bella-companion 0.0.43__py3-none-any.whl → 0.0.45__py3-none-any.whl

bella_companion/cli.py

@@ -7,14 +7,26 @@ from dotenv import load_dotenv
 from bella_companion.eucovid import run_beast as run_eucovid_beast
 from bella_companion.platyrrhine import plot_platyrrhine_results
 from bella_companion.platyrrhine import run_beast as run_platyrrhine
-from bella_companion.platyrrhine import summarize_logs as summarize_platyrrhine
+from bella_companion.platyrrhine import summarize as summarize_platyrrhine
 from bella_companion.simulations import generate_data, generate_figures, print_metrics
 from bella_companion.simulations import run_beast as run_simulations
-from bella_companion.simulations import summarize_logs as summarize_simulations
+from bella_companion.simulations import summarize as summarize_simulations
 
 
 def main():
     load_dotenv(Path(os.getcwd()) / ".env")
+    os.environ["BELLA_RUN_BEAST_CMD"] = " ".join(
+        [
+            "java",
+            os.getenv("JAVA_OPTIONS", ""),
+            f"-jar {Path(__file__).parent / 'BELLA.jar'}",
+            f"-version_file {Path(__file__).parent / 'version.xml'}",
+            "-seed 42",
+            "-overwrite",
+            "-statefile /tmp/state",
+            "-DFout /dev/null",
+        ]
+    )
 
     parser = argparse.ArgumentParser(
         prog="bella",

bella_companion/platyrrhine/__init__.py

@@ -1,5 +1,5 @@
 from bella_companion.platyrrhine.results import plot_platyrrhine_results
 from bella_companion.platyrrhine.run_beast import run_beast
-from bella_companion.platyrrhine.summarize_logs import summarize_logs
+from bella_companion.platyrrhine.summarize import summarize
 
-__all__ = ["plot_platyrrhine_results", "run_beast", "summarize_logs"]
+__all__ = ["plot_platyrrhine_results", "run_beast", "summarize"]

bella_companion/platyrrhine/results.py

@@ -5,12 +5,48 @@ import matplotlib.pyplot as plt
 import numpy as np
 import polars as pl
 from numpy.typing import NDArray
-from phylogenie import get_node_depths, load_newick
+from phylogenie import draw_tree, get_node_depths, load_newick, load_nexus
 
 
-def _plot_predictions(output_dir: Path):
-    log_summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"])
-    log_summary = pl.read_csv(log_summaries_dir / "platyrrhine" / "MLP.csv")
+def _plot_tree(output_dir: Path, tree_file: str | Path):
+    sample_trees = load_nexus(tree_file)
+    trees = [sample_trees[f"STATE_{i*100_000}"] for i in range(11, 101)]
+
+    for tree in trees:
+        for node in tree:
+            if node.parent is not None and not node.branch_length:
+                node.parent.remove_child(node)
+
+    avg_tree = trees[0].copy()
+    for node in avg_tree:
+        node.clear()
+    for avg_node, nodes in zip(avg_tree, zip(*trees)):
+        avg_node.set("birthRateSP", np.mean([n["birthRateSP"] for n in nodes]))
+        avg_node.set("deathRateSP", np.mean([n["deathRateSP"] for n in nodes]))
+
+    avg_tree.ladderize()
+    for rate in ["birthRateSP", "deathRateSP"]:
+        ax = plt.gca()
+        draw_tree(
+            avg_tree,
+            ax,
+            color_by=rate,
+            hist_axes_kwargs={
+                "loc": "upper left",
+                "bbox_to_anchor": (0.06, 0, 1, 1),
+                "bbox_transform": ax.transAxes,
+            },
+        )
+        height = avg_tree.height
+        ticks = np.arange(height, 0, -10)
+        ax.set_xticks(ticks, [str(round(height - t)) for t in ticks])  # pyright: ignore
+        plt.xlabel("Time (mya)")  # pyright: ignore
+        plt.savefig(output_dir / f"{rate}-tree.svg")  # pyright: ignore
+        plt.close()
+
+
+def _plot_predictions(output_dir: Path, log_summary_file: str | Path):
+    log_summary = pl.read_csv(log_summary_file)
 
     data_dir = Path(__file__).parent / "data"
     change_times = (
@@ -24,14 +60,15 @@ def _plot_predictions(output_dir: Path):
     )
     time_bins = list(reversed([0.0, *change_times, max_time]))
 
+    gradient = np.linspace(0.4, 0.9, 4)
     colors: dict[str, NDArray[np.floating]] = {
-        "birth": plt.cm.Blues(np.linspace(0.4, 0.9, 4)),  # pyright: ignore
-        "death": plt.cm.Oranges(np.linspace(0.4, 0.9, 4)),  # pyright: ignore
-        "diversification": plt.cm.Greens(np.linspace(0.4, 0.9, 4)),  # pyright: ignore
+        "birthRateSP": plt.cm.Blues(gradient),  # pyright: ignore
+        "deathRateSP": plt.cm.Oranges(gradient),  # pyright: ignore
+        "diversificationRateSP": plt.cm.Greens(gradient),  # pyright: ignore
     }
-    for rate in ["birth", "death", "diversification"]:
+    for rate in colors:
         for type in [0, 1, 2, 3]:
-            if rate == "diversification":
+            if rate == "diversificationRateSP":
                 estimates = log_summary.select(
                     [
                         pl.col(f"birthRateSPi{i}_{type}_median")
@@ -42,7 +79,7 @@ def _plot_predictions(output_dir: Path):
             else:
                 estimates = log_summary.select(
                     [
-                        pl.col(f"{rate}RateSPi{i}_{type}_median")
+                        pl.col(f"{rate}i{i}_{type}_median")
                         for i in range(len(change_times) + 1)
                     ]
                 ).to_numpy()
@@ -52,18 +89,21 @@ def _plot_predictions(output_dir: Path):
                 time_bins, [median[0], *median], color=color, label=type
             )
 
-        ax = plt.gca()
-        ax.invert_xaxis()
+        plt.gca().invert_xaxis()
         plt.legend(title="Body mass")  # pyright: ignore
         plt.xlabel("Time (mya)")  # pyright: ignore
         plt.ylabel(  # pyright: ignore
-            r"$\lambda$" if rate == "birth" else r"$\mu$" if rate == "death" else r"$d$"
+            r"$\lambda$"
+            if rate == "birthRateSP"
+            else r"$\mu$" if rate == "deathRateSP" else r"$d$"
         )
         plt.savefig(output_dir / f"{rate}-predictions.svg")  # pyright: ignore
         plt.close()
 
 
 def plot_platyrrhine_results():
+    summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"]) / "platyrrhine"
     output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "platyrrhine"
     os.makedirs(output_dir, exist_ok=True)
-    _plot_predictions(output_dir)
+    _plot_predictions(output_dir, summaries_dir / "MLP.csv")
+    _plot_tree(output_dir, summaries_dir / "sample-trees.nexus")

bella_companion/platyrrhine/{summarize_logs.py → summarize.py}

@@ -5,13 +5,13 @@ from pathlib import Path
 
 import joblib
 import polars as pl
-from phylogenie import Tree, load_nexus
+from phylogenie import Tree, dump_newick, load_nexus
 from tqdm import tqdm
 
 from bella_companion.utils import read_weights_dir, summarize_logs_dir
 
 
-def summarize_logs():
+def summarize():
     data_dir = Path(__file__).parent / "data"
     change_times = pl.read_csv(data_dir / "change_times.csv", has_header=False)
     n_time_bins = len(change_times) + 1
@@ -28,14 +28,14 @@ def summarize_logs():
     )
     weights = read_weights_dir(logs_dir)
 
-    summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"], "platyrrhine")
+    summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"], "platyrrhine")
     os.makedirs(summaries_dir, exist_ok=True)
     summaries.write_csv(summaries_dir / "MLP.csv")
     joblib.dump(weights, summaries_dir / "MLP.weights.pkl")
 
     trees: list[Tree] = []
     for tree_file in tqdm(glob(str(logs_dir / "*.trees")), "Summarizing trees"):
-        trees.extend(list(load_nexus(tree_file).values())[:-10])
-    joblib.dump(trees, summaries_dir / "trees.pkl")
+        trees.extend(list(load_nexus(tree_file).values())[-10:])
+    dump_newick(trees, summaries_dir / "trees.nwk")
 
-    shutil.copy(logs_dir / "0.trees", summaries_dir / "sample-tree.nexus")
+    shutil.copy(logs_dir / "0.trees", summaries_dir / "sample-trees.nexus")

bella_companion/simulations/__init__.py

@@ -2,12 +2,12 @@ from bella_companion.simulations.generate_data import generate_data
 from bella_companion.simulations.generate_figures import generate_figures
 from bella_companion.simulations.metrics import print_metrics
 from bella_companion.simulations.run_beast import run_beast
-from bella_companion.simulations.summarize_logs import summarize_logs
+from bella_companion.simulations.summarize import summarize
 
 __all__ = [
     "generate_data",
     "generate_figures",
     "print_metrics",
     "run_beast",
-    "summarize_logs",
+    "summarize",
 ]

bella_companion/simulations/figures/__init__.py

@@ -1,15 +1,7 @@
-from bella_companion.simulations.figures.epi_multitype_results import (
-    plot_epi_multitype_results,
-)
-from bella_companion.simulations.figures.epi_skyline_results import (
-    plot_epi_skyline_results,
-)
-from bella_companion.simulations.figures.fbd_2traits_results import (
-    plot_fbd_2traits_results,
-)
-from bella_companion.simulations.figures.fbd_no_traits_results import (
-    plot_fbd_no_traits_results,
-)
+from bella_companion.simulations.figures.epi_multitype import plot_epi_multitype_results
+from bella_companion.simulations.figures.epi_skyline import plot_epi_skyline_results
+from bella_companion.simulations.figures.fbd_2traits import plot_fbd_2traits_results
+from bella_companion.simulations.figures.fbd_no_traits import plot_fbd_no_traits_results
 from bella_companion.simulations.figures.scenarios import plot_scenarios
 
 __all__ = [

bella_companion/simulations/figures/{epi_multitype_results.py → epi_multitype.py}

@@ -58,10 +58,10 @@ def plot_epi_multitype_results():
     output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "epi-multitype"
     os.makedirs(output_dir, exist_ok=True)
 
-    log_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / "epi-multitype"
+    summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"]) / "epi-multitype"
     model = "MLP-32_16"
-    log_summary = pl.read_csv(log_dir / f"{model}.csv")
-    weights = joblib.load(log_dir / f"{model}.weights.pkl")
+    log_summary = pl.read_csv(summaries_dir / f"{model}.csv")
+    weights = joblib.load(summaries_dir / f"{model}.weights.pkl")
     weights = [w["migrationRate"] for w in weights]
 
     _plot_predictions(log_summary, output_dir)

bella_companion/simulations/figures/{epi_skyline_results.py → epi_skyline.py}

@@ -14,11 +14,10 @@ from bella_companion.simulations.scenarios.epi_skyline import REPRODUCTION_NUMBE
 
 
 def plot_epi_skyline_results():
-    output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "epi-skyline"
-    os.makedirs(output_dir, exist_ok=True)
+    base_output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "epi-skyline"
 
     for i, reproduction_number in enumerate(REPRODUCTION_NUMBERS, start=1):
-        summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / f"epi-skyline_{i}"
+        summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"]) / f"epi-skyline_{i}"
         logs_summaries = {
             "Nonparametric": pl.read_csv(summaries_dir / "Nonparametric.csv"),
             "GLM": pl.read_csv(summaries_dir / "GLM.csv"),
@@ -26,6 +25,8 @@ def plot_epi_skyline_results():
         }
         true_values = {"reproductionNumberSP": reproduction_number}
 
+        output_dir = base_output_dir / str(i)
+        os.makedirs(output_dir, exist_ok=True)
         for log_summary in logs_summaries.values():
             step(
                 [
@@ -35,12 +36,10 @@ def plot_epi_skyline_results():
             )
         step(reproduction_number, color="k", linestyle="--")
         plt.ylabel("Reproduction number")  # pyright: ignore
-        plt.savefig(output_dir / f"predictions-{i}.svg")  # pyright: ignore
+        plt.savefig(output_dir / "predictions.svg")  # pyright: ignore
         plt.close()
 
         plot_coverage_per_time_bin(
-            logs_summaries, true_values, output_dir / f"coverage-{i}.svg"
-        )
-        plot_maes_per_time_bin(
-            logs_summaries, true_values, output_dir / f"maes-{i}.svg"
+            logs_summaries, true_values, output_dir / "coverage.svg"
         )
+        plot_maes_per_time_bin(logs_summaries, true_values, output_dir / "maes.svg")

bella_companion/simulations/figures/{fbd_2traits_results.py → fbd_2traits.py}

@@ -58,10 +58,10 @@ def _plot_predictions(log_summary: pl.DataFrame, output_dir: Path):
 def plot_fbd_2traits_results():
     output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "fbd-2traits"
 
-    log_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / "fbd-2traits"
+    summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"]) / "fbd-2traits"
     model = "MLP-32_16"
-    log_summary = pl.read_csv(log_dir / f"{model}.csv")
-    weights = joblib.load(log_dir / f"{model}.weights.pkl")
+    log_summary = pl.read_csv(summaries_dir / f"{model}.csv")
+    weights = joblib.load(summaries_dir / f"{model}.weights.pkl")
 
     for rate in RATES:
         os.makedirs(output_dir / rate, exist_ok=True)

bella_companion/simulations/figures/{fbd_no_traits_results.py → fbd_no_traits.py}

@@ -14,13 +14,10 @@ from bella_companion.simulations.scenarios.fbd_no_traits import RATES
 
 
 def plot_fbd_no_traits_results():
-    output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "fbd-no-traits"
-    os.makedirs(output_dir, exist_ok=True)
+    base_output = Path(os.environ["BELLA_FIGURES_DIR"]) / "fbd-no-traits"
 
     for i, rates in enumerate(RATES, start=1):
-        summaries_dir = (
-            Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / f"fbd-no-traits_{i}"
-        )
+        summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"]) / f"fbd-no-traits_{i}"
         logs_summaries = {
             "Nonparametric": pl.read_csv(summaries_dir / "Nonparametric.csv"),
             "GLM": pl.read_csv(summaries_dir / "GLM.csv"),
@@ -28,6 +25,7 @@ def plot_fbd_no_traits_results():
         }
         true_values = {"birthRateSP": rates["birth"], "deathRateSP": rates["death"]}
 
+        output_dir = base_output / str(i)
         for id, rate in true_values.items():
             for log_summary in logs_summaries.values():
                 step(
@@ -41,18 +39,18 @@ def plot_fbd_no_traits_results():
             plt.ylabel(  # pyright: ignore
                 r"$\lambda$" if id == "birthRateSP" else r"$\mu$"
             )
-            plt.savefig(output_dir / f"{id}-predictions-{i}-.svg")  # pyright: ignore
+            plt.savefig(output_dir / f"{id}-predictions.svg")  # pyright: ignore
             plt.close()
 
         plot_coverage_per_time_bin(
             logs_summaries,
             true_values,
-            output_dir / f"coverage-{i}.svg",
+            output_dir / "coverage.svg",
             reverse_xticks=True,
         )
         plot_maes_per_time_bin(
             logs_summaries,
             true_values,
-            output_dir / f"maes-{i}.svg",
+            output_dir / "maes.svg",
             reverse_xticks=True,
         )

bella_companion/simulations/metrics.py

@@ -36,9 +36,10 @@ def _avg_ci_width(summary: pl.DataFrame, true_values: dict[str, float]) -> float
 
 
 def print_metrics():
+    base_summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"])
     metrics = {}
     for name, scenario in SCENARIOS.items():
-        summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / name
+        summaries_dir = base_summaries_dir / name
         summaries = {
             Path(log_summary).stem: pl.read_csv(log_summary)
             for log_summary in glob(str(summaries_dir / "*.csv"))
@@ -54,5 +55,5 @@ def print_metrics():
             }
             for target, true_values in scenario.targets.items()
         }
-    with open("simulation-metrics.json", "w") as f:
+    with open(base_summaries_dir / "sim-metrics.json", "w") as f:
         json.dump(metrics, f)

bella_companion/simulations/{summarize_logs.py → summarize.py}

@@ -8,13 +8,13 @@ from bella_companion.simulations.scenarios import SCENARIOS
 from bella_companion.utils import read_weights_dir, summarize_logs_dir
 
 
-def summarize_logs():
+def summarize():
     output_dir = Path(os.environ["BELLA_BEAST_OUTPUT_DIR"])
     with open(output_dir / "simulations_job_ids.json", "r") as f:
         job_ids: dict[str, dict[str, dict[str, str]]] = json.load(f)
 
     for scenario_name, scenario in SCENARIOS.items():
-        summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / scenario_name
+        summaries_dir = Path(os.environ["BELLA_SUMMARIES_DIR"]) / scenario_name
         os.makedirs(summaries_dir, exist_ok=True)
         for model in job_ids[scenario_name]:
             logs_dir = output_dir / scenario_name / model

bella_companion/version.xml

@@ -0,0 +1,13 @@
+<addon name='BELLA' version='0.0.1'>
+    <depends on="BEAST.base" atleast="2.7.0" atmost="2.7.9"/>
+    <depends on="BEAST.app" atleast="2.7.0" atmost="2.7.9"/>
+
+    <service type="beast.base.core.BEASTInterface">
+        <provider classname="bella.BayesMLP"/>
+        <provider classname="bella.ReLu"/>
+        <provider classname="bella.SoftPlus"/>
+        <provider classname="bella.Sigmoid"/>
+        <provider classname="bella.Tanh"/>
+        <provider classname="bella.SkylineNodeTreeLogger"/>
+    </service>
+</addon>

{bella_companion-0.0.43.dist-info → bella_companion-0.0.45.dist-info}/METADATA

@@ -1,12 +1,12 @@
 Metadata-Version: 2.4
 Name: bella-companion
-Version: 0.0.43
+Version: 0.0.45
 Summary: Add your description here
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 Requires-Dist: arviz>=0.22.0
 Requires-Dist: bella-lumiere>=0.0.14
 Requires-Dist: dotenv>=0.9.9
-Requires-Dist: phylogenie>=3.1.2
+Requires-Dist: phylogenie>=3.1.3
 Requires-Dist: poetry>=2.2.1
 Requires-Dist: seaborn>=0.13.2

{bella_companion-0.0.43.dist-info → bella_companion-0.0.45.dist-info}/RECORD

@@ -1,7 +1,13 @@
+bella_companion/BELLA.jar,sha256=4mKDzPfz263rTqA9KS2f4Mc-UWGMuj8G48ZDonKSqVw,67408597
 bella_companion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-bella_companion/cli.py,sha256=0SwDxkDPqvsp36kGnrBMLPIhAQM8PIpNXrztZayqmDc,2409
+bella_companion/cli.py,sha256=v2kGrcZ9g448W4Bj-4AU5hwQGmpTRBIbgxhMT8li30s,2786
+bella_companion/version.xml,sha256=Gr3nsYqFhVNP0Mszl_IfilxefsPN8ZpQlGlB8OJSwnE,522
+bella_companion/__pycache__/__init__.cpython-310.pyc,sha256=OWbv3-oQ0uVrCKYMlnplMpvDhv5Ytf3aYb7Eu_UONkU,151
+bella_companion/__pycache__/cli.cpython-310.pyc,sha256=KbutcYiFHY833JXUWR_zA5md-_XQK58BUPpsfpjTYB4,2425
 bella_companion/eucovid/__init__.py,sha256=09Ld_G7fZvCDCgEWsmaOyLVQ8pFc9QHAGnXKJ9Zm2AM,81
 bella_companion/eucovid/run_beast.py,sha256=etaD_4SVdy_Pmz5s4jvDLzp2K_QV8leEY8Pe3xySBsk,3443
+bella_companion/eucovid/__pycache__/__init__.cpython-310.pyc,sha256=cwLb8j-Jrl5beRcoZEtbpvQlG9KENPuB2F4fa1RBYIQ,248
+bella_companion/eucovid/__pycache__/run_beast.cpython-310.pyc,sha256=jEqqaPBugV7B8YZQjNIgYnhpCwDOV21xyG1N_IbRdJo,1922
 bella_companion/eucovid/beast_configs/GLM.xml,sha256=b5rAeKVEam3u2AGSJsm7EHB6LcC0l9bp1SyZT2QyjpI,10892
 bella_companion/eucovid/beast_configs/MLP.xml,sha256=M0_B6t0bZpjCAQqAmjrFshW96pt9sNREcoLUjwchX6Q,10616
 bella_companion/eucovid/beast_configs/Nonparametric.xml,sha256=n-t4sUfDS9AzC02tbIk5mx_RDg2l62ELhdR3I3_jjHE,17783
@@ -21,21 +27,34 @@ bella_companion/eucovid/data/predictors/all/osi_y_7e_ls.tsv,sha256=5YDXe4GstyyRK
 bella_companion/eucovid/data/predictors/all/pop_x_7e_ls.tsv,sha256=3fVYRQ1ylwsa7YptMU8f_xELwwqIF3Ux8akL9UaXKis,1904
 bella_companion/eucovid/data/predictors/all/pop_y_7e_ls.tsv,sha256=Ku39Ts0HW9r5lThAZ01V7HJDi0aoRYs0aQs5EXlZCkQ,1904
 bella_companion/eucovid/data/predictors/all/sharedborders_7e_nt.tsv,sha256=pPVT5DIaZuc3B0mSs-B3kw3G2zja1LfmL_xLwlNtLDo,280
-bella_companion/platyrrhine/__init__.py,sha256=dIx6exNz-vuKiG5FZumvq74QUWcIEFd3L6ErqnOa83c,274
+bella_companion/platyrrhine/__init__.py,sha256=gySgNPoKaEdhcZppKMsCmS-aAcYw_rDEw0viz72Udaw,259
 bella_companion/platyrrhine/beast_config.xml,sha256=bLzavt-Zd8cmSgQQnlCBfZ9KyM7d1inOGx12VNjPFb4,7056
-bella_companion/platyrrhine/results.py,sha256=qosxqstTy7uadHARRt1WqmxZzxnQ3hiTjtw6V-YWKGA,2556
+bella_companion/platyrrhine/results.py,sha256=x5NluhwATa136Gb1lEC_tfl7zhFzFaQnOp9ZRO11zhM,3991
 bella_companion/platyrrhine/run_beast.py,sha256=_9Ex2B65zu6I68uY6s3_dohPYPaFP3E7u-uyWuDLAJc,2477
-bella_companion/platyrrhine/summarize_logs.py,sha256=zVM8YvdXd3eFP14armkgNUVFpNC3P-XXKYytmfgobjg,1351
+bella_companion/platyrrhine/summarize.py,sha256=Qc3GE2vUspTqU_QjLdULvK0r7AZ3JTdqsBmd71izt7M,1356
+bella_companion/platyrrhine/__pycache__/__init__.cpython-310.pyc,sha256=_7OOgWWr8apuTVm7TLhvmP41QHTDFlDNjTtJ9J3vpZc,425
+bella_companion/platyrrhine/__pycache__/results.cpython-310.pyc,sha256=q-9Hd0jDV6WSMI3lL-wiASAxVttekmmJ_FHSOGqaj9c,4028
+bella_companion/platyrrhine/__pycache__/run_beast.cpython-310.pyc,sha256=oTFWqKQCeMUnS7ci8BuRMK2ChGFFV-G2xqcwfCOeI30,2172
+bella_companion/platyrrhine/__pycache__/summarize.cpython-310.pyc,sha256=rU_4ZNKn-XmnGDxATy6bObTDlaRmHDSMBfP3aVlBNA4,1622
+bella_companion/platyrrhine/__pycache__/summarize_logs.cpython-310.pyc,sha256=yKvebBShpNqMoVI2g3VzseuJrMG43A8U8vF7Yg288AE,1616
 bella_companion/platyrrhine/data/change_times.csv,sha256=tedobHbaY7-6M3V6F6HSqGAU9dpeeajR5mu1XGJfp6w,68
 bella_companion/platyrrhine/data/traits.csv,sha256=N_mCnaM9Gy0Qot7-l_mK0vMvr7e_5BZ4bgUHpcoG9UM,3949
 bella_companion/platyrrhine/data/trees.nwk,sha256=lpSiGUG5s3zE--IKPOyWrJ5vpJb_xAPnfxychs3YNIs,488232
-bella_companion/simulations/__init__.py,sha256=ShYRdp1iSjnS_SzcsH-8jbqXz6P1nyRQZqAtPZJCMVE,454
+bella_companion/simulations/__init__.py,sha256=gjO_QB2wp335l7UO-zA9fFQ5vmZauGItBuO-QZFu93E,439
 bella_companion/simulations/features.py,sha256=DZOBpJGlQ0UinqUZYbEtoemZ2eQGVLV_i-DfpW31qJI,104
 bella_companion/simulations/generate_data.py,sha256=edfhXrs76hl30i_xizup4z6qgzXZyaDzX_PVC62Ytpw,849
 bella_companion/simulations/generate_figures.py,sha256=layMgoj3Bfl78Ceb1oE7YirAQ8zhjDyD9IrxDRXf6go,657
-bella_companion/simulations/metrics.py,sha256=duIkPb8cCXmIzjKA2yk9HLf4Y9eFIB_hRWaH05uIDws,1876
+bella_companion/simulations/metrics.py,sha256=kSX7-B4a-LDm1V--S8CvEJDktlJ8qkpo_gY6V7XbOXw,1930
 bella_companion/simulations/run_beast.py,sha256=qniy326i-vDCeHzzHpQRrSnY2ULqNNrO0z3GEsWx4Mc,3208
-bella_companion/simulations/summarize_logs.py,sha256=Shf3Dx9k4lTbmO__MSLw-aIA8a8kTCXhbctBcV6Izug,1216
+bella_companion/simulations/summarize.py,sha256=hfYpgmv2irD8wNQ-GYtJA324w94SKoYhx0bpDG2bb3w,1207
+bella_companion/simulations/__pycache__/__init__.cpython-310.pyc,sha256=IoVTIDdo1s8l5t8qtw71HwOMnHnc-HrfbapHEuY_ItA,588
+bella_companion/simulations/__pycache__/features.cpython-310.pyc,sha256=lKPxu0fteOgho5ZuC0MNQJssIGZ1L5YP6G6wtdKZhH0,437
+bella_companion/simulations/__pycache__/generate_data.cpython-310.pyc,sha256=0lBmxKXXmllkzfzk2_s_T9Mi-ehbAOGeMb92_WGIHtk,1273
+bella_companion/simulations/__pycache__/generate_figures.cpython-310.pyc,sha256=jB-WY4Wc3zRvAF6abzLyELklHqdF8GvleUCbvGN-Teo,816
+bella_companion/simulations/__pycache__/metrics.cpython-310.pyc,sha256=39dzyU2PWUDpR0npJlO-MMha1jTFJ40sDQF9BLhPZRE,2652
+bella_companion/simulations/__pycache__/run_beast.cpython-310.pyc,sha256=ByrndOcAAyCJ8vOCCSsISLPjGRMDzkDCsZAqMge2iAw,2635
+bella_companion/simulations/__pycache__/summarize.cpython-310.pyc,sha256=bIi5Iwro1QlZ5iDtdoG_Ze4mW-2yWHglyeaRWpbUXdI,1340
+bella_companion/simulations/__pycache__/summarize_logs.cpython-310.pyc,sha256=N3unUXsBHq5rrC4GHK6i0O0uzh71AIGdPFN3Lxb-el8,1359
 bella_companion/simulations/beast_configs/epi-multitype/GLM.xml,sha256=VymAYsaZVuB3EPE0DCQSXpKepVq8pPjKaB5yhEpaVkE,4334
 bella_companion/simulations/beast_configs/epi-multitype/MLP.xml,sha256=AoJyjvVcwKtut64d7sB2gnnenx5sXyuTTNCivykUyqU,4077
 bella_companion/simulations/beast_configs/epi-multitype/Nonparametric.xml,sha256=DfCMcLM53b-XP9oIiQ9wJWOVTEP3GnoZaL5BMzLLfIQ,3208
@@ -48,16 +67,26 @@ bella_companion/simulations/beast_configs/fbd-2traits/Nonparametric.xml,sha256=e
 bella_companion/simulations/beast_configs/fbd-no-traits/GLM.xml,sha256=Caq7Gxqx-wYAu3_YkMikVqni3DjBv1Wt00sc1Upo1X8,4743
 bella_companion/simulations/beast_configs/fbd-no-traits/MLP.xml,sha256=JE_cGh2DW5yPAXyXXr0D3DlovmV-aIbze7qrhENHK3w,4275
 bella_companion/simulations/beast_configs/fbd-no-traits/Nonparametric.xml,sha256=m2xaHZwskCFInvVY1QH1fwQqH6p_fgESlPX2BbBeUhk,2822
-bella_companion/simulations/figures/__init__.py,sha256=aBYbJntH4egFmkSSWiVMYDEApXPYxJD7eA3TCPNNegM,658
-bella_companion/simulations/figures/epi_multitype_results.py,sha256=j85WgvN5AyAtX-CalMegr2lwlAZBmzyJxkikBPXRjCc,2629
-bella_companion/simulations/figures/epi_skyline_results.py,sha256=jwognQspt0e1qvrhaYA-MQScsDxpDZd3YKJ5-RHfU6U,1659
-bella_companion/simulations/figures/fbd_2traits_results.py,sha256=JiXrbYkH1HwdJQhTHXj6KhMEXYgQmQ6LmDboAIO1CPA,2728
-bella_companion/simulations/figures/fbd_no_traits_results.py,sha256=kwDbgUTQUk-LXAvMGvKf1kInFvK7kTJld4BWpgS1sVU,1950
+bella_companion/simulations/figures/__init__.py,sha256=LeHPeBb4vxJo0pxLZi_9s6iRBKvWC32yhAZBByqK2_8,590
+bella_companion/simulations/figures/epi_multitype.py,sha256=Ni-hqIiPw0XV_WlypVQD7M1wlpDVz089SqIHly6NsLM,2643
+bella_companion/simulations/figures/epi_skyline.py,sha256=SyFOsb8dwLuoN5IOCiQbG-ZCPDS8Wua_LL-cOuLtu_s,1673
+bella_companion/simulations/figures/fbd_2traits.py,sha256=eU302inVrFDFvKLqNb6t7Z69HLrG0tBrDqRp9AlIjac,2742
+bella_companion/simulations/figures/fbd_no_traits.py,sha256=-_c-qnrFAYZ7vd4Ieeb-uYA3VUwURfrcP11BN9PG8JY,1907
 bella_companion/simulations/figures/scenarios.py,sha256=gbMz1TUxxT2RSIq2kQlFioNdgSHk-gQY2OQuf6-7Fww,2817
 bella_companion/simulations/figures/utils.py,sha256=0M5OrxaEuqcj9rR2uAc_O7utQvhEceZGH0sKrGRWaWs,3129
+bella_companion/simulations/figures/__pycache__/__init__.cpython-310.pyc,sha256=hCtbzMhTC_u8-mCqttWA6ZIWKWxEMuqCZRBPcc2UJrg,693
+bella_companion/simulations/figures/__pycache__/epi_multitype.cpython-310.pyc,sha256=Nfj99laMNw8DZ1C1brUQdUZF0-Xs-ly_DuommvooQVM,2716
+bella_companion/simulations/figures/__pycache__/epi_skyline.cpython-310.pyc,sha256=2iGKtV-j4TYyNP5F0JUTVaIRuxZ28P2KgoOeKYsqcgc,1705
+bella_companion/simulations/figures/__pycache__/fbd_2traits.cpython-310.pyc,sha256=YuaELsTfQPDE5-wr_RPLB8wd_GBbP9KpwbZgu5VT0xk,2764
+bella_companion/simulations/figures/__pycache__/fbd_no_traits.cpython-310.pyc,sha256=cXjyTnxGiypA3weFvkg9x5IWXgC0T9W0Jkf9Xhp65ck,1781
+bella_companion/simulations/figures/__pycache__/scenarios.cpython-310.pyc,sha256=vFCwHYIN9Ss5l87diB2eECycEEsSDZSgfL_jxzfxnp8,2140
+bella_companion/simulations/figures/__pycache__/utils.cpython-310.pyc,sha256=ls2I9vw1jwKXyuESgGiHsyomon1c0QCGVRIe47mhTOM,3979
 bella_companion/simulations/figures/explain/__init__.py,sha256=DnmVIWO65nTT5VsWnbS7NyYgKEY_eo4oMCtCY_ML2Vk,260
 bella_companion/simulations/figures/explain/pdp.py,sha256=3n3ssgufW_43pn2hO5V5J_jgcJH3Fpb8stIRtTnlQ8w,3801
 bella_companion/simulations/figures/explain/shap.py,sha256=1PkbCgynbW-PXkkRpIcY7JoBYqOxqmu1OEOif_roFY8,2207
+bella_companion/simulations/figures/explain/__pycache__/__init__.cpython-310.pyc,sha256=fTqKAgUlMz5E6IXn_bFMd2H5ZzUkF0RAkhZdmC1BOpg,407
+bella_companion/simulations/figures/explain/__pycache__/pdp.cpython-310.pyc,sha256=qr4hCch0Nw8TvQ4IhU0vaQcQnpeNx_j-WvhOF0ITvnY,3474
+bella_companion/simulations/figures/explain/__pycache__/shap.cpython-310.pyc,sha256=AsZkMfZpjwiAK2gvbCD4flhCZOour-mIQU_fVd8RTQ0,2756
 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=fTkFeGHxyV_1f2nX3g_Oyr_e6wkorhXEicJjIAgeZKA,2439
@@ -65,12 +94,23 @@ bella_companion/simulations/scenarios/epi_skyline.py,sha256=JqnOVATECxBUqEbkR5lB
 bella_companion/simulations/scenarios/fbd_2traits.py,sha256=-amB3NX0GsVgYbFuHH71t93FuXUEnRUyhWf2Qpcpia4,3541
 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/scenarios/__pycache__/__init__.cpython-310.pyc,sha256=u8Myq0Jl4dr5i0IzQoZiBxkGfEHQrLfhS2gRnPgFm-g,1081
+bella_companion/simulations/scenarios/__pycache__/common.cpython-310.pyc,sha256=qLAVMzuY5Q2YGmeUlaLUqa_81dAdhKnX2FkYdC82GEw,1226
+bella_companion/simulations/scenarios/__pycache__/epi_multitype.cpython-310.pyc,sha256=qyesYumfFnaXSenM1T0p1sjqDKUnzT_-aMWt0bPEJ9Q,2390
+bella_companion/simulations/scenarios/__pycache__/epi_skyline.cpython-310.pyc,sha256=wg5eyiA3grtlNE0KzSr-xAQaYHdw2d5UjpFT_MSXoyM,2194
+bella_companion/simulations/scenarios/__pycache__/fbd_2traits.cpython-310.pyc,sha256=gg15HCp0Q_oqOxXYrbM9uOPjw58HpRNVWexO5p6Jb14,3028
+bella_companion/simulations/scenarios/__pycache__/fbd_no_traits.cpython-310.pyc,sha256=TMz7ljrkXDCwKlqKP1wSOfbxvqvkFfzzUwZSqQtaQMs,2637
+bella_companion/simulations/scenarios/__pycache__/scenario.cpython-310.pyc,sha256=1cWwz_MoZopfAt9ErEbWZnLutFODPwkujkTkS2NHsQg,1147
 bella_companion/utils/__init__.py,sha256=UtMwPK9dWf9NAl0ic8CSsgdW7aSm-5J49OqgvD7UpYw,480
 bella_companion/utils/beast.py,sha256=TBa0cLklX1_tXqoQE4LRYvds7mLg_9fS2-6U6OHENHo,2184
 bella_companion/utils/explain.py,sha256=uP7HPyn2YiykAI69BQV3RooDpC6qKoCLXfp3Uibp4zk,1475
 bella_companion/utils/slurm.py,sha256=xEyf-Jxk8fy71t3fko_Ic9WtUFSdLFE3w4tR17gaBPw,1868
-bella_companion-0.0.43.dist-info/METADATA,sha256=FHwaRLEDuz_6yvFM2QExhAlXKFQ3gdgV_Ez--8kk3BM,347
-bella_companion-0.0.43.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-bella_companion-0.0.43.dist-info/entry_points.txt,sha256=SVEYDBrkBWPrOGwnEH2aO5TSVIAvfKE37sqm-9ut9jg,51
-bella_companion-0.0.43.dist-info/top_level.txt,sha256=q0loZYv4vf3zF_tOATyAJqeyLOEuPyLbObNqIGP7Fmc,16
-bella_companion-0.0.43.dist-info/RECORD,,
+bella_companion/utils/__pycache__/__init__.cpython-310.pyc,sha256=QKECw9gSF8x3G4oXI06atZpaLDPSxm3k4qJ_-0nADbo,527
+bella_companion/utils/__pycache__/beast.cpython-310.pyc,sha256=q6nsN-b5UBTLiZYOSqbUk9KlLFy_QE9unWLw-ldXz4c,2537
+bella_companion/utils/__pycache__/explain.cpython-310.pyc,sha256=K7YHxY520Q0nJtTVa-eEKw3B99MsrO_b-U50X_yihGQ,1819
+bella_companion/utils/__pycache__/slurm.cpython-310.pyc,sha256=kKWmJwCTlotpPuXi4kzXNx2-zY9BXuzjhGi5ZrcN0oI,1785
+bella_companion-0.0.45.dist-info/METADATA,sha256=RbUbp2pwCDhwJe0YD2QX0r-Au1rlvg7Vv9ddZR5GbC4,347
+bella_companion-0.0.45.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+bella_companion-0.0.45.dist-info/entry_points.txt,sha256=SVEYDBrkBWPrOGwnEH2aO5TSVIAvfKE37sqm-9ut9jg,51
+bella_companion-0.0.45.dist-info/top_level.txt,sha256=q0loZYv4vf3zF_tOATyAJqeyLOEuPyLbObNqIGP7Fmc,16
+bella_companion-0.0.45.dist-info/RECORD,,