archeo 2.0.0.dev5__tar.gz → 2.0.0.dev7__tar.gz

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: archeo
-Version: 2.0.0.dev5
+Version: 2.0.0.dev7
 Summary: Bayesian framework for inferring natal kick, ancestral masses and spins of black holes.
 Author-email: wyhwong <wyhwong@link.cuhk.edu.hk>
 License-Expression: MIT

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/bayesian/ancestral_posterior.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pandas as pd
 
+from archeo.constants.bayesian import DEFAULT_BINSIZE_MASS, DEFAULT_BINSIZE_SPIN
 from archeo.utils.parallel import get_n_workers, multiprocess_run, multithread_run
 
 
@@ -8,8 +9,8 @@ def _retrieve_sample(
     df_binaries: pd.DataFrame,
     mass_measure: float,
     spin_measure: float,
-    binsize_mass: float = 2.0,
-    binsize_spin: float = 0.1,
+    binsize_mass: float = DEFAULT_BINSIZE_MASS,
+    binsize_spin: float = DEFAULT_BINSIZE_SPIN,
 ) -> pd.DataFrame:
     """Retrieve the samples from data frame of binaries"""
 
@@ -36,8 +37,8 @@ def infer_ancestral_posterior_distribution(
     df_binaries: pd.DataFrame,
     mass_posterior_samples: list[float],
     spin_posterior_samples: list[float],
-    binsize_mass: float = 2.0,
-    binsize_spin: float = 0.1,
+    binsize_mass: float = DEFAULT_BINSIZE_MASS,
+    binsize_spin: float = DEFAULT_BINSIZE_SPIN,
     random_state: int = 42,
     n_workers: int = 1,
 ) -> pd.DataFrame:

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/bayesian/importance_sampling/__init__.py

@@ -1,2 +1,3 @@
 from archeo.bayesian.importance_sampling.bayes_factor_curve import BayesFactorCurve, CandidatePrior
 from archeo.bayesian.importance_sampling.resampler.interface import ImportanceSamplingData
+from archeo.data_structures.bayesian.bayes_factor import BayesFactorCurveMetadata

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/bayesian/importance_sampling/bayes_factor_curve.py

@@ -38,7 +38,7 @@ class CandidatePrior(BaseModel):
         df_bh1_prior = self.df_bh1.loc[self.df_bh1["v_esc"] <= v_esc]
         df_bh2_prior = self.df_bh2.loc[self.df_bh2["v_esc"] <= v_esc]
 
-        if df_bh1_prior.empty and df_bh2_prior.empty:
+        if df_bh1_prior.empty or df_bh2_prior.empty:
             return pd.DataFrame(columns=self.df_bh1.columns.union(self.df_bh2.columns))
 
         n_samples = max(len(df_bh1_prior), len(df_bh2_prior), n_min)
@@ -57,14 +57,10 @@ class CandidatePrior(BaseModel):
         v_esc_max = max(self.df_bh1["v_esc"].max(), self.df_bh2["v_esc"].max())
 
         if log_scale:
-            v_escs = np.logspace(np.log10(v_esc_min), np.log10(v_esc_max), n_pts)
+            v_escs = np.logspace(max(np.log10(v_esc_min), np.log10(0.1)), np.log10(v_esc_max), n_pts)
         else:
             v_escs = np.linspace(v_esc_min, v_esc_max, n_pts)
 
-        # Add zero in the beginning of the list if it's not already included
-        if v_escs[0] > 0:
-            v_escs = np.insert(v_escs, 0, 0.0)
-
         # Add 5000 km/s in the end of the list if it's not already included
         if v_escs[-1] < 5000:
             v_escs = np.append(v_escs, 5000.0)
@@ -78,7 +74,6 @@ class BayesFactorCurve(BaseModel, frozen=True):
     n_bootstrapping: int = 50
     n_pts: int = 10
     log_scale: bool = False
-    assume_parameter_independence: bool = False
     metadata: BayesFactorCurveMetadata = BayesFactorCurveMetadata()
 
     def _sample_bayes_factor(
@@ -95,7 +90,7 @@ class BayesFactorCurve(BaseModel, frozen=True):
             new_prior_samples=candidate_prior.get_conditional_prior(v_esc),
             binsize_spin=self.metadata.binsize_spin,
             binsize_mass=self.metadata.binsize_mass,
-            assume_parameter_independence=self.assume_parameter_independence,
+            assume_parameter_independence=self.metadata.assume_parameter_independence,
         ).sample_bayes_factor(n=self.n_bootstrapping, is_parallel=True)
 
     @pre_release

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/bayesian/importance_sampling/resampler/base.py

@@ -2,6 +2,7 @@ import numpy as np
 import pandas as pd
 from pydantic import BaseModel, ConfigDict
 
+from archeo.constants.bayesian import DEFAULT_BINSIZE_MASS, DEFAULT_BINSIZE_SPIN
 from archeo.data_structures.math import Domain
 from archeo.utils.logger import get_logger
 
@@ -17,8 +18,8 @@ class ImportanceSamplingDataBase(BaseModel, frozen=True):
     posterior_samples: pd.DataFrame
     prior_samples: pd.DataFrame
     new_prior_samples: pd.DataFrame
-    binsize_spin: float = 0.05
-    binsize_mass: float = 1.0
+    binsize_spin: float = DEFAULT_BINSIZE_SPIN
+    binsize_mass: float = DEFAULT_BINSIZE_MASS
     ztol: float = 1e-8
 
     @property

archeo-2.0.0.dev7/archeo/constants/bayesian.py

@@ -0,0 +1,3 @@
+DEFAULT_BINSIZE_MASS: float = 2.0
+DEFAULT_BINSIZE_SPIN: float = 0.1
+ASSUME_PARAMETER_INDEPENDENCE: bool = False

archeo-2.0.0.dev7/archeo/constants/physics.py

@@ -0,0 +1,58 @@
+import enum
+
+import pandas as pd
+from pydantic import BaseModel, NonNegativeFloat
+
+
+SPEED_OF_LIGHT = 299792.458  # km/s
+
+
+class _TypicalHostEscapeVelocityMeta(BaseModel):
+    v_esc: NonNegativeFloat  # km s^-1
+    short: str
+    latex: str
+
+
+class TypicalHostEscapeVelocity(enum.Enum):
+    """Escape velocity (units: km s^-1)."""
+
+    GLOBULAR_CLUSTER = _TypicalHostEscapeVelocityMeta(v_esc=50.0, short="GC", latex=r"$v_{esc, GC}$")
+    MILKY_WAY = _TypicalHostEscapeVelocityMeta(v_esc=600.0, short="MW", latex=r"$v_{esc, MW}$")
+    NUCLEAR_STAR_CLUSTER = _TypicalHostEscapeVelocityMeta(v_esc=1500.0, short="NSC", latex=r"$v_{esc, NSC}$")
+    ELLIPTICAL_GALAXY = _TypicalHostEscapeVelocityMeta(v_esc=2500.0, short="EG", latex=r"$v_{esc, EG}$")
+
+    @property
+    def v_esc(self) -> float:
+        return self.value.v_esc
+
+    @property
+    def short(self) -> str:
+        return self.value.short
+
+    @property
+    def latex(self) -> str:
+        return self.value.latex
+
+    def compute_p2g(
+        self,
+        df: pd.DataFrame,
+        max_mass: float = 65.0,
+        kf_col: str = "k_f",
+        m1_col: str = "m_1",
+        m2_col: str = "m_2",
+    ) -> float:
+        """Probability of being 2nd-generation under this escape velocity."""
+
+        if df.empty:
+            return 0.0
+
+        mask = (df[kf_col] <= self.v_esc) & (df[m1_col] <= max_mass) & (df[m2_col] <= max_mass)
+        return mask.mean() * 100.0
+
+    @classmethod
+    def latex_to_values(cls) -> dict[str, float]:
+        return {m.latex: m.v_esc for m in cls}
+
+    @classmethod
+    def short_to_values(cls) -> dict[str, float]:
+        return {m.short: m.v_esc for m in cls}

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/data_structures/bayesian/bayes_factor.py

@@ -3,6 +3,8 @@ from typing import TypeAlias
 import numpy as np
 from pydantic import BaseModel, NonNegativeFloat
 
+from archeo.constants.bayesian import ASSUME_PARAMETER_INDEPENDENCE, DEFAULT_BINSIZE_MASS, DEFAULT_BINSIZE_SPIN
+
 
 class BayesFactor(BaseModel, frozen=True):
     """Data class for Bayes factor with bootstrapping samples."""
@@ -33,5 +35,6 @@ class BayesFactorCurveMetadata(BaseModel, frozen=True):
 
     reference_candidate_name: str = "original"
     reference_bayes_factor: NonNegativeFloat = 1.0
-    binsize_spin: float = 0.05
-    binsize_mass: float = 1.0
+    binsize_spin: float = DEFAULT_BINSIZE_SPIN
+    binsize_mass: float = DEFAULT_BINSIZE_MASS
+    assume_parameter_independence: bool = ASSUME_PARAMETER_INDEPENDENCE

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/visualization/base.py

@@ -5,7 +5,7 @@ import matplotlib.pyplot as plt
 import numpy as np
 import pandas as pd
 
-from archeo.constants.physics import EscapeVelocity
+from archeo.constants.physics import TypicalHostEscapeVelocity
 from archeo.data_structures.visualization import Labels, Padding
 from archeo.utils.fs import check_and_create_dir
 from archeo.utils.logger import get_logger
@@ -112,7 +112,7 @@ def add_escape_velocity(ax, v_max: float, y_max: float, log_xscale: bool = False
 
     colors = iter(mcolors.TABLEAU_COLORS.keys())
     # Plot vertical lines and labels (escape velocities)
-    for label, v_esc in EscapeVelocity.to_vlines().items():
+    for label, v_esc in TypicalHostEscapeVelocity.latex_to_values().items():
         # Skip if out of scope
         if v_esc > v_max:
             return

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo/visualization/estimation.py

@@ -8,7 +8,7 @@ import numpy as np
 import pandas as pd
 import seaborn as sns
 
-from archeo.constants.physics import EscapeVelocity
+from archeo.constants.physics import TypicalHostEscapeVelocity
 from archeo.data_structures.visualization import Labels, Padding
 from archeo.utils.logger import get_logger
 from archeo.visualization import base
@@ -363,7 +363,7 @@ def table_estimates(
     data = {
         "": dfs.keys(),
         "Recovery Rate": [df["m_1"].notna().sum() / df.shape[0] for df in dfs.values()],
-        **{f"p2g_{v_esc.short()}": [v_esc.compute_p2g(df) for df in dfs.values()] for v_esc in EscapeVelocity},
+        **{f"p2g_{v_esc.short}": [v_esc.compute_p2g(df) for df in dfs.values()] for v_esc in TypicalHostEscapeVelocity},
     }
 
     for col, name in col_to_names.items():

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: archeo
-Version: 2.0.0.dev5
+Version: 2.0.0.dev7
 Summary: Bayesian framework for inferring natal kick, ancestral masses and spins of black holes.
 Author-email: wyhwong <wyhwong@link.cuhk.edu.hk>
 License-Expression: MIT

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/archeo.egg-info/SOURCES.txt

@@ -20,6 +20,7 @@ archeo/bayesian/importance_sampling/resampler/base.py
 archeo/bayesian/importance_sampling/resampler/generic.py
 archeo/bayesian/importance_sampling/resampler/interface.py
 archeo/constants/__init__.py
+archeo/constants/bayesian.py
 archeo/constants/enum.py
 archeo/constants/physics.py
 archeo/data_structures/__init__.py

{archeo-2.0.0.dev5 → archeo-2.0.0.dev7}/pyproject.toml

@@ -16,7 +16,7 @@ classifiers = [
     "Operating System :: OS Independent"
 ]
 keywords = ["black-holes", "gravitational-waves", "black-hole-archeology"]
-version = "2.0.0.dev5"
+version = "2.0.0.dev7"
 readme = "README.md"
 requires-python = ">=3.11,<3.14"
 dependencies = [

archeo-2.0.0.dev5/archeo/constants/physics.py

@@ -1,70 +0,0 @@
-import enum
-
-import pandas as pd
-
-
-SPEED_OF_LIGHT = 299792.458  # km/s
-
-
-class EscapeVelocity(enum.Enum):
-    """Escape velocity (Unit in km s^-1)"""
-
-    GLOBULAR_CLUSTER = 50.0
-    MILKY_WAY = 600.0
-    NUCLEAR_STAR_CLUSTER = 1500.0
-    ELLIPTICAL_GALAXY = 2500.0
-
-    def label(self) -> str:
-        """Return the escape velocity label"""
-
-        if self is EscapeVelocity.GLOBULAR_CLUSTER:
-            return "$v_{esc, GC}$"
-
-        if self is EscapeVelocity.MILKY_WAY:
-            return "$v_{esc, MW}$"
-
-        if self is EscapeVelocity.NUCLEAR_STAR_CLUSTER:
-            return "$v_{esc, NSC}$"
-
-        if self is EscapeVelocity.ELLIPTICAL_GALAXY:
-            return "$v_{esc, EG}$"
-
-        raise ValueError(f"Unknown escape velocity {self}")
-
-    def short(self) -> str:
-        """Return the short name of the escape velocity"""
-
-        if self is EscapeVelocity.GLOBULAR_CLUSTER:
-            return "GC"
-
-        if self is EscapeVelocity.MILKY_WAY:
-            return "MW"
-
-        if self is EscapeVelocity.NUCLEAR_STAR_CLUSTER:
-            return "NSC"
-
-        if self is EscapeVelocity.ELLIPTICAL_GALAXY:
-            return "EG"
-
-        raise ValueError(f"Unknown escape velocity {self}")
-
-    def compute_p2g(self, df: pd.DataFrame) -> float:
-        """Return the probability of
-        the black hole being a 2nd generation black hole
-        under different escape velocity conditions."""
-
-        if df.empty:
-            return 0.0
-
-        mask = (df["k_f"] <= self.value) & (df["m_1"] <= 65) & (df["m_2"] <= 65)
-        return mask.sum() / len(df) * 100.0
-
-    @classmethod
-    def to_vlines(cls) -> dict[str, float]:
-        """Return a dictionary for vlines plotting
-
-        Returns:
-            vlines (Dict[str, float]): The escape velocity vlines.
-        """
-
-        return {esc_vel.label(): esc_vel.value for esc_vel in cls}