Skip to content

added alpha decay parser #3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
afloers wants to merge 1 commit into
base: master
Choose a base branch
from
Open

added alpha decay parser #3

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
70 changes: 35 additions & 35 deletions nuclear/io/nndc/parsers.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,25 +6,24 @@
import numpy as np


def uncertainty_parser(unc_raw_str, split_unc_symbol='%'):
unc_raw_str = unc_raw_str.lower()

value_unc_pair = [item.strip()
for item in unc_raw_str.split(split_unc_symbol)]

if len(value_unc_pair) == 1: # if no uncertainty given
return float(value_unc_pair[0]), np.nan
else:
value, unc = value_unc_pair[:2] # limit to two
if unc == "" or unc == "?": # if uncertainty_str is empty or unknown
unc = np.nan
if "e" in value:
exp_pos = value.find("e")
unc_str = value[:exp_pos] + f"({unc})" + value[exp_pos:]
else:
unc_str = value + f"({unc})"
parsed_uncertainty = ufloat_fromstr(unc_str)
return parsed_uncertainty.nominal_value, parsed_uncertainty.std_dev
def uncertainty_parser(unc_raw_str, split_unc_symbol="%"):
unc_raw_str = unc_raw_str.lower()

value_unc_pair = [item.strip() for item in unc_raw_str.split(split_unc_symbol)]

if len(value_unc_pair) == 1: # if no uncertainty given
return float(value_unc_pair[0]), np.nan
else:
value, unc = value_unc_pair[:2] # limit to two
if unc == "" or unc == "?": # if uncertainty_str is empty or unknown
unc = np.nan
if "e" in value:
exp_pos = value.find("e")
unc_str = value[:exp_pos] + f"({unc})" + value[exp_pos:]
else:
unc_str = value + f"({unc})"
parsed_uncertainty = ufloat_fromstr(unc_str)
return parsed_uncertainty.nominal_value, parsed_uncertainty.std_dev


class BaseParser(metaclass=ABCMeta):
Expand All @@ -40,34 +39,30 @@ def _sanititze_table(self, df):
df.dropna(inplace=True)

if "intensity" in df.columns:
intensity_raw = df["intensity"].apply(
uncertainty_parser)
intensity_raw = df["intensity"].apply(uncertainty_parser)
df.loc[:, "intensity"] = [item[0] for item in intensity_raw]
df.loc[:, "intensity_unc"] = [item[1]
for item in intensity_raw]
df.loc[:, "intensity_unc"] = [item[1] for item in intensity_raw]
if "energy" in df.columns:
energy = df["energy"].apply(
uncertainty_parser, split_unc_symbol=' ')
energy = df["energy"].apply(uncertainty_parser, split_unc_symbol=" ")
df.loc[:, "energy"] = [item[0] for item in energy]
df.loc[:, "energy_unc"] = [item[1] for item in energy]

if "end_point_energy" in df.columns:
end_point_energy = df["end_point_energy"].apply(
uncertainty_parser, split_unc_symbol=' ')
df.loc[:, "end_point_energy"] = [
item[0] for item in end_point_energy]
df.loc[:, "end_point_energy_unc"] = [
item[1] for item in end_point_energy]
uncertainty_parser, split_unc_symbol=" "
)
df.loc[:, "end_point_energy"] = [item[0] for item in end_point_energy]
df.loc[:, "end_point_energy_unc"] = [item[1] for item in end_point_energy]

if "dose" in df.columns:
del df["dose"]
df['heading'] = self.html_name
df["heading"] = self.html_name
return df

def _default_parse(self, html_table):
df = self._convert_html_to_df(html_table, self.columns)
df = self._sanititze_table(df)
df['type'] = self.type
df["type"] = self.type
return df

def parse(self, html_table):
Expand All @@ -80,7 +75,6 @@ class ElectronTableParser(BaseParser):
columns = ["type", "energy", "intensity", "dose"]



class BetaPlusTableParser(BaseParser):
html_name = "Beta+"
type = "e+"
Expand All @@ -93,6 +87,12 @@ class BetaMinusTableParser(BaseParser):
columns = ["energy", "end_point_energy", "intensity", "dose"]


class AlphaTableParser(BaseParser):
html_name = "Alphas"
type = "alpha"
columns = ["energy", "intensity", "dose"]


class XGammaRayParser(BaseParser):
html_name = "Gamma and X-ray radiation"
columns = ["type", "energy", "intensity", "dose"]
Expand All @@ -103,8 +103,8 @@ def parse(self, html_table):

x_ray_mask = df.type.str.startswith("XR")

df['type'] = 'x_rays'
df.loc[~x_ray_mask, 'type'] = 'gamma_rays'
df["type"] = "x_rays"
df.loc[~x_ray_mask, "type"] = "gamma_rays"
return df


Expand Down