Upload 12 files

.gitattributes

@@ -0,0 +1 @@
+background_top.png filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,49 @@
+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
+
+# System deps: R + compilers + common R pkg build deps
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    r-base \
+    r-base-dev \
+    build-essential \
+    curl \
+    git \
+    libcurl4-openssl-dev \
+    libssl-dev \
+    libxml2-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install required R packages
+RUN R -e "install.packages(c('forecast','ggplot2','jsonlite','readr','dplyr','tidyr','stringr','lubridate','broom'), repos='https://cloud.r-project.org')"
+
+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 that the notebooks install via !pip install
+# so papermill doesn't waste time or fail on them at runtime:
+#   datacreation.ipynb:  beautifulsoup4 pandas matplotlib seaborn numpy textblob
+#   pythonanalysis.ipynb: pandas matplotlib seaborn numpy textblob faker transformers vaderSentiment
+# Most are already in requirements.txt; add the extras:
+RUN pip install --no-cache-dir textblob faker transformers
+
+RUN python -m ipykernel install --user --name python3 --display-name "Python 3"
+
+# R deps for notebook execution via papermill (IRkernel)
+RUN R -e "install.packages('IRkernel', repos='https://cloud.r-project.org/')"
+RUN R -e "IRkernel::installspec(user = FALSE)"
+
+EXPOSE 7860
+
+CMD ["python", "app.py"]

README.md

@@ -0,0 +1,10 @@
+---
+title: RX12WorkshopApp
+emoji: 📊
+colorFrom: blue
+colorTo: red
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,622 @@
+import os
+import re
+import json
+import time
+import traceback
+from pathlib import Path
+from typing import Dict, Any, List, Optional, Tuple
+
+import pandas as pd
+import gradio as gr
+import papermill as pm
+
+# 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()
+NB3 = os.environ.get("NB3", "ranalysis.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"
+R_FIG_DIR = ART_DIR / "r" / "figures"
+R_TAB_DIR = ART_DIR / "r" / "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()
+
+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, R_FIG_DIR, R_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")),
+        },
+        "r": {
+            "figures": _ls(R_FIG_DIR, (".png", ".jpg", ".jpeg")),
+            "tables": _ls(R_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_r() -> str:
+    try:
+        log = run_notebook(NB3)
+        idx = artifacts_index()
+        figs = idx["r"]["figures"]
+        tabs = idx["r"]["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 1/3: Data Creation (web scraping + synthetic data)")
+    logs.append("=" * 50)
+    logs.append(run_datacreation())
+    logs.append("")
+    logs.append("=" * 50)
+    logs.append("STEP 2/3: Python Analysis (sentiment, ARIMA, dashboard)")
+    logs.append("=" * 50)
+    logs.append(run_pythonanalysis())
+    logs.append("")
+    logs.append("=" * 50)
+    logs.append("STEP 3/3: R Analysis (ETS/ARIMA forecasting)")
+    logs.append("=" * 50)
+    logs.append(run_r())
+    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), f"Python | {p.stem.replace('_', ' ').title()}"))
+    for p in sorted(R_FIG_DIR.glob("*.png")):
+        items.append((str(p), f"R | {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()
+
+    # Build table choices
+    table_choices = []
+    for scope in ("python", "r"):
+        for name in idx[scope]["tables"]:
+            table_choices.append(f"{scope}/{name}")
+
+    # Default: show first table if available
+    default_df = pd.DataFrame()
+    if table_choices:
+        parts = table_choices[0].split("/", 1)
+        base = PY_TAB_DIR if parts[0] == "python" else R_TAB_DIR
+        default_df = _load_table_safe(base / parts[1])
+
+    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 or "/" not in choice:
+        return pd.DataFrame([{"hint": "Select a table above."}])
+    scope, name = choice.split("/", 1)
+    base = {"python": PY_TAB_DIR, "r": R_TAB_DIR}.get(scope)
+    if not base:
+        return pd.DataFrame([{"error": f"Unknown scope: {scope}"}])
+    path = base / name
+    if not path.exists():
+        return pd.DataFrame([{"error": f"File not found: {path}"}])
+    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 (Tab 3) -- 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 Python and R analysis pipelines.
+
+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"|"r", "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 R regression, the R notebook focuses on forecasting, show accuracy_table.csv.
+- If the user asks about forecast accuracy or model comparison, show accuracy_table.csv or forecast_compare.png.
+- 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 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()
+
+    if 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 artifact paths
+    fig_out = None
+    tab_out = None
+    show = directive.get("show", "none")
+    scope = directive.get("scope", "")
+    fname = directive.get("filename", "")
+
+    if show == "figure" and scope and fname:
+        base = {"python": PY_FIG_DIR, "r": R_FIG_DIR}.get(scope)
+        if base and (base / fname).exists():
+            fig_out = str(base / fname)
+        else:
+            reply += f"\n\n*(Could not find figure: {scope}/{fname})*"
+
+    if show == "table" and scope and fname:
+        base = {"python": PY_TAB_DIR, "r": R_TAB_DIR}.get(scope)
+        if base and (base / fname).exists():
+            tab_out = _load_table_safe(base / fname)
+        else:
+            reply += f"\n\n*(Could not find table: {scope}/{fname})*"
+
+    new_history = (history or []) + [
+        {"role": "user", "content": user_msg},
+        {"role": "assistant", "content": reply},
+    ]
+
+    return new_history, "", fig_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 any(idx[s]["figures"] or idx[s]["tables"] for s in ("python", "r")):
+        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 for sampled titles. {kpi_text}",
+            {"show": "figure", "scope": "python", "filename": "sales_trends_sampled_titles.png"},
+        )
+
+    if any(w in msg_lower for w in ["sentiment", "review", "positive", "negative"]):
+        return (
+            f"Here is the sentiment distribution across sampled book titles. {kpi_text}",
+            {"show": "figure", "scope": "python", "filename": "sentiment_distribution_sampled_titles.png"},
+        )
+
+    if any(w in msg_lower for w in ["arima", "forecast", "predict"]):
+        if "compar" in msg_lower or "ets" in msg_lower or "accuracy" in msg_lower:
+            if "forecast_compare.png" in idx.get("r", {}).get("figures", []):
+                return (
+                    "Here is the ARIMA+Fourier vs ETS forecast comparison from the R analysis.",
+                    {"show": "figure", "scope": "r", "filename": "forecast_compare.png"},
+                )
+        return (
+            f"Here are the ARIMA forecasts for sampled titles from the Python analysis. {kpi_text}",
+            {"show": "figure", "scope": "python", "filename": "arima_forecasts_sampled_titles.png"},
+        )
+
+    if any(w in msg_lower for w in ["regression", "lm", "coefficient", "price effect", "rating effect"]):
+        return (
+            "The R notebook focuses on forecasting rather than regression. "
+            "Here is the forecast accuracy comparison instead.",
+            {"show": "table", "scope": "r", "filename": "accuracy_table.csv"},
+        )
+
+    if any(w in msg_lower for w in ["top", "best sell", "popular", "rank"]):
+        return (
+            f"Here are the top-selling titles by units sold. {kpi_text}",
+            {"show": "table", "scope": "python", "filename": "top_titles_by_units_sold.csv"},
+        )
+
+    if any(w in msg_lower for w in ["accuracy", "benchmark", "rmse", "mape"]):
+        return (
+            "Here is the forecast accuracy comparison (ARIMA+Fourier vs ETS) from the R analysis.",
+            {"show": "table", "scope": "r", "filename": "accuracy_table.csv"},
+        )
+
+    if any(w in msg_lower for w in ["r analysis", "r output", "r result"]):
+        if "forecast_compare.png" in idx.get("r", {}).get("figures", []):
+            return (
+                "Here is the main R output: forecast model comparison plot.",
+                {"show": "figure", "scope": "r", "filename": "forecast_compare.png"},
+            )
+
+    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, "
+            "forecast accuracy, or top sellers to see specific visualizations.",
+            {"show": "table", "scope": "python", "filename": "df_dashboard.csv"},
+        )
+
+    # Default
+    return (
+        f"I can show you various analyses. {kpi_text}\n\n"
+        "Try asking about: **sales trends**, **sentiment**, **ARIMA forecasts**, "
+        "**forecast accuracy**, **top sellers**, or **dashboard overview**.",
+        {"show": "none"},
+    )
+
+
+# =========================================================
+# 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 ""
+
+
+with gr.Blocks(title="RX12 Workshop App") as demo:
+
+    gr.Markdown(
+        "# RX12 - Intro to Python and R - Workshop App\n"
+        "*The app to integrate the three notebooks in to get a functioning blueprint of the group project's final product*",
+        elem_id="escp_title",
+    )
+
+    # ===========================================================
+    # TAB 1 -- Pipeline Runner
+    # ===========================================================
+    with gr.Tab("Pipeline Runner"):
+        gr.Markdown(
+        )
+
+        with gr.Row():
+            with gr.Column(scale=1):
+                btn_nb1 = gr.Button(
+                    "Step 1: Data Creation",
+                    variant="secondary",
+                )
+                gr.Markdown(
+                )
+            with gr.Column(scale=1):
+                btn_nb2 = gr.Button(
+                    "Step 2a: Python Analysis",
+                    variant="secondary",
+                )
+                gr.Markdown(
+                )
+            with gr.Column(scale=1):
+                btn_r = gr.Button(
+                    "Step 2b: R Analysis",
+                    variant="secondary",
+                )
+                gr.Markdown(
+                )
+
+        with gr.Row():
+            btn_all = gr.Button(
+                "Run All 3 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_r.click(run_r, outputs=[run_log])
+        btn_all.click(run_full_pipeline, outputs=[run_log])
+
+    # ===========================================================
+    # TAB 2 -- Results Gallery
+    # ===========================================================
+    with gr.Tab("Results Gallery"):
+        gr.Markdown(
+            "### All generated artifacts\n\n"
+            "After running the pipeline, click **Refresh** to load all figures and tables. "
+            "Figures are shown in the gallery; select a table from the dropdown to inspect it."
+        )
+
+        refresh_btn = gr.Button("Refresh Gallery", variant="primary")
+
+        gr.Markdown("#### Figures")
+        gallery = gr.Gallery(
+            label="All Figures (Python + R)",
+            columns=2,
+            height=480,
+            object_fit="contain",
+        )
+
+        gr.Markdown("#### Tables")
+        table_dropdown = gr.Dropdown(
+            label="Select a table to view",
+            choices=[],
+            interactive=True,
+        )
+        table_display = gr.Dataframe(
+            label="Table Preview",
+            interactive=False,
+        )
+
+        refresh_btn.click(
+            refresh_gallery,
+            outputs=[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'):
+        gr.Markdown(
+            "### Ask questions, get visualisations\n\n"
+            "Describe what you want to see and the AI will pick the right chart or table. "
+            + (
+                "*LLM is active.*"
+                if LLM_ENABLED
+                else "*No API key detected \u2014 using keyword matching. "
+                     "Set `HF_API_KEY` in Space secrets for full LLM support.*"
+            )
+        )
+
+        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 drives revenue? / Compare forecast models",
+                    lines=1,
+                )
+                gr.Examples(
+                    examples=[
+                        "Show me the sales trends",
+                        "What does the sentiment look like?",
+                        "Which titles sell the most?",
+                        "Show the forecast accuracy comparison",
+                        "Compare the ARIMA and ETS forecasts",
+                        "Give me a dashboard overview",
+                    ],
+                    inputs=user_input,
+                )
+
+            with gr.Column(scale=1):
+                ai_figure = gr.Image(
+                    label="Visualisation",
+                    height=350,
+                )
+                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(css=load_css(), allowed_paths=[str(BASE_DIR)])

datacreation.ipynb

@@ -0,0 +1,1087 @@
+{
+  "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": 1,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "f48c8f8c",
+        "outputId": "13d0dd5e-82c6-489f-b1f0-e970186a4eb7"
+      },
+      "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": 2,
+      "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": 3,
+      "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": 4,
+      "metadata": {
+        "id": "l5FkkNhUYTHh"
+      },
+      "outputs": [],
+      "source": [
+        "# 🗂️ Create DataFrame\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": 5,
+      "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": 6,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 0
+        },
+        "id": "O_wIvTxYZqCK",
+        "outputId": "349b36b0-c008-4fd5-d4a4-dba38ae18337"
+      },
+      "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-04c87660-4415-45e9-ad3b-3fa19d9402c2\" 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-04c87660-4415-45e9-ad3b-3fa19d9402c2')\"\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-04c87660-4415-45e9-ad3b-3fa19d9402c2 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-04c87660-4415-45e9-ad3b-3fa19d9402c2');\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\": 1000,\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\": 14.446689669952772,\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": 6
+        }
+      ],
+      "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": 7,
+      "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": 8,
+      "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": 9,
+      "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": 10,
+      "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": 11,
+      "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": 12,
+      "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": 13,
+      "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": 14,
+      "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": 15,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "MzbZvLcAhGaH",
+        "outputId": "c692bb04-7263-4115-a2ba-c72fe0180722"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "                  title    month  units_sold sentiment_label\n",
+            "0  A Light in the Attic  2024-08         100         neutral\n",
+            "1  A Light in the Attic  2024-09         109         neutral\n",
+            "2  A Light in the Attic  2024-10         102         neutral\n",
+            "3  A Light in the Attic  2024-11         107         neutral\n",
+            "4  A Light in the Attic  2024-12         108         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": 16,
+      "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",
+        "        \"The author's storytelling was vivid and powerful. Highly recommended!\",\n",
+        "        \"An absolute masterpiece. I couldn't put it down from start to finish.\",\n",
+        "        \"Gripping, intelligent, and beautifully crafted — I loved every page.\",\n",
+        "        \"The emotional depth and layered narrative were just perfect.\",\n",
+        "        \"A thought-provoking journey with stunning character development.\",\n",
+        "        \"Everything about this book just clicked. A top-tier read!\",\n",
+        "        \"A flawless blend of emotion, intrigue, and style. Truly impressive.\",\n",
+        "        \"Absolutely stunning work of fiction. Five stars from me.\",\n",
+        "        \"Remarkably executed with breathtaking prose.\",\n",
+        "        \"The pacing was perfect and I was hooked from page one.\",\n",
+        "        \"Heartfelt and hopeful — a story well worth telling.\",\n",
+        "        \"A vivid journey through complex emotions and stunning imagery.\",\n",
+        "        \"This book had soul. Every word felt like it mattered.\",\n",
+        "        \"It delivered more than I ever expected. Powerful and wise.\",\n",
+        "        \"The characters leapt off the page and into my heart.\",\n",
+        "        \"I could see every scene clearly in my mind — beautifully descriptive.\",\n",
+        "        \"Refreshing, original, and impossible to forget.\",\n",
+        "        \"A radiant celebration of resilience and love.\",\n",
+        "        \"Powerful themes handled with grace and insight.\",\n",
+        "        \"An unforgettable literary experience.\",\n",
+        "        \"The best book club pick we’ve had all year.\",\n",
+        "        \"A layered, lyrical narrative that resonates deeply.\",\n",
+        "        \"Surprising, profound, and deeply humane.\",\n",
+        "        \"One of those rare books I wish I could read again for the first time.\",\n",
+        "        \"Both epic and intimate — a perfect balance.\",\n",
+        "        \"It reads like a love letter to the human spirit.\",\n",
+        "        \"Satisfying and uplifting with a memorable ending.\",\n",
+        "        \"This novel deserves every bit of praise it gets.\",\n",
+        "        \"Introspective, emotional, and elegantly composed.\",\n",
+        "        \"A tour de force in contemporary fiction.\",\n",
+        "        \"Left me smiling, teary-eyed, and completely fulfilled.\",\n",
+        "        \"A novel with the rare ability to entertain and enlighten.\",\n",
+        "        \"Incredibly moving. I highlighted so many lines.\",\n",
+        "        \"A smart, sensitive take on relationships and identity.\",\n",
+        "        \"You feel wiser by the end of it.\",\n",
+        "        \"A gorgeously crafted tale about hope and second chances.\",\n",
+        "        \"Poignant and real — a beautiful escape.\",\n",
+        "        \"Brims with insight and authenticity.\",\n",
+        "        \"Compelling characters and a satisfying plot.\",\n",
+        "        \"An empowering and important read.\",\n",
+        "        \"Elegantly crafted and deeply humane.\",\n",
+        "        \"Taut storytelling that never lets go.\",\n",
+        "        \"Each chapter offered a new treasure.\",\n",
+        "        \"Lyrical writing that stays with you.\",\n",
+        "        \"A wonderful blend of passion and thoughtfulness.\",\n",
+        "        \"Uplifting, honest, and completely engrossing.\",\n",
+        "        \"This one made me believe in storytelling again.\"\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",
+        "        \"The writing was fine, though I didn’t fully connect with the story.\",\n",
+        "        \"Had a few memorable moments but lacked depth in some areas.\",\n",
+        "        \"A mixed experience — neither fully engaging nor forgettable.\",\n",
+        "        \"There was potential, but it didn't quite come together for me.\",\n",
+        "        \"A reasonable effort that just didn’t leave a lasting impression.\",\n",
+        "        \"Serviceable but not something I'd go out of my way to recommend.\",\n",
+        "        \"Not much to dislike, but not much to rave about either.\",\n",
+        "        \"It had its strengths, though they didn’t shine consistently.\",\n",
+        "        \"I’m on the fence — parts were enjoyable, others not so much.\",\n",
+        "        \"The book had a unique concept but lacked execution.\",\n",
+        "        \"A middle-of-the-road read.\",\n",
+        "        \"Engaging at times, but it lost momentum.\",\n",
+        "        \"Would have benefited from stronger character development.\",\n",
+        "        \"It passed the time, but I wouldn't reread it.\",\n",
+        "        \"The plot had some holes that affected immersion.\",\n",
+        "        \"Mediocre pacing made it hard to stay invested.\",\n",
+        "        \"Satisfying in parts, underwhelming in others.\",\n",
+        "        \"Neutral on this one — didn’t love it or hate it.\",\n",
+        "        \"Fairly forgettable but with glimpses of promise.\",\n",
+        "        \"The themes were solid, but not well explored.\",\n",
+        "        \"Competent, just not compelling.\",\n",
+        "        \"Had moments of clarity and moments of confusion.\",\n",
+        "        \"I didn’t regret reading it, but I wouldn’t recommend it.\",\n",
+        "        \"Readable, yet uninspired.\",\n",
+        "        \"There was a spark, but it didn’t ignite.\",\n",
+        "        \"A slow burn that didn’t quite catch fire.\",\n",
+        "        \"I expected more nuance given the premise.\",\n",
+        "        \"A safe, inoffensive choice.\",\n",
+        "        \"Some parts lagged, others piqued my interest.\",\n",
+        "        \"Decent, but needed polish.\",\n",
+        "        \"Moderately engaging but didn’t stick the landing.\",\n",
+        "        \"It simply lacked that emotional punch.\",\n",
+        "        \"Just fine — no better, no worse.\",\n",
+        "        \"Some thoughtful passages amid otherwise dry writing.\",\n",
+        "        \"I appreciated the ideas more than the execution.\",\n",
+        "        \"Struggled with cohesion.\",\n",
+        "        \"Solidly average.\",\n",
+        "        \"Good on paper, flat in practice.\",\n",
+        "        \"A few bright spots, but mostly dim.\",\n",
+        "        \"The kind of book that fades from memory.\",\n",
+        "        \"It scratched the surface but didn’t dig deep.\",\n",
+        "        \"Standard fare with some promise.\",\n",
+        "        \"Okay, but not memorable.\",\n",
+        "        \"Had potential that went unrealized.\",\n",
+        "        \"Could have been tighter, sharper, deeper.\",\n",
+        "        \"A blend of mediocrity and mild interest.\",\n",
+        "        \"I kept reading, but barely.\"\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",
+        "        \"Uninspired writing and a story that never quite took off.\",\n",
+        "        \"Unfortunately, it was dull and predictable throughout.\",\n",
+        "        \"The pacing dragged and I couldn’t find anything compelling.\",\n",
+        "        \"This felt like a chore to read — lacked heart and originality.\",\n",
+        "        \"Nothing really worked for me in this book.\",\n",
+        "        \"A frustrating read that left me unsatisfied.\",\n",
+        "        \"I kept hoping it would improve, but it never did.\",\n",
+        "        \"The characters didn’t feel real, and the dialogue was forced.\",\n",
+        "        \"I couldn't connect with the story at all.\",\n",
+        "        \"A slow, meandering narrative with little payoff.\",\n",
+        "        \"Tried too hard to be deep, but just felt empty.\",\n",
+        "        \"The tone was uneven and confusing.\",\n",
+        "        \"Way too repetitive and lacking progression.\",\n",
+        "        \"The ending was abrupt and unsatisfying.\",\n",
+        "        \"No emotional resonance — I felt nothing throughout.\",\n",
+        "        \"I expected much more, but this fell flat.\",\n",
+        "        \"Poorly edited and full of clichés.\",\n",
+        "        \"The premise was interesting, but poorly executed.\",\n",
+        "        \"Just didn’t live up to the praise.\",\n",
+        "        \"A disjointed mess from start to finish.\",\n",
+        "        \"Overly long and painfully dull.\",\n",
+        "        \"Dialogue that felt robotic and unrealistic.\",\n",
+        "        \"A hollow shell of what it could’ve been.\",\n",
+        "        \"It lacked a coherent structure.\",\n",
+        "        \"More confusing than complex.\",\n",
+        "        \"Reading it felt like a task, not a treat.\",\n",
+        "        \"There was no tension, no emotion — just words.\",\n",
+        "        \"Characters with no motivation or development.\",\n",
+        "        \"The plot twists were nonsensical.\",\n",
+        "        \"Regret buying this book.\",\n",
+        "        \"Nothing drew me in, nothing made me stay.\",\n",
+        "        \"Too many subplots and none were satisfying.\",\n",
+        "        \"Tedious and unimaginative.\",\n",
+        "        \"Like reading a rough draft.\",\n",
+        "        \"Disjointed, distant, and disappointing.\",\n",
+        "        \"A lot of buildup with no payoff.\",\n",
+        "        \"I don’t understand the hype.\",\n",
+        "        \"This book simply didn’t work.\",\n",
+        "        \"Forgettable in every sense.\",\n",
+        "        \"More effort should’ve gone into editing.\",\n",
+        "        \"The story lost its way early on.\",\n",
+        "        \"It dragged endlessly.\",\n",
+        "        \"I kept checking how many pages were left.\",\n",
+        "        \"This lacked vision and clarity.\",\n",
+        "        \"I expected substance — got fluff.\",\n",
+        "        \"It failed to make me care.\"\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": 17,
+      "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": 18,
+      "metadata": {
+        "id": "ZUKUqZsuumsp"
+      },
+      "outputs": [],
+      "source": [
+        "df_reviews = pd.DataFrame(review_rows)\n",
+        "df_reviews.to_csv(\"synthetic_book_reviews.csv\", index=False)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 19,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "3946e521",
+        "outputId": "514d7bef-0488-4933-b03c-953b9e8a7f66"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ Wrote synthetic_title_level_features.csv\n",
+            "✅ Wrote synthetic_monthly_revenue_series.csv\n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "# ============================================================\n",
+        "# ✅ Create \"R-ready\" derived inputs (root-level files)\n",
+        "# ============================================================\n",
+        "# These two files make the R notebook robust and fast:\n",
+        "# 1) synthetic_title_level_features.csv  -> regression-ready, one row per title\n",
+        "# 2) synthetic_monthly_revenue_series.csv -> forecasting-ready, one row per month\n",
+        "\n",
+        "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": 20,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "xfE8NMqOurKo",
+        "outputId": "191730ba-d5e2-4df7-97d2-99feb0b704af"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "                  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                Had potential that went unrealized.  Three                 3  \n",
+            "1      The themes were solid, but not well explored.  Three                 3  \n",
+            "2             It simply lacked that emotional punch.  Three                 3  \n",
+            "3  Serviceable but not something I'd go out of my...  Three                 3  \n",
+            "4                   Standard fare with some promise.  Three                 3  \n"
+          ]
+        }
+      ],
+      "source": [
+        "print(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

@@ -0,0 +1,38 @@
+*.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
+ESCP_BANNER[[:space:]](2).png filter=lfs diff=lfs merge=lfs -text
+background.png filter=lfs diff=lfs merge=lfs -text
+background_top.png filter=lfs diff=lfs merge=lfs -text

ranalysis.ipynb

@@ -0,0 +1,463 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "id": "75fd9cc6",
+      "metadata": {
+        "id": "75fd9cc6"
+      },
+      "source": [
+        "# **🤖 Benchmarking & Modeling**"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "fb807724",
+      "metadata": {
+        "id": "fb807724"
+      },
+      "source": [
+        "## **1.** 📦 Setup"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "d40cd131",
+      "metadata": {
+        "id": "d40cd131"
+      },
+      "outputs": [],
+      "source": [
+        "\n",
+        "# Uncomment the next line once:\n",
+        "install.packages(c(\"readr\",\"dplyr\",\"stringr\",\"tidyr\",\"lubridate\",\"ggplot2\",\"forecast\",\"broom\",\"jsonlite\"), repos=\"https://cloud.r-project.org\")\n",
+        "\n",
+        "suppressPackageStartupMessages({\n",
+        "  library(readr)\n",
+        "  library(dplyr)\n",
+        "  library(stringr)\n",
+        "  library(tidyr)\n",
+        "  library(lubridate)\n",
+        "  library(ggplot2)\n",
+        "  library(forecast)\n",
+        "  library(broom)\n",
+        "  library(jsonlite)\n",
+        "})"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f01d02e7",
+      "metadata": {
+        "id": "f01d02e7"
+      },
+      "source": [
+        "## **2.** ✅️ Load & inspect inputs"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "29e8f6ce",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "29e8f6ce",
+        "outputId": "5a1bda1c-c58d-43d0-c85e-db5041c8bc49"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Loaded: 1000 rows (title-level), 18 rows (monthly)\n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "must_exist <- function(path, label) {\n",
+        "  if (!file.exists(path)) stop(paste0(\"Missing \", label, \": \", path))\n",
+        "}\n",
+        "\n",
+        "TITLE_PATH <- \"synthetic_title_level_features.csv\"\n",
+        "MONTH_PATH <- \"synthetic_monthly_revenue_series.csv\"\n",
+        "\n",
+        "must_exist(TITLE_PATH, \"TITLE_PATH\")\n",
+        "must_exist(MONTH_PATH, \"MONTH_PATH\")\n",
+        "\n",
+        "df_title <- read_csv(TITLE_PATH, show_col_types = FALSE)\n",
+        "df_month <- read_csv(MONTH_PATH, show_col_types = FALSE)\n",
+        "\n",
+        "cat(\"Loaded:\", nrow(df_title), \"rows (title-level),\", nrow(df_month), \"rows (monthly)\n",
+        "\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "9fd04262",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "9fd04262",
+        "outputId": "5f031538-96be-4758-904d-9201ec3c3ea7"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "\u001b[90m# A tibble: 1 × 6\u001b[39m\n",
+            "      n na_avg_revenue na_price na_rating na_share_pos na_share_neg\n",
+            "  \u001b[3m\u001b[90m<int>\u001b[39m\u001b[23m          \u001b[3m\u001b[90m<int>\u001b[39m\u001b[23m    \u001b[3m\u001b[90m<int>\u001b[39m\u001b[23m     \u001b[3m\u001b[90m<int>\u001b[39m\u001b[23m        \u001b[3m\u001b[90m<int>\u001b[39m\u001b[23m        \u001b[3m\u001b[90m<int>\u001b[39m\u001b[23m\n",
+            "\u001b[90m1\u001b[39m  \u001b[4m1\u001b[24m000              0        0      \u001b[4m1\u001b[24m000            0            0\n",
+            "Monthly rows after parsing: 18 \n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "# ---------- helpers ----------\n",
+        "safe_num <- function(x) {\n",
+        "  # strips anything that is not digit or dot\n",
+        "  suppressWarnings(as.numeric(str_replace_all(as.character(x), \"[^0-9.]\", \"\")))\n",
+        "}\n",
+        "\n",
+        "parse_rating <- function(x) {\n",
+        "  # Accept: 4, \"4\", \"4.0\", \"4/5\", \"4 out of 5\", \"⭐⭐⭐⭐\", etc.\n",
+        "  x <- as.character(x)\n",
+        "  x <- str_replace_all(x, \"⭐\", \"\")\n",
+        "  x <- str_to_lower(x)\n",
+        "  x <- str_replace_all(x, \"stars?\", \"\")\n",
+        "  x <- str_replace_all(x, \"out of\", \"/\")\n",
+        "  x <- str_replace_all(x, \"\\\\s+\", \"\")\n",
+        "  x <- str_replace_all(x, \"[^0-9./]\", \"\")\n",
+        "  suppressWarnings(as.numeric(str_extract(x, \"^[0-9.]+\")))\n",
+        "}\n",
+        "\n",
+        "parse_month <- function(x) {\n",
+        "  x <- as.character(x)\n",
+        "  # try YYYY-MM-DD, then YYYY-MM\n",
+        "  out <- suppressWarnings(ymd(x))\n",
+        "  if (mean(is.na(out)) > 0.5) out <- suppressWarnings(ymd(paste0(x, \"-01\")))\n",
+        "  na_idx <- which(is.na(out))\n",
+        "  if (length(na_idx) > 0) out[na_idx] <- suppressWarnings(ymd(paste0(x[na_idx], \"-01\")))\n",
+        "  out\n",
+        "}\n",
+        "\n",
+        "# ---------- normalize keys ----------\n",
+        "df_title <- df_title %>% mutate(title = str_squish(as.character(title)))\n",
+        "df_month <- df_month %>% mutate(month = as.character(month))\n",
+        "\n",
+        "# ---------- parse numeric columns defensively ----------\n",
+        "need_cols_title <- c(\"title\",\"avg_revenue\",\"total_revenue\",\"price\",\"rating\",\"share_positive\",\"share_negative\",\"share_neutral\")\n",
+        "missing_title <- setdiff(need_cols_title, names(df_title))\n",
+        "if (length(missing_title) > 0) stop(paste0(\"df_title missing columns: \", paste(missing_title, collapse=\", \")))\n",
+        "\n",
+        "df_title <- df_title %>%\n",
+        "  mutate(\n",
+        "    avg_revenue    = safe_num(avg_revenue),\n",
+        "    total_revenue  = safe_num(total_revenue),\n",
+        "    price          = safe_num(price),\n",
+        "    rating         = parse_rating(rating),\n",
+        "    share_positive = safe_num(share_positive),\n",
+        "    share_negative = safe_num(share_negative),\n",
+        "    share_neutral  = safe_num(share_neutral)\n",
+        "  )\n",
+        "\n",
+        "# basic sanity stats\n",
+        "hyg <- df_title %>%\n",
+        "  summarise(\n",
+        "    n = n(),\n",
+        "    na_avg_revenue = sum(is.na(avg_revenue)),\n",
+        "    na_price = sum(is.na(price)),\n",
+        "    na_rating = sum(is.na(rating)),\n",
+        "    na_share_pos = sum(is.na(share_positive)),\n",
+        "    na_share_neg = sum(is.na(share_negative))\n",
+        "  )\n",
+        "\n",
+        "print(hyg)\n",
+        "\n",
+        "# monthly parsing\n",
+        "need_cols_month <- c(\"month\",\"total_revenue\")\n",
+        "missing_month <- setdiff(need_cols_month, names(df_month))\n",
+        "if (length(missing_month) > 0) stop(paste0(\"df_month missing columns: \", paste(missing_month, collapse=\", \")))\n",
+        "\n",
+        "df_month2 <- df_month %>%\n",
+        "  mutate(\n",
+        "    month = parse_month(month),\n",
+        "    total_revenue = safe_num(total_revenue)\n",
+        "  ) %>%\n",
+        "  filter(!is.na(month)) %>%\n",
+        "  arrange(month)\n",
+        "\n",
+        "cat(\"Monthly rows after parsing:\", nrow(df_month2), \"\\n\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "b8971bc4",
+      "metadata": {
+        "id": "b8971bc4"
+      },
+      "source": [
+        "## **3.** 💾 Folder for R outputs for Hugging Face"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "dfaa06b1",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "dfaa06b1",
+        "outputId": "73f6437a-39f4-4968-f88a-99f10a3fd8ae"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "R outputs will be written to: /content/artifacts/r \n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "ART_DIR  <- \"artifacts\"\n",
+        "R_FIG_DIR <- file.path(ART_DIR, \"r\", \"figures\")\n",
+        "R_TAB_DIR <- file.path(ART_DIR, \"r\", \"tables\")\n",
+        "\n",
+        "dir.create(R_FIG_DIR, recursive = TRUE, showWarnings = FALSE)\n",
+        "dir.create(R_TAB_DIR, recursive = TRUE, showWarnings = FALSE)\n",
+        "\n",
+        "cat(\"R outputs will be written to:\", normalizePath(file.path(ART_DIR, \"r\"), winslash = \"/\"), \"\n",
+        "\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "f880c72d",
+      "metadata": {
+        "id": "f880c72d"
+      },
+      "source": [
+        "## **4.** 🔮 Forecast book sales benchmarking with `accuracy()`"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "source": [
+        "We benchmark **three** models on a holdout window (last *h* months):\n",
+        "- ARIMA + Fourier (seasonality upgrade)\n",
+        "- ETS\n",
+        "- Naive baseline\n",
+        "\n",
+        "Then we export:\n",
+        "- `accuracy_table.csv`\n",
+        "- `forecast_compare.png`\n",
+        "- `rmse_comparison.png`"
+      ],
+      "metadata": {
+        "id": "R0JZlzKegmzW"
+      },
+      "id": "R0JZlzKegmzW"
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "62e87992",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "62e87992",
+        "outputId": "73b36487-a25d-4bb9-cf80-8d5a654a2f0d"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ Saved: artifacts/r/tables/accuracy_table.csv\n",
+            "✅ Saved: artifacts/r/figures/rmse_comparison.png\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/html": [
+              "<strong>agg_record_872216040:</strong> 2"
+            ],
+            "text/markdown": "**agg_record_872216040:** 2",
+            "text/latex": "\\textbf{agg\\textbackslash{}\\_record\\textbackslash{}\\_872216040:} 2",
+            "text/plain": [
+              "agg_record_872216040 \n",
+              "                   2 "
+            ]
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ Saved: artifacts/r/figures/forecast_compare.png\n"
+          ]
+        }
+      ],
+      "source": [
+        "\n",
+        "# Build monthly ts\n",
+        "start_year <- year(min(df_month2$month, na.rm = TRUE))\n",
+        "start_mon  <- month(min(df_month2$month, na.rm = TRUE))\n",
+        "\n",
+        "y <- ts(df_month2$total_revenue, frequency = 12, start = c(start_year, start_mon))\n",
+        "\n",
+        "# holdout size: min(6, 20% of series), at least 1\n",
+        "h_test <- min(6, max(1, floor(length(y) / 5)))\n",
+        "train_ts <- head(y, length(y) - h_test)\n",
+        "test_ts  <- tail(y, h_test)\n",
+        "\n",
+        "# Model A: ARIMA + Fourier\n",
+        "K <- 2\n",
+        "xreg_train <- fourier(train_ts, K = K)\n",
+        "fit_arima <- auto.arima(train_ts, xreg = xreg_train)\n",
+        "xreg_future <- fourier(train_ts, K = K, h = h_test)\n",
+        "fc_arima <- forecast(fit_arima, xreg = xreg_future, h = h_test)\n",
+        "\n",
+        "# Model B: ETS\n",
+        "fit_ets <- ets(train_ts)\n",
+        "fc_ets  <- forecast(fit_ets, h = h_test)\n",
+        "\n",
+        "# Model C: Naive baseline\n",
+        "fc_naive <- naive(train_ts, h = h_test)\n",
+        "\n",
+        "# accuracy() tables\n",
+        "acc_arima <- as.data.frame(accuracy(fc_arima, test_ts))\n",
+        "acc_ets   <- as.data.frame(accuracy(fc_ets, test_ts))\n",
+        "acc_naive <- as.data.frame(accuracy(fc_naive, test_ts))\n",
+        "\n",
+        "accuracy_tbl <- bind_rows(\n",
+        "  acc_arima %>% mutate(model = \"ARIMA+Fourier\"),\n",
+        "  acc_ets   %>% mutate(model = \"ETS\"),\n",
+        "  acc_naive %>% mutate(model = \"Naive\")\n",
+        ") %>% relocate(model)\n",
+        "\n",
+        "write_csv(accuracy_tbl, file.path(R_TAB_DIR, \"accuracy_table.csv\"))\n",
+        "cat(\"✅ Saved: artifacts/r/tables/accuracy_table.csv\\n\")\n",
+        "\n",
+        "# RMSE bar chart\n",
+        "p_rmse <- ggplot(accuracy_tbl, aes(x = reorder(model, RMSE), y = RMSE)) +\n",
+        "  geom_col() +\n",
+        "  coord_flip() +\n",
+        "  labs(title = \"Forecast model comparison (RMSE on holdout)\", x = \"\", y = \"RMSE\") +\n",
+        "  theme_minimal()\n",
+        "\n",
+        "ggsave(file.path(R_FIG_DIR, \"rmse_comparison.png\"), p_rmse, width = 8, height = 4, dpi = 160)\n",
+        "cat(\"✅ Saved: artifacts/r/figures/rmse_comparison.png\\n\")\n",
+        "\n",
+        "# Side-by-side forecast plots (simple, no extra deps)\n",
+        "png(file.path(R_FIG_DIR, \"forecast_compare.png\"), width = 1200, height = 500)\n",
+        "par(mfrow = c(1, 3))\n",
+        "plot(fc_arima, main = \"ARIMA + Fourier\", xlab = \"Time\", ylab = \"Total revenue\"); lines(test_ts, col = \"black\")\n",
+        "plot(fc_ets, main = \"ETS\", xlab = \"Time\", ylab = \"Total revenue\"); lines(test_ts, col = \"black\")\n",
+        "plot(fc_naive, main = \"Naive\", xlab = \"Time\", ylab = \"Total revenue\"); lines(test_ts, col = \"black\")\n",
+        "dev.off()\n",
+        "cat(\"✅ Saved: artifacts/r/figures/forecast_compare.png\\n\")"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "id": "30bc017b",
+      "metadata": {
+        "id": "30bc017b"
+      },
+      "source": [
+        "## **5.** 💾 Some R metadata for Hugging Face"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "id": "645cb12b",
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "645cb12b",
+        "outputId": "c00c26da-7d27-4c78-a296-aa33807495d4"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "✅ Saved: artifacts/r/tables/r_meta.json\n",
+            "DONE. R artifacts written to: artifacts/r \n"
+          ]
+        }
+      ],
+      "source": [
+        "# =========================================================\n",
+        "# Metadata export (aligned with current notebook objects)\n",
+        "# =========================================================\n",
+        "\n",
+        "meta <- list(\n",
+        "\n",
+        "  # ---------------------------\n",
+        "  # Dataset footprint\n",
+        "  # ---------------------------\n",
+        "  n_titles = nrow(df_title),\n",
+        "  n_months = nrow(df_month2),\n",
+        "\n",
+        "  # ---------------------------\n",
+        "  # Forecasting info\n",
+        "  # (only if these objects exist in your forecasting section)\n",
+        "  # ---------------------------\n",
+        "  forecasting = list(\n",
+        "    holdout_h = h_test,\n",
+        "    arima_order = forecast::arimaorder(fit_arima),\n",
+        "    ets_method = fit_ets$method\n",
+        "  )\n",
+        ")\n",
+        "\n",
+        "jsonlite::write_json(\n",
+        "  meta,\n",
+        "  path = file.path(R_TAB_DIR, \"r_meta.json\"),\n",
+        "  pretty = TRUE,\n",
+        "  auto_unbox = TRUE\n",
+        ")\n",
+        "\n",
+        "cat(\"✅ Saved: artifacts/r/tables/r_meta.json\\n\")\n",
+        "cat(\"DONE. R artifacts written to:\", file.path(ART_DIR, \"r\"), \"\\n\")\n"
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "collapsed_sections": [
+        "f01d02e7",
+        "b8971bc4",
+        "f880c72d",
+        "30bc017b"
+      ]
+    },
+    "kernelspec": {
+      "name": "ir",
+      "display_name": "R"
+    },
+    "language_info": {
+      "name": "R"
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 5
+}

requirements.txt

@@ -0,0 +1,16 @@
+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

style.css

@@ -0,0 +1,336 @@
+/* --- Target the Gradio app wrapper for backgrounds --- */
+gradio-app,
+.gradio-app,
+.main,
+#app,
+[data-testid="app"] {
+  background-color: rgb(40,9,109) !important;
+  background-image: 
+    url('https://huggingface.co/spaces/escp/rx12workshoptemplate/resolve/main/background_top.png'),
+    url('https://huggingface.co/spaces/escp/rx12workshoptemplate/resolve/main/background_mid.png') !important;
+  background-position: 
+    top center,
+    0 913px !important;
+  background-repeat: 
+    no-repeat,
+    repeat-y !important;
+  background-size:
+    100% auto,
+    100% auto !important;
+  min-height: 100vh !important;
+}
+
+/* --- Fallback on html/body --- */
+html, body {
+  background-color: rgb(40,9,109) !important;
+  margin: 0 !important;
+  padding: 0 !important;
+  min-height: 100vh !important;
+}
+
+/* --- Fixed bottom banner using ::after on body --- */
+body::after {
+  content: '' !important;
+  position: fixed !important;
+  bottom: 0 !important;
+  left: 0 !important;
+  right: 0 !important;
+  height: 130px !important;
+  background-image: url('https://huggingface.co/spaces/escp/rx12workshoptemplate/resolve/main/background_bottom.png') !important;
+  background-size: 100% 100% !important;
+  background-repeat: no-repeat !important;
+  background-position: bottom center !important;
+  pointer-events: none !important;
+  z-index: 9999 !important;
+}
+
+/* --- Main container --- */
+.gradio-container {
+  max-width: 1400px !important;
+  width: 94vw !important;
+  margin: 0 auto !important;
+  padding-top: 220px !important;
+  padding-bottom: 150px !important;
+  background: transparent !important;
+}
+
+/* --- Title in ESCP gold --- */
+#escp_title h1 {
+  color: rgb(242,198,55) !important;
+  font-size: 3rem !important;
+  font-weight: 800 !important;
+  text-align: center !important;
+  margin: 0 0 12px 0 !important;
+}
+
+/* --- Subtitle --- */
+#escp_title p, #escp_title em {
+  color: rgba(255,255,255,0.85) !important;
+  text-align: center !important;
+}
+
+/* --- Tab bar background --- */
+.tabs > .tab-nav,
+.tab-nav,
+div[role="tablist"],
+.svelte-tabs > .tab-nav {
+  background: rgba(40,9,109,0.6) !important;
+  border-radius: 10px 10px 0 0 !important;
+  padding: 4px !important;
+}
+
+/* --- ALL tab buttons: force white text --- */
+.tabs > .tab-nav button,
+.tab-nav button,
+div[role="tablist"] button,
+button[role="tab"],
+.svelte-tabs button,
+.tab-nav > button,
+.tabs button {
+  color: #ffffff !important;
+  font-weight: 600 !important;
+  border: none !important;
+  background: transparent !important;
+  padding: 10px 20px !important;
+  border-radius: 8px 8px 0 0 !important;
+  opacity: 1 !important;
+}
+
+/* --- Selected tab: ESCP gold --- */
+.tabs > .tab-nav button.selected,
+.tab-nav button.selected,
+button[role="tab"][aria-selected="true"],
+button[role="tab"].selected,
+div[role="tablist"] button[aria-selected="true"],
+.svelte-tabs button.selected {
+  color: rgb(242,198,55) !important;
+  background: rgba(255,255,255,0.12) !important;
+}
+
+/* --- Unselected tabs: ensure visibility --- */
+.tabs > .tab-nav button:not(.selected),
+.tab-nav button:not(.selected),
+button[role="tab"][aria-selected="false"],
+button[role="tab"]:not(.selected),
+div[role="tablist"] button:not([aria-selected="true"]) {
+  color: #ffffff !important;
+  opacity: 1 !important;
+}
+
+/* --- White card panels --- */
+.gradio-container .gr-block,
+.gradio-container .gr-box,
+.gradio-container .gr-panel,
+.gradio-container .gr-group {
+  background: #ffffff !important;
+  border-radius: 10px !important;
+}
+
+/* --- Tab content area --- */
+.tabitem {
+  background: rgba(255,255,255,0.95) !important;
+  border-radius: 0 0 10px 10px !important;
+  padding: 16px !important;
+}
+
+/* --- Inputs --- */
+.gradio-container input,
+.gradio-container textarea,
+.gradio-container select {
+  background: #ffffff !important;
+  border: 1px solid #d1d5db !important;
+  border-radius: 8px !important;
+}
+
+/* --- Buttons: ESCP purple primary --- */
+.gradio-container button:not([role="tab"]) {
+  font-weight: 600 !important;
+  padding: 10px 16px !important;
+  border-radius: 10px !important;
+}
+
+button.primary {
+  background-color: rgb(40,9,109) !important;
+  color: #ffffff !important;
+  border: none !important;
+}
+
+button.primary:hover {
+  background-color: rgb(60,20,140) !important;
+}
+
+button.secondary {
+  background-color: #ffffff !important;
+  color: rgb(40,9,109) !important;
+  border: 2px solid rgb(40,9,109) !important;
+}
+
+button.secondary:hover {
+  background-color: rgb(240,238,250) !important;
+}
+
+/* --- Dataframes --- */
+[data-testid="dataframe"] {
+  background-color: #ffffff !important;
+  border-radius: 10px !important;
+}
+
+table {
+  font-size: 0.85rem !important;
+}
+
+/* --- Chatbot (AI Dashboard tab) --- */
+.gr-chatbot {
+  min-height: 380px !important;
+  background-color: #ffffff !important;
+  border-radius: 12px !important;
+}
+
+.gr-chatbot .message.user {
+  background-color: rgb(232,225,250) !important;
+  border-radius: 12px !important;
+}
+
+.gr-chatbot .message.bot {
+  background-color: #f3f4f6 !important;
+  border-radius: 12px !important;
+}
+
+/* --- Gallery --- */
+.gallery {
+  background: #ffffff !important;
+  border-radius: 10px !important;
+}
+
+/* --- Log textbox --- */
+textarea {
+  font-family: monospace !important;
+  font-size: 0.8rem !important;
+}
+
+/* --- Markdown headings inside tabs --- */
+.tabitem h3 {
+  color: rgb(40,9,109) !important;
+  font-weight: 700 !important;
+}
+
+.tabitem h4 {
+  color: #374151 !important;
+}
+
+/* --- Examples row (AI Dashboard) --- */
+.examples-row button {
+  background: rgb(240,238,250) !important;
+  color: rgb(40,9,109) !important;
+  border: 1px solid rgb(40,9,109) !important;
+  border-radius: 8px !important;
+  font-size: 0.85rem !important;
+}
+
+.examples-row button:hover {
+  background: rgb(232,225,250) !important;
+}
+
+/* --- Header / footer: transparent over banner --- */
+header, header *,
+footer, footer * {
+  background: transparent !important;
+  box-shadow: none !important;
+}
+
+footer a, footer button,
+header a, header button {
+  background: transparent !important;
+  border: none !important;
+  box-shadow: none !important;
+}
+
+#footer, #footer *,
+[class*="footer"], [class*="footer"] *,
+[class*="chip"], [class*="pill"], [class*="chip"] *, [class*="pill"] * {
+  background: transparent !important;
+  border: none !important;
+  box-shadow: none !important;
+}
+
+[data-testid*="api"], [data-testid*="settings"],
+[id*="api"], [id*="settings"],
+[class*="api"], [class*="settings"],
+[class*="bottom"], [class*="toolbar"], [class*="controls"] {
+  background: transparent !important;
+  box-shadow: none !important;
+}
+
+[data-testid*="api"] *, [data-testid*="settings"] *,
+[id*="api"] *, [id*="settings"] *,
+[class*="api"] *, [class*="settings"] * {
+  background: transparent !important;
+  box-shadow: none !important;
+}
+
+section footer {
+  background: transparent !important;
+}
+
+section footer button,
+section footer a {
+  background: transparent !important;
+  background-color: transparent !important;
+  border: none !important;
+  box-shadow: none !important;
+  color: white !important;
+}
+
+section footer button:hover,
+section footer button:focus,
+section footer a:hover,
+section footer a:focus {
+  background: transparent !important;
+  background-color: transparent !important;
+  box-shadow: none !important;
+}
+
+section footer button,
+section footer button * {
+  background: transparent !important;
+  background-color: transparent !important;
+  background-image: none !important;
+  box-shadow: none !important;
+  filter: none !important;
+}
+
+section footer button::before,
+section footer button::after {
+  background: transparent !important;
+  background-color: transparent !important;
+  background-image: none !important;
+  box-shadow: none !important;
+  filter: none !important;
+}
+
+section footer a,
+section footer a * {
+  background: transparent !important;
+  background-color: transparent !important;
+  box-shadow: none !important;
+}
+
+.gradio-container footer button,
+.gradio-container footer button *,
+.gradio-container .footer button,
+.gradio-container .footer button * {
+  background: transparent !important;
+  background-color: transparent !important;
+  background-image: none !important;
+  box-shadow: none !important;
+}
+
+.gradio-container footer button::before,
+.gradio-container footer button::after,
+.gradio-container .footer button::before,
+.gradio-container .footer button::after {
+  background: transparent !important;
+  background-color: transparent !important;
+  background-image: none !important;
+  box-shadow: none !important;
+}