bella-companion 0.0.6__py3-none-any.whl → 0.0.8__py3-none-any.whl

bella_companion/fbd_empirical/run_beast.py

@@ -1,3 +1,4 @@
+import json
 import os
 from pathlib import Path
 
@@ -7,48 +8,61 @@ from phylogenie import load_newick
 from phylogenie.utils import get_node_depths
 from tqdm import tqdm
 
-import src.config as cfg
-from src.utils import run_sbatch
+from bella_companion.utils import submit_job
 
 THIS_DIR = Path(__file__).parent
-AADD LAYERS RANGE
 
-def main():
-    output_dir = cfg.BEAST_OUTPUTS_DIR / "fbd-empirical"
+
+def run_beast():
+    base_output_dir = Path(os.environ["BELLA_BEAST_OUTPUT_DIR"])
+    output_dir = base_output_dir / "fbd-empirical"
     os.makedirs(output_dir, exist_ok=True)
 
-    tree_file = THIS_DIR / "data" / "trees.nwk"
-    change_times_file = THIS_DIR / "data" / "change_times.csv"
-    sampling_change_times_file = THIS_DIR / "data" / "sampling_change_times.csv"
+    data_dir = THIS_DIR / "data"
+    tree_file = data_dir / "trees.nwk"
+    change_times_file = data_dir / "change_times.csv"
 
+    trees = load_newick(str(tree_file))
+    assert isinstance(trees, list)
     change_times = (
         pl.read_csv(change_times_file, has_header=False).to_series().to_numpy()
     )
-    time_predictor = " ".join(
-        list(map(str, np.repeat(np.insert(change_times, 0, 0), 4)))
-    )
+    time_predictor = " ".join(list(map(str, np.repeat([0, *change_times], 4))))
     body_mass_predictor = " ".join(["0", "1", "2", "3"] * (len(change_times) + 1))
 
-    trees = load_newick(str(tree_file))
-    assert isinstance(trees, list)
+    job_ids = {}
     for i, tree in enumerate(tqdm(trees)):
         process_length = max(get_node_depths(tree).values())
-        for model in ["hidden-relu", "hidden-tanh"]:
-            command = " ".join(
-                [
-                    cfg.RUN_BEAST,
-                    f'-D treeFile={tree_file},treeIndex={i},typeTraitFile={THIS_DIR / "data" / "body_mass.csv"},changeTimesFile={change_times_file},samplingChangeTimesFile={sampling_change_times_file},processLength={process_length},timePredictor="{time_predictor}",bodyMassPredictor="{body_mass_predictor}"',
-                    f"-DF {THIS_DIR / 'params.json'}",
-                    f"-prefix {output_dir / model}",
-                    str(cfg.BEAST_CONFIGS_DIR / "fbd-empirical" / f"{model}.xml"),
-                ]
-            )
-            run_sbatch(
-                command,
-                cfg.SBATCH_LOGS_DIR / "fbd-empirical" / model / str(i),
-                mem_per_cpu="12000",
-            )
-
-
-if __name__ == "__main__":
-    main()
+        command = " ".join(
+            [
+                os.environ["BELLA_RUN_BEAST_CMD"],
+                f"-D types=0,1,2,3",
+                f'-D startTypePriorProbs="0.25 0.25 0.25 0.25"',
+                f"-D birthRateUpper=10",
+                f"-D deathRateUpper=10",
+                f"-D samplingRateUpper=10",
+                f'-D samplingRateInit="5 5 5 5 5 5 5"',
+                f"-D migrationRateUpper=10",
+                f'-D migrationRateInit="5 0 0 5 5 0 0 5 5 0 0 5"',
+                f'-D nodes="16 8"',
+                f'-D layersRange="0,1,2"',
+                f"-D treeFile={tree_file}",
+                f"-D treeIndex={i}",
+                f"-D changeTimesFile={change_times_file}",
+                f"-D samplingChangeTimesFile={data_dir / 'sampling_change_times.csv'}",
+                f"-D typeTraitFile={data_dir / 'body_mass.csv'}",
+                f"-D processLength={process_length}",
+                f'-D timePredictor="{time_predictor}"',
+                f'-D bodyMassPredictor="{body_mass_predictor}"',
+                f"-prefix {output_dir}{os.sep}",
+                str(Path(os.environ["BELLA_BEAST_CONFIGS_DIR"]) / "fbd-empirical.xml"),
+            ]
+        )
+        job_ids[i] = submit_job(
+            command,
+            Path(os.environ["BELLA_SBATCH_LOG_DIR"]) / "fbd-empirical" / str(i),
+            mem_per_cpu="12000",
+        )
+
+    with open(base_output_dir / "fbd_empirical_job_ids.json", "w") as f:
+        json.dump(job_ids, f)

bella_companion/fbd_empirical/summarize_logs.py

@@ -1,50 +1,33 @@
-import json
 import os
 from pathlib import Path
 
 import joblib
 import polars as pl
 
-from src.config import BEAST_LOGS_SUMMARIES_DIR, BEAST_OUTPUTS_DIR
-from src.utils import summarize_logs
+from bella_companion.utils import read_weights_dir, summarize_logs_dir
 
 THIS_DIR = Path(__file__).parent
 
 
-def main():
-    summaries_dir = os.path.join(BEAST_LOGS_SUMMARIES_DIR, "fbd-empirical")
-    os.makedirs(summaries_dir, exist_ok=True)
-
-    with open(os.path.join(THIS_DIR, "params", "MLP.json"), "r") as f:
-        params = json.load(f)
-    hidden_nodes = list(map(int, params["nodes"].split()))[:-1]
-    print(hidden_nodes)
-    states = params["types"].split(",")
-    logs_dir = os.path.join(BEAST_OUTPUTS_DIR, "fbd-empirical", "MLP")
-    change_times = (
-        pl.read_csv(
-            os.path.join(THIS_DIR, "data", "change_times.csv"), has_header=False
-        )
-        .to_series()
-        .to_list()
+def summarize_logs():
+    change_times = pl.read_csv(
+        Path(THIS_DIR) / "data" / "change_times.csv", has_header=False
     )
     n_time_bins = len(change_times) + 1
-    logs_summary, weights = summarize_logs(
-        logs_dir,
+
+    logs_dir = Path(os.environ["BELLA_BEAST_OUTPUT_DIR"]) / "fbd-empirical"
+    summaries = summarize_logs_dir(
+        logs_dir=logs_dir,
         target_columns=[
-            f"{rate}Ratei{i}_{s}"
+            f"{rate}RateSPi{i}_{s}"
             for rate in ["birth", "death"]
             for i in range(n_time_bins)
-            for s in states
+            for s in ["0", "1", "2", "3"]
         ],
-        hidden_nodes=hidden_nodes,
-        n_features={f"{rate}Rate": 2 for rate in ["birth", "death"]},
-        layers_range_start=0,
     )
+    weights = read_weights_dir(logs_dir)
 
-    logs_summary.write_csv(os.path.join(summaries_dir, f"MLP.csv"))
-    joblib.dump(weights, os.path.join(summaries_dir, "weights.pkl"))
-
-
-if __name__ == "__main__":
-    main()
+    summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"], "fbd-empirical")
+    os.makedirs(summaries_dir, exist_ok=True)
+    summaries.write_csv(summaries_dir / "MLP.csv")
+    joblib.dump(weights, summaries_dir / "MLP.weights.pkl")

bella_companion/simulations/__init__.py

@@ -1,6 +1,13 @@
 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
 
-__all__ = ["generate_data", "generate_figures", "run_beast", "summarize_logs"]
+__all__ = [
+    "generate_data",
+    "generate_figures",
+    "print_metrics",
+    "run_beast",
+    "summarize_logs",
+]

bella_companion/simulations/figures/epi_skyline_results.py

@@ -5,12 +5,12 @@ import matplotlib.pyplot as plt
 import numpy as np
 import polars as pl
 
-from bella_companion.simulations.scenarios.epi_skyline import REPRODUCTION_NUMBERS
-from bella_companion.utils import (
+from bella_companion.simulations.figures.utils import (
     plot_coverage_per_time_bin,
     plot_maes_per_time_bin,
     step,
 )
+from bella_companion.simulations.scenarios.epi_skyline import REPRODUCTION_NUMBERS
 
 
 def plot_epi_skyline_results():

bella_companion/simulations/figures/explain/pdp.py

@@ -45,12 +45,10 @@ def plot_partial_dependencies(
         np.array(mcmc_pds).T for mcmc_pds in zip(*pdvalues)
     ]  # shape: (n_features, n_grid_points, n_runs)
 
-    if any(not feature.is_binary for feature in features.values()):
-        for (feature_name, feature), feature_pdvalues in zip(
-            features.items(), pdvalues
-        ):
+    if any(not f.is_binary for f in features.values()):
+        for (label, feature), feature_pdvalues in zip(features.items(), pdvalues):
             if not feature.is_binary:
-                color = "red" if feature.is_relevant else "gray"
+                color = "#E74C3C" if feature.is_relevant else "gray"
                 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)
@@ -62,7 +60,7 @@ def plot_partial_dependencies(
                         continuous_grid, mcmc_pds, color=color, alpha=0.2, linewidth=1
                     )
                 plt.plot(  # pyright: ignore
-                    continuous_grid, median, color=color, label=feature_name
+                    continuous_grid, median, color=color, label=label
                 )
         plt.xlabel("Feature value")  # pyright: ignore
         plt.ylabel("MLP Output")  # pyright: ignore
@@ -70,32 +68,28 @@ def plot_partial_dependencies(
         plt.savefig(output_dir / "PDPs-continuous.svg")  # pyright: ignore
         plt.close()
 
-    if any(feature.is_binary for feature in features.values()):
+    if any(f.is_binary for f in features.values()):
         data: list[float] = []
-        grid_labels: list[int] = []
-        feature_labels: list[str] = []
-        for (feature_name, feature), feature_pdvalues in zip(
-            features.items(), pdvalues
-        ):
+        grid: list[int] = []
+        labels: list[str] = []
+        for (label, feature), feature_pdvalues in zip(features.items(), pdvalues):
             if feature.is_binary:
                 for i in [0, 1]:
                     data.extend(feature_pdvalues[i])
-                    grid_labels.extend([i] * len(feature_pdvalues[i]))
-                    feature_labels.extend([feature_name] * len(feature_pdvalues[i]))
-        sns.violinplot(
-            x=grid_labels,
-            y=data,
-            hue=feature_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_binary
-            },
+                    grid.extend([i] * len(feature_pdvalues[i]))
+                    labels.extend([label] * len(feature_pdvalues[i]))
+
+        ax = sns.violinplot(
+            x=labels, y=data, hue=grid, split=True, cut=0, inner="quartile"
         )
-        plt.xlabel("Feature value")  # pyright: ignore
+        ax.get_legend().remove()  # pyright: ignore
+
+        for i, f in enumerate([f for f in features.values() if f.is_binary]):
+            color = "#E74C3C" if f.is_relevant else "gray"
+            for coll in ax.collections[i * 2 : i * 2 + 2]:
+                coll.set_facecolor(color)
+
+        plt.xlabel("Feature")  # pyright: ignore
         plt.ylabel("MLP Output")  # pyright: ignore
-        plt.legend()  # pyright: ignore
         plt.savefig(output_dir / "PDPs-categorical.svg")  # pyright: ignore
         plt.close()

bella_companion/simulations/figures/explain/shap.py

@@ -48,7 +48,7 @@ def plot_shap_features_importance(
             y=features_importances[:, i],
             x=[feature_name] * len(features_importances),
             cut=0,
-            color="red" if feature.is_relevant else "gray",
+            color="#E74C3C" if feature.is_relevant else "gray",
         )
     plt.xlabel("Feature")  # pyright: ignore
     plt.ylabel("Importance")  # pyright: ignore

bella_companion/simulations/figures/fbd_2traits_results.py

@@ -12,6 +12,7 @@ from bella_companion.simulations.figures.explain import (
     plot_partial_dependencies,
     plot_shap_features_importance,
 )
+from bella_companion.simulations.figures.utils import step
 from bella_companion.simulations.scenarios.fbd_2traits import (
     FBD_RATE_UPPER,
     N_TIME_BINS,
@@ -19,7 +20,6 @@ from bella_companion.simulations.scenarios.fbd_2traits import (
     SCENARIO,
     STATES,
 )
-from bella_companion.utils import step
 
 
 def _plot_predictions(log_summary: pl.DataFrame, output_dir: Path):

bella_companion/simulations/figures/fbd_no_traits_results.py

@@ -5,12 +5,12 @@ import matplotlib.pyplot as plt
 import numpy as np
 import polars as pl
 
-from bella_companion.simulations.scenarios.fbd_no_traits import RATES
-from bella_companion.utils import (
+from bella_companion.simulations.figures.utils import (
     plot_coverage_per_time_bin,
     plot_maes_per_time_bin,
     step,
 )
+from bella_companion.simulations.scenarios.fbd_no_traits import RATES
 
 
 def plot_fbd_no_traits_results():

bella_companion/simulations/figures/scenarios.py

@@ -4,6 +4,7 @@ from pathlib import Path
 import matplotlib.pyplot as plt
 import numpy as np
 
+from bella_companion.simulations.figures.utils import step
 from bella_companion.simulations.scenarios.epi_multitype import (
     MIGRATION_PREDICTOR,
     MIGRATION_RATES,
@@ -16,11 +17,10 @@ from bella_companion.simulations.scenarios.fbd_2traits import (
     DEATH_RATE_TRAIT1_UNSET,
 )
 from bella_companion.simulations.scenarios.fbd_no_traits import RATES
-from bella_companion.utils import step
 
 
 def plot_scenarios():
-    output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "targets"
+    output_dir = Path(os.environ["BELLA_FIGURES_DIR"]) / "scenarios"
     os.makedirs(output_dir, exist_ok=True)
 
     # -----------

bella_companion/simulations/generate_data.py

@@ -1,4 +1,5 @@
 import os
+from pathlib import Path
 
 from phylogenie import generate_trees
 
@@ -10,10 +11,10 @@ MAX_TIPS = 500
 
 
 def generate_data():
-    base_output_dir = os.environ["BELLA_SIMULATIONS_DATA_DIR"]
+    base_output_dir = Path(os.environ["BELLA_SIMULATIONS_DATA_DIR"])
     for scenario_name, scenario in SCENARIOS.items():
         generate_trees(
-            output_dir=os.path.join(base_output_dir, scenario_name),
+            output_dir=base_output_dir / scenario_name,
             n_trees=N_TREES,
             events=scenario.events,
             init_state=scenario.init_state,
@@ -22,4 +23,5 @@ def generate_data():
             min_tips=MIN_TIPS,
             max_tips=MAX_TIPS,
             seed=42,
+            n_jobs=2,
         )

bella_companion/simulations/metrics.py

@@ -0,0 +1,62 @@
+import json
+import os
+from glob import glob
+from pathlib import Path
+
+import numpy as np
+import polars as pl
+
+from bella_companion.simulations.scenarios import SCENARIOS
+
+
+def _mae(summary: pl.DataFrame, true_values: dict[str, float]) -> float:
+    preds = [float(np.median(summary[f"{target}_median"])) for target in true_values]
+    targets = list(true_values.values())
+    return float(np.mean([np.abs(np.array(preds) - np.array(targets))]))
+
+
+def _coverage(summary: pl.DataFrame, true_values: dict[str, float]) -> float:
+    coverages = [
+        (
+            (summary[f"{target}_lower"] <= true_values[target])
+            & (true_values[target] <= summary[f"{target}_upper"])
+        ).sum()
+        / len(summary)
+        for target in true_values
+    ]
+    return float(np.mean(coverages))
+
+
+def _avg_ci_width(summary: pl.DataFrame, true_values: dict[str, float]) -> float:
+    widths = [
+        np.median(summary[f"{target}_upper"] - summary[f"{target}_lower"])
+        for target in true_values
+    ]
+    return float(np.mean(widths))
+
+
+def print_metrics():
+    metrics = {}
+    for name, scenario in SCENARIOS.items():
+        summaries_dir = Path(os.environ["BELLA_LOG_SUMMARIES_DIR"]) / name
+        summaries = {
+            Path(log_summary).stem: pl.read_csv(log_summary)
+            for log_summary in glob(str(summaries_dir / "*.csv"))
+        }
+        metrics[name] = {
+            target: {
+                model: {
+                    "MAE": _mae(summary, true_values),
+                    "coverage": _coverage(summary, true_values),
+                    "avg_CI_width": _avg_ci_width(summary, true_values),
+                }
+                for model, summary in summaries.items()
+            }
+            for target, true_values in scenario.targets.items()
+        }
+    with open("simulation-metrics.json", "w") as f:
+        json.dump(metrics, f)
+
+
+if __name__ == "__main__":
+    print_metrics()

bella_companion/simulations/scenarios/epi_multitype.py

@@ -54,7 +54,7 @@ SCENARIO = Scenario(
     },
     targets={
         "migrationRate": {
-            f"migrationRateSP{t1}_to_{t2}": MIGRATION_RATES[i, j]
+            f"migrationRateSP{t1}_to_{t2}": float(MIGRATION_RATES[i, j])
             for i, t1 in enumerate(TYPES)
             for j, t2 in enumerate([t for t in TYPES if t != t1])
         }

bella_companion/simulations/scenarios/fbd_2traits.py

@@ -41,10 +41,7 @@ DEATH_RATES = {
     "10": DEATH_RATE_TRAIT1_SET,
     "11": DEATH_RATE_TRAIT1_SET,
 }
-RATES = {
-    "birth": BIRTH_RATES,
-    "death": DEATH_RATES,
-}
+RATES = {"birth": BIRTH_RATES, "death": DEATH_RATES}
 _MIGRATION_RATES = (
     np.array([[1, 1, 0], [1, 0, 1], [1, 0, 1], [0, 1, 1]]) * 0.1
 ).tolist()

bella_companion/simulations/summarize_logs.py

@@ -5,8 +5,7 @@ from pathlib import Path
 import joblib
 
 from bella_companion.simulations.scenarios import SCENARIOS
-from bella_companion.utils import summarize_logs as _summarize_logs
-from bella_companion.utils import summarize_weights
+from bella_companion.utils import read_weights_dir, summarize_logs_dir
 
 
 def summarize_logs():
@@ -20,12 +19,12 @@ def summarize_logs():
         for model in job_ids[scenario_name]:
             logs_dir = output_dir / scenario_name / model
             print(f"Summarizing {scenario_name} - {model}")
-            summary = _summarize_logs(
+            summary = summarize_logs_dir(
                 logs_dir,
                 target_columns=[c for t in scenario.targets.values() for c in t],
                 job_ids=job_ids[scenario_name][model],
             )
             summary.write_csv(summaries_dir / f"{model}.csv")
             if model.startswith("MLP"):
-                weights = summarize_weights(logs_dir)
+                weights = read_weights_dir(logs_dir)
                 joblib.dump(weights, summaries_dir / f"{model}.weights.pkl")

bella_companion/utils/__init__.py

@@ -1,23 +1,19 @@
-from bella_companion.utils.beast import summarize_log, summarize_logs, summarize_weights
+from bella_companion.utils.beast import (
+    read_weights_dir,
+    summarize_log,
+    summarize_logs_dir,
+)
 from bella_companion.utils.explain import (
     get_median_partial_dependence_values,
     get_median_shap_features_importance,
 )
-from bella_companion.utils.plots import (
-    plot_coverage_per_time_bin,
-    plot_maes_per_time_bin,
-    step,
-)
 from bella_companion.utils.slurm import submit_job
 
 __all__ = [
     "summarize_log",
-    "summarize_logs",
-    "summarize_weights",
+    "summarize_logs_dir",
+    "read_weights_dir",
     "get_median_partial_dependence_values",
     "get_median_shap_features_importance",
-    "plot_coverage_per_time_bin",
-    "plot_maes_per_time_bin",
-    "step",
     "submit_job",
 ]

bella_companion/utils/beast.py

@@ -36,7 +36,7 @@ def summarize_log(
     return summary
 
 
-def summarize_logs(
+def summarize_logs_dir(
     logs_dir: Path,
     target_columns: list[str],
     burn_in: float = 0.1,
@@ -59,7 +59,7 @@ def summarize_logs(
     return pl.DataFrame(summaries)
 
 
-def summarize_weights(
+def read_weights_dir(
     logs_dir: Path, n_samples: int = 100, burn_in: float = 0.1
 ) -> list[dict[str, list[Weights]]]:
     os.environ["POLARS_MAX_THREADS"] = "1"

{bella_companion-0.0.6.dist-info → bella_companion-0.0.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bella-companion
-Version: 0.0.6
+Version: 0.0.8
 Summary: 
 Author: gabriele-marino
 Author-email: gabmarino.8601@gmail.com
@@ -12,5 +12,5 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: arviz (>=0.22.0,<0.23.0)
 Requires-Dist: bella-lumiere (>=0.0.13,<0.0.14)
 Requires-Dist: dotenv (>=0.9.9,<0.10.0)
-Requires-Dist: phylogenie (>=2.1.28,<3.0.0)
+Requires-Dist: phylogenie (>=2.1.29,<3.0.0)
 Requires-Dist: seaborn (>=0.13.2,<0.14.0)

bella_companion-0.0.8.dist-info/RECORD

@@ -0,0 +1,42 @@
+bella_companion/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+bella_companion/cli.py,sha256=ykq62Qjt9Kk1g0HZZMMA_nAqoG5E7vnWEWGfqDJx3hU,1937
+bella_companion/fbd_empirical/__init__.py,sha256=nQdZfS56ZsU26davkyK4isTqvKjMVw9OniHqjWRt3q0,177
+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/notbooks.ipynb,sha256=0ptmZC-_QfXtfCBrrag7NLtupiVn4gdG-oqVCworT_U,81588
+bella_companion/fbd_empirical/run_beast.py,sha256=Oa5R9absmc9zYGb5bPdf_3o6cjoenxLcS5Sgp1uBpzM,2522
+bella_companion/fbd_empirical/summarize_logs.py,sha256=TBLdW5LWS5ensEQFFQ8hrzJFJ3t0l-Mzu_SNa-Q8D_w,972
+bella_companion/simulations/__init__.py,sha256=ShYRdp1iSjnS_SzcsH-8jbqXz6P1nyRQZqAtPZJCMVE,454
+bella_companion/simulations/features.py,sha256=DZOBpJGlQ0UinqUZYbEtoemZ2eQGVLV_i-DfpW31qJI,104
+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=gI5Ha-OIEShcZLmqVuy0W8hJzkrsydQE-Coa65_BFCo,1667
+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=qRfOMNwkU-hsBy5MHMTfVFAszaPESVOugCKQTVY8Q4Y,1940
+bella_companion/simulations/figures/fbd_2traits_results.py,sha256=JiXrbYkH1HwdJQhTHXj6KhMEXYgQmQ6LmDboAIO1CPA,2728
+bella_companion/simulations/figures/fbd_no_traits_results.py,sha256=fLsgpV3IbLLtxQEFNOL9K4jEEJrG324ziUM0rxIv7_k,1962
+bella_companion/simulations/figures/scenarios.py,sha256=gbMz1TUxxT2RSIq2kQlFioNdgSHk-gQY2OQuf6-7Fww,2817
+bella_companion/simulations/figures/utils.py,sha256=dB_GiJ1HGrZ93cqODz6kB-HeDRPwlm2MkMe9rJZGnfs,3117
+bella_companion/simulations/generate_data.py,sha256=ZFQnusmGWDjRixKOid0l49Aj4qfrI5zxyf1n21wf0p0,768
+bella_companion/simulations/generate_figures.py,sha256=layMgoj3Bfl78Ceb1oE7YirAQ8zhjDyD9IrxDRXf6go,657
+bella_companion/simulations/metrics.py,sha256=TwLgK4Eui4DlG10V9m6zEbmuGfUIli2dE0Ph-gX_6bU,1925
+bella_companion/simulations/run_beast.py,sha256=Sw9wKNe1VlGNvYr-yiYv3LqUYVlcjcMAz_9Pzr-xyL0,3214
+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
+bella_companion/simulations/scenarios/epi_skyline.py,sha256=JqnOVATECxBUqEbkR5lBlMI2O8k4hO6ipR8k9cHUsm0,2365
+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/summarize_logs.py,sha256=Shf3Dx9k4lTbmO__MSLw-aIA8a8kTCXhbctBcV6Izug,1216
+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=v5DaG7YHVyK8KRFptgGDC6I8jxEhyJuMVK9N08pZSAI,1812
+bella_companion-0.0.8.dist-info/METADATA,sha256=e7ZtRd2kPoER6o1m6zSZtLplX7dOox3WLqlZlH45og0,576
+bella_companion-0.0.8.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
+bella_companion-0.0.8.dist-info/entry_points.txt,sha256=rSeKoAhmjnQqAYFcXBv0gAM2ViJfJe0D8_dD-fWrXeg,50
+bella_companion-0.0.8.dist-info/RECORD,,

bella_companion/fbd_empirical/figure.py

@@ -1,37 +0,0 @@
-import json
-import os
-from pathlib import Path
-
-import polars as pl
-
-import src.config as cfg
-from src.utils import set_plt_rcparams
-
-THIS_DIR = Path(__file__).parent
-
-if __name__ == "__main__":
-    with open(os.path.join(THIS_DIR, "params", "MLP.json"), "r") as f:
-        params = json.load(f)
-    states = params["types"].split(",")
-    change_times = (
-        pl.read_csv(
-            os.path.join(THIS_DIR, "data", "change_times.csv"), has_header=False
-        )
-        .to_series()
-        .to_list()
-    )
-    n_time_bins = len(change_times) + 1
-
-    set_plt_rcparams()
-
-    log_summary = pl.read_csv(
-        os.path.join(cfg.BEAST_LOGS_SUMMARIES_DIR, "fbd-empirical", "MLP.csv")
-    )
-    for s in states:
-        estimates: list[float] = [
-            log_summary[f"birthRatei{i}_{s}_median"].median()
-            for i in range(n_time_bins)
-        ]
-        plt.step(change_times, estimates[:-1], label=rf"$\lambda_{{{s}}}$")
-        plt.legend()
-    plt.gca().invert_xaxis()  # This reverses the x-axis

bella_companion/fbd_empirical/params.json

@@ -1,11 +0,0 @@
-{
-    "types": "0,1,2,3",
-    "startTypePriorProbs": "0.25 0.25 0.25 0.25",
-    "birthRateUpper": 2,
-    "deathRateUpper": 2,
-    "samplingRateUpper": 10,
-    "samplingRateInit": "5 5 5 5 5 5 5",
-    "migrationRateUpper": 10,
-    "migrationRateInit": "0.5 0 0 0.5 0.5 0 0 0.5 0.5 0 0 0.5",
-    "nodes": "16 8"
-}