bella-companion 0.0.4__py3-none-any.whl → 0.0.6__py3-none-any.whl

bella_companion/simulations/figures/utils.py

@@ -1,250 +0,0 @@
-import os
-from itertools import product
-from typing import Any
-
-import matplotlib.pyplot as plt
-import numpy as np
-import polars as pl
-import seaborn as sns
-from joblib import Parallel, delayed
-from lumiere.backend import (
-    ActivationFunction,
-    get_partial_dependence_values,
-    get_shap_features_importance,
-    sigmoid,
-)
-from lumiere.backend.typings import Weights
-from tqdm import tqdm
-
-from src.simulations.features import Feature
-
-
-def _set_xticks(n: int, reverse: bool = False):
-    xticks_labels = range(n)
-    if reverse:
-        xticks_labels = reversed(xticks_labels)
-    plt.xticks(ticks=range(n), labels=list(map(str, xticks_labels)))
-
-
-def step(
-    x: list[float],
-    reverse_xticks: bool = False,
-    **kwargs: dict[str, Any],
-):
-    data = x.copy()
-    data.insert(0, data[0])
-    plt.step(list(range(len(data))), data, **kwargs)
-    _set_xticks(len(data), reverse_xticks)
-    plt.xlabel("Time bin")
-
-
-def _count_time_bins(true_values: dict[str, list[float]]) -> int:
-    assert (
-        len({len(true_value) for true_value in true_values.values()}) == 1
-    ), "All targets must have the same number of change times."
-    return len(next(iter((true_values.values()))))
-
-
-def plot_maes_per_time_bin(
-    logs_summaries: dict[str, pl.DataFrame],
-    true_values: dict[str, list[float]],
-    output_filepath: str,
-    reverse_xticks: bool = False,
-):
-    def _mae(target: str, i: int) -> pl.Expr:
-        return (pl.col(f"{target}i{i}_median") - true_values[target][i]).abs()
-
-    n_time_bins = _count_time_bins(true_values)
-    df = pl.concat(
-        logs_summaries[model]
-        .select(
-            pl.mean_horizontal([_mae(target, i) for target in true_values]).alias("MAE")
-        )
-        .with_columns(pl.lit(i).alias("Time bin"), pl.lit(model).alias("Model"))
-        for i in range(n_time_bins)
-        for model in logs_summaries
-    )
-    sns.violinplot(
-        x="Time bin",
-        y="MAE",
-        hue="Model",
-        data=df,
-        inner=None,
-        cut=0,
-        density_norm="width",
-        legend=False,
-    )
-    _set_xticks(n_time_bins, reverse_xticks)
-    plt.savefig(output_filepath)
-    plt.close()
-
-
-def plot_coverage_per_time_bin(
-    logs_summaries: dict[str, pl.DataFrame],
-    true_values: dict[str, list[float]],
-    output_filepath: str,
-    reverse_xticks: bool = False,
-):
-    def _coverage(model: str, target: str, i: int) -> float:
-        lower_bound = logs_summaries[model][f"{target}i{i}_lower"]
-        upper_bound = logs_summaries[model][f"{target}i{i}_upper"]
-        true_value = true_values[target][i]
-        N = len(logs_summaries[model])
-        return ((lower_bound <= true_value) & (true_value <= upper_bound)).sum() / N
-
-    n_time_bins = _count_time_bins(true_values)
-    for model in logs_summaries:
-        avg_coverage_by_time_bin = [
-            np.mean([_coverage(model, target, i) for target in true_values])
-            for i in range(_count_time_bins(true_values))
-        ]
-        plt.plot(avg_coverage_by_time_bin, marker="o")
-
-    _set_xticks(n_time_bins, reverse_xticks)
-    plt.xlabel("Time bin")
-    plt.ylabel("Coverage")
-    plt.ylim((0, 1.05))
-    plt.savefig(output_filepath)
-    plt.close()
-
-
-def plot_partial_dependencies(
-    weights: list[list[Weights]],  # shape: (n_mcmcs, n_weights_samples, ...)
-    features: dict[str, Feature],
-    output_dir: str,
-    hidden_activation: ActivationFunction = sigmoid,
-    output_activation: ActivationFunction = sigmoid,
-):
-    os.makedirs(output_dir, exist_ok=True)
-    features_grid = [feature.grid for feature in features.values()]
-
-    def _get_median_partial_dependence_values(
-        weights: list[Weights],
-    ) -> list[list[float]]:
-        pdvalues_distribution = [
-            get_partial_dependence_values(
-                weights=w,
-                features_grid=features_grid,
-                hidden_activation=hidden_activation,
-                output_activation=output_activation,
-            )
-            for w in weights
-        ]
-        return [
-            np.median(
-                [pdvalues[feature_idx] for pdvalues in pdvalues_distribution], axis=0
-            ).tolist()
-            for feature_idx in range(len(features))
-        ]
-
-    jobs = Parallel(n_jobs=-1)(
-        delayed(_get_median_partial_dependence_values)(w) for w in weights
-    )
-    pdvalues = [
-        job for job in tqdm(jobs, total=len(weights), desc="Evaluating PDPs")
-    ]  # shape: (n_mcmcs, n_features, n_grid_points)
-    pdvalues = [
-        np.array(mcmc_pds).T for mcmc_pds in zip(*pdvalues)
-    ]  # shape: (n_features, n_grid_points, n_mcmcs)
-
-    for feature_idx, (feature_name, feature) in enumerate(features.items()):
-        color = "red" if feature.is_relevant else "gray"
-        feature_pdvalues = pdvalues[feature_idx]  # shape: (n_grid_points, n_mcmcs)
-        if not feature.is_categorical:
-            median = np.median(feature_pdvalues, axis=1)
-            lower = np.percentile(feature_pdvalues, 2.5, axis=1)
-            high = np.percentile(feature_pdvalues, 100 - 2.5, axis=1)
-            plt.fill_between(feature.grid, lower, high, alpha=0.25, color=color)
-            for mcmc_pds in feature_pdvalues.T:
-                plt.plot(
-                    feature.grid,
-                    mcmc_pds,
-                    color=color,
-                    alpha=0.2,
-                    linewidth=1,
-                )
-            plt.plot(feature.grid, median, color=color, label=feature_name)
-    plt.xlabel("Feature value")
-    plt.ylabel(f"MLP Output")
-    plt.legend()
-    plt.savefig(os.path.join(output_dir, "PDPs-continuous.svg"))
-    plt.close()
-
-    plot_data = []
-    grid_labels = []
-    list_labels = []
-    for feature_idx, (feature_name, feature) in enumerate(features.items()):
-        feature_pdvalues = pdvalues[feature_idx]  # shape: (n_grid_points, n_mcmcs)
-        if feature.is_categorical:
-            for i, grid_point in enumerate(feature.grid):
-                plot_data.extend(feature_pdvalues[i])
-                grid_labels.extend([grid_point] * len(feature_pdvalues[i]))
-                list_labels.extend([feature_name] * len(feature_pdvalues[i]))
-    if not (any(feature.is_categorical for feature in features.values())):
-        return
-    sns.violinplot(
-        x=grid_labels,
-        y=plot_data,
-        hue=list_labels,
-        split=False,
-        cut=0,
-        palette={
-            feature_name: "red" if feature.is_relevant else "gray"
-            for feature_name, feature in features.items()
-            if feature.is_categorical
-        },
-    )
-    plt.xlabel("Feature value")
-    plt.ylabel(f"MLP Output")
-    plt.legend()
-    plt.savefig(os.path.join(output_dir, "PDPs-categorical.svg"))
-    plt.close()
-
-
-def plot_shap_features_importance(
-    weights: list[list[Weights]],  # shape: (n_mcmcs, n_weights_samples, ...)
-    features: dict[str, Feature],
-    output_file: str,
-    hidden_activation: ActivationFunction = sigmoid,
-    output_activation: ActivationFunction = sigmoid,
-):
-    features_grid = [feature.grid for feature in features.values()]
-    inputs = list(product(*features_grid))
-
-    def _get_median_shap_features_importance(
-        weights: list[Weights],
-    ) -> list[list[float]]:
-        features_importance = np.array(
-            [
-                get_shap_features_importance(
-                    weights=w,
-                    inputs=inputs,
-                    hidden_activation=hidden_activation,
-                    output_activation=output_activation,
-                )
-                for w in weights
-            ]
-        )  # shape: (n_weights_samples, n_features)
-        return np.median(features_importance, axis=0).tolist()  # shape: (n_features,)
-
-    jobs = Parallel(n_jobs=-1, return_as="generator_unordered")(
-        delayed(_get_median_shap_features_importance)(w) for w in weights
-    )
-    features_importance_distribution = np.array(
-        [job for job in tqdm(jobs, total=len(weights), desc="Evaluating SHAPs")]
-    )  # shape: (n_mcmcs, n_features)
-    features_importance_distribution /= features_importance_distribution.sum(
-        axis=1, keepdims=True
-    )
-
-    for i, (feature_name, feature) in enumerate(features.items()):
-        sns.violinplot(
-            y=features_importance_distribution[:, i],
-            x=[feature_name] * features_importance_distribution.shape[0],
-            cut=0,
-            color="red" if feature.is_relevant else "gray",
-        )
-    plt.xlabel("Feature")
-    plt.ylabel("Importance")
-    plt.savefig(output_file)
-    plt.close()

bella_companion-0.0.4.dist-info/RECORD

@@ -1,37 +0,0 @@
-bella_companion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bella_companion/cli.py,sha256=0sPnzGyUGo2OBZ0rj17ZGzMdwNH0o-BXKsYtCJjzGvQ,968
-bella_companion/fbd_empirical/data/body_mass.csv,sha256=-UkKNtm9m3g4PjY3BcfdP6z5nL_I6p9cq6cgZ-bWKI8,30360
-bella_companion/fbd_empirical/data/change_times.csv,sha256=zmc9_z91-XMwKyIoP9v9dVlLcf4MeIHkQiHLjoMriOo,120
-bella_companion/fbd_empirical/data/sampling_change_times.csv,sha256=Gwi9RcMFy89RyvfxKVZ_MoKVRHOZLuwB_3LEaq8asMQ,32
-bella_companion/fbd_empirical/data/trees.nwk,sha256=zhvLvPLZelhMThVmvOENkmi3p2aPAARb8KMdHTm6mss,4645318
-bella_companion/fbd_empirical/figure.py,sha256=4paOXCB1EcxuHzLPxDSleQU2AQ_ndTedtzS1ugiKICs,1018
-bella_companion/fbd_empirical/notbooks.ipynb,sha256=O45kmz0lZENRDFbKXEWPsIKATfF5GVeS5tCYmrGLnqk,83326
-bella_companion/fbd_empirical/params.json,sha256=hU23LniClZL_GSBAxIEJUJgMa93AM8zdtFOq6mt3vkI,311
-bella_companion/fbd_empirical/run_beast.py,sha256=2sV2UmxOfWmbueiU6D0p3lueMYiZyIkSKYoblTMrYuA,1935
-bella_companion/fbd_empirical/summarize_logs.py,sha256=O6rhE606Wa98a8b1KKlLPjUOro1pfyqVTLdQksQMG0g,1439
-bella_companion/simulations/__init__.py,sha256=i6Fe7l5sUJY9hPxdg6L_FVhwbSPhNxQNMb-m33JlfxI,258
-bella_companion/simulations/features.py,sha256=DZOBpJGlQ0UinqUZYbEtoemZ2eQGVLV_i-DfpW31qJI,104
-bella_companion/simulations/figures/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bella_companion/simulations/figures/epi_explainations.py,sha256=omiJgyIY-I6zcJAcyOF7GJ2pba6pMZySLkWy7OFrjFY,3093
-bella_companion/simulations/figures/epi_predictions.py,sha256=4yXwOBKxUv4kgZdI9zAMEhZ0QCNKZdkAafRQ1RTeaWg,1835
-bella_companion/simulations/figures/fbd_explainations.py,sha256=9Uj7yttpn_TH5HqycW8R-Nlky9A9aFXDXRpXQuT1L4s,3037
-bella_companion/simulations/figures/fbd_predictions.py,sha256=jdXYCLledZEWoPCIuTLhHEPMdeG6YXvf5xZnEOslv-U,2119
-bella_companion/simulations/figures/scenarios.py,sha256=vyybn3Qhfq96N8tvW0wSzpFoHHP8EIc8dkOz63o_Atw,2492
-bella_companion/simulations/figures/utils.py,sha256=sY8wFBg02fv5ugpJ80EqQishD_HEdLwhqsw2LfM7wEo,8539
-bella_companion/simulations/generate_data.py,sha256=H8OV4ZlTGZB-jXaROTPmOsK3UxRiU-GrX40l-shliw8,728
-bella_companion/simulations/run_beast.py,sha256=xOuwE0w4IbOqqCSym6kHsAEhfGT2mWdA-jmUZuviMbc,3121
-bella_companion/simulations/scenarios/__init__.py,sha256=3Kl1lKcFpfb3vLX64DmSW4XCF5kXU1ZoHtstFH-ZIzU,876
-bella_companion/simulations/scenarios/common.py,sha256=_ddaSuTvEVdttGkXB4HPc2B7IB1F_GBOCW3cVOPZ-ZM,807
-bella_companion/simulations/scenarios/epi_multitype.py,sha256=GWGIiqvYwX_FrT_3RXkZKYGDht9nZ7ceHRBKUvXDPnA,2432
-bella_companion/simulations/scenarios/epi_skyline.py,sha256=JqnOVATECxBUqEbkR5lBlMI2O8k4hO6ipR8k9cHUsm0,2365
-bella_companion/simulations/scenarios/fbd_2traits.py,sha256=sCtdWyV6GQQOIhnL9Dd8NIbAR-StTwUTD9-b_BalmFQ,3552
-bella_companion/simulations/scenarios/fbd_no_traits.py,sha256=R6CH0fVeQg-Iesl39pq2uY8ICVEO4VZbvUVUCGwauJU,2520
-bella_companion/simulations/scenarios/scenario.py,sha256=_FRWAyOFbw94lAzd3zCD-1ek4TrssoiXfXRQPShLiIA,620
-bella_companion/simulations/summarize_logs.py,sha256=5IdzR9IwjeF2LgZmzpuK0rPfYMct2OUgEp0QyUbUS7g,1263
-bella_companion/utils/__init__.py,sha256=_5tLPH_3GHtimNcH0Yd9Z6yIM3WkWkNApNGLzFnF6nY,222
-bella_companion/utils/beast.py,sha256=RG-iSEFuL92K6yxUV2nxdmcVqfrEiPhaYTmReW4ZoWk,2189
-bella_companion/utils/slurm.py,sha256=v5DaG7YHVyK8KRFptgGDC6I8jxEhyJuMVK9N08pZSAI,1812
-bella_companion-0.0.4.dist-info/METADATA,sha256=UKU-LZpRje6oxM1GDM6Qxa82sb8eyFKjOEfHu8Xb0fw,534
-bella_companion-0.0.4.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
-bella_companion-0.0.4.dist-info/entry_points.txt,sha256=rSeKoAhmjnQqAYFcXBv0gAM2ViJfJe0D8_dD-fWrXeg,50
-bella_companion-0.0.4.dist-info/RECORD,,