{ "cells": [ { "cell_type": "markdown", "id": "a5a92aa6", "metadata": {}, "source": [ "# A century of baseball: dating the home-run regime shifts\n", "\n", "The Major League Baseball home-run rate has a rich regime structure. It has been reshaped repeatedly by rule changes, equipment, new ballparks and performance-enhancing drugs. The associated folklore is well known: a \"dead-ball\" era of bunts and singles, an abrupt 1920 \"live-ball\" revolution, the 1968 \"Year of the Pitcher\", and the late-twentieth-century steroid era. Here we ask whether a single time-varying parameter, inferred with *bayesloop*, can reconstruct this century and a half of history and date its two most consequential structural breaks from the data alone.\n", "\n", "This is a natural fit for a time-varying-parameter model. The home-run rate is one number per season, but the process generating it clearly changes over time, sometimes smoothly and sometimes in a jump. We let the rate drift and use the marginal likelihood (model evidence) to decide whether the data prefer a constant level, a gradually varying one, or a single break, and then run focused `ChangepointStudy` scans to put a date, with a posterior, on the live-ball and steroid-era transitions. Along the way we exercise the `Gaussian` observation model with an inferred scatter, `HyperStudy`, `ChangepointStudy`, and evidence-based model selection." ] }, { "cell_type": "code", "execution_count": 1, "id": "40951bfa", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:52:55.333106Z", "iopub.status.busy": "2026-06-12T09:52:55.333020Z", "iopub.status.idle": "2026-06-12T09:52:56.805518Z", "shell.execute_reply": "2026-06-12T09:52:56.804912Z" } }, "outputs": [], "source": [ "%matplotlib inline\n", "import io\n", "import urllib.request\n", "\n", "import numpy as np\n", "import pandas as pd\n", "import matplotlib as mpl\n", "import matplotlib.pyplot as plt\n", "\n", "import bayesloop as bl\n", "\n", "try:\n", " import seaborn as sns\n", " sns.set_style(\"whitegrid\")\n", "except ImportError:\n", " plt.style.use(\"default\")\n", "mpl.rcParams.update({\n", " \"figure.dpi\": 110, \"font.size\": 10.5, \"axes.titlesize\": 12,\n", " \"axes.titleweight\": \"bold\", \"axes.edgecolor\": \"#444444\", \"grid.color\": \"#d9d9d9\",\n", "})\n", "C = {\"data\": \"#8a8a8a\", \"accent\": \"#c1272d\", \"accent2\": \"#0b6e99\",\n", " \"green\": \"#2e7d32\", \"amber\": \"#e8a33d\", \"muted\": \"#8a8a8a\",\n", " \"band\": \"#c1272d\", \"band2\": \"#0b6e99\"}\n", "\n", "\n", "def posterior_band(S, name, lo=0.05, hi=0.95):\n", " \"\"\"Posterior mean and an equal-tailed credible band for a time-varying parameter.\"\"\"\n", " x, p = S.get_parameter_distributions(name, density=False)\n", " p = np.asarray(p, dtype=float)\n", " p /= p.sum(axis=1, keepdims=True)\n", " mean = (p * x[None, :]).sum(axis=1)\n", " cdf = np.cumsum(p, axis=1)\n", " low = np.array([np.interp(lo, cdf[t], x) for t in range(p.shape[0])])\n", " high = np.array([np.interp(hi, cdf[t], x) for t in range(p.shape[0])])\n", " return mean, low, high\n", "\n", "\n", "def prob_in(S, name, lo=None, hi=None):\n", " \"\"\"Posterior probability the parameter lies in (lo, hi] at each time step.\"\"\"\n", " x, p = S.get_parameter_distributions(name, density=False)\n", " p = np.asarray(p, dtype=float)\n", " p /= p.sum(axis=1, keepdims=True)\n", " mask = np.ones_like(x, dtype=bool)\n", " if lo is not None:\n", " mask &= x > lo\n", " if hi is not None:\n", " mask &= x <= hi\n", " return p[:, mask].sum(axis=1)" ] }, { "cell_type": "markdown", "id": "10fb743b", "metadata": {}, "source": [ "## The data\n", "\n", "We use the Lahman Baseball Database `Teams.csv` table (Chadwick Bureau mirror), which has one row per team per season with that team's games (`G`) and home runs (`HR`). For every season we sum home runs and games across all teams and form home runs per team-game. This rate is directly comparable across eras despite league expansion (8 → 30 teams) and changing schedule lengths, because it is already exposure-normalised. The series runs 1871–2016 (146 seasons). The mirror ends at 2016, so we capture the dead-ball, live-ball, pitcher's-era, steroid and testing regimes; the 2019 \"juiced-ball\" record peak lies just beyond the window." ] }, { "cell_type": "code", "execution_count": 2, "id": "3f003c17", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:52:56.807125Z", "iopub.status.busy": "2026-06-12T09:52:56.806975Z", "iopub.status.idle": "2026-06-12T09:52:57.003071Z", "shell.execute_reply": "2026-06-12T09:52:57.002360Z" }, "lines_to_next_cell": 1 }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Seasons: 146 1871-2016\n" ] } ], "source": [ "url = \"https://raw.githubusercontent.com/orrski/baseballdatabank/master/core/Teams.csv\"\n", "try:\n", " req = urllib.request.Request(url, headers={\"User-Agent\": \"Mozilla/5.0 (bayesloop docs)\"})\n", " raw = urllib.request.urlopen(req, timeout=90).read()\n", "except Exception: # noqa: BLE001 — fall back to an alternate mirror\n", " url = \"https://raw.githubusercontent.com/cbwinslow/baseballdatabank/master/core/Teams.csv\"\n", " req = urllib.request.Request(url, headers={\"User-Agent\": \"Mozilla/5.0 (bayesloop docs)\"})\n", " raw = urllib.request.urlopen(req, timeout=90).read()\n", "t = pd.read_csv(io.BytesIO(raw))\n", "\n", "ag = t.groupby(\"yearID\").agg(HR=(\"HR\", \"sum\"), TG=(\"G\", \"sum\")).reset_index()\n", "ag = ag[ag[\"yearID\"] <= 2016]\n", "years = ag[\"yearID\"].values.astype(float)\n", "rate = (ag[\"HR\"] / ag[\"TG\"]).values.astype(float) # home runs per team-game\n", "print(f\"Seasons: {len(years)} {int(years.min())}-{int(years.max())}\")" ] }, { "cell_type": "markdown", "id": "37fd740b", "metadata": {}, "source": [ "## Modelling the rate: a Gaussian with inferred scatter\n", "\n", "A first instinct is to model the season HR totals as Poisson. With thousands of home runs per season, however, a Poisson implies a per-season precision of about 3%, far tighter than the real year-to-year variability driven by parks, balls, weather and rule tweaks. Forcing a Poisson on the totals makes every rigid model underflow. We therefore model the per-game rate HR/team-game with a `Gaussian` observation model whose standard deviation, the season-to-season scatter, is itself a free, inferred parameter (`noise`). This is the same robust treatment used for incidence data elsewhere, here applied to a linear rate." ] }, { "cell_type": "code", "execution_count": 3, "id": "e125182f", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:52:57.004862Z", "iopub.status.busy": "2026-06-12T09:52:57.004743Z", "iopub.status.idle": "2026-06-12T09:52:57.006690Z", "shell.execute_reply": "2026-06-12T09:52:57.006276Z" } }, "outputs": [], "source": [ "def obs():\n", " return bl.om.Gaussian(\"rate\", bl.cint(0.0, 1.5, 300), \"noise\", bl.oint(0.01, 0.5, 60))" ] }, { "cell_type": "markdown", "id": "7c060ecd", "metadata": {}, "source": [ "## A smooth time-varying rate over the full history\n", "\n", "First we let the rate drift smoothly from season to season with a `GaussianRandomWalk`, wrapped in a `HyperStudy` that marginalises over the unknown magnitude (`sigma`) of that drift. The result is a single inferred curve that traces the arc of baseball offense." ] }, { "cell_type": "code", "execution_count": 4, "id": "762bdd71", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:52:57.007693Z", "iopub.status.busy": "2026-06-12T09:52:57.007621Z", "iopub.status.idle": "2026-06-12T09:53:00.079098Z", "shell.execute_reply": "2026-06-12T09:53:00.078698Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "+ Created new study.\n", " --> Hyper-study\n", "+ Successfully imported array.\n", "+ Observation model: Gaussian observations. Parameter(s): ['rate', 'noise']\n", "+ Transition model: Gaussian random walk. Hyper-Parameter(s): ['sigma']\n" ] } ], "source": [ "Sr = bl.HyperStudy()\n", "Sr.load_data(rate, timestamps=years)\n", "Sr.set(obs(), bl.tm.GaussianRandomWalk(\"sigma\", bl.cint(0, 0.06, 30), target=\"rate\"))\n", "Sr.fit(silent=True)\n", "r_mean, r_lo, r_hi = posterior_band(Sr, \"rate\")" ] }, { "cell_type": "markdown", "id": "be384433", "metadata": {}, "source": [ "## Letting the evidence choose: constant, gradual, or one break\n", "\n", "The smooth fit assumes gradual drift. To test whether the data prefer this, we compare models. Because every model below shares the identical observation model and data, their log₁₀ marginal likelihoods (`S.log10_evidence`) are directly comparable. We compare three hypotheses: a static constant rate, the gradually varying random walk above, and a single change-point, a `ChangepointStudy` that scans every possible break season and returns a posterior over the break year." ] }, { "cell_type": "code", "execution_count": 5, "id": "4d32bbc1", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:53:00.080598Z", "iopub.status.busy": "2026-06-12T09:53:00.080517Z", "iopub.status.idle": "2026-06-12T09:53:05.985537Z", "shell.execute_reply": "2026-06-12T09:53:05.984958Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "+ Created new study.\n", "+ Successfully imported array.\n", "+ Observation model: Gaussian observations. Parameter(s): ['rate', 'noise']\n", "+ Transition model: Static/constant parameter values. Hyper-Parameter(s): []\n", "+ Created new study.\n", " --> Hyper-study\n", " --> Change-point analysis\n", "+ Successfully imported array.\n", "+ Observation model: Gaussian observations. Parameter(s): ['rate', 'noise']\n", "+ Transition model: Change-point. Hyper-Parameter(s): ['t_change']\n", "+ Detected 1 change-point(s) in transition model: ['t_change']\n", "+ Set hyper-prior(s): ['uniform']\n" ] } ], "source": [ "# Static (constant) rate — the null hypothesis.\n", "S0 = bl.Study()\n", "S0.load_data(rate, timestamps=years)\n", "S0.set(obs(), bl.tm.Static())\n", "S0.fit(silent=True)\n", "\n", "# A single abrupt change-point; ChangepointStudy scans *every* possible break season.\n", "Scp = bl.ChangepointStudy()\n", "Scp.load_data(rate, timestamps=years)\n", "Scp.set(obs(), bl.tm.ChangePoint(\"t_change\", \"all\"))\n", "Scp.fit(silent=True)\n", "cp_x, cp_p = Scp.get_hyper_parameter_distribution(\"t_change\")\n", "cp_mode = float(cp_x[np.argmax(cp_p)])\n", "\n", "evid = {\n", " \"Static (constant)\": float(S0.log10_evidence),\n", " \"Gradually varying\": float(Sr.log10_evidence),\n", " \"Single change-point\": float(Scp.log10_evidence),\n", "}" ] }, { "cell_type": "markdown", "id": "174fdc5d", "metadata": {}, "source": [ "## Isolating the steroid-era onset\n", "\n", "The full-series change-point locks onto the single biggest break in 150 years (the 1920 jump), so it cannot also tell us when the steroid era began. To isolate that later transition we run a second `ChangepointStudy` on a 1980–2004 window, long enough to straddle the surge but short enough that the live-ball jump is excluded. This shows how a windowed change-point scan can pinpoint a specific transition even when many exist in the full record." ] }, { "cell_type": "code", "execution_count": 6, "id": "3c1aab08", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:53:05.986894Z", "iopub.status.busy": "2026-06-12T09:53:05.986799Z", "iopub.status.idle": "2026-06-12T09:53:06.176812Z", "shell.execute_reply": "2026-06-12T09:53:06.176292Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "+ Created new study.\n", " --> Hyper-study\n", " --> Change-point analysis\n", "+ Successfully imported array.\n", "+ Observation model: Gaussian observations. Parameter(s): ['rate', 'noise']\n", "+ Transition model: Change-point. Hyper-Parameter(s): ['t_change']\n", "+ Detected 1 change-point(s) in transition model: ['t_change']\n", "+ Set hyper-prior(s): ['uniform']\n" ] } ], "source": [ "mod = ag[(ag[\"yearID\"] >= 1980) & (ag[\"yearID\"] <= 2004)].reset_index(drop=True)\n", "Scp2 = bl.ChangepointStudy()\n", "Scp2.load_data((mod[\"HR\"] / mod[\"TG\"]).values.astype(float),\n", " timestamps=mod[\"yearID\"].values.astype(float))\n", "Scp2.set(obs(), bl.tm.ChangePoint(\"t_change\", \"all\"))\n", "Scp2.fit(silent=True)\n", "cp2_x, cp2_p = Scp2.get_hyper_parameter_distribution(\"t_change\")\n", "cp2_mode = float(cp2_x[np.argmax(cp2_p)])" ] }, { "cell_type": "markdown", "id": "8f194f36", "metadata": {}, "source": [ "## Quantifying the regimes from the raw series\n", "\n", "We can also read a model-free magnitude directly from the data: the mean dead-ball rate (1901–1919) versus the early live-ball rate (1921–1930), and the 1968 pitcher's-year trough versus the 2000 steroid-era peak." ] }, { "cell_type": "code", "execution_count": 7, "id": "430577b0", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:53:06.177923Z", "iopub.status.busy": "2026-06-12T09:53:06.177830Z", "iopub.status.idle": "2026-06-12T09:53:06.180390Z", "shell.execute_reply": "2026-06-12T09:53:06.180069Z" } }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "\n", "MODEL EVIDENCE (log10):\n", " Static (constant) -24.5\n", " Gradually varying 67.6\n", " Single change-point 17.1\n", "Dominant change-point: 1920 (live-ball revolution)\n", "Steroid-era onset change-point (1980-2004 window): 1993\n", "Dead-ball 0.152 -> live-ball 0.439 HR/team-game (2.9x); 1968=0.614, 2000 peak=1.172\n" ] } ], "source": [ "deadball = rate[(years >= 1901) & (years <= 1919)].mean()\n", "liveball = rate[(years >= 1921) & (years <= 1930)].mean()\n", "trough_1968 = rate[years == 1968][0]\n", "peak_2000 = rate[years == 2000][0]\n", "\n", "print(\"\\nMODEL EVIDENCE (log10):\")\n", "for k, v in evid.items():\n", " print(f\" {k:22s} {v:10.1f}\")\n", "print(f\"Dominant change-point: {cp_mode:.0f} (live-ball revolution)\")\n", "print(f\"Steroid-era onset change-point (1980-2004 window): {cp2_mode:.0f}\")\n", "print(f\"Dead-ball {deadball:.3f} -> live-ball {liveball:.3f} HR/team-game \"\n", " f\"({liveball/deadball:.1f}x); 1968={trough_1968:.3f}, 2000 peak={peak_2000:.3f}\")" ] }, { "cell_type": "markdown", "id": "97e6da5a", "metadata": {}, "source": [ "The result is clear. A time-varying rate is favoured over a constant one by a large margin (tens of log₁₀ units), and over a single break by tens more, which confirms quantitatively that baseball offense is a multi-regime system rather than a one-shift one. The two focused change-point scans land squarely on the textbook dates: 1920 for the live-ball revolution (the year the spitball was banned, umpires began swapping out scuffed balls after Ray Chapman's fatal beaning, and Babe Ruth hit a then-astonishing 54 home runs) and 1993 for the steroid-era onset (coincident with the 1993 expansion, the run-up to Coors Field, and the offensive explosion that culminated in the 1998 McGwire–Sosa chase and Bonds' 73 in 2001)." ] }, { "cell_type": "markdown", "id": "1573922a", "metadata": {}, "source": [ "## The home run as one time-varying parameter\n", "\n", "The first figure overlays the observed rate (bars) with the single inferred rate (`HyperStudy` posterior mean, red) and its 90% credible band. Read left to right, this one curve traces the history of the home run." ] }, { "cell_type": "code", "execution_count": 8, "id": "e39c7e13", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:53:06.181524Z", "iopub.status.busy": "2026-06-12T09:53:06.181450Z", "iopub.status.idle": "2026-06-12T09:53:06.295029Z", "shell.execute_reply": "2026-06-12T09:53:06.294506Z" } }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fig, ax = plt.subplots(figsize=(9.2, 4.4))\n", "ax.bar(years, rate, width=0.8, color=C[\"muted\"], alpha=0.45, label=\"observed HR/team-game\")\n", "ax.plot(years, r_mean, color=C[\"accent\"], lw=2.2, label=\"inferred rate (posterior mean)\")\n", "ax.fill_between(years, r_lo, r_hi, color=C[\"band\"], alpha=0.20, label=\"90% credible band\")\n", "anns = [(1919, 0.05, \"dead-ball\\nera\"), (1921, 0.62, \"1920 live-ball\\nrevolution\"),\n", " (1968, 0.40, \"1968 'Year of\\nthe Pitcher'\"), (2000, 1.28, \"steroid-era\\npeak\"),\n", " (2014, 0.72, \"testing-era\\ndip\")]\n", "for xx, yy, txt in anns:\n", " ax.text(xx, yy, txt, fontsize=7.5, ha=\"center\", color=C[\"data\"])\n", "ax.axvline(cp_mode, color=\"k\", ls=\"--\", lw=1, alpha=0.7)\n", "ax.set_xlim(1869, 2018)\n", "ax.set_ylim(0, 1.45)\n", "ax.set_ylabel(\"home runs per team-game\")\n", "ax.set_xlabel(\"season\")\n", "ax.set_title(\"150 years of MLB home-run rates, as a single time-varying parameter\")\n", "ax.legend(loc=\"upper left\", fontsize=8)\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "357b1f98", "metadata": {}, "source": [ "The inferred rate reconstructs the history of baseball offense: the dead-ball era (~0.15 HR/team-game, bottoming out around 1918), the abrupt 1920 jump, the rise through mid-century, the 1968 \"Year of the Pitcher\" dip, the climb to the steroid-era peak around 2000, the post-2005 testing-era decline, and the 2015–16 rebound.\n", "\n", "## The two dated breaks\n", "\n", "Finally we show the two change-point posteriors side by side: the full-series scan, which dates the live-ball revolution, and the windowed scan, which dates the steroid-era onset. These are distributions over years, so each transition comes with its own uncertainty, which a hand-defined \"era\" boundary cannot provide." ] }, { "cell_type": "code", "execution_count": 9, "id": "8a06adbc", "metadata": { "execution": { "iopub.execute_input": "2026-06-12T09:53:06.296251Z", "iopub.status.busy": "2026-06-12T09:53:06.296151Z", "iopub.status.idle": "2026-06-12T09:53:06.500494Z", "shell.execute_reply": "2026-06-12T09:53:06.499937Z" } }, "outputs": [ { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "fig, (axa, axb) = plt.subplots(1, 2, figsize=(9.2, 3.4))\n", "axa.bar(cp_x, cp_p, width=0.9, color=C[\"green\"], alpha=0.85)\n", "axa.axvline(1920, color=C[\"accent\"], ls=\"--\", lw=1.2, label=\"1920\")\n", "axa.set_xlim(1912, 1928)\n", "axa.set_xlabel(\"year of dominant break\")\n", "axa.set_ylabel(\"posterior probability\")\n", "axa.set_title(f\"Live-ball revolution: {cp_mode:.0f}\")\n", "axa.legend(fontsize=8)\n", "axb.bar(cp2_x, cp2_p, width=0.9, color=C[\"accent2\"], alpha=0.85)\n", "axb.set_xlim(1985, 2000)\n", "axb.set_xlabel(\"year of break (1980–2004 window)\")\n", "axb.set_ylabel(\"posterior probability\")\n", "axb.set_title(f\"Steroid-era onset: {cp2_mode:.0f}\")\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "241306c0", "metadata": {}, "source": [ "## What this example showed\n", "\n", "On a single, readily interpretable dataset we used *bayesloop* to:\n", "\n", "- express baseball folklore as measurement: one continuously varying parameter reconstructs 150 years of home-run history, and the figure traces that history directly;\n", "- settle a structural question with model evidence: a time-varying rate is favoured over both a constant level and a single break by tens of log₁₀ units, which confirms that baseball offense is a multi-regime system;\n", "- date two transitions with posteriors rather than assumptions: full-series and windowed `ChangepointStudy` scans place the live-ball revolution at 1920 and the steroid-era onset at 1993, both within a year of the dates historians cite;\n", "- apply a practical modelling lesson: why a naive Poisson-on-totals model underflows on large counts, and how reframing to a Gaussian rate with inferred scatter fixes it, guidance that transfers to any bayesloop user with large count data." ] } ], "metadata": { "jupytext": { "cell_metadata_filter": "-all", "main_language": "python", "notebook_metadata_filter": "-all", "text_representation": { "extension": ".py", "format_name": "percent" } }, "kernelspec": { "display_name": "Python 3", "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": "3.12.4" } }, "nbformat": 4, "nbformat_minor": 5 }