{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "# Lesson 16: System Design and Deployment Readiness\n",
        "\n",
        "**CS230 inspiration:** Full-cycle deep learning projects, project milestones, and practical ML systems.\n",
        "\n",
        "**Demand forecasting focus:** Design the interfaces, artifacts, checks, and rollout plan for a forecasting model.\n",
        "\n",
        "**Learning objectives**\n",
        "\n",
        "- Separate training, feature generation, inference, and monitoring concerns.\n",
        "- Define model cards and data contracts for forecasts.\n",
        "- Plan batch inference and human review workflows.\n",
        "\n",
        "**Senior-readiness checkpoint:** You can lead a design review for a forecasting system before code is written.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Code Cell 1 Explanation\n",
        "\n",
        "**What this cell does:** This setup cell imports the shared scientific Python stack and the curriculum helpers used by later cells. It also establishes the deterministic seed convention so repeated runs are comparable.\n",
        "\n",
        "**Why it matters:** A restart-and-run notebook should make its dependencies explicit before any modeling work begins. For forecasting, reproducibility is especially important because small data or seed changes can change validation conclusions.\n",
        "\n",
        "**Key operations to notice:** confirm that shared helper imports match the lesson's code path; check that `SEED` is defined before any generated data or model training\n",
        "\n",
        "**What to inspect:** Check that imports are grouped by purpose: general analysis packages, forecasting data helpers, metrics, plotting utilities, and any lesson-specific libraries.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "\n",
        "from demand_forecasting_curriculum.data import (\n",
        "    DEFAULT_FEATURE_COLUMNS,\n",
        "    generate_daily_demand,\n",
        "    make_sequence_dataset,\n",
        "    make_supervised_table,\n",
        "    time_series_split,\n",
        ")\n",
        "from demand_forecasting_curriculum.metrics import (\n",
        "    interval_coverage,\n",
        "    mase,\n",
        "    pinball_loss,\n",
        "    smape,\n",
        "    wmape,\n",
        ")\n",
        "from demand_forecasting_curriculum.plotting import plot_predictions, plot_series\n",
        "\n",
        "SEED = 42\n",
        "np.random.seed(SEED)\n",
        "\n",
        "from dataclasses import dataclass\n",
        "from sklearn.ensemble import HistGradientBoostingRegressor\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Code Cell 2 Explanation\n",
        "\n",
        "**What this cell does:** This cell advances **System Design and Deployment Readiness** by working on model definition. It creates or updates `contract` and prepares evidence that later cells use rather than hiding state in prose.\n",
        "\n",
        "**Why it matters:** The goal is tied to this lesson's forecasting focus: Design the interfaces, artifacts, checks, and rollout plan for a forecasting model. Each object is kept inspectable so the learner can connect code, assumptions, and modeling consequences.\n",
        "\n",
        "**Key operations to notice:** follow the assignments, final displayed object, and any checks in the cell because those are the evidence the next cell depends on\n",
        "\n",
        "**What to inspect:** Before moving on, inspect shapes, date ranges, metric values, segment behavior, or generated tables. If a value looks surprisingly good, surprisingly bad, or unavailable at forecast time, treat that as a modeling clue.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "@dataclass(frozen=True)\n",
        "class ForecastContract:\n",
        "    horizon_days: int\n",
        "    required_features: tuple[str, ...]\n",
        "    grain: tuple[str, ...] = (\"store_id\", \"item_id\", \"date\")\n",
        "\n",
        "    def validate(self, frame):\n",
        "        missing = sorted(set(self.required_features) - set(frame.columns))\n",
        "        if missing:\n",
        "            raise ValueError(f\"Missing required features: {missing}\")\n",
        "        if frame[list(self.grain)].duplicated().any():\n",
        "            raise ValueError(\"Forecast grain must be unique.\")\n",
        "\n",
        "contract = ForecastContract(\n",
        "    horizon_days=7,\n",
        "    required_features=tuple([\"store_id\", \"item_id\", *DEFAULT_FEATURE_COLUMNS]),\n",
        ")\n",
        "contract\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Code Cell 3 Explanation\n",
        "\n",
        "**What this cell does:** This cell advances **System Design and Deployment Readiness** by working on synthetic demand generation, time-based splitting, supervised feature construction. It creates or updates `df`, `supervised`, `train`, `valid`, `test`, `model` and prepares evidence that later cells use rather than hiding state in prose.\n",
        "\n",
        "**Why it matters:** The goal is tied to this lesson's forecasting focus: Design the interfaces, artifacts, checks, and rollout plan for a forecasting model. Each object is kept inspectable so the learner can connect code, assumptions, and modeling consequences.\n",
        "\n",
        "**Key operations to notice:** creates a synthetic retail panel with known demand drivers; turns time series rows into forecast-origin training examples; keeps train, validation, and test windows ordered by date; trains a strong tabular baseline\n",
        "\n",
        "**What to inspect:** Before moving on, inspect shapes, date ranges, metric values, segment behavior, or generated tables. If a value looks surprisingly good, surprisingly bad, or unavailable at forecast time, treat that as a modeling clue.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "df = generate_daily_demand(n_stores=4, n_items=6, periods=540, seed=SEED)\n",
        "supervised = make_supervised_table(df, horizon=contract.horizon_days)\n",
        "train, valid, test = time_series_split(supervised, valid_days=60, test_days=60)\n",
        "contract.validate(train[[\"date\", *contract.required_features]])\n",
        "\n",
        "model = HistGradientBoostingRegressor(max_iter=120, learning_rate=0.04, random_state=SEED)\n",
        "model.fit(train[list(contract.required_features)], train[\"y\"])\n",
        "predictions = test[[\"date\", \"store_id\", \"item_id\", \"y\"]].assign(\n",
        "    prediction=model.predict(test[list(contract.required_features)])\n",
        ")\n",
        "predictions.head()\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Code Cell 4 Explanation\n",
        "\n",
        "**What this cell does:** This cell advances **System Design and Deployment Readiness** by working on portfolio communication. It creates or updates `model_card` and prepares evidence that later cells use rather than hiding state in prose.\n",
        "\n",
        "**Why it matters:** The goal is tied to this lesson's forecasting focus: Design the interfaces, artifacts, checks, and rollout plan for a forecasting model. Each object is kept inspectable so the learner can connect code, assumptions, and modeling consequences.\n",
        "\n",
        "**Key operations to notice:** evaluates scale-weighted forecast error\n",
        "\n",
        "**What to inspect:** Before moving on, inspect shapes, date ranges, metric values, segment behavior, or generated tables. If a value looks surprisingly good, surprisingly bad, or unavailable at forecast time, treat that as a modeling clue.\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": [
        "model_card = {\n",
        "    \"model_type\": type(model).__name__,\n",
        "    \"forecast_horizon_days\": contract.horizon_days,\n",
        "    \"training_start\": str(train[\"date\"].min().date()),\n",
        "    \"training_end\": str(train[\"date\"].max().date()),\n",
        "    \"validation_wmape\": wmape(valid[\"y\"], model.predict(valid[list(contract.required_features)])),\n",
        "    \"test_wmape\": wmape(test[\"y\"], predictions[\"prediction\"]),\n",
        "    \"known_limitations\": [\n",
        "        \"Synthetic data only\",\n",
        "        \"No causal treatment of price or promotions\",\n",
        "        \"Stockout censoring is observed but not corrected\",\n",
        "    ],\n",
        "}\n",
        "model_card\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Lesson Recap\n",
        "\n",
        "In this lesson, we used 4 runnable code cells to work through **System Design and Deployment Readiness**. The practical focus was: Design the interfaces, artifacts, checks, and rollout plan for a forecasting model.\n",
        "\n",
        "We did this because deep learning for demand forecasting is not only about choosing an architecture. The learner needs to understand the data contract, the target and horizon, the validation path, the metric, and the operational decision supported by the forecast.\n",
        "\n",
        "The core takeaways were:\n",
        "\n",
        "- Separate training, feature generation, inference, and monitoring concerns.\n",
        "- Define model cards and data contracts for forecasts.\n",
        "- Plan batch inference and human review workflows.\n",
        "\n",
        "By the end, you should be able to explain not just what the code produced, but why each step was necessary and what could go wrong if the same step were skipped or performed with leakage.\n",
        "\n",
        "**Senior-readiness reminder:** You can lead a design review for a forecasting system before code is written.\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "## Exercises\n",
        "\n",
        "- Add a field to the contract for feature availability time.\n",
        "- Write pre-launch checks for data freshness, schema drift, and backtest quality.\n",
        "- Sketch a fallback plan for failed batch inference.\n"
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python (deep-learning-demand)",
      "language": "python",
      "name": "deep-learning-demand"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.12"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}