{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "crude-importance-0",
   "metadata": {},
   "source": [
    "# Crude: Which variables are the strongest predictors for supply and demand?\n",
    "\n",
    "This notebook ranks individual predictors for next-month U.S. supply and demand. \n",
    "\n",
    "Supply and demand are separate targets.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "crude-importance-1",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:37.104912Z",
     "iopub.status.busy": "2026-09-16T21:16:37.104661Z",
     "iopub.status.idle": "2026-09-16T21:16:38.387824Z",
     "shell.execute_reply": "2026-09-16T21:16:38.386768Z"
    }
   },
   "outputs": [],
   "source": [
    "FUEL = 'crude'\n",
    "\n",
    "# Load the scientific stack used by the analysis. FUEL is the only setting that\n",
    "# differs between the crude and gasoline versions of this notebook.\n",
    "from pathlib import Path\n",
    "import sys, hashlib, platform\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from IPython.display import display\n",
    "from sklearn.pipeline import make_pipeline\n",
    "from sklearn.preprocessing import StandardScaler\n",
    "from sklearn.linear_model import Ridge\n",
    "import sklearn\n",
    "\n",
    "# Show all ranking rows and keep the long, descriptive predictor names readable.\n",
    "pd.set_option('display.max_rows', 60)\n",
    "pd.set_option('display.max_colwidth', 100)\n",
    "\n",
    "# Locate the shared project root whether the notebook is launched from this\n",
    "# product folder or from a parent directory, then make both data loaders importable.\n",
    "ROOT = next(p for p in [Path.cwd(), *Path.cwd().parents] if (p/'oil/us_snd_crude/crude_data.py').exists())\n",
    "for fuel in ['crude', 'gasoline']:\n",
    "    sys.path.insert(0, str(ROOT/f'oil/us_snd_{fuel}'))\n",
    "from crude_data import load_panel as load_crude, FLOWS as CRUDE_FLOWS\n",
    "from gasoline_data import load_panel as load_gasoline, FLOWS as GAS_FLOWS\n",
    "\n",
    "# Load monthly PADD-level histories for both products. The second product is\n",
    "# needed later for cross-market predictors such as crude inputs for gasoline.\n",
    "panels = {'crude': load_crude(), 'gasoline': load_gasoline()}\n",
    "national = {}\n",
    "for fuel, panel in panels.items():\n",
    "    # A national observation is valid only when all five PADD regions are present.\n",
    "    assert panel.groupby('month').padd.nunique().eq(5).all()\n",
    "    cols = (CRUDE_FLOWS + ['stock_kb', 'cdu_capacity_kbd']) if fuel == 'crude' else GAS_FLOWS + ['stock_kb']\n",
    "    # min_count=5 prevents a missing PADD from silently producing a partial U.S. total.\n",
    "    # asfreq also exposes any missing month in the national time series.\n",
    "    z = panel.groupby('month')[cols].sum(min_count=5).asfreq('MS')\n",
    "    assert z.notna().all().all()\n",
    "\n",
    "    # Crude flows already arrive as daily rates. Gasoline flows are stored as\n",
    "    # monthly thousand-barrel totals, so divide by the exact days in each month.\n",
    "    # Stocks are point-in-time levels and are converted from thousand to million barrels.\n",
    "    if fuel == 'gasoline':\n",
    "        for c in GAS_FLOWS:\n",
    "            z[c.replace('_kb', '_kbd')] = z[c] / z.index.days_in_month\n",
    "    z['stock_mb'] = z.stock_kb / 1000\n",
    "    z['change_mb'] = z.stock_mb.diff()\n",
    "\n",
    "    # These derived series summarize trade and the simplified physical balance.\n",
    "    # The core balance excludes adjustments, transfers and other secondary flows.\n",
    "    z['net_imports_kbd'] = z.imports_kbd - z.exports_kbd\n",
    "    z['core_balance_kbd'] = z.production_kbd + z.net_imports_kbd - z.demand_kbd\n",
    "    if fuel == 'crude':\n",
    "        # Refinery utilization compares actual crude inputs with operable capacity.\n",
    "        z['utilization'] = z.demand_kbd / z.cdu_capacity_kbd\n",
    "    national[fuel] = z\n",
    "\n",
    "# Record the data range and source-file hash so an executed notebook identifies\n",
    "# the exact local EIA snapshots used to produce its rankings.\n",
    "manifest = []\n",
    "for fuel in national:\n",
    "    path = ROOT/f'oil/us_snd_{fuel}/data/eia_observations.csv'\n",
    "    manifest.append({'fuel': fuel, 'start': national[fuel].index.min(), 'end': national[fuel].index.max(),\n",
    "                     'months': len(national[fuel]), 'sha256': hashlib.sha256(path.read_bytes()).hexdigest()})\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-2",
   "metadata": {},
   "source": [
    "## How variable importantce is measured\n",
    "\n",
    "We test each variable separately while accounting for seasonal pattersn (which variables are most important other than season. Controlling for season). Variables that reduce prediction errors the most are the most important.\n",
    "\n",
    "The test uses six historical periods, with each prediction based only on earlier data.\n",
    "\n",
    "We  remove each variable from the model containing all inputs and refit to measure the information it adds alongside the other variables."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "crude-importance-3",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:38.390066Z",
     "iopub.status.busy": "2026-09-16T21:16:38.389854Z",
     "iopub.status.idle": "2026-09-16T21:16:38.425587Z",
     "shell.execute_reply": "2026-09-16T21:16:38.424498Z"
    }
   },
   "outputs": [],
   "source": [
    "# Select the product being ranked and align the other product to the same calendar.\n",
    "z = national[FUEL]\n",
    "other_fuel = 'gasoline' if FUEL == 'crude' else 'crude'\n",
    "other = national[other_fuel].reindex(z.index)\n",
    "demand_name = 'Crude refinery inputs' if FUEL == 'crude' else 'Gasoline product supplied'\n",
    "production_name = 'Crude production' if FUEL == 'crude' else 'Gasoline net production'\n",
    "\n",
    "# Rank predictors separately for gross supply and demand. Gross supply includes\n",
    "# domestic production and imports; exports remain an explanatory outflow.\n",
    "targets = pd.DataFrame({\n",
    "    'Supply: production + imports': z.production_kbd + z.imports_kbd,\n",
    "    'Demand: ' + demand_name.lower(): z.demand_kbd,\n",
    "})\n",
    "\n",
    "# Twelve month indicators form the seasonality-only benchmark. Each later\n",
    "# single-variable test asks whether a predictor improves on this calendar model.\n",
    "X = pd.DataFrame(index=z.index)\n",
    "for month in range(1, 13):\n",
    "    X[f'Calendar month {month:02}'] = (X.index.month == month).astype(float)\n",
    "calendar = list(X.columns)\n",
    "\n",
    "def history(name, series):\n",
    "    \"\"\"Add one-month and smoothed three-month lags without using forecast-month data.\"\"\"\n",
    "    # Shift before rolling: for a forecast at month t, these features end at t-1.\n",
    "    X[f'{name} — previous month'] = series.shift(1)\n",
    "    X[f'{name} — previous 3-month average'] = series.shift(1).rolling(3).mean()\n",
    "\n",
    "# Add recent histories of the product's main supply, trade and demand variables.\n",
    "history(production_name, z.production_kbd)\n",
    "history(FUEL.title() + ' imports', z.imports_kbd)\n",
    "history(FUEL.title() + ' exports', z.exports_kbd)\n",
    "history(demand_name, z.demand_kbd)\n",
    "history('Supply (production + imports)', targets.iloc[:, 0])\n",
    "history('Core balance (production + imports − exports − demand)', z.core_balance_kbd)\n",
    "\n",
    "# Inventory features describe the latest level, recent changes, and the deviation\n",
    "# from the same point one year earlier. Both levels in the last feature precede t.\n",
    "X['Inventory level — previous month'] = z.stock_mb.shift(1)\n",
    "X['Inventory change — previous month'] = z.change_mb.shift(1)\n",
    "X['Inventory change — previous 3-month average'] = z.change_mb.shift(1).rolling(3).mean()\n",
    "X['Inventory level minus year-earlier level'] = z.stock_mb.shift(1) - z.stock_mb.shift(13)\n",
    "\n",
    "# Include the remaining balance components available for each product.\n",
    "for column, name in [('adjustments_kbd', 'Adjustments'), ('net_receipts_kbd', 'Net regional receipts')]:\n",
    "    history(name, z[column])\n",
    "if FUEL == 'crude':\n",
    "    history('Transfers', z.transfers_kbd)\n",
    "    history('Direct crude use', z.direct_use_kbd)\n",
    "else:\n",
    "    history('Biofuel production', z.biofuels_kbd)\n",
    "\n",
    "# Refinery operations can affect crude demand and gasoline output, so both\n",
    "# notebooks receive lagged crude utilization and physical distillation capacity.\n",
    "crude = national['crude'].reindex(z.index)\n",
    "X['Crude refinery utilization — previous month'] = crude.utilization.shift(1)\n",
    "X['Crude distillation capacity — previous month'] = crude.cdu_capacity_kbd.shift(1)\n",
    "\n",
    "# Cross-product features test whether activity in the linked petroleum market\n",
    "# contains information beyond the selected product's own recent history.\n",
    "other_demand = 'Gasoline product supplied' if other_fuel == 'gasoline' else 'Crude refinery inputs'\n",
    "other_production = 'Gasoline net production' if other_fuel == 'gasoline' else 'Crude production'\n",
    "X[f'{other_demand} — previous month'] = other.demand_kbd.shift(1)\n",
    "X[f'{other_production} — previous month'] = other.production_kbd.shift(1)\n",
    "X[f'{other_fuel.title()} inventory change — previous month'] = other.change_mb.shift(1)\n",
    "\n",
    "# Use one common sample for every comparison. This prevents a feature from looking\n",
    "# better merely because it was evaluated on a different set of months.\n",
    "keep = X.notna().all(axis=1) & targets.notna().all(axis=1)\n",
    "X, targets = X.loc[keep], targets.loc[keep]\n",
    "\n",
    "# Exclude March 2020 through March 2021 and any target whose lag window reaches\n",
    "# that disruption. Offsets 0..13 cover the target month and the longest lag used.\n",
    "eligible = pd.Series(True, index=X.index)\n",
    "for offset in range(14):\n",
    "    dates = X.index - pd.DateOffset(months=offset)\n",
    "    eligible &= ~((dates >= pd.Timestamp('2020-03-01')) & (dates <= pd.Timestamp('2021-03-01')))\n",
    "\n",
    "# Score the latest 72 eligible observations in six consecutive 12-month blocks.\n",
    "# Every block is trained on all eligible observations strictly before that block.\n",
    "scored_dates = X.index[eligible][-72:]\n",
    "assert len(scored_dates) == 72\n",
    "# A block can span a calendar gap because excluded COVID-related dates are absent.\n",
    "folds = [pd.DatetimeIndex(d) for d in np.array_split(scored_dates, 6)]\n",
    "features = [c for c in X if c not in calendar]\n",
    "\n",
    "# Fail early if alignment, missing values, or duplicate feature names could make\n",
    "# the ranking invalid or silently change the observations being compared.\n",
    "assert X.index.is_monotonic_increasing and not X.index.has_duplicates\n",
    "assert np.isfinite(X.to_numpy()).all() and np.isfinite(targets.to_numpy()).all()\n",
    "assert len(features) == len(set(features))\n",
    "periods = pd.DataFrame([{\n",
    "    'Period': i + 1, 'First scored month': dates.min().strftime('%Y-%m'),\n",
    "    'Last scored month': dates.max().strftime('%Y-%m'), 'Scored months': len(dates),\n",
    "    'Earlier training months': int(((X.index < dates.min()) & eligible).sum()),\n",
    "} for i, dates in enumerate(folds)])\n",
    "# Require a meaningful training history even for the earliest validation block.\n",
    "assert periods['Earlier training months'].min() >= 36\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "crude-importance-4",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:38.427645Z",
     "iopub.status.busy": "2026-09-16T21:16:38.427458Z",
     "iopub.status.idle": "2026-09-16T21:16:44.427035Z",
     "shell.execute_reply": "2026-09-16T21:16:44.426182Z"
    }
   },
   "outputs": [],
   "source": [
    "# Keep regularization fixed so alpha is not tuned on the periods used to rank\n",
    "# predictors. Standardization puts differently scaled inputs on comparable footing.\n",
    "ALPHA = 10\n",
    "\n",
    "def errors(y, columns):\n",
    "    \"\"\"Return out-of-sample absolute errors from expanding-window validation.\"\"\"\n",
    "    blocks = []\n",
    "    for period, dates in enumerate(folds, 1):\n",
    "        # Training uses only eligible observations before the first scored month.\n",
    "        # This chronological split prevents future observations from leaking backward.\n",
    "        train = (X.index < dates.min()) & eligible\n",
    "        assert X.index[train].max() < dates.min()\n",
    "        model = make_pipeline(StandardScaler(), Ridge(alpha=ALPHA))\n",
    "        model.fit(X.loc[train, columns], y.loc[train])\n",
    "        prediction = model.predict(X.loc[dates, columns])\n",
    "        blocks.append(pd.DataFrame({\n",
    "            'period': period,\n",
    "            # Absolute error keeps the result in the target's thousand-b/d units.\n",
    "            'error': np.abs(y.loc[dates].to_numpy() - prediction),\n",
    "        }, index=dates))\n",
    "    return pd.concat(blocks)\n",
    "\n",
    "rankings, calendar_importance = {}, []\n",
    "for target_name in targets:\n",
    "    y = targets[target_name]\n",
    "\n",
    "    # These two reference models support the two definitions of importance:\n",
    "    # calendar-only for individual value, and all inputs for conditional value.\n",
    "    calendar_error = errors(y, calendar)\n",
    "    full_error = errors(y, list(X.columns))\n",
    "    rows = []\n",
    "    for feature in features:\n",
    "        # Individual test: add one feature to the calendar-only baseline.\n",
    "        added = errors(y, calendar + [feature])\n",
    "        # Conditional test: remove one feature from the full model and refit.\n",
    "        removed = errors(y, [c for c in X if c != feature])\n",
    "\n",
    "        # Positive gain means the feature reduces error beyond seasonality.\n",
    "        # Positive conditional value means the full model gets worse without it.\n",
    "        gain = calendar_error.error - added.error\n",
    "        conditional = removed.error - full_error.error\n",
    "        by_period = gain.groupby(calendar_error.period).mean()\n",
    "        rows.append({\n",
    "            'Predictor': feature,\n",
    "            'Error reduction vs calendar (thousand b/d)': gain.mean(),\n",
    "            'Error reduction vs calendar (%)': 100 * gain.mean() / calendar_error.error.mean(),\n",
    "            'Periods helped (of 6)': int((by_period > 0).sum()),\n",
    "            'Error increase when removed (thousand b/d)': conditional.mean(),\n",
    "            'Periods hurt by removal (of 6)': int((conditional.groupby(full_error.period).mean() > 0).sum()),\n",
    "            # Retain fold-level gains to show whether the average is historically stable.\n",
    "            **{f'Period {i} gain': by_period.loc[i] for i in range(1, 7)},\n",
    "        })\n",
    "\n",
    "    # The main rank is based on individual improvement over calendar seasonality.\n",
    "    table = pd.DataFrame(rows).sort_values(\n",
    "        'Error reduction vs calendar (thousand b/d)', ascending=False\n",
    "    ).reset_index(drop=True)\n",
    "    table.index = table.index + 1\n",
    "    table.index.name = 'Rank'\n",
    "    rankings[target_name] = table\n",
    "\n",
    "    # Treat all 12 calendar indicators as one conceptual predictor when measuring\n",
    "    # how much seasonality contributes alongside every noncalendar feature.\n",
    "    without_calendar = errors(y, features)\n",
    "    calendar_importance.append({\n",
    "        'Target': target_name,\n",
    "        'Predictor': 'Calendar month (all 12 month indicators)',\n",
    "        'Error increase when removed (thousand b/d)': (without_calendar.error - full_error.error).mean(),\n",
    "    })\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-5",
   "metadata": {},
   "source": [
    "## Most important variables\n",
    "\n",
    "The top three individual predictors for each target appear first."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "crude-importance-6",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:44.431796Z",
     "iopub.status.busy": "2026-09-16T21:16:44.431625Z",
     "iopub.status.idle": "2026-09-16T21:16:44.470559Z",
     "shell.execute_reply": "2026-09-16T21:16:44.469854Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<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>Target</th>\n",
       "      <th>Rank</th>\n",
       "      <th>Predictor</th>\n",
       "      <th>Error reduction (thousand b/d)</th>\n",
       "      <th>Periods helped (of 6)</th>\n",
       "      <th>Adds information alongside other inputs</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Supply: production + imports</td>\n",
       "      <td>1</td>\n",
       "      <td>Supply (production + imports) — previous 3-month average</td>\n",
       "      <td>2785.23</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Supply: production + imports</td>\n",
       "      <td>2</td>\n",
       "      <td>Supply (production + imports) — previous month</td>\n",
       "      <td>2714.99</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Supply: production + imports</td>\n",
       "      <td>3</td>\n",
       "      <td>Crude production — previous 3-month average</td>\n",
       "      <td>2689.13</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Demand: crude refinery inputs</td>\n",
       "      <td>1</td>\n",
       "      <td>Crude refinery inputs — previous 3-month average</td>\n",
       "      <td>532.84</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Demand: crude refinery inputs</td>\n",
       "      <td>2</td>\n",
       "      <td>Crude refinery inputs — previous month</td>\n",
       "      <td>518.87</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Demand: crude refinery inputs</td>\n",
       "      <td>3</td>\n",
       "      <td>Gasoline net production — previous month</td>\n",
       "      <td>422.99</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Target  Rank  \\\n",
       "0   Supply: production + imports     1   \n",
       "1   Supply: production + imports     2   \n",
       "2   Supply: production + imports     3   \n",
       "3  Demand: crude refinery inputs     1   \n",
       "4  Demand: crude refinery inputs     2   \n",
       "5  Demand: crude refinery inputs     3   \n",
       "\n",
       "                                                  Predictor  \\\n",
       "0  Supply (production + imports) — previous 3-month average   \n",
       "1            Supply (production + imports) — previous month   \n",
       "2               Crude production — previous 3-month average   \n",
       "3          Crude refinery inputs — previous 3-month average   \n",
       "4                    Crude refinery inputs — previous month   \n",
       "5                  Gasoline net production — previous month   \n",
       "\n",
       "   Error reduction (thousand b/d)  Periods helped (of 6)  \\\n",
       "0                         2785.23                      6   \n",
       "1                         2714.99                      6   \n",
       "2                         2689.13                      6   \n",
       "3                          532.84                      6   \n",
       "4                          518.87                      6   \n",
       "5                          422.99                      6   \n",
       "\n",
       "   Adds information alongside other inputs  \n",
       "0                                     True  \n",
       "1                                     True  \n",
       "2                                     True  \n",
       "3                                     True  \n",
       "4                                     True  \n",
       "5                                     True  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Build a compact table from the full rankings. Only predictors that improve on\n",
    "# the calendar baseline are eligible, and at most three are shown for each target.\n",
    "gain_column = 'Error reduction vs calendar (thousand b/d)'\n",
    "conditional_column = 'Error increase when removed (thousand b/d)'\n",
    "summary = []\n",
    "for target_name, table in rankings.items():\n",
    "    positive = table[table[gain_column] > 0].head(3)\n",
    "    for rank, row in positive.iterrows():\n",
    "        summary.append({\n",
    "            'Target': target_name,\n",
    "            'Rank': rank,\n",
    "            'Predictor': row.Predictor,\n",
    "            'Error reduction (thousand b/d)': row[gain_column],\n",
    "            'Periods helped (of 6)': row['Periods helped (of 6)'],\n",
    "            # This flag distinguishes a strong stand-alone predictor from one that\n",
    "            # still contributes after correlated inputs enter the full model.\n",
    "            'Adds information alongside other inputs': bool(row[conditional_column] > 0),\n",
    "        })\n",
    "display(pd.DataFrame(summary).round(2))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-discussion-0",
   "metadata": {},
   "source": [
    "For crude supply, the previous three month average of production plus imports was most important.\n",
    "\n",
    "For crude demand, the previous three month average of refinery inputs was most important."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-7",
   "metadata": {},
   "source": [
    "## Individual predictor rankings"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-8-heading-1",
   "metadata": {},
   "source": [
    "### Supply: production + imports\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "crude-importance-8",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:44.481301Z",
     "iopub.status.busy": "2026-09-16T21:16:44.481048Z",
     "iopub.status.idle": "2026-09-16T21:16:44.710070Z",
     "shell.execute_reply": "2026-09-16T21:16:44.709422Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1300x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<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>Predictor</th>\n",
       "      <th>Error reduction vs calendar (thousand b/d)</th>\n",
       "      <th>Error reduction vs calendar (%)</th>\n",
       "      <th>Periods helped (of 6)</th>\n",
       "      <th>Error increase when removed (thousand b/d)</th>\n",
       "      <th>Periods hurt by removal (of 6)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Rank</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Supply (production + imports) — previous 3-month average</td>\n",
       "      <td>2785.23</td>\n",
       "      <td>88.79</td>\n",
       "      <td>6</td>\n",
       "      <td>4.65</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Supply (production + imports) — previous month</td>\n",
       "      <td>2714.99</td>\n",
       "      <td>86.55</td>\n",
       "      <td>6</td>\n",
       "      <td>1.17</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Crude production — previous 3-month average</td>\n",
       "      <td>2689.13</td>\n",
       "      <td>85.72</td>\n",
       "      <td>6</td>\n",
       "      <td>0.41</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Crude production — previous month</td>\n",
       "      <td>2680.78</td>\n",
       "      <td>85.46</td>\n",
       "      <td>6</td>\n",
       "      <td>0.51</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Crude exports — previous month</td>\n",
       "      <td>2165.55</td>\n",
       "      <td>69.03</td>\n",
       "      <td>6</td>\n",
       "      <td>-16.66</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Crude exports — previous 3-month average</td>\n",
       "      <td>2123.85</td>\n",
       "      <td>67.70</td>\n",
       "      <td>6</td>\n",
       "      <td>6.87</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Crude imports — previous 3-month average</td>\n",
       "      <td>1824.12</td>\n",
       "      <td>58.15</td>\n",
       "      <td>6</td>\n",
       "      <td>-0.71</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Crude imports — previous month</td>\n",
       "      <td>1750.54</td>\n",
       "      <td>55.80</td>\n",
       "      <td>6</td>\n",
       "      <td>-1.12</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Transfers — previous 3-month average</td>\n",
       "      <td>1654.87</td>\n",
       "      <td>52.75</td>\n",
       "      <td>4</td>\n",
       "      <td>3.71</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Transfers — previous month</td>\n",
       "      <td>1617.65</td>\n",
       "      <td>51.57</td>\n",
       "      <td>4</td>\n",
       "      <td>-6.69</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Crude refinery inputs — previous 3-month average</td>\n",
       "      <td>1167.89</td>\n",
       "      <td>37.23</td>\n",
       "      <td>6</td>\n",
       "      <td>0.79</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Crude refinery inputs — previous month</td>\n",
       "      <td>1066.39</td>\n",
       "      <td>33.99</td>\n",
       "      <td>6</td>\n",
       "      <td>2.85</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Crude distillation capacity — previous month</td>\n",
       "      <td>1004.89</td>\n",
       "      <td>32.03</td>\n",
       "      <td>6</td>\n",
       "      <td>9.19</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Gasoline net production — previous month</td>\n",
       "      <td>850.51</td>\n",
       "      <td>27.11</td>\n",
       "      <td>6</td>\n",
       "      <td>1.23</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Core balance (production + imports − exports − demand) — previous 3-month average</td>\n",
       "      <td>828.17</td>\n",
       "      <td>26.40</td>\n",
       "      <td>6</td>\n",
       "      <td>13.71</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Inventory level — previous month</td>\n",
       "      <td>803.74</td>\n",
       "      <td>25.62</td>\n",
       "      <td>6</td>\n",
       "      <td>1.41</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Crude refinery utilization — previous month</td>\n",
       "      <td>758.10</td>\n",
       "      <td>24.17</td>\n",
       "      <td>6</td>\n",
       "      <td>-0.27</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Core balance (production + imports − exports − demand) — previous month</td>\n",
       "      <td>586.74</td>\n",
       "      <td>18.70</td>\n",
       "      <td>6</td>\n",
       "      <td>7.71</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Inventory level minus year-earlier level</td>\n",
       "      <td>29.77</td>\n",
       "      <td>0.95</td>\n",
       "      <td>4</td>\n",
       "      <td>17.12</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Adjustments — previous 3-month average</td>\n",
       "      <td>25.10</td>\n",
       "      <td>0.80</td>\n",
       "      <td>3</td>\n",
       "      <td>-1.52</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Direct crude use — previous 3-month average</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.00</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>Direct crude use — previous month</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>-0.00</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Gasoline inventory change — previous month</td>\n",
       "      <td>-2.04</td>\n",
       "      <td>-0.07</td>\n",
       "      <td>2</td>\n",
       "      <td>3.61</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Inventory change — previous month</td>\n",
       "      <td>-2.16</td>\n",
       "      <td>-0.07</td>\n",
       "      <td>3</td>\n",
       "      <td>-2.93</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Inventory change — previous 3-month average</td>\n",
       "      <td>-6.51</td>\n",
       "      <td>-0.21</td>\n",
       "      <td>2</td>\n",
       "      <td>-12.00</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>Gasoline product supplied — previous month</td>\n",
       "      <td>-8.77</td>\n",
       "      <td>-0.28</td>\n",
       "      <td>2</td>\n",
       "      <td>-2.88</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>Adjustments — previous month</td>\n",
       "      <td>-14.18</td>\n",
       "      <td>-0.45</td>\n",
       "      <td>3</td>\n",
       "      <td>3.70</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>Net regional receipts — previous month</td>\n",
       "      <td>-15.27</td>\n",
       "      <td>-0.49</td>\n",
       "      <td>1</td>\n",
       "      <td>1.51</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>Net regional receipts — previous 3-month average</td>\n",
       "      <td>-49.39</td>\n",
       "      <td>-1.57</td>\n",
       "      <td>1</td>\n",
       "      <td>0.91</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                              Predictor  \\\n",
       "Rank                                                                                      \n",
       "1                              Supply (production + imports) — previous 3-month average   \n",
       "2                                        Supply (production + imports) — previous month   \n",
       "3                                           Crude production — previous 3-month average   \n",
       "4                                                     Crude production — previous month   \n",
       "5                                                        Crude exports — previous month   \n",
       "6                                              Crude exports — previous 3-month average   \n",
       "7                                              Crude imports — previous 3-month average   \n",
       "8                                                        Crude imports — previous month   \n",
       "9                                                  Transfers — previous 3-month average   \n",
       "10                                                           Transfers — previous month   \n",
       "11                                     Crude refinery inputs — previous 3-month average   \n",
       "12                                               Crude refinery inputs — previous month   \n",
       "13                                         Crude distillation capacity — previous month   \n",
       "14                                             Gasoline net production — previous month   \n",
       "15    Core balance (production + imports − exports − demand) — previous 3-month average   \n",
       "16                                                     Inventory level — previous month   \n",
       "17                                          Crude refinery utilization — previous month   \n",
       "18              Core balance (production + imports − exports − demand) — previous month   \n",
       "19                                             Inventory level minus year-earlier level   \n",
       "20                                               Adjustments — previous 3-month average   \n",
       "21                                          Direct crude use — previous 3-month average   \n",
       "22                                                    Direct crude use — previous month   \n",
       "23                                           Gasoline inventory change — previous month   \n",
       "24                                                    Inventory change — previous month   \n",
       "25                                          Inventory change — previous 3-month average   \n",
       "26                                           Gasoline product supplied — previous month   \n",
       "27                                                         Adjustments — previous month   \n",
       "28                                               Net regional receipts — previous month   \n",
       "29                                     Net regional receipts — previous 3-month average   \n",
       "\n",
       "      Error reduction vs calendar (thousand b/d)  \\\n",
       "Rank                                               \n",
       "1                                        2785.23   \n",
       "2                                        2714.99   \n",
       "3                                        2689.13   \n",
       "4                                        2680.78   \n",
       "5                                        2165.55   \n",
       "6                                        2123.85   \n",
       "7                                        1824.12   \n",
       "8                                        1750.54   \n",
       "9                                        1654.87   \n",
       "10                                       1617.65   \n",
       "11                                       1167.89   \n",
       "12                                       1066.39   \n",
       "13                                       1004.89   \n",
       "14                                        850.51   \n",
       "15                                        828.17   \n",
       "16                                        803.74   \n",
       "17                                        758.10   \n",
       "18                                        586.74   \n",
       "19                                         29.77   \n",
       "20                                         25.10   \n",
       "21                                          0.00   \n",
       "22                                          0.00   \n",
       "23                                         -2.04   \n",
       "24                                         -2.16   \n",
       "25                                         -6.51   \n",
       "26                                         -8.77   \n",
       "27                                        -14.18   \n",
       "28                                        -15.27   \n",
       "29                                        -49.39   \n",
       "\n",
       "      Error reduction vs calendar (%)  Periods helped (of 6)  \\\n",
       "Rank                                                           \n",
       "1                               88.79                      6   \n",
       "2                               86.55                      6   \n",
       "3                               85.72                      6   \n",
       "4                               85.46                      6   \n",
       "5                               69.03                      6   \n",
       "6                               67.70                      6   \n",
       "7                               58.15                      6   \n",
       "8                               55.80                      6   \n",
       "9                               52.75                      4   \n",
       "10                              51.57                      4   \n",
       "11                              37.23                      6   \n",
       "12                              33.99                      6   \n",
       "13                              32.03                      6   \n",
       "14                              27.11                      6   \n",
       "15                              26.40                      6   \n",
       "16                              25.62                      6   \n",
       "17                              24.17                      6   \n",
       "18                              18.70                      6   \n",
       "19                               0.95                      4   \n",
       "20                               0.80                      3   \n",
       "21                               0.00                      0   \n",
       "22                               0.00                      0   \n",
       "23                              -0.07                      2   \n",
       "24                              -0.07                      3   \n",
       "25                              -0.21                      2   \n",
       "26                              -0.28                      2   \n",
       "27                              -0.45                      3   \n",
       "28                              -0.49                      1   \n",
       "29                              -1.57                      1   \n",
       "\n",
       "      Error increase when removed (thousand b/d)  \\\n",
       "Rank                                               \n",
       "1                                           4.65   \n",
       "2                                           1.17   \n",
       "3                                           0.41   \n",
       "4                                           0.51   \n",
       "5                                         -16.66   \n",
       "6                                           6.87   \n",
       "7                                          -0.71   \n",
       "8                                          -1.12   \n",
       "9                                           3.71   \n",
       "10                                         -6.69   \n",
       "11                                          0.79   \n",
       "12                                          2.85   \n",
       "13                                          9.19   \n",
       "14                                          1.23   \n",
       "15                                         13.71   \n",
       "16                                          1.41   \n",
       "17                                         -0.27   \n",
       "18                                          7.71   \n",
       "19                                         17.12   \n",
       "20                                         -1.52   \n",
       "21                                         -0.00   \n",
       "22                                         -0.00   \n",
       "23                                          3.61   \n",
       "24                                         -2.93   \n",
       "25                                        -12.00   \n",
       "26                                         -2.88   \n",
       "27                                          3.70   \n",
       "28                                          1.51   \n",
       "29                                          0.91   \n",
       "\n",
       "      Periods hurt by removal (of 6)  \n",
       "Rank                                  \n",
       "1                                  4  \n",
       "2                                  3  \n",
       "3                                  2  \n",
       "4                                  5  \n",
       "5                                  1  \n",
       "6                                  3  \n",
       "7                                  2  \n",
       "8                                  4  \n",
       "9                                  3  \n",
       "10                                 2  \n",
       "11                                 2  \n",
       "12                                 6  \n",
       "13                                 4  \n",
       "14                                 4  \n",
       "15                                 4  \n",
       "16                                 4  \n",
       "17                                 3  \n",
       "18                                 4  \n",
       "19                                 5  \n",
       "20                                 3  \n",
       "21                                 2  \n",
       "22                                 2  \n",
       "23                                 4  \n",
       "24                                 1  \n",
       "25                                 0  \n",
       "26                                 3  \n",
       "27                                 5  \n",
       "28                                 4  \n",
       "29                                 4  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot and print the individual rankings for supply and demand separately.\n",
    "target_name = 'Supply: production + imports'\n",
    "table = rankings[target_name]\n",
    "# Reverse the top 12 so the highest-ranked predictor appears at the top of barh.\n",
    "top = table.head(12).iloc[::-1]\n",
    "fig, ax = plt.subplots(figsize=(13, 7))\n",
    "# Green bars improve on calendar; red bars increase average error.\n",
    "colors = ['#237a57' if value > 0 else '#b65a52' for value in top[gain_column]]\n",
    "ax.barh(top.Predictor, top[gain_column], color=colors)\n",
    "ax.axvline(0, color='black', linewidth=0.8)\n",
    "ax.set_title(FUEL.title() + ' ' + target_name.lower() + ': strongest individual predictors')\n",
    "ax.set_xlabel('Reduction in average absolute error vs calendar month (thousand barrels/day)')\n",
    "ax.set_ylabel('')\n",
    "fig.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# Period-level columns are shown later; omit them here to keep this table readable.\n",
    "display(table.drop(columns=[f'Period {i} gain' for i in range(1, 7)]).round(2))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-8-heading-2",
   "metadata": {},
   "source": [
    "### Demand: crude refinery inputs\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "crude-importance-8-second",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:44.711802Z",
     "iopub.status.busy": "2026-09-16T21:16:44.711611Z",
     "iopub.status.idle": "2026-09-16T21:16:44.825549Z",
     "shell.execute_reply": "2026-09-16T21:16:44.825051Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1300x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<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>Predictor</th>\n",
       "      <th>Error reduction vs calendar (thousand b/d)</th>\n",
       "      <th>Error reduction vs calendar (%)</th>\n",
       "      <th>Periods helped (of 6)</th>\n",
       "      <th>Error increase when removed (thousand b/d)</th>\n",
       "      <th>Periods hurt by removal (of 6)</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Rank</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Crude refinery inputs — previous 3-month average</td>\n",
       "      <td>532.84</td>\n",
       "      <td>67.46</td>\n",
       "      <td>6</td>\n",
       "      <td>8.34</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>Crude refinery inputs — previous month</td>\n",
       "      <td>518.87</td>\n",
       "      <td>65.69</td>\n",
       "      <td>6</td>\n",
       "      <td>5.96</td>\n",
       "      <td>6</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>Gasoline net production — previous month</td>\n",
       "      <td>422.99</td>\n",
       "      <td>53.55</td>\n",
       "      <td>6</td>\n",
       "      <td>3.23</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>Crude refinery utilization — previous month</td>\n",
       "      <td>363.68</td>\n",
       "      <td>46.04</td>\n",
       "      <td>6</td>\n",
       "      <td>0.89</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>Crude distillation capacity — previous month</td>\n",
       "      <td>359.87</td>\n",
       "      <td>45.56</td>\n",
       "      <td>6</td>\n",
       "      <td>7.58</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>Inventory level — previous month</td>\n",
       "      <td>334.02</td>\n",
       "      <td>42.29</td>\n",
       "      <td>6</td>\n",
       "      <td>12.87</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>Crude imports — previous month</td>\n",
       "      <td>265.04</td>\n",
       "      <td>33.55</td>\n",
       "      <td>5</td>\n",
       "      <td>-1.31</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>Crude imports — previous 3-month average</td>\n",
       "      <td>259.92</td>\n",
       "      <td>32.91</td>\n",
       "      <td>5</td>\n",
       "      <td>-2.33</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>Transfers — previous month</td>\n",
       "      <td>172.88</td>\n",
       "      <td>21.89</td>\n",
       "      <td>4</td>\n",
       "      <td>-7.27</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>Transfers — previous 3-month average</td>\n",
       "      <td>169.71</td>\n",
       "      <td>21.49</td>\n",
       "      <td>4</td>\n",
       "      <td>1.29</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>Supply (production + imports) — previous month</td>\n",
       "      <td>164.47</td>\n",
       "      <td>20.82</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.80</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>Crude production — previous month</td>\n",
       "      <td>148.69</td>\n",
       "      <td>18.82</td>\n",
       "      <td>4</td>\n",
       "      <td>-0.11</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>Crude production — previous 3-month average</td>\n",
       "      <td>138.24</td>\n",
       "      <td>17.50</td>\n",
       "      <td>4</td>\n",
       "      <td>-1.11</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>Core balance (production + imports − exports − demand) — previous 3-month average</td>\n",
       "      <td>131.37</td>\n",
       "      <td>16.63</td>\n",
       "      <td>5</td>\n",
       "      <td>8.16</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>Supply (production + imports) — previous 3-month average</td>\n",
       "      <td>126.27</td>\n",
       "      <td>15.99</td>\n",
       "      <td>4</td>\n",
       "      <td>-1.99</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>Core balance (production + imports − exports − demand) — previous month</td>\n",
       "      <td>117.35</td>\n",
       "      <td>14.86</td>\n",
       "      <td>5</td>\n",
       "      <td>-10.11</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>Gasoline product supplied — previous month</td>\n",
       "      <td>20.60</td>\n",
       "      <td>2.61</td>\n",
       "      <td>2</td>\n",
       "      <td>-3.31</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>Gasoline inventory change — previous month</td>\n",
       "      <td>0.25</td>\n",
       "      <td>0.03</td>\n",
       "      <td>2</td>\n",
       "      <td>5.02</td>\n",
       "      <td>5</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>Direct crude use — previous 3-month average</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>Direct crude use — previous month</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>0</td>\n",
       "      <td>0.00</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>Inventory change — previous month</td>\n",
       "      <td>-2.38</td>\n",
       "      <td>-0.30</td>\n",
       "      <td>3</td>\n",
       "      <td>-4.46</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>Inventory change — previous 3-month average</td>\n",
       "      <td>-3.43</td>\n",
       "      <td>-0.43</td>\n",
       "      <td>1</td>\n",
       "      <td>-15.73</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>Net regional receipts — previous month</td>\n",
       "      <td>-5.25</td>\n",
       "      <td>-0.66</td>\n",
       "      <td>1</td>\n",
       "      <td>0.62</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>Inventory level minus year-earlier level</td>\n",
       "      <td>-5.85</td>\n",
       "      <td>-0.74</td>\n",
       "      <td>4</td>\n",
       "      <td>19.36</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>Net regional receipts — previous 3-month average</td>\n",
       "      <td>-15.96</td>\n",
       "      <td>-2.02</td>\n",
       "      <td>2</td>\n",
       "      <td>-1.79</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>Adjustments — previous 3-month average</td>\n",
       "      <td>-20.09</td>\n",
       "      <td>-2.54</td>\n",
       "      <td>2</td>\n",
       "      <td>-5.81</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>Adjustments — previous month</td>\n",
       "      <td>-34.49</td>\n",
       "      <td>-4.37</td>\n",
       "      <td>2</td>\n",
       "      <td>-0.30</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>Crude exports — previous month</td>\n",
       "      <td>-194.10</td>\n",
       "      <td>-24.57</td>\n",
       "      <td>2</td>\n",
       "      <td>-2.65</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>Crude exports — previous 3-month average</td>\n",
       "      <td>-241.42</td>\n",
       "      <td>-30.56</td>\n",
       "      <td>2</td>\n",
       "      <td>-10.74</td>\n",
       "      <td>3</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                                              Predictor  \\\n",
       "Rank                                                                                      \n",
       "1                                      Crude refinery inputs — previous 3-month average   \n",
       "2                                                Crude refinery inputs — previous month   \n",
       "3                                              Gasoline net production — previous month   \n",
       "4                                           Crude refinery utilization — previous month   \n",
       "5                                          Crude distillation capacity — previous month   \n",
       "6                                                      Inventory level — previous month   \n",
       "7                                                        Crude imports — previous month   \n",
       "8                                              Crude imports — previous 3-month average   \n",
       "9                                                            Transfers — previous month   \n",
       "10                                                 Transfers — previous 3-month average   \n",
       "11                                       Supply (production + imports) — previous month   \n",
       "12                                                    Crude production — previous month   \n",
       "13                                          Crude production — previous 3-month average   \n",
       "14    Core balance (production + imports − exports − demand) — previous 3-month average   \n",
       "15                             Supply (production + imports) — previous 3-month average   \n",
       "16              Core balance (production + imports − exports − demand) — previous month   \n",
       "17                                           Gasoline product supplied — previous month   \n",
       "18                                           Gasoline inventory change — previous month   \n",
       "19                                          Direct crude use — previous 3-month average   \n",
       "20                                                    Direct crude use — previous month   \n",
       "21                                                    Inventory change — previous month   \n",
       "22                                          Inventory change — previous 3-month average   \n",
       "23                                               Net regional receipts — previous month   \n",
       "24                                             Inventory level minus year-earlier level   \n",
       "25                                     Net regional receipts — previous 3-month average   \n",
       "26                                               Adjustments — previous 3-month average   \n",
       "27                                                         Adjustments — previous month   \n",
       "28                                                       Crude exports — previous month   \n",
       "29                                             Crude exports — previous 3-month average   \n",
       "\n",
       "      Error reduction vs calendar (thousand b/d)  \\\n",
       "Rank                                               \n",
       "1                                         532.84   \n",
       "2                                         518.87   \n",
       "3                                         422.99   \n",
       "4                                         363.68   \n",
       "5                                         359.87   \n",
       "6                                         334.02   \n",
       "7                                         265.04   \n",
       "8                                         259.92   \n",
       "9                                         172.88   \n",
       "10                                        169.71   \n",
       "11                                        164.47   \n",
       "12                                        148.69   \n",
       "13                                        138.24   \n",
       "14                                        131.37   \n",
       "15                                        126.27   \n",
       "16                                        117.35   \n",
       "17                                         20.60   \n",
       "18                                          0.25   \n",
       "19                                          0.00   \n",
       "20                                          0.00   \n",
       "21                                         -2.38   \n",
       "22                                         -3.43   \n",
       "23                                         -5.25   \n",
       "24                                         -5.85   \n",
       "25                                        -15.96   \n",
       "26                                        -20.09   \n",
       "27                                        -34.49   \n",
       "28                                       -194.10   \n",
       "29                                       -241.42   \n",
       "\n",
       "      Error reduction vs calendar (%)  Periods helped (of 6)  \\\n",
       "Rank                                                           \n",
       "1                               67.46                      6   \n",
       "2                               65.69                      6   \n",
       "3                               53.55                      6   \n",
       "4                               46.04                      6   \n",
       "5                               45.56                      6   \n",
       "6                               42.29                      6   \n",
       "7                               33.55                      5   \n",
       "8                               32.91                      5   \n",
       "9                               21.89                      4   \n",
       "10                              21.49                      4   \n",
       "11                              20.82                      4   \n",
       "12                              18.82                      4   \n",
       "13                              17.50                      4   \n",
       "14                              16.63                      5   \n",
       "15                              15.99                      4   \n",
       "16                              14.86                      5   \n",
       "17                               2.61                      2   \n",
       "18                               0.03                      2   \n",
       "19                               0.00                      0   \n",
       "20                               0.00                      0   \n",
       "21                              -0.30                      3   \n",
       "22                              -0.43                      1   \n",
       "23                              -0.66                      1   \n",
       "24                              -0.74                      4   \n",
       "25                              -2.02                      2   \n",
       "26                              -2.54                      2   \n",
       "27                              -4.37                      2   \n",
       "28                             -24.57                      2   \n",
       "29                             -30.56                      2   \n",
       "\n",
       "      Error increase when removed (thousand b/d)  \\\n",
       "Rank                                               \n",
       "1                                           8.34   \n",
       "2                                           5.96   \n",
       "3                                           3.23   \n",
       "4                                           0.89   \n",
       "5                                           7.58   \n",
       "6                                          12.87   \n",
       "7                                          -1.31   \n",
       "8                                          -2.33   \n",
       "9                                          -7.27   \n",
       "10                                          1.29   \n",
       "11                                         -0.80   \n",
       "12                                         -0.11   \n",
       "13                                         -1.11   \n",
       "14                                          8.16   \n",
       "15                                         -1.99   \n",
       "16                                        -10.11   \n",
       "17                                         -3.31   \n",
       "18                                          5.02   \n",
       "19                                          0.00   \n",
       "20                                          0.00   \n",
       "21                                         -4.46   \n",
       "22                                        -15.73   \n",
       "23                                          0.62   \n",
       "24                                         19.36   \n",
       "25                                         -1.79   \n",
       "26                                         -5.81   \n",
       "27                                         -0.30   \n",
       "28                                         -2.65   \n",
       "29                                        -10.74   \n",
       "\n",
       "      Periods hurt by removal (of 6)  \n",
       "Rank                                  \n",
       "1                                  4  \n",
       "2                                  6  \n",
       "3                                  4  \n",
       "4                                  4  \n",
       "5                                  4  \n",
       "6                                  1  \n",
       "7                                  1  \n",
       "8                                  2  \n",
       "9                                  4  \n",
       "10                                 4  \n",
       "11                                 3  \n",
       "12                                 4  \n",
       "13                                 3  \n",
       "14                                 5  \n",
       "15                                 4  \n",
       "16                                 2  \n",
       "17                                 2  \n",
       "18                                 5  \n",
       "19                                 4  \n",
       "20                                 4  \n",
       "21                                 2  \n",
       "22                                 0  \n",
       "23                                 3  \n",
       "24                                 3  \n",
       "25                                 1  \n",
       "26                                 1  \n",
       "27                                 3  \n",
       "28                                 3  \n",
       "29                                 3  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "target_name = 'Demand: crude refinery inputs'\n",
    "table = rankings[target_name]\n",
    "# Reverse the top 12 so the highest-ranked predictor appears at the top of barh.\n",
    "top = table.head(12).iloc[::-1]\n",
    "fig, ax = plt.subplots(figsize=(13, 7))\n",
    "# Green bars improve on calendar; red bars increase average error.\n",
    "colors = ['#237a57' if value > 0 else '#b65a52' for value in top[gain_column]]\n",
    "ax.barh(top.Predictor, top[gain_column], color=colors)\n",
    "ax.axvline(0, color='black', linewidth=0.8)\n",
    "ax.set_title(FUEL.title() + ' ' + target_name.lower() + ': strongest individual predictors')\n",
    "ax.set_xlabel('Reduction in average absolute error vs calendar month (thousand barrels/day)')\n",
    "ax.set_ylabel('')\n",
    "fig.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# Period-level columns are shown later; omit them here to keep this table readable.\n",
    "display(table.drop(columns=[f'Period {i} gain' for i in range(1, 7)]).round(2))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-discussion-1",
   "metadata": {},
   "source": [
    "The three-month average of supply reduces error by about 2,785 thousand barrels/day versus calendar month alone. \n",
    "\n",
    "For demand, the three-month average of refinery inputs reduces error by about 533 thousand barrels/day."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-9",
   "metadata": {},
   "source": [
    "## Which variables matter alongside the others?\n",
    "\n",
    "These rankings remove one input at a time from a ridge model. Positive values mean that removing the input makes predictions worse. Negative values mean predictions improve without it. \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "crude-importance-10",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:44.827067Z",
     "iopub.status.busy": "2026-09-16T21:16:44.826863Z",
     "iopub.status.idle": "2026-09-16T21:16:45.090560Z",
     "shell.execute_reply": "2026-09-16T21:16:45.089919Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1300x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1300x700 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<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>Target</th>\n",
       "      <th>Predictor</th>\n",
       "      <th>Error increase when removed (thousand b/d)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>Supply: production + imports</td>\n",
       "      <td>Calendar month (all 12 month indicators)</td>\n",
       "      <td>10.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>Demand: crude refinery inputs</td>\n",
       "      <td>Calendar month (all 12 month indicators)</td>\n",
       "      <td>70.65</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                          Target                                 Predictor  \\\n",
       "0   Supply: production + imports  Calendar month (all 12 month indicators)   \n",
       "1  Demand: crude refinery inputs  Calendar month (all 12 month indicators)   \n",
       "\n",
       "   Error increase when removed (thousand b/d)  \n",
       "0                                       10.96  \n",
       "1                                       70.65  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Reorder the same ranking tables by conditional importance: the change in\n",
    "# full-model error when one predictor is removed and the model is refitted.\n",
    "for target_name, table in rankings.items():\n",
    "    ordered = table.sort_values(conditional_column, ascending=False).head(12).iloc[::-1]\n",
    "    fig, ax = plt.subplots(figsize=(13, 7))\n",
    "    # Green means removal hurts predictions; red means removal improves them.\n",
    "    ax.barh(ordered.Predictor, ordered[conditional_column],\n",
    "            color=['#237a57' if v > 0 else '#b65a52' for v in ordered[conditional_column]])\n",
    "    ax.axvline(0, color='black', linewidth=0.8)\n",
    "    ax.set_title(target_name + ': which variables add information alongside all other inputs?')\n",
    "    ax.set_xlabel('Increase in average absolute error after removing and refitting (thousand barrels/day)')\n",
    "    fig.tight_layout()\n",
    "    plt.show()\n",
    "\n",
    "# Calendar month is removed as a 12-column block, so report it separately from\n",
    "# the one-column removal rankings plotted above.\n",
    "display(pd.DataFrame(calendar_importance).round(2))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-discussion-2",
   "metadata": {},
   "source": [
    "The inventory level minus its year-earlier level adds the most information in the removal test for both supply and demand as removing it increases error by about 17 and 19 thousand barrels/day, respectively.\n",
    "\n",
    "These variables are weak on their own as above they did not provide much error reduction but helps the model interpret the other inputs."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-11",
   "metadata": {},
   "source": [
    "## How consistent is each predictor?"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-12-heading-1",
   "metadata": {},
   "source": [
    "### Supply: production + imports\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "crude-importance-12",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:45.092326Z",
     "iopub.status.busy": "2026-09-16T21:16:45.092152Z",
     "iopub.status.idle": "2026-09-16T21:16:45.100779Z",
     "shell.execute_reply": "2026-09-16T21:16:45.100172Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<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>Period 1 gain</th>\n",
       "      <th>Period 2 gain</th>\n",
       "      <th>Period 3 gain</th>\n",
       "      <th>Period 4 gain</th>\n",
       "      <th>Period 5 gain</th>\n",
       "      <th>Period 6 gain</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Predictor</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Supply (production + imports) — previous 3-month average</th>\n",
       "      <td>2948.14</td>\n",
       "      <td>2770.35</td>\n",
       "      <td>2296.66</td>\n",
       "      <td>2963.14</td>\n",
       "      <td>2867.23</td>\n",
       "      <td>2865.89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Supply (production + imports) — previous month</th>\n",
       "      <td>2832.89</td>\n",
       "      <td>2658.28</td>\n",
       "      <td>2315.81</td>\n",
       "      <td>2824.48</td>\n",
       "      <td>2840.18</td>\n",
       "      <td>2818.30</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude production — previous 3-month average</th>\n",
       "      <td>2259.66</td>\n",
       "      <td>2765.29</td>\n",
       "      <td>2447.02</td>\n",
       "      <td>2885.96</td>\n",
       "      <td>2886.88</td>\n",
       "      <td>2889.98</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude production — previous month</th>\n",
       "      <td>2280.37</td>\n",
       "      <td>2775.27</td>\n",
       "      <td>2429.86</td>\n",
       "      <td>2850.80</td>\n",
       "      <td>2868.68</td>\n",
       "      <td>2879.71</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude exports — previous month</th>\n",
       "      <td>2269.84</td>\n",
       "      <td>1646.04</td>\n",
       "      <td>947.51</td>\n",
       "      <td>2845.58</td>\n",
       "      <td>2801.79</td>\n",
       "      <td>2482.57</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude exports — previous 3-month average</th>\n",
       "      <td>2013.54</td>\n",
       "      <td>1499.73</td>\n",
       "      <td>823.63</td>\n",
       "      <td>2899.20</td>\n",
       "      <td>2867.48</td>\n",
       "      <td>2639.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude imports — previous 3-month average</th>\n",
       "      <td>639.94</td>\n",
       "      <td>1837.42</td>\n",
       "      <td>2196.10</td>\n",
       "      <td>1915.91</td>\n",
       "      <td>2045.95</td>\n",
       "      <td>2309.38</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude imports — previous month</th>\n",
       "      <td>637.45</td>\n",
       "      <td>1731.04</td>\n",
       "      <td>2133.58</td>\n",
       "      <td>1763.34</td>\n",
       "      <td>2022.97</td>\n",
       "      <td>2214.84</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transfers — previous 3-month average</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1787.08</td>\n",
       "      <td>2824.23</td>\n",
       "      <td>2847.98</td>\n",
       "      <td>2469.95</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transfers — previous month</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>1967.93</td>\n",
       "      <td>2890.00</td>\n",
       "      <td>2717.39</td>\n",
       "      <td>2130.61</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                          Period 1 gain  \\\n",
       "Predictor                                                                 \n",
       "Supply (production + imports) — previous 3-month average        2948.14   \n",
       "Supply (production + imports) — previous month                  2832.89   \n",
       "Crude production — previous 3-month average                     2259.66   \n",
       "Crude production — previous month                               2280.37   \n",
       "Crude exports — previous month                                  2269.84   \n",
       "Crude exports — previous 3-month average                        2013.54   \n",
       "Crude imports — previous 3-month average                         639.94   \n",
       "Crude imports — previous month                                   637.45   \n",
       "Transfers — previous 3-month average                               0.00   \n",
       "Transfers — previous month                                         0.00   \n",
       "\n",
       "                                                          Period 2 gain  \\\n",
       "Predictor                                                                 \n",
       "Supply (production + imports) — previous 3-month average        2770.35   \n",
       "Supply (production + imports) — previous month                  2658.28   \n",
       "Crude production — previous 3-month average                     2765.29   \n",
       "Crude production — previous month                               2775.27   \n",
       "Crude exports — previous month                                  1646.04   \n",
       "Crude exports — previous 3-month average                        1499.73   \n",
       "Crude imports — previous 3-month average                        1837.42   \n",
       "Crude imports — previous month                                  1731.04   \n",
       "Transfers — previous 3-month average                               0.00   \n",
       "Transfers — previous month                                         0.00   \n",
       "\n",
       "                                                          Period 3 gain  \\\n",
       "Predictor                                                                 \n",
       "Supply (production + imports) — previous 3-month average        2296.66   \n",
       "Supply (production + imports) — previous month                  2315.81   \n",
       "Crude production — previous 3-month average                     2447.02   \n",
       "Crude production — previous month                               2429.86   \n",
       "Crude exports — previous month                                   947.51   \n",
       "Crude exports — previous 3-month average                         823.63   \n",
       "Crude imports — previous 3-month average                        2196.10   \n",
       "Crude imports — previous month                                  2133.58   \n",
       "Transfers — previous 3-month average                            1787.08   \n",
       "Transfers — previous month                                      1967.93   \n",
       "\n",
       "                                                          Period 4 gain  \\\n",
       "Predictor                                                                 \n",
       "Supply (production + imports) — previous 3-month average        2963.14   \n",
       "Supply (production + imports) — previous month                  2824.48   \n",
       "Crude production — previous 3-month average                     2885.96   \n",
       "Crude production — previous month                               2850.80   \n",
       "Crude exports — previous month                                  2845.58   \n",
       "Crude exports — previous 3-month average                        2899.20   \n",
       "Crude imports — previous 3-month average                        1915.91   \n",
       "Crude imports — previous month                                  1763.34   \n",
       "Transfers — previous 3-month average                            2824.23   \n",
       "Transfers — previous month                                      2890.00   \n",
       "\n",
       "                                                          Period 5 gain  \\\n",
       "Predictor                                                                 \n",
       "Supply (production + imports) — previous 3-month average        2867.23   \n",
       "Supply (production + imports) — previous month                  2840.18   \n",
       "Crude production — previous 3-month average                     2886.88   \n",
       "Crude production — previous month                               2868.68   \n",
       "Crude exports — previous month                                  2801.79   \n",
       "Crude exports — previous 3-month average                        2867.48   \n",
       "Crude imports — previous 3-month average                        2045.95   \n",
       "Crude imports — previous month                                  2022.97   \n",
       "Transfers — previous 3-month average                            2847.98   \n",
       "Transfers — previous month                                      2717.39   \n",
       "\n",
       "                                                          Period 6 gain  \n",
       "Predictor                                                                \n",
       "Supply (production + imports) — previous 3-month average        2865.89  \n",
       "Supply (production + imports) — previous month                  2818.30  \n",
       "Crude production — previous 3-month average                     2889.98  \n",
       "Crude production — previous month                               2879.71  \n",
       "Crude exports — previous month                                  2482.57  \n",
       "Crude exports — previous 3-month average                        2639.53  \n",
       "Crude imports — previous 3-month average                        2309.38  \n",
       "Crude imports — previous month                                  2214.84  \n",
       "Transfers — previous 3-month average                            2469.95  \n",
       "Transfers — previous month                                      2130.61  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Show the top ten individual predictors' gains within each validation block.\n",
    "# This reveals whether a high overall average is broad or driven by one period.\n",
    "target_name = 'Supply: production + imports'\n",
    "table = rankings[target_name]\n",
    "columns = [f'Period {i} gain' for i in range(1, 7)]\n",
    "display(table.head(10).set_index('Predictor')[columns].round(2))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-importance-12-heading-2",
   "metadata": {},
   "source": [
    "### Demand: crude refinery inputs\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "crude-importance-12-second",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:45.102174Z",
     "iopub.status.busy": "2026-09-16T21:16:45.102033Z",
     "iopub.status.idle": "2026-09-16T21:16:45.110661Z",
     "shell.execute_reply": "2026-09-16T21:16:45.110043Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<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>Period 1 gain</th>\n",
       "      <th>Period 2 gain</th>\n",
       "      <th>Period 3 gain</th>\n",
       "      <th>Period 4 gain</th>\n",
       "      <th>Period 5 gain</th>\n",
       "      <th>Period 6 gain</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Predictor</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>Crude refinery inputs — previous 3-month average</th>\n",
       "      <td>1180.18</td>\n",
       "      <td>723.90</td>\n",
       "      <td>100.87</td>\n",
       "      <td>162.37</td>\n",
       "      <td>435.21</td>\n",
       "      <td>594.49</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude refinery inputs — previous month</th>\n",
       "      <td>1149.94</td>\n",
       "      <td>693.03</td>\n",
       "      <td>137.86</td>\n",
       "      <td>133.80</td>\n",
       "      <td>451.07</td>\n",
       "      <td>547.53</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Gasoline net production — previous month</th>\n",
       "      <td>990.77</td>\n",
       "      <td>692.43</td>\n",
       "      <td>155.77</td>\n",
       "      <td>117.26</td>\n",
       "      <td>289.92</td>\n",
       "      <td>291.78</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude refinery utilization — previous month</th>\n",
       "      <td>807.61</td>\n",
       "      <td>276.94</td>\n",
       "      <td>92.14</td>\n",
       "      <td>63.61</td>\n",
       "      <td>388.54</td>\n",
       "      <td>553.25</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude distillation capacity — previous month</th>\n",
       "      <td>987.72</td>\n",
       "      <td>463.80</td>\n",
       "      <td>47.34</td>\n",
       "      <td>223.92</td>\n",
       "      <td>359.60</td>\n",
       "      <td>76.84</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Inventory level — previous month</th>\n",
       "      <td>532.47</td>\n",
       "      <td>607.69</td>\n",
       "      <td>24.76</td>\n",
       "      <td>240.23</td>\n",
       "      <td>310.27</td>\n",
       "      <td>288.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude imports — previous month</th>\n",
       "      <td>450.37</td>\n",
       "      <td>509.41</td>\n",
       "      <td>-473.32</td>\n",
       "      <td>55.88</td>\n",
       "      <td>403.96</td>\n",
       "      <td>643.96</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Crude imports — previous 3-month average</th>\n",
       "      <td>487.37</td>\n",
       "      <td>505.49</td>\n",
       "      <td>-583.87</td>\n",
       "      <td>63.74</td>\n",
       "      <td>458.07</td>\n",
       "      <td>628.70</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transfers — previous month</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>119.15</td>\n",
       "      <td>195.06</td>\n",
       "      <td>345.31</td>\n",
       "      <td>377.76</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Transfers — previous 3-month average</th>\n",
       "      <td>0.00</td>\n",
       "      <td>0.00</td>\n",
       "      <td>123.93</td>\n",
       "      <td>171.49</td>\n",
       "      <td>354.78</td>\n",
       "      <td>368.08</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                                  Period 1 gain  \\\n",
       "Predictor                                                         \n",
       "Crude refinery inputs — previous 3-month average        1180.18   \n",
       "Crude refinery inputs — previous month                  1149.94   \n",
       "Gasoline net production — previous month                 990.77   \n",
       "Crude refinery utilization — previous month              807.61   \n",
       "Crude distillation capacity — previous month             987.72   \n",
       "Inventory level — previous month                         532.47   \n",
       "Crude imports — previous month                           450.37   \n",
       "Crude imports — previous 3-month average                 487.37   \n",
       "Transfers — previous month                                 0.00   \n",
       "Transfers — previous 3-month average                       0.00   \n",
       "\n",
       "                                                  Period 2 gain  \\\n",
       "Predictor                                                         \n",
       "Crude refinery inputs — previous 3-month average         723.90   \n",
       "Crude refinery inputs — previous month                   693.03   \n",
       "Gasoline net production — previous month                 692.43   \n",
       "Crude refinery utilization — previous month              276.94   \n",
       "Crude distillation capacity — previous month             463.80   \n",
       "Inventory level — previous month                         607.69   \n",
       "Crude imports — previous month                           509.41   \n",
       "Crude imports — previous 3-month average                 505.49   \n",
       "Transfers — previous month                                 0.00   \n",
       "Transfers — previous 3-month average                       0.00   \n",
       "\n",
       "                                                  Period 3 gain  \\\n",
       "Predictor                                                         \n",
       "Crude refinery inputs — previous 3-month average         100.87   \n",
       "Crude refinery inputs — previous month                   137.86   \n",
       "Gasoline net production — previous month                 155.77   \n",
       "Crude refinery utilization — previous month               92.14   \n",
       "Crude distillation capacity — previous month              47.34   \n",
       "Inventory level — previous month                          24.76   \n",
       "Crude imports — previous month                          -473.32   \n",
       "Crude imports — previous 3-month average                -583.87   \n",
       "Transfers — previous month                               119.15   \n",
       "Transfers — previous 3-month average                     123.93   \n",
       "\n",
       "                                                  Period 4 gain  \\\n",
       "Predictor                                                         \n",
       "Crude refinery inputs — previous 3-month average         162.37   \n",
       "Crude refinery inputs — previous month                   133.80   \n",
       "Gasoline net production — previous month                 117.26   \n",
       "Crude refinery utilization — previous month               63.61   \n",
       "Crude distillation capacity — previous month             223.92   \n",
       "Inventory level — previous month                         240.23   \n",
       "Crude imports — previous month                            55.88   \n",
       "Crude imports — previous 3-month average                  63.74   \n",
       "Transfers — previous month                               195.06   \n",
       "Transfers — previous 3-month average                     171.49   \n",
       "\n",
       "                                                  Period 5 gain  Period 6 gain  \n",
       "Predictor                                                                       \n",
       "Crude refinery inputs — previous 3-month average         435.21         594.49  \n",
       "Crude refinery inputs — previous month                   451.07         547.53  \n",
       "Gasoline net production — previous month                 289.92         291.78  \n",
       "Crude refinery utilization — previous month              388.54         553.25  \n",
       "Crude distillation capacity — previous month             359.60          76.84  \n",
       "Inventory level — previous month                         310.27         288.70  \n",
       "Crude imports — previous month                           403.96         643.96  \n",
       "Crude imports — previous 3-month average                 458.07         628.70  \n",
       "Transfers — previous month                               345.31         377.76  \n",
       "Transfers — previous 3-month average                     354.78         368.08  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "target_name = 'Demand: crude refinery inputs'\n",
    "table = rankings[target_name]\n",
    "columns = [f'Period {i} gain' for i in range(1, 7)]\n",
    "display(table.head(10).set_index('Predictor')[columns].round(2))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "crude-importance-12-periods",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2026-09-16T21:16:45.112351Z",
     "iopub.status.busy": "2026-09-16T21:16:45.112177Z",
     "iopub.status.idle": "2026-09-16T21:16:45.117442Z",
     "shell.execute_reply": "2026-09-16T21:16:45.116907Z"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<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>Period</th>\n",
       "      <th>First scored month</th>\n",
       "      <th>Last scored month</th>\n",
       "      <th>Scored months</th>\n",
       "      <th>Earlier training months</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1</td>\n",
       "      <td>2018-05</td>\n",
       "      <td>2019-04</td>\n",
       "      <td>12</td>\n",
       "      <td>123</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>2</td>\n",
       "      <td>2019-05</td>\n",
       "      <td>2022-06</td>\n",
       "      <td>12</td>\n",
       "      <td>135</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>3</td>\n",
       "      <td>2022-07</td>\n",
       "      <td>2023-06</td>\n",
       "      <td>12</td>\n",
       "      <td>147</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>4</td>\n",
       "      <td>2023-07</td>\n",
       "      <td>2024-06</td>\n",
       "      <td>12</td>\n",
       "      <td>159</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>5</td>\n",
       "      <td>2024-07</td>\n",
       "      <td>2025-06</td>\n",
       "      <td>12</td>\n",
       "      <td>171</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>6</td>\n",
       "      <td>2025-07</td>\n",
       "      <td>2026-06</td>\n",
       "      <td>12</td>\n",
       "      <td>183</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Period First scored month Last scored month  Scored months  \\\n",
       "0       1            2018-05           2019-04             12   \n",
       "1       2            2019-05           2022-06             12   \n",
       "2       3            2022-07           2023-06             12   \n",
       "3       4            2023-07           2024-06             12   \n",
       "4       5            2024-07           2025-06             12   \n",
       "5       6            2025-07           2026-06             12   \n",
       "\n",
       "   Earlier training months  \n",
       "0                      123  \n",
       "1                      135  \n",
       "2                      147  \n",
       "3                      159  \n",
       "4                      171  \n",
       "5                      183  "
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Print the exact scored dates and the amount of earlier training data available\n",
    "# for each block so the expanding-window design can be audited from the notebook.\n",
    "display(periods)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-discussion-3",
   "metadata": {},
   "source": [
    "Recent supply, crude production, exports and imports help predict supply in all six periods when tested individually.\n",
    "\n",
    "For demand, recent refinery inputs, gasoline net production, refinery utilization and distillation capacity also help in all six periods.\n",
    "\n",
    "The additional value of a variable is less uniform once all inputs are present. For example, the year-over-year inventory difference helps the full supply model in five periods, but the full demand model in only three."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "crude-conclusion",
   "metadata": {},
   "source": [
    "## Conclusion\n",
    "\n",
    "For crude supply, recent production and supply levels are the strongest individual predictors. For crude demand, recent refinery inputs are strongest, with gasoline production and refinery operating measures as other strong predictors. The three-month averages of supply and refinery inputs are stronger than their previous-month values.\n",
    "\n",
    "Inventory information is generally less important on its own, but the year-over-year inventory difference adds information alongside the other variables. (This is kind of a proxy for seasonality)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "b409a631",
   "metadata": {},
   "source": [
    "## Comparing crude and gasoline\n",
    "\n",
    "Gasoline is easier to predict compared to crude based on these tests as its errors are smaller both in barrels/day and relative to the size of supply or demand.\n",
    "\n",
    "The strongest predictors are similar, but the variables that add information alongside the other inputs differ.\n",
    "\n",
    "Table below shows average absolute error by the average target level to account for crude volumes being larger than gasoline volumes.\n",
    "\n",
    "| Target | Full-model error, thousand barrels/day | Error as % of average target | Best individual predictor + calendar: error % |\n",
    "|---|---:|---:|---:|\n",
    "| Crude supply | 354 | 1.82% | 1.81% |\n",
    "| Gasoline supply | 138 | 1.40% | 1.63% |\n",
    "| Crude demand | 338 | 2.07% | 1.57% |\n",
    "| Gasoline demand | 110 | 1.22% | 1.20% |\n",
    "\n",
    "Gasoline has lower relative errors for both targets, even when using just the strongest individual predictor plus calendar effects.\n",
    "\n",
    "However, crude improves more relative to the baseline of only using the month of the year. Its full model reduces supply error by 89%, compared with 60% for gasoline. For demand, the reductions are 57% and 46%. This means crude has larger error reductions.\n",
    "\n",
    "### Do the important predictors differ?\n",
    "\n",
    "The strongest individual predictor are the same.\n",
    "\n",
    "| Target | Crude | Gasoline |\n",
    "|---|---|---|\n",
    "| Supply | Previous three-month average of production + imports | Previous three-month average of production + imports |\n",
    "| Demand | Previous three-month average of refinery inputs | Previous three-month average of product supplied |\n",
    "\n",
    "Second most important predictors were:\n",
    "\n",
    "- **Crude supply:** recent crude production \n",
    "- **Crude demand:** gasoline production\n",
    "\n",
    "- **Gasoline supply:** crude distillation capacity\n",
    "- **Gasoline demand:** recent product supplied\n",
    "\n",
    "\n",
    "| Target | Largest error increase when a variable is removed |\n",
    "|---|---|\n",
    "| Crude supply | Crude year-over-year inventory difference: **17.1 thousand b/d** |\n",
    "| Crude demand | Crude year-over-year inventory difference: **19.4 thousand b/d** |\n",
    "| Gasoline supply | Previous-month crude inventory change: **7.6 thousand b/d** |\n",
    "| Gasoline demand | Three-month average gasoline product supplied: **9.2 thousand b/d** |\n",
    "\n",
    "Previous-month crude inventory change also helps the full gasoline demand model: removing it increases error by 6.0 thousand b/d."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv (3.13.9)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}