales_profit function that would generate sales patterns based on sentiment_label (with some randomness)*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 34,
+      "metadata": {
+        "id": "qkVhYPXGbgEn"
+      },
+      "outputs": [],
+      "source": [
+        "def generate_sales_profile(sentiment):\n",
+        "    months = pd.date_range(end=datetime.today(), periods=18, freq=\"M\")\n",
+        "\n",
+        "    if sentiment == \"positive\":\n",
+        "        base = random.randint(200, 300)\n",
+        "        trend = np.linspace(base, base + random.randint(20, 60), len(months))\n",
+        "    elif sentiment == \"negative\":\n",
+        "        base = random.randint(20, 80)\n",
+        "        trend = np.linspace(base, base - random.randint(10, 30), len(months))\n",
+        "    else:  # neutral\n",
+        "        base = random.randint(80, 160)\n",
+        "        trend = np.full(len(months), base + random.randint(-10, 10))\n",
+        "\n",
+        "    seasonality = 10 * np.sin(np.linspace(0, 3 * np.pi, len(months)))\n",
+        "    noise = np.random.normal(0, 5, len(months))\n",
+        "    monthly_sales = np.clip(trend + seasonality + noise, a_min=0, a_max=None).astype(int)\n",
+        "\n",
+        "    return list(zip(months.strftime(\"%Y-%m\"), monthly_sales))"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "L2ak1HlcgoTe"
+      },
+      "source": [
+        "### *b. Run the function as part of building sales_data*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 35,
+      "metadata": {
+        "id": "SlJ24AUafoDB"
+      },
+      "outputs": [],
+      "source": [
+        "sales_data = []\n",
+        "for _, row in df_books.iterrows():\n",
+        "    records = generate_sales_profile(row[\"sentiment_label\"])\n",
+        "    for month, units in records:\n",
+        "        sales_data.append({\n",
+        "            \"title\": row[\"title\"],\n",
+        "            \"month\": month,\n",
+        "            \"units_sold\": units,\n",
+        "            \"sentiment_label\": row[\"sentiment_label\"]\n",
+        "        })"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "4IXZKcCSgxnq"
+      },
+      "source": [
+        "### *c. ✋🏻🛑⛔️ Create a df_sales DataFrame from sales_data*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 37,
+      "metadata": {
+        "id": "wcN6gtiZg-ws"
+      },
+      "outputs": [],
+      "source": [
+        "df_sales = pd.DataFrame(sales_data)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "EhIjz9WohAmZ"
+      },
+      "source": [
+        "### *d. Save df_sales as synthetic_sales_data.csv & view first few lines*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 38,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "MzbZvLcAhGaH",
+        "outputId": "312074f9-b3dc-440e-a0e0-e48642fbd8ca"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "                  title    month  units_sold sentiment_label\n",
+            "0  A Light in the Attic  2024-09          79         neutral\n",
+            "1  A Light in the Attic  2024-10          88         neutral\n",
+            "2  A Light in the Attic  2024-11          81         neutral\n",
+            "3  A Light in the Attic  2024-12          86         neutral\n",
+            "4  A Light in the Attic  2025-01          87         neutral\n"
+          ]
+        }
+      ],
+      "source": [
+        "df_sales.to_csv(\"synthetic_sales_data.csv\", index=False)\n",
+        "\n",
+        "print(df_sales.head())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "7g9gqBgQMtJn"
+      },
+      "source": [
+        "## **5.** 🎯 Generate synthetic customer reviews"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "Gi4y9M9KuDWx"
+      },
+      "source": [
+        "### *a. ✋🏻🛑⛔️ Ask ChatGPT to create a list of 50 distinct generic book review texts for the sentiment labels \"positive\", \"neutral\", and \"negative\" called synthetic_reviews_by_sentiment*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 40,
+      "metadata": {
+        "id": "b3cd2a50"
+      },
+      "outputs": [],
+      "source": [
+        "synthetic_reviews_by_sentiment = {\n",
+        "    \"positive\": [\n",
+        "        \"A compelling and heartwarming read that stayed with me long after I finished.\",\n",
+        "        \"Brilliantly written! The characters were unforgettable and the plot was engaging.\",\n",
+        "        \"One of the best books I've read this year — inspiring and emotionally rich.\",\n",
+        "        \"A masterpiece of storytelling. Every page felt purposeful and alive.\",\n",
+        "        \"I couldn't put it down. The pacing was perfect and the ending left me breathless.\",\n",
+        "        \"An absolute gem. The author has a gift for making you care deeply about every character.\",\n",
+        "        \"Beautifully crafted. The prose is lyrical and the themes resonate deeply.\",\n",
+        "        \"A refreshing and original story that exceeded all my expectations.\",\n",
+        "        \"Utterly captivating from the first page to the last. A must-read.\",\n",
+        "        \"The world-building was extraordinary — I felt completely immersed.\",\n",
+        "        \"This book changed the way I see the world. Profound and thought-provoking.\",\n",
+        "        \"A joy to read. Witty, warm, and full of heart.\",\n",
+        "        \"I laughed, I cried, and I didn't want it to end. Truly special.\",\n",
+        "        \"The character development was exceptional — I grew to love them all.\",\n",
+        "        \"A beautifully told story with depth, nuance, and genuine emotional impact.\",\n",
+        "        \"One of those rare books that feels like it was written just for you.\",\n",
+        "        \"Gripping, intelligent, and deeply moving. Highly recommend.\",\n",
+        "        \"The writing is sharp and confident. A truly impressive debut.\",\n",
+        "        \"I've recommended this to everyone I know. It's just that good.\",\n",
+        "        \"An uplifting and unforgettable story that restores your faith in humanity.\",\n",
+        "        \"Every chapter pulled me deeper in. I read the whole thing in one sitting.\",\n",
+        "        \"The dialogue felt so real and natural — the characters jumped off the page.\",\n",
+        "        \"A powerful narrative with a message that will stay with me for years.\",\n",
+        "        \"Simply wonderful. Funny, touching, and beautifully observed.\",\n",
+        "        \"A rare find — a book that is both entertaining and genuinely meaningful.\",\n",
+        "        \"The plot twists were stunning. I never saw them coming but they felt earned.\",\n",
+        "        \"Rich in detail and atmosphere. The author clearly did their research.\",\n",
+        "        \"An emotional rollercoaster in the best possible way.\",\n",
+        "        \"Flawlessly executed. This is exactly what great fiction should feel like.\",\n",
+        "        \"A brilliant exploration of the human condition, told with grace and insight.\",\n",
+        "        \"I finished this with a huge smile on my face. Pure reading pleasure.\",\n",
+        "        \"Warm, wise, and wonderfully written. A new favourite.\",\n",
+        "        \"The kind of book that reminds you why you love reading.\",\n",
+        "        \"Exceptional storytelling — complex, compassionate, and completely absorbing.\"\n",
+        "    ],\n",
+        "    \"neutral\": [\n",
+        "        \"An average book — not great, but not bad either.\",\n",
+        "        \"Some parts really stood out, others felt a bit flat.\",\n",
+        "        \"It was okay overall. A decent way to pass the time.\",\n",
+        "        \"Interesting enough premise, but the execution was a bit uneven.\",\n",
+        "        \"I enjoyed parts of it, though it didn't quite live up to the hype.\",\n",
+        "        \"A solid read, but nothing I'd rush to recommend.\",\n",
+        "        \"The story had potential, but it felt like it never fully delivered.\",\n",
+        "        \"Not bad, not great. I finished it, which counts for something.\",\n",
+        "        \"Some chapters were genuinely gripping; others dragged on a bit.\",\n",
+        "        \"A competent book. Well-written in places, forgettable in others.\",\n",
+        "        \"It kept my interest without ever truly exciting me.\",\n",
+        "        \"A middle-of-the-road read — pleasant but unmemorable.\",\n",
+        "        \"The writing was fine. The story was fine. Overall, just fine.\",\n",
+        "        \"I can see why others loved it, even if it didn't click for me personally.\",\n",
+        "        \"Has its moments, but also has its lulls. A mixed bag.\",\n",
+        "        \"Worth reading if you're a fan of the genre, but it won't blow you away.\",\n",
+        "        \"I liked the concept more than the execution.\",\n",
+        "        \"A reasonable effort. I don't regret reading it, but I wouldn't reread it.\",\n",
+        "        \"The first half was stronger than the second.\",\n",
+        "        \"Enjoyable in a lightweight way. Nothing that will linger long.\",\n",
+        "        \"Not particularly original, but competently done.\",\n",
+        "        \"A functional story that does what it sets out to do, nothing more.\",\n",
+        "        \"The characters were likeable enough, if not especially memorable.\",\n",
+        "        \"It passed the time pleasantly. No strong feelings either way.\",\n",
+        "        \"Somewhere between a 3 and a 4 out of 5 — solidly average.\",\n",
+        "        \"Some good ideas here, but they weren't fully developed.\",\n",
+        "        \"The plot moved along, though I never felt urgently compelled to keep reading.\",\n",
+        "        \"A book that plays it safe — comforting but not particularly challenging.\",\n",
+        "        \"Decent writing, predictable story. A passable read.\",\n",
+        "        \"I'd neither seek out this author again nor actively avoid them.\",\n",
+        "        \"It scratched the itch for light reading, without being particularly memorable.\",\n",
+        "        \"Readable and inoffensive, if not especially inspiring.\",\n",
+        "        \"The ending felt a little too neat, but the journey was okay.\"\n",
+        "    ],\n",
+        "    \"negative\": [\n",
+        "        \"I struggled to get through this one — it just didn't grab me.\",\n",
+        "        \"The plot was confusing and the characters felt underdeveloped.\",\n",
+        "        \"Disappointing. I had high hopes, but they weren't met.\",\n",
+        "        \"I forced myself to finish it but honestly wish I hadn't bothered.\",\n",
+        "        \"The pacing was painfully slow and I found myself skipping pages.\",\n",
+        "        \"The characters were flat and I couldn't connect with any of them.\",\n",
+        "        \"Overhyped and underwhelming. Not sure what all the fuss is about.\",\n",
+        "        \"The writing felt clunky and the dialogue was unconvincing.\",\n",
+        "        \"I lost the plot entirely around chapter five and never recovered.\",\n",
+        "        \"A promising premise completely wasted by poor execution.\",\n",
+        "        \"Tedious and repetitive. The story went in circles.\",\n",
+        "        \"I kept waiting for it to get interesting. It never did.\",\n",
+        "        \"The ending was a massive letdown after an already slow build.\",\n",
+        "        \"I found the main character deeply unlikeable and hard to root for.\",\n",
+        "        \"Far too long for the story it was trying to tell.\",\n",
+        "        \"The world-building was confusing and the rules kept changing.\",\n",
+        "        \"I've read better books in the same genre that cost half the price.\",\n",
+        "        \"Felt like a first draft. Could have used a much stronger edit.\",\n",
+        "        \"The tone was inconsistent — I couldn't tell if it was trying to be funny or serious.\",\n",
+        "        \"Not for me at all. I abandoned it at the halfway mark.\",\n",
+        "        \"The prose was purple and overwrought. Less would have been more.\",\n",
+        "        \"I found the themes heavy-handed and the message preachy.\",\n",
+        "        \"Predictable from page one. Nothing surprised or delighted me.\",\n",
+        "        \"The secondary characters were more interesting than the lead, which was a problem.\",\n",
+        "        \"A real struggle to finish. I persisted out of stubbornness, not enjoyment.\",\n",
+        "        \"The plot holes were too large to ignore and broke my immersion completely.\",\n",
+        "        \"Felt generic and derivative. I've seen this story told much better elsewhere.\",\n",
+        "        \"The romance subplot felt forced and took away from the main story.\",\n",
+        "        \"Poorly structured — the story jumped around in a way that felt chaotic.\",\n",
+        "        \"I didn't care what happened to any of the characters by the end.\",\n",
+        "        \"The humour fell flat for me throughout. More cringeworthy than funny.\",\n",
+        "        \"A disappointment from start to finish. I won't be reading the sequel.\",\n",
+        "        \"Too much telling and not enough showing. A basic craft issue.\"\n",
+        "    ]\n",
+        "}"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "fQhfVaDmuULT"
+      },
+      "source": [
+        "### *b. Generate 10 reviews per book using random sampling from the corresponding 50*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 41,
+      "metadata": {
+        "id": "l2SRc3PjuTGM"
+      },
+      "outputs": [],
+      "source": [
+        "review_rows = []\n",
+        "for _, row in df_books.iterrows():\n",
+        "    title = row['title']\n",
+        "    sentiment_label = row['sentiment_label']\n",
+        "    review_pool = synthetic_reviews_by_sentiment[sentiment_label]\n",
+        "    sampled_reviews = random.sample(review_pool, 10)\n",
+        "    for review_text in sampled_reviews:\n",
+        "        review_rows.append({\n",
+        "            \"title\": title,\n",
+        "            \"sentiment_label\": sentiment_label,\n",
+        "            \"review_text\": review_text,\n",
+        "            \"rating\": row['rating'],\n",
+        "            \"popularity_score\": row['popularity_score']\n",
+        "        })"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "bmJMXF-Bukdm"
+      },
+      "source": [
+        "### *c. Create the final dataframe df_reviews & save it as synthetic_book_reviews.csv*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 42,
+      "metadata": {
+        "id": "ZUKUqZsuumsp"
+      },
+      "outputs": [],
+      "source": [
+        "df_reviews = pd.DataFrame(review_rows)\n",
+        "df_reviews.to_csv(\"synthetic_book_reviews.csv\", index=False)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "### *c. inputs for R*"
+      ],
+      "metadata": {
+        "id": "_602pYUS3gY5"
+      }
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 43,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "3946e521",
+        "outputId": "64c9005b-3916-4d9b-b9fa-a5b90ad256d7"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ Wrote synthetic_title_level_features.csv\n",
+            "✅ Wrote synthetic_monthly_revenue_series.csv\n"
+          ]
+        }
+      ],
+      "source": [
+        "import numpy as np\n",
+        "\n",
+        "def _safe_num(s):\n",
+        "    return pd.to_numeric(\n",
+        "        pd.Series(s).astype(str).str.replace(r\"[^0-9.]\", \"\", regex=True),\n",
+        "        errors=\"coerce\"\n",
+        "    )\n",
+        "\n",
+        "# --- Clean book metadata (price/rating) ---\n",
+        "df_books_r = df_books.copy()\n",
+        "if \"price\" in df_books_r.columns:\n",
+        "    df_books_r[\"price\"] = _safe_num(df_books_r[\"price\"])\n",
+        "if \"rating\" in df_books_r.columns:\n",
+        "    df_books_r[\"rating\"] = _safe_num(df_books_r[\"rating\"])\n",
+        "\n",
+        "df_books_r[\"title\"] = df_books_r[\"title\"].astype(str).str.strip()\n",
+        "\n",
+        "# --- Clean sales ---\n",
+        "df_sales_r = df_sales.copy()\n",
+        "df_sales_r[\"title\"] = df_sales_r[\"title\"].astype(str).str.strip()\n",
+        "df_sales_r[\"month\"] = pd.to_datetime(df_sales_r[\"month\"], errors=\"coerce\")\n",
+        "df_sales_r[\"units_sold\"] = _safe_num(df_sales_r[\"units_sold\"])\n",
+        "\n",
+        "# --- Clean reviews ---\n",
+        "df_reviews_r = df_reviews.copy()\n",
+        "df_reviews_r[\"title\"] = df_reviews_r[\"title\"].astype(str).str.strip()\n",
+        "df_reviews_r[\"sentiment_label\"] = df_reviews_r[\"sentiment_label\"].astype(str).str.lower().str.strip()\n",
+        "if \"rating\" in df_reviews_r.columns:\n",
+        "    df_reviews_r[\"rating\"] = _safe_num(df_reviews_r[\"rating\"])\n",
+        "if \"popularity_score\" in df_reviews_r.columns:\n",
+        "    df_reviews_r[\"popularity_score\"] = _safe_num(df_reviews_r[\"popularity_score\"])\n",
+        "\n",
+        "# --- Sentiment shares per title (from reviews) ---\n",
+        "sent_counts = (\n",
+        "    df_reviews_r.groupby([\"title\", \"sentiment_label\"])\n",
+        "    .size()\n",
+        "    .unstack(fill_value=0)\n",
+        ")\n",
+        "for lab in [\"positive\", \"neutral\", \"negative\"]:\n",
+        "    if lab not in sent_counts.columns:\n",
+        "        sent_counts[lab] = 0\n",
+        "\n",
+        "sent_counts[\"total_reviews\"] = sent_counts[[\"positive\", \"neutral\", \"negative\"]].sum(axis=1)\n",
+        "den = sent_counts[\"total_reviews\"].replace(0, np.nan)\n",
+        "sent_counts[\"share_positive\"] = sent_counts[\"positive\"] / den\n",
+        "sent_counts[\"share_neutral\"]  = sent_counts[\"neutral\"]  / den\n",
+        "sent_counts[\"share_negative\"] = sent_counts[\"negative\"] / den\n",
+        "sent_counts = sent_counts.reset_index()\n",
+        "\n",
+        "# --- Sales aggregation per title ---\n",
+        "sales_by_title = (\n",
+        "    df_sales_r.dropna(subset=[\"title\"])\n",
+        "    .groupby(\"title\", as_index=False)\n",
+        "    .agg(\n",
+        "        months_observed=(\"month\", \"nunique\"),\n",
+        "        avg_units_sold=(\"units_sold\", \"mean\"),\n",
+        "        total_units_sold=(\"units_sold\", \"sum\"),\n",
+        "    )\n",
+        ")\n",
+        "\n",
+        "# --- Title-level features (join sales + books + sentiment) ---\n",
+        "df_title = (\n",
+        "    sales_by_title\n",
+        "    .merge(df_books_r[[\"title\", \"price\", \"rating\"]], on=\"title\", how=\"left\")\n",
+        "    .merge(sent_counts[[\"title\", \"share_positive\", \"share_neutral\", \"share_negative\", \"total_reviews\"]],\n",
+        "           on=\"title\", how=\"left\")\n",
+        ")\n",
+        "\n",
+        "df_title[\"avg_revenue\"] = df_title[\"avg_units_sold\"] * df_title[\"price\"]\n",
+        "df_title[\"total_revenue\"] = df_title[\"total_units_sold\"] * df_title[\"price\"]\n",
+        "\n",
+        "df_title.to_csv(\"synthetic_title_level_features.csv\", index=False)\n",
+        "print(\"✅ Wrote synthetic_title_level_features.csv\")\n",
+        "\n",
+        "# --- Monthly revenue series (proxy: units_sold * price) ---\n",
+        "monthly_rev = (\n",
+        "    df_sales_r.merge(df_books_r[[\"title\", \"price\"]], on=\"title\", how=\"left\")\n",
+        ")\n",
+        "monthly_rev[\"revenue\"] = monthly_rev[\"units_sold\"] * monthly_rev[\"price\"]\n",
+        "\n",
+        "df_monthly = (\n",
+        "    monthly_rev.dropna(subset=[\"month\"])\n",
+        "    .groupby(\"month\", as_index=False)[\"revenue\"]\n",
+        "    .sum()\n",
+        "    .rename(columns={\"revenue\": \"total_revenue\"})\n",
+        "    .sort_values(\"month\")\n",
+        ")\n",
+        "# if revenue is all NA (e.g., missing price), fallback to units_sold as a teaching proxy\n",
+        "if df_monthly[\"total_revenue\"].notna().sum() == 0:\n",
+        "    df_monthly = (\n",
+        "        df_sales_r.dropna(subset=[\"month\"])\n",
+        "        .groupby(\"month\", as_index=False)[\"units_sold\"]\n",
+        "        .sum()\n",
+        "        .rename(columns={\"units_sold\": \"total_revenue\"})\n",
+        "        .sort_values(\"month\")\n",
+        "    )\n",
+        "\n",
+        "df_monthly[\"month\"] = pd.to_datetime(df_monthly[\"month\"], errors=\"coerce\").dt.strftime(\"%Y-%m-%d\")\n",
+        "df_monthly.to_csv(\"synthetic_monthly_revenue_series.csv\", index=False)\n",
+        "print(\"✅ Wrote synthetic_monthly_revenue_series.csv\")\n"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "RYvGyVfXuo54"
+      },
+      "source": [
+        "### *d. ✋🏻🛑⛔️ View the first few lines*"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 44,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 206
+        },
+        "id": "xfE8NMqOurKo",
+        "outputId": "87a8b891-5b0a-4581-d1e9-e6c3052f569a"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "                  title sentiment_label  \\\n",
+              "0  A Light in the Attic         neutral   \n",
+              "1  A Light in the Attic         neutral   \n",
+              "2  A Light in the Attic         neutral   \n",
+              "3  A Light in the Attic         neutral   \n",
+              "4  A Light in the Attic         neutral   \n",
+              "\n",
+              "                                         review_text rating  popularity_score  \n",
+              "0   A solid read, but nothing I'd rush to recommend.  Three                 3  \n",
+              "1  It kept my interest without ever truly excitin...  Three                 3  \n",
+              "2  Enjoyable in a lightweight way. Nothing that w...  Three                 3  \n",
+              "3  Has its moments, but also has its lulls. A mix...  Three                 3  \n",
+              "4  Worth reading if you're a fan of the genre, bu...  Three                 3  "
+            ],
+            "text/html": [
+              "\n",
+              "  <div id=\"df-df099fdf-fd04-4b7a-82e8-3749cda27cda\" class=\"colab-df-container\">\n",
+              "    <div>\n",
+              "<style scoped>\n",
+              "    .dataframe tbody tr th:only-of-type {\n",
+              "        vertical-align: middle;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe tbody tr th {\n",
+              "        vertical-align: top;\n",
+              "    }\n",
+              "\n",
+              "    .dataframe thead th {\n",
+              "        text-align: right;\n",
+              "    }\n",
+              "</style>\n",
+              "<table border=\"1\" class=\"dataframe\">\n",
+              "  <thead>\n",
+              "    <tr style=\"text-align: right;\">\n",
+              "      <th></th>\n",
+              "      <th>title</th>\n",
+              "      <th>sentiment_label</th>\n",
+              "      <th>review_text</th>\n",
+              "      <th>rating</th>\n",
+              "      <th>popularity_score</th>\n",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <th>0</th>\n",
+              "      <td>A Light in the Attic</td>\n",
+              "      <td>neutral</td>\n",
+              "      <td>A solid read, but nothing I'd rush to recommend.</td>\n",
+              "      <td>Three</td>\n",
+              "      <td>3</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>1</th>\n",
+              "      <td>A Light in the Attic</td>\n",
+              "      <td>neutral</td>\n",
+              "      <td>It kept my interest without ever truly excitin...</td>\n",
+              "      <td>Three</td>\n",
+              "      <td>3</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>2</th>\n",
+              "      <td>A Light in the Attic</td>\n",
+              "      <td>neutral</td>\n",
+              "      <td>Enjoyable in a lightweight way. Nothing that w...</td>\n",
+              "      <td>Three</td>\n",
+              "      <td>3</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>3</th>\n",
+              "      <td>A Light in the Attic</td>\n",
+              "      <td>neutral</td>\n",
+              "      <td>Has its moments, but also has its lulls. A mix...</td>\n",
+              "      <td>Three</td>\n",
+              "      <td>3</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>4</th>\n",
+              "      <td>A Light in the Attic</td>\n",
+              "      <td>neutral</td>\n",
+              "      <td>Worth reading if you're a fan of the genre, bu...</td>\n",
+              "      <td>Three</td>\n",
+              "      <td>3</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table>\n",
+              "</div>\n",
+              "    <div class=\"colab-df-buttons\">\n",
+              "\n",
+              "  <div class=\"colab-df-container\">\n",
+              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-df099fdf-fd04-4b7a-82e8-3749cda27cda')\"\n",
+              "            title=\"Convert this dataframe to an interactive table.\"\n",
+              "            style=\"display:none;\">\n",
+              "\n",
+              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
+              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
+              "  </svg>\n",
+              "    </button>\n",
+              "\n",
+              "  <style>\n",
+              "    .colab-df-container {\n",
+              "      display:flex;\n",
+              "      gap: 12px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert {\n",
+              "      background-color: #E8F0FE;\n",
+              "      border: none;\n",
+              "      border-radius: 50%;\n",
+              "      cursor: pointer;\n",
+              "      display: none;\n",
+              "      fill: #1967D2;\n",
+              "      height: 32px;\n",
+              "      padding: 0 0 0 0;\n",
+              "      width: 32px;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-convert:hover {\n",
+              "      background-color: #E2EBFA;\n",
+              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
+              "      fill: #174EA6;\n",
+              "    }\n",
+              "\n",
+              "    .colab-df-buttons div {\n",
+              "      margin-bottom: 4px;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert {\n",
+              "      background-color: #3B4455;\n",
+              "      fill: #D2E3FC;\n",
+              "    }\n",
+              "\n",
+              "    [theme=dark] .colab-df-convert:hover {\n",
+              "      background-color: #434B5C;\n",
+              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
+              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
+              "      fill: #FFFFFF;\n",
+              "    }\n",
+              "  </style>\n",
+              "\n",
+              "    <script>\n",
+              "      const buttonEl =\n",
+              "        document.querySelector('#df-df099fdf-fd04-4b7a-82e8-3749cda27cda button.colab-df-convert');\n",
+              "      buttonEl.style.display =\n",
+              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
+              "\n",
+              "      async function convertToInteractive(key) {\n",
+              "        const element = document.querySelector('#df-df099fdf-fd04-4b7a-82e8-3749cda27cda');\n",
+              "        const dataTable =\n",
+              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
+              "                                                    [key], {});\n",
+              "        if (!dataTable) return;\n",
+              "\n",
+              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
+              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
+              "          + ' to learn more about interactive tables.';\n",
+              "        element.innerHTML = '';\n",
+              "        dataTable['output_type'] = 'display_data';\n",
+              "        await google.colab.output.renderOutput(dataTable, element);\n",
+              "        const docLink = document.createElement('div');\n",
+              "        docLink.innerHTML = docLinkHtml;\n",
+              "        element.appendChild(docLink);\n",
+              "      }\n",
+              "    </script>\n",
+              "  </div>\n",
+              "\n",
+              "\n",
+              "    </div>\n",
+              "  </div>\n"
+            ],
+            "application/vnd.google.colaboratory.intrinsic+json": {
+              "type": "dataframe",
+              "variable_name": "df_reviews",
+              "summary": "{\n  \"name\": \"df_reviews\",\n  \"rows\": 15000,\n  \"fields\": [\n    {\n      \"column\": \"title\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 999,\n        \"samples\": [\n          \"The Grownup\",\n          \"Persepolis: The Story of a Childhood (Persepolis #1-2)\",\n          \"Ayumi's Violin\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"sentiment_label\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 3,\n        \"samples\": [\n          \"neutral\",\n          \"negative\",\n          \"positive\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"review_text\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 100,\n        \"samples\": [\n          \"Warm, wise, and wonderfully written. A new favourite.\",\n          \"A masterpiece of storytelling. Every page felt purposeful and alive.\",\n          \"I can see why others loved it, even if it didn't click for me personally.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"rating\",\n      \"properties\": {\n        \"dtype\": \"category\",\n        \"num_unique_values\": 5,\n        \"samples\": [\n          \"One\",\n          \"Two\",\n          \"Four\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"popularity_score\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 1,\n        \"min\": 1,\n        \"max\": 5,\n        \"num_unique_values\": 5,\n        \"samples\": [\n          2,\n          5,\n          4\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
+            }
+          },
+          "metadata": {},
+          "execution_count": 44
+        }
+      ],
+      "source": [
+        "df_reviews.head()"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "collapsed_sections": [
+        "jpASMyIQMaAq",
+        "lquNYCbfL9IM",
+        "0IWuNpxxYDJF",
+        "oCdTsin2Yfp3",
+        "T0TOeRC4Yrnn",
+        "duI5dv3CZYvF",
+        "qMjRKMBQZlJi",
+        "p-1Pr2szaqLk",
+        "SIaJUGIpaH4V",
+        "pY4yCoIuaQqp",
+        "n4-TaNTFgPak",
+        "HnngRNTgacYt",
+        "HF9F9HIzgT7Z",
+        "T8AdKkmASq9a",
+        "OhXbdGD5fH0c",
+        "L2ak1HlcgoTe",
+        "4IXZKcCSgxnq",
+        "EhIjz9WohAmZ",
+        "Gi4y9M9KuDWx",
+        "fQhfVaDmuULT",
+        "bmJMXF-Bukdm",
+        "RYvGyVfXuo54"
+      ],
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}

gitattributes (2)

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+background_top.png filter=lfs diff=lfs merge=lfs -text

gitattributes (3)

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+background_top.png filter=lfs diff=lfs merge=lfs -text

requirements (1).txt

@@ -0,0 +1,17 @@
+gradio==6.0.0
+pandas>=2.0.0
+numpy>=1.24.0
+matplotlib>=3.7.0
+seaborn>=0.13.0
+statsmodels>=0.14.0
+scikit-learn>=1.3.0
+papermill>=2.5.0
+nbformat>=5.9.0
+pillow>=10.0.0
+requests>=2.31.0
+beautifulsoup4>=4.12.0
+vaderSentiment>=3.3.2
+huggingface_hub>=0.20.0
+textblob>=0.18.0
+faker>=20.0.0
+plotly>=5.18.0