goad-toolkit 0.2.2__tar.gz → 0.2.3__tar.gz

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/MCP_SERVER.md

@@ -103,13 +103,13 @@ You pin a version with `GOAD_REF` — a git ref (branch, tag, or commit). That o
 selects both the script (in the URL) and the docs it fetches (inside the script), so a whole
 cohort runs exactly the same thing and the two cannot drift apart.
 
-> **Note:** the docs and this server land in **v0.2.0**. Until that tag exists, point
-> `GOAD_REF` at the branch (`feat/docs-and-mcp`) or work from a local clone (see below).
+> **Note:** the docs and this server land in **v0.2.2**. 
+> You can also point `GOAD_REF` to a branch or work from a local clone (see below).
 
 ### Claude Code
 
 ```bash
-claude mcp add goad -e GOAD_REF=v0.2.0 -- \
+claude mcp add goad -e GOAD_REF=v0.2.2 -- \
   sh -c 'uv run --no-project https://raw.githubusercontent.com/raoulg/goad_toolkit/$GOAD_REF/goad_mcp.py'
 ```
 
@@ -123,7 +123,7 @@ Add to `.cursor/mcp.json` (per-project) or `~/.cursor/mcp.json` (global):
     "goad": {
       "command": "sh",
       "args": ["-c", "uv run --no-project https://raw.githubusercontent.com/raoulg/goad_toolkit/$GOAD_REF/goad_mcp.py"],
-      "env": { "GOAD_REF": "v0.2.0" }
+      "env": { "GOAD_REF": "v0.2.2" }
     }
   }
 }
@@ -137,7 +137,7 @@ Add to `~/.codex/config.toml`:
 [mcp_servers.goad]
 command = "sh"
 args = ["-c", "uv run --no-project https://raw.githubusercontent.com/raoulg/goad_toolkit/$GOAD_REF/goad_mcp.py"]
-env = { GOAD_REF = "v0.2.0" }
+env = { GOAD_REF = "v0.2.2" }
 ```
 
 ### Claude Desktop
@@ -151,7 +151,7 @@ app:
     "goad": {
       "command": "sh",
       "args": ["-c", "uv run --no-project https://raw.githubusercontent.com/raoulg/goad_toolkit/$GOAD_REF/goad_mcp.py"],
-      "env": { "GOAD_REF": "v0.2.0" }
+      "env": { "GOAD_REF": "v0.2.2" }
     }
   }
 }
@@ -187,7 +187,7 @@ add with the new tag:
 
 ```bash
 claude mcp remove goad -s user
-claude mcp add goad -s user -e GOAD_REF=v0.2.0 -- \
+claude mcp add goad -s user -e GOAD_REF=v0.2.2 -- \
   sh -c 'uv run --no-project https://raw.githubusercontent.com/raoulg/goad_toolkit/$GOAD_REF/goad_mcp.py'
 ```
 

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.4
+Metadata-Version: 2.5
 Name: goad-toolkit
-Version: 0.2.2
+Version: 0.2.3
 Summary: An extensible toolkit for Goal Oriented Analysis of Data
 Project-URL: Github, https://github.com/raoulg/goad_toolkit
 Author-email: raoul grouls <Raoul.Grouls@han.nl>
@@ -13,6 +13,7 @@ Requires-Dist: pydantic>=2.10.6
 Requires-Dist: requests>=2.32.3
 Requires-Dist: scipy>=1.15.2
 Requires-Dist: seaborn>=0.13.2
+Requires-Dist: statsmodels>=0.14.4
 Requires-Dist: tqdm>=4.67.1
 Provides-Extra: parquet
 Requires-Dist: pyarrow>=19.0.0; extra == 'parquet'

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/docs/02-pipelines.md

@@ -58,6 +58,7 @@ input frame is safe, and the steps stay cheap.
 | `SelectDataRange` | keep rows in a date range | `start_date`, `end_date` |
 | `RollingAvg` | rolling mean, drops the leading NaNs | `column`, `window`, `rename` |
 | `ZScaler` | standardise to mean 0, std 1 | `column`, `rename` |
+| `TimeFeatures` | derive calendar columns from a timestamp | `column`, `features` |
 
 `rename=True` writes to a new column (`deaths_shifted`, `deaths_zscore`, …) instead of
 overwriting. Prefer it. An overwritten column is a step you cannot debug, and the whole
@@ -75,20 +76,17 @@ Subclass `TransformBase` and implement `transform`. That is the entire contract.
 from goad_toolkit.datatransforms import TransformBase
 import pandas as pd
 
-class TimeFeatures(TransformBase):
-    """Derive calendar features from a timestamp column."""
+class IsWeekend(TransformBase):
+    """Flag Saturday/Sunday from a timestamp column."""
 
     def transform(self, data: pd.DataFrame, column: str) -> pd.DataFrame:
         ts = pd.to_datetime(data[column])
-        data["date"] = ts.dt.date
-        data["hour"] = ts.dt.hour
-        data["day_name"] = ts.dt.day_name()
-        data["isoweek"] = ts.dt.isocalendar().week
+        data["is_weekend"] = ts.dt.dayofweek >= 5
         return data
 ```
 
 ```python
-pipeline.add(TimeFeatures, column="timestamp")
+pipeline.add(IsWeekend, column="timestamp")
 ```
 
 What the base class does for you:

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/docs/03-plot-composition.md

@@ -151,6 +151,8 @@ step 3.
 | `ComparePlotDate` | `ComparePlot` + `VerticalDate` | |
 | `BarWithDates` | bars with a month locator on the x axis | |
 | `ResidualPlot` | `BarWithDates` + `VerticalDate` | the residual-over-time view |
+| `DecomposePlot` | `seasonal_decompose`, one panel each | observed/trend/seasonal/residual, overrides `plot` |
+| `ACFPlot` | `acf` as bars with a confidence band | see [Five families §4.2](04-five-families.md) |
 | `HistogramPlot` | `sns.histplot`, `stat="density"` | density so a pdf can be overlaid |
 | `DistPlot` | a scipy distribution's pdf or pmf | estimates its own x-range from `ppf` |
 | `PlotFits` | histogram + fitted pdf, one panel per fit | see [Distributions](05-distributions.md) |
@@ -216,9 +218,11 @@ lines of code.
   `self.ax.axvline(...)`, `self.fig.suptitle(...)`. Keeping to them is what makes
   `plot_on_axes` reliable.
 
-`PlotFits` overrides `plot` rather than `build`, because it needs to know how many panels to
-create before the figure exists. Its `build` is a no-op. It is the exception, not a pattern to
-copy.
+`PlotFits` and `DecomposePlot` override `plot` rather than `build`, because both need to know
+how many panels to create before the figure exists — variable for `PlotFits` (one per fit),
+fixed at four for `DecomposePlot`. Either way, `build` alone cannot decide the panel count
+before `create_figure` runs, so both leave it as a no-op. This is the exception, not a pattern
+to copy for a plot that only ever needs one axis.
 
 ---
 

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/docs/04-five-families.md

@@ -76,10 +76,12 @@ the period is long relative to your intuition.
   the same data support different stories. Choose the window from the mechanism you are
   studying, before you look.
 
-**In GOAD:** `ShiftValues`, `DiffValues`, `RollingAvg`, `SelectDataRange` are all pipeline
-steps, so the smoothing window is a named parameter you can change in one line and rerun.
-`ComparePlot` puts raw and smoothed on the same axes; `VerticalDate` marks the moment you
-claim something changed, with a label, on the plot.
+**In GOAD:** `ShiftValues`, `DiffValues`, `RollingAvg`, `SelectDataRange`, `TimeFeatures` are
+all pipeline steps, so the smoothing window is a named parameter you can change in one line
+and rerun. `ComparePlot` puts raw and smoothed on the same axes; `VerticalDate` marks the
+moment you claim something changed, with a label, on the plot. `DecomposePlot` wraps
+`seasonal_decompose` into the four-panel observed/trend/seasonal/residual view; `ACFPlot`
+wraps `acf` with its confidence band, for finding a period you did not already suspect.
 
 ---
 

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/docs/08-api-reference.md

@@ -83,10 +83,15 @@ class TransformBase(ABC):
 | `SelectDataRange` | `start_date: str, end_date: str` |
 | `RollingAvg` | `column: str, window: int, rename: bool = False` |
 | `ZScaler` | `column: str, rename: bool = False` |
+| `TimeFeatures` | `column: str, features: Optional[List[str]] = None` |
 
 `rename=True` writes to `{column}_shifted` / `_diff` / `_rolling_avg` / `_zscore` instead of
 overwriting.
 
+`TimeFeatures.AVAILABLE` is `("date", "hour", "day_name", "isoweek", "year_week")`;
+`TimeFeatures.DEFAULT` — used when `features` is omitted — is `("day_name", "isoweek",
+"year_week")`. A feature named the same as `column` overwrites it.
+
 ```python
 class Pipeline:
     def add(self, transform_class: Type[T], name: Optional[str] = None, **kwargs) -> "Pipeline"
@@ -267,12 +272,17 @@ class BasePlot(ABC):
 | `ResidualPlot` | `data, x, y, date, datelabel, interval: int = 1` |
 | `HistogramPlot` | `data: np.ndarray, bins=None, kde=False, color="skyblue", alpha=0.7, **kwargs` |
 | `DistPlot` | `distribution, x_range=None, samples=1000, color="crimson", linewidth=2, label=None, **kwargs` |
+| `ACFPlot` | `data, nlags=40, alpha=0.05, color="steelblue", band_color="gray", **kwargs` |
 
 ```python
 class PlotFits(BasePlot):
     def plot(self, data: np.ndarray,
              fit_results: List[Result],
              fitplotsettings: FitPlotSettings) -> Figure
+
+class DecomposePlot(BasePlot):
+    def plot(self, data: pd.DataFrame, column: str, period: int,
+             model: str = "additive", **kwargs) -> Figure
 ```
 
 Every `build` returns `(self.fig, self.ax)`, and every plot draws on `self.ax` / `self.fig`
@@ -309,12 +319,16 @@ of `likelihood`, `ks`, `combined`; `--method` is passed to `scipy.stats.fit`.
 
 ## 8.10 Rough edges worth knowing
 
-- `PlotFits` overrides `plot` rather than `build`; its `build` is a no-op. It is the one
-  exception to the `build` contract.
+- `PlotFits` and `DecomposePlot` override `plot` rather than `build`; their `build` is a
+  no-op. Both need the panel count decided before `create_figure` runs — from the fit results
+  for `PlotFits`, always four for `DecomposePlot` — which `build` alone cannot do.
 - Fits that fail come back as `FailedFit` values in the result list rather than raising, so
   a list of results can contain both kinds and needs an `isinstance` check.
 - `Pipeline.apply` copies the frame once and then mutates that copy in place, so transforms
   see each other's columns — the order you add steps in matters.
+- `ACFPlot` raises `ValueError` if the data contains NaNs, rather than passing them through.
+  `statsmodels.tsa.stattools.acf` does not raise on missing values — it silently returns an
+  all-NaN result — so a decomposition's residual needs `.dropna()` before it reaches `ACFPlot`.
 
 ---
 

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "goad-toolkit"
-version = "0.2.2"
+version = "0.2.3"
 description = "An extensible toolkit for Goal Oriented Analysis of Data"
 readme = "README.md"
 authors = [
@@ -16,6 +16,7 @@ dependencies = [
     "requests>=2.32.3",
     "scipy>=1.15.2",
     "seaborn>=0.13.2",
+    "statsmodels>=0.14.4",
     "tqdm>=4.67.1",
 ]
 urls = {Github = "https://github.com/raoulg/goad_toolkit"}

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/src/goad_toolkit/datatransforms.py

@@ -1,5 +1,5 @@
 from abc import ABC, abstractmethod
-from typing import Any, Dict, Optional, Type, TypeVar
+from typing import Any, Dict, List, Optional, Type, TypeVar
 
 import pandas as pd
 from tqdm import tqdm
@@ -122,6 +122,45 @@ class ZScaler(TransformBase):
         return data
 
 
+class TimeFeatures(TransformBase):
+    """Derive calendar features from a timestamp column.
+
+    `features` picks which columns to write, from `"date"`, `"hour"`,
+    `"day_name"`, `"isoweek"`, `"year_week"`. Defaults to `"day_name"`,
+    `"isoweek"`, `"year_week"` — the three lesson 1 already relies on.
+    A feature named the same as `column` overwrites it.
+    """
+
+    AVAILABLE = ("date", "hour", "day_name", "isoweek", "year_week")
+    DEFAULT = ("day_name", "isoweek", "year_week")
+
+    def transform(
+        self,
+        data: pd.DataFrame,
+        column: str,
+        features: Optional[List[str]] = None,
+    ) -> pd.DataFrame:
+        selected = list(features) if features is not None else list(self.DEFAULT)
+        unknown = set(selected) - set(self.AVAILABLE)
+        if unknown:
+            raise ValueError(
+                f"Unknown feature(s) {sorted(unknown)}; choose from {self.AVAILABLE}"
+            )
+
+        ts = pd.to_datetime(data[column])
+        if "date" in selected:
+            data["date"] = ts.dt.date
+        if "hour" in selected:
+            data["hour"] = ts.dt.hour
+        if "day_name" in selected:
+            data["day_name"] = ts.dt.day_name()
+        if "isoweek" in selected:
+            data["isoweek"] = ts.dt.isocalendar().week
+        if "year_week" in selected:
+            data["year_week"] = ts.dt.strftime("%Y-%W")
+        return data
+
+
 class Pipeline:
     """Pipeline for chaining data transformations."""
 

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/src/goad_toolkit/visualizer.py

@@ -11,6 +11,8 @@ import seaborn as sns
 from loguru import logger
 from matplotlib.axes import Axes
 from matplotlib.figure import Figure
+from statsmodels.tsa.seasonal import seasonal_decompose
+from statsmodels.tsa.stattools import acf
 
 from goad_toolkit.analytics import FitResult, Result
 
@@ -248,6 +250,118 @@ class ResidualPlot(BasePlot):
         return self.fig, self.ax
 
 
+class DecomposePlot(BasePlot):
+    """Decompose a series into observed, trend, seasonal and residual panels."""
+
+    def plot(
+        self,
+        data: pd.DataFrame,
+        column: str,
+        period: int,
+        model: str = "additive",
+        **kwargs,
+    ) -> Figure:
+        """
+        Run `statsmodels.tsa.seasonal.seasonal_decompose` and draw each
+        component on its own panel.
+
+        Parameters:
+        -----------
+        data : pd.DataFrame
+            Frame with a datetime index and the series to decompose.
+        column : str
+            Column to decompose.
+        period : int
+            Number of observations per cycle (e.g. 24 for hourly data with a
+            daily cycle, 7 for daily data with a weekly cycle).
+        model : str
+            `"additive"` or `"multiplicative"`, passed to `seasonal_decompose`.
+        **kwargs : Additional keyword arguments passed to `seasonal_decompose`.
+
+        Returns:
+        --------
+        fig : The created figure, with one panel per component.
+        """
+        result = seasonal_decompose(data[column], model=model, period=period, **kwargs)
+        components = [
+            ("Observed", result.observed),
+            ("Trend", result.trend),
+            ("Seasonal", result.seasonal),
+            ("Residual", result.resid),
+        ]
+
+        self.settings.subplot_titles = [name for name, _ in components]
+        self.fig, axes = self.create_figure(n_plots=len(components))
+
+        for ax, (_, values) in zip(axes, components):
+            comp_data = values.rename("value").reset_index()
+            index_col = comp_data.columns[0]
+            line = LinePlot(self.settings)
+            self.plot_on_axes(line, ax=ax, data=comp_data, x=index_col, y="value")
+
+        return self.fig
+
+    def build(self):
+        """No-op: `DecomposePlot` overrides `plot` because the panel count is fixed at four."""
+        pass
+
+
+class ACFPlot(BasePlot):
+    """Bar plot of the autocorrelation function with a Bartlett confidence band."""
+
+    def build(
+        self,
+        data: Any,
+        nlags: int = 40,
+        alpha: float = 0.05,
+        color: str = "steelblue",
+        band_color: str = "gray",
+        **kwargs,
+    ):
+        """
+        Plot the autocorrelation function for a series.
+
+        Parameters:
+        -----------
+        data : array-like
+            Series to compute the ACF for. Must not contain missing values —
+            drop NaNs first (a decomposition's residual has them at the edges).
+        nlags : int
+            Number of lags to compute and plot.
+        alpha : float
+            Significance level for the confidence band.
+        color : str
+            Bar color.
+        band_color : str
+            Confidence band color.
+        **kwargs : Additional keyword arguments passed to `ax.bar`.
+
+        Returns:
+        --------
+        fig, ax : The created figure and axes.
+        """
+        if self.ax is None:
+            raise ValueError("No axes available for plotting")
+
+        series = pd.Series(data)
+        if series.isna().any():
+            raise ValueError(
+                "ACFPlot got missing values; statsmodels.tsa.stattools.acf does not "
+                "raise on NaN, it silently returns an all-NaN result. Drop NaNs first "
+                "(a decomposition's residual has them at the edges)."
+            )
+
+        values, confint = acf(series, nlags=nlags, alpha=alpha, fft=True)  # type: ignore
+        lags = np.arange(len(values))
+        band = (confint[:, 1] - confint[:, 0]) / 2
+
+        self.ax.fill_between(lags, -band, band, color=band_color, alpha=0.2)
+        self.ax.axhline(0, color="black", linewidth=0.8)
+        self.ax.bar(lags, values, color=color, width=0.3, **kwargs)
+
+        return self.fig, self.ax
+
+
 class HistogramPlot(BasePlot):
     """Plot a histogram using seaborn."""
 

goad_toolkit-0.2.3/tests/test_datatransforms.py

@@ -0,0 +1,66 @@
+import pandas as pd
+import pytest
+
+from goad_toolkit.datatransforms import Pipeline, TimeFeatures
+
+
+@pytest.fixture
+def data() -> pd.DataFrame:
+    # 2024-01-01 is a Monday
+    timestamps = pd.date_range("2024-01-01 08:00", periods=10, freq="6h")
+    return pd.DataFrame({"timestamp": timestamps, "value": range(10)})
+
+
+def test_default_features_match_lesson_one(data):
+    result = TimeFeatures(column="timestamp")(data.copy())
+
+    assert "day_name" in result.columns
+    assert "isoweek" in result.columns
+    assert "year_week" in result.columns
+    assert "date" not in result.columns
+    assert "hour" not in result.columns
+
+
+def test_selected_features_only(data):
+    result = TimeFeatures(column="timestamp", features=["date", "hour"])(data.copy())
+
+    assert "date" in result.columns
+    assert "hour" in result.columns
+    assert "day_name" not in result.columns
+    assert result["hour"].tolist() == [8, 14, 20, 2, 8, 14, 20, 2, 8, 14]
+
+
+def test_all_features(data):
+    result = TimeFeatures(
+        column="timestamp",
+        features=list(TimeFeatures.AVAILABLE),
+    )(data.copy())
+
+    for feature in TimeFeatures.AVAILABLE:
+        assert feature in result.columns
+    assert result["day_name"].iloc[0] == "Monday"
+    assert result["isoweek"].iloc[0] == 1
+
+
+def test_unknown_feature_raises(data):
+    with pytest.raises(ValueError, match="Unknown feature"):
+        TimeFeatures(column="timestamp", features=["not_a_feature"])(data.copy())
+
+
+def test_feature_overwrites_same_named_source_column():
+    # mirrors lesson 1's own pipeline: source column is called "date"
+    df = pd.DataFrame({"date": pd.date_range("2024-01-01", periods=3, freq="D")})
+
+    result = TimeFeatures(column="date", features=["date"])(df)
+
+    assert result["date"].iloc[0] == pd.Timestamp("2024-01-01").date()
+
+
+def test_works_in_a_pipeline(data):
+    pipeline = Pipeline()
+    pipeline.add(TimeFeatures, column="timestamp", features=["day_name", "hour"])
+
+    result = pipeline.apply(data)
+
+    assert "day_name" in result.columns
+    assert "hour" in result.columns

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/tests/test_visualizer.py

@@ -7,9 +7,11 @@ import pandas as pd  # noqa: E402
 import pytest  # noqa: E402
 
 from goad_toolkit.visualizer import (  # noqa: E402
+    ACFPlot,
     BarWithDates,
     ComparePlot,
     ComparePlotDate,
+    DecomposePlot,
     LinePlot,
     PlotSettings,
     ResidualPlot,
@@ -111,3 +113,37 @@ def test_compare_plot_date_returns_fig_and_ax(data):
 
     assert fig is not None
     assert ax is not None
+
+
+@pytest.fixture
+def weekly_cycle() -> pd.DataFrame:
+    dates = pd.date_range("2021-01-01", periods=56, freq="D")
+    day_of_week = dates.dayofweek.to_numpy()
+    seasonal = [0, 1, 2, 3, 4, -8, -8][:7]  # weekday-shaped, weekend dip
+    values = [10 + i * 0.1 + seasonal[d] for i, d in enumerate(day_of_week)]
+    return pd.DataFrame({"value": values}, index=dates)
+
+
+def test_decompose_plot_returns_one_panel_per_component(weekly_cycle):
+    fig = DecomposePlot(PlotSettings()).plot(
+        data=weekly_cycle, column="value", period=7
+    )
+
+    visible_axes = [ax for ax in fig.axes if ax.get_visible()]
+    assert len(visible_axes) == 4
+    titles = [ax.get_title() for ax in visible_axes]
+    assert titles == ["Observed", "Trend", "Seasonal", "Residual"]
+
+
+def test_acf_plot_returns_fig_and_ax(weekly_cycle):
+    fig, ax = ACFPlot(PlotSettings()).plot(data=weekly_cycle["value"], nlags=14)
+
+    assert fig is not None
+    assert len(ax.patches) == 15  # lags 0..14 inclusive
+
+
+def test_acf_plot_rejects_missing_values():
+    series = pd.Series([1.0, 2.0, float("nan"), 4.0, 5.0])
+
+    with pytest.raises(ValueError, match="missing values"):
+        ACFPlot(PlotSettings()).plot(data=series, nlags=2)

{goad_toolkit-0.2.2 → goad_toolkit-0.2.3}/uv.lock

@@ -383,7 +383,7 @@ wheels = [
 
 [[package]]
 name = "goad-toolkit"
-version = "0.2.1"
+version = "0.2.2"
 source = { editable = "." }
 dependencies = [
     { name = "loguru" },
@@ -394,6 +394,7 @@ dependencies = [
     { name = "requests" },
     { name = "scipy" },
     { name = "seaborn" },
+    { name = "statsmodels" },
     { name = "tqdm" },
 ]
 
@@ -423,6 +424,7 @@ requires-dist = [
     { name = "requests", specifier = ">=2.32.3" },
     { name = "scipy", specifier = ">=1.15.2" },
     { name = "seaborn", specifier = ">=0.13.2" },
+    { name = "statsmodels", specifier = ">=0.14.4" },
     { name = "tqdm", specifier = ">=4.67.1" },
 ]
 provides-extras = ["parquet"]
@@ -1236,6 +1238,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/c6/ac/dac4a63f978e4dcb3c6d3a78c4d8e0192a113d288502a1216950c41b1027/parso-0.8.4-py2.py3-none-any.whl", hash = "sha256:a418670a20291dacd2dddc80c377c5c3791378ee1e8d12bffc35420643d43f18", size = 103650, upload-time = "2024-04-05T09:43:53.299Z" },
 ]
 
+[[package]]
+name = "patsy"
+version = "1.0.2"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/be/44/ed13eccdd0519eff265f44b670d46fbb0ec813e2274932dc1c0e48520f7d/patsy-1.0.2.tar.gz", hash = "sha256:cdc995455f6233e90e22de72c37fcadb344e7586fb83f06696f54d92f8ce74c0", size = 399942, upload-time = "2025-10-20T16:17:37.535Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/f1/70/ba4b949bdc0490ab78d545459acd7702b211dfccf7eb89bbc1060f52818d/patsy-1.0.2-py2.py3-none-any.whl", hash = "sha256:37bfddbc58fcf0362febb5f54f10743f8b21dd2aa73dec7e7ef59d1b02ae668a", size = 233301, upload-time = "2025-10-20T16:17:36.563Z" },
+]
+
 [[package]]
 name = "pexpect"
 version = "4.9.0"
@@ -1857,6 +1871,39 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/f1/7b/ce1eafaf1a76852e2ec9b22edecf1daa58175c090266e9f6c64afcd81d91/stack_data-0.6.3-py3-none-any.whl", hash = "sha256:d5558e0c25a4cb0853cddad3d77da9891a08cb85dd9f9f91b9f8cd66e511e695", size = 24521, upload-time = "2023-09-30T13:58:03.53Z" },
 ]
 
+[[package]]
+name = "statsmodels"
+version = "0.14.6"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "numpy" },
+    { name = "packaging" },
+    { name = "pandas" },
+    { name = "patsy" },
+    { name = "scipy" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/0d/81/e8d74b34f85285f7335d30c5e3c2d7c0346997af9f3debf9a0a9a63de184/statsmodels-0.14.6.tar.gz", hash = "sha256:4d17873d3e607d398b85126cd4ed7aad89e4e9d89fc744cdab1af3189a996c2a", size = 20689085, upload-time = "2025-12-05T23:08:39.522Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/25/ce/308e5e5da57515dd7cab3ec37ea2d5b8ff50bef1fcc8e6d31456f9fae08e/statsmodels-0.14.6-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:fe76140ae7adc5ff0e60a3f0d56f4fffef484efa803c3efebf2fcd734d72ecb5", size = 10091932, upload-time = "2025-12-05T19:28:55.446Z" },
+    { url = "https://files.pythonhosted.org/packages/05/30/affbabf3c27fb501ec7b5808230c619d4d1a4525c07301074eb4bda92fa9/statsmodels-0.14.6-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:26d4f0ed3b31f3c86f83a92f5c1f5cbe63fc992cd8915daf28ca49be14463a1c", size = 9997345, upload-time = "2025-12-05T19:29:10.278Z" },
+    { url = "https://files.pythonhosted.org/packages/48/f5/3a73b51e6450c31652c53a8e12e24eac64e3824be816c0c2316e7dbdcb7d/statsmodels-0.14.6-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:d8c00a42863e4f4733ac9d078bbfad816249c01451740e6f5053ecc7db6d6368", size = 10058649, upload-time = "2025-12-05T23:10:12.775Z" },
+    { url = "https://files.pythonhosted.org/packages/81/68/dddd76117df2ef14c943c6bbb6618be5c9401280046f4ddfc9fb4596a1b8/statsmodels-0.14.6-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:19b58cf7474aa9e7e3b0771a66537148b2df9b5884fbf156096c0e6c1ff0469d", size = 10339446, upload-time = "2025-12-05T23:10:28.503Z" },
+    { url = "https://files.pythonhosted.org/packages/56/4a/dce451c74c4050535fac1ec0c14b80706d8fc134c9da22db3c8a0ec62c33/statsmodels-0.14.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:81e7dcc5e9587f2567e52deaff5220b175bf2f648951549eae5fc9383b62bc37", size = 10368705, upload-time = "2025-12-05T23:10:44.339Z" },
+    { url = "https://files.pythonhosted.org/packages/60/15/3daba2df40be8b8a9a027d7f54c8dedf24f0d81b96e54b52293f5f7e3418/statsmodels-0.14.6-cp312-cp312-win_amd64.whl", hash = "sha256:b5eb07acd115aa6208b4058211138393a7e6c2cf12b6f213ede10f658f6a714f", size = 9543991, upload-time = "2025-12-05T23:10:58.536Z" },
+    { url = "https://files.pythonhosted.org/packages/81/59/a5aad5b0cc266f5be013db8cde563ac5d2a025e7efc0c328d83b50c72992/statsmodels-0.14.6-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:47ee7af083623d2091954fa71c7549b8443168f41b7c5dce66510274c50fd73e", size = 10072009, upload-time = "2025-12-05T23:11:14.021Z" },
+    { url = "https://files.pythonhosted.org/packages/53/dd/d8cfa7922fc6dc3c56fa6c59b348ea7de829a94cd73208c6f8202dd33f17/statsmodels-0.14.6-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:aa60d82e29fcd0a736e86feb63a11d2380322d77a9369a54be8b0965a3985f71", size = 9980018, upload-time = "2025-12-05T23:11:30.907Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/77/0ec96803eba444efd75dba32f2ef88765ae3e8f567d276805391ec2c98c6/statsmodels-0.14.6-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:89ee7d595f5939cc20bf946faedcb5137d975f03ae080f300ebb4398f16a5bd4", size = 10060269, upload-time = "2025-12-05T23:11:46.338Z" },
+    { url = "https://files.pythonhosted.org/packages/10/b9/fd41f1f6af13a1a1212a06bb377b17762feaa6d656947bf666f76300fc05/statsmodels-0.14.6-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:730f3297b26749b216a06e4327fe0be59b8d05f7d594fb6caff4287b69654589", size = 10324155, upload-time = "2025-12-05T23:12:01.805Z" },
+    { url = "https://files.pythonhosted.org/packages/ee/0f/a6900e220abd2c69cd0a07e3ad26c71984be6061415a60e0f17b152ecf08/statsmodels-0.14.6-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:f1c08befa85e93acc992b72a390ddb7bd876190f1360e61d10cf43833463bc9c", size = 10349765, upload-time = "2025-12-05T23:12:18.018Z" },
+    { url = "https://files.pythonhosted.org/packages/98/08/b79f0c614f38e566eebbdcff90c0bcacf3c6ba7a5bbb12183c09c29ca400/statsmodels-0.14.6-cp313-cp313-win_amd64.whl", hash = "sha256:8021271a79f35b842c02a1794465a651a9d06ec2080f76ebc3b7adce77d08233", size = 9540043, upload-time = "2025-12-05T23:12:33.887Z" },
+    { url = "https://files.pythonhosted.org/packages/71/de/09540e870318e0c7b58316561d417be45eff731263b4234fdd2eee3511a8/statsmodels-0.14.6-cp314-cp314-macosx_10_15_x86_64.whl", hash = "sha256:00781869991f8f02ad3610da6627fd26ebe262210287beb59761982a8fa88cae", size = 10069403, upload-time = "2025-12-05T23:12:48.424Z" },
+    { url = "https://files.pythonhosted.org/packages/ab/f0/63c1bfda75dc53cee858006e1f46bd6d6f883853bea1b97949d0087766ca/statsmodels-0.14.6-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:73f305fbf31607b35ce919fae636ab8b80d175328ed38fdc6f354e813b86ee37", size = 9989253, upload-time = "2025-12-05T23:13:05.274Z" },
+    { url = "https://files.pythonhosted.org/packages/c1/98/b0dfb4f542b2033a3341aa5f1bdd97024230a4ad3670c5b0839d54e3dcab/statsmodels-0.14.6-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:e443e7077a6e2d3faeea72f5a92c9f12c63722686eb80bb40a0f04e4a7e267ad", size = 10090802, upload-time = "2025-12-05T23:13:20.653Z" },
+    { url = "https://files.pythonhosted.org/packages/34/0e/2408735aca9e764643196212f9069912100151414dd617d39ffc72d77eee/statsmodels-0.14.6-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:3414e40c073d725007a6603a18247ab7af3467e1af4a5e5a24e4c27bc26673b4", size = 10337587, upload-time = "2025-12-05T23:13:37.597Z" },
+    { url = "https://files.pythonhosted.org/packages/0f/36/4d44f7035ab3c0b2b6a4c4ebb98dedf36246ccbc1b3e2f51ebcd7ac83abb/statsmodels-0.14.6-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:a518d3f9889ef920116f9fa56d0338069e110f823926356946dae83bc9e33e19", size = 10363350, upload-time = "2025-12-05T23:13:53.08Z" },
+    { url = "https://files.pythonhosted.org/packages/26/33/f1652d0c59fa51de18492ee2345b65372550501ad061daa38f950be390b6/statsmodels-0.14.6-cp314-cp314-win_amd64.whl", hash = "sha256:151b73e29f01fe619dbce7f66d61a356e9d1fe5e906529b78807df9189c37721", size = 9588010, upload-time = "2025-12-05T23:14:07.28Z" },
+]
+
 [[package]]
 name = "terminado"
 version = "0.18.1"