def compute_sleepingbeauty(df, colgroupby, colcountby, show_progress=False):
"""
Calculate the sleeping beauty and awakening time for each group in the DataFrame. See :cite:`ke2015beauty` for details.
The algorithmic implementation for each publication can be found in :py:func:`sleepingbeauty.beauty_coefficient`.
Parameters
----------
df : DataFrame
A DataFrame with the citation information for each Author.
colgroupby : str
The DataFrame column with Author Ids.
colcountby : str
The DataFrame column with Citation counts for each publication.
Returns
-------
DataFrame
DataFrame with 3 columns: colgroupby, 'Beauty' and 'Awakening'
"""
# register our pandas apply with tqdm for a progress bar
tqdm.pandas(desc='Beauty', disable=not show_progress)
newname_dict = zip2dict([str(colcountby), '0', '1'],
[str(colgroupby) + 'Beauty'] * 2 + ['Awakening'])
return df.groupby(colgroupby, sort=False)[colcountby].progress_apply(
beauty_coefficient).to_frame().reset_index().rename(
columns=newname_dict)
def compute_hindex(df, colgroupby, colcountby, show_progress=False):
"""
Calculate the h index for each group in the DataFrame. See :cite:`hirsch2005index` for the definition.
The algorithmic implementation for each author can be found in :py:func:`citationanalysis.author_hindex`.
Parameters
----------
:param df : DataFrame
A DataFrame with the citation information for each Author.
:param colgroupby : str
The DataFrame column with Author Ids.
:param colcountby : str
The DataFrame column with Citation counts for each publication.
Returns
-------
DataFrame
DataFrame with 2 columns: colgroupby, 'Hindex'
"""
# register our pandas apply with tqdm for a progress bar
tqdm.pandas(desc='Hindex', disable=not show_progress)
newname_dict = zip2dict([str(colcountby), '0'],
[str(colgroupby) + 'Hindex'] * 2)
return df.groupby(colgroupby, sort=False)[colcountby].progress_apply(
author_hindex).to_frame().reset_index().rename(columns=newname_dict)
def author_yearly_productivity(self, df=None, colgroupby = 'AuthorId', datecol = 'Year', colcountby = 'PublicationId', show_progress=False):
"""
Calculate the number of publications for each author in each year.
Parameters
----------
:param df : DataFrame, default None, Optional
A DataFrame with the author2publication information. If None then the database 'author2pub_df' is used.
:param colgroupby : str, default 'AuthorId', Optional
The DataFrame column with Author Ids. If None then the database 'AuthorId' is used.
:param datecol : str, default 'Year', Optional
The DataFrame column with Year information. If None then the database 'Year' is used.
:param colcountby : str, default 'PublicationId', Optional
The DataFrame column with Publication Ids. If None then the database 'PublicationId' is used.
Returns
-------
DataFrame
Productivity DataFrame with 3 columns: 'AuthorId', 'Year', 'YearlyProductivity'
"""
if df is None:
df = self.author2pub_df
# we can use show_progress to pass a label for the progress bar
if show_progress:
show_progress='Yearly Productivity'
newname_dict = zip2dict([str(colcountby)+'Count', '0'], ['YearlyProductivity']*2)
return groupby_count(df, [colgroupby, datecol], colcountby, count_unique=True, show_progress=show_progress).rename(columns=newname_dict)
def author_career_length(self, df = None, colgroupby = 'AuthorId', colrange = 'Year', show_progress=False):
"""
Calculate the career length for each author. The career length is the length of time from the first
publication to the last publication.
Parameters
----------
:param df : DataFrame, default None, Optional
A DataFrame with the author2publication information. If None then the database 'author2pub_df' is used.
:param colgroupby : str, default 'AuthorId', Optional
The DataFrame column with Author Ids. If None then the database 'AuthorId' is used.
:param colrange : str, default 'Year', Optional
The DataFrame column with Date information. If None then the database 'Year' is used.
Returns
-------
DataFrame
Productivity DataFrame with 2 columns: 'AuthorId', 'CareerLength'
"""
if df is None:
df = self.author2pub_df
# we can use show_progress to pass a label for the progress bar
if show_progress:
show_progress='Career Length'
newname_dict = zip2dict([str(colrange)+'Range', '0'], ['CareerLength']*2)
return groupby_range(df, colgroupby, colrange, show_progress=show_progress).rename(columns=newname_dict)
def author_productivity(pub2author_df, colgroupby = 'AuthorId', colcountby = 'PublicationId', show_progress=False):
"""
Calculate the total number of publications for each author.
Parameters
----------
pub2author_df : DataFrame, default None, Optional
A DataFrame with the author2publication information.
colgroupby : str, default 'AuthorId', Optional
The DataFrame column with Author Ids. If None then the database 'AuthorId' is used.
colcountby : str, default 'PublicationId', Optional
The DataFrame column with Publication Ids. If None then the database 'PublicationId' is used.
Returns
-------
DataFrame
Productivity DataFrame with 2 columns: 'AuthorId', 'Productivity'
"""
# we can use show_progress to pass a label for the progress bar
if show_progress:
show_progress='Author Productivity'
newname_dict = zip2dict([str(colcountby)+'Count', '0'], ['Productivity']*2)
return groupby_count(pub2author_df, colgroupby, colcountby, count_unique=True, show_progress=show_progress).rename(columns=newname_dict)
def author_top_field(pub2author_df, colgroupby = 'AuthorId', colcountby = 'FieldId', fractional_field_counts = False, show_progress=False):
"""
Calculate the most frequent field in the authors career.
Parameters
----------
pub2author_df : DataFrame
A DataFrame with the author2publication field information.
colgroupby : str, default 'AuthorId'
The DataFrame column with Author Ids. If None then the database 'AuthorId' is used.
colcountby : str, default 'FieldId'
The DataFrame column with Citation counts for each publication. If None then the database 'FieldId' is used.
fractional_field_counts : bool, default False
How to count publications that are assigned to multiple fields:
- If False, each publication-field assignment is counted once.
- If True, each publication is counted once, contributing 1/#fields to each field.
Returns
-------
DataFrame
DataFrame with 2 columns: 'AuthorId', 'TopFieldId'
"""
check4columns(pub2author_df, [colgroupby, 'PublicationId', colcountby])
# register our pandas apply with tqdm for a progress bar
tqdm.pandas(desc='Author Top Field', disable= not show_progress)
if not fractional_field_counts:
author2field = pub2author_df.groupby(colgroupby)[colcountby].progress_apply(lambda x: x.mode()[0])
else:
# first calculate how many fields each publication maps too
pub2nfields = groupby_count(pub2author_df, colgroupby='PublicationId', colcountby=colcountby)
# each pub2field mapping is weighted by the number of fields for the publication
pub2nfields['PublicationWeight'] = 1.0/pub2nfields['PublicationIdCount']
del pub2nfields[str(colcountby)+'Count']
# merge counts
author2field = pub2author_df.merge(pub2nfields, how='left', on='PublicationId')
# custom weighted mode based on
def weighted_mode(adf):
p = adf.groupby(colcountby)['PublicationWeight'].sum()
return p.idxmax()
# now take the weighted mode for each groupby column
author2field = author2field.groupby(colgroupby).progress_apply(weighted_mode)
newname_dict = zip2dict([str(colcountby), '0'], ['Top' + str(colcountby)]*2)
return author2field.to_frame().reset_index().rename(columns=newname_dict)
def yearly_productivity_traj(df,
colgroupby='AuthorId',
colx='Year',
coly='YearlyProductivity'):
"""
Calculate the piecewise linear yearly productivity trajectory original studied in :cite:`way2017misleading`.
"""
newname_dict = zip2dict(list(
range(4)), ['t_break', 'b', 'm1', 'm2']) #[str(i) for i in range(4)]
return df.groupby(colgroupby, sort=False).apply(
_fit_piecewise_lineardf,
args=(colx, coly)).reset_index().rename(columns=newname_dict)
def compute_yearly_productivity_traj(df,
colgroupby='AuthorId',
colx='Year',
coly='YearlyProductivity'):
"""
This function calculates the piecewise linear yearly productivity trajectory original studied in [w].
References
----------
.. [w] Way, Larremore (2018): "title", *PNAS*.
DOI: xxx
"""
newname_dict = zip2dict(list(
range(4)), ['t_break', 'b', 'm1', 'm2']) #[str(i) for i in range(4)]
return df.groupby(colgroupby, sort=False).apply(
_fit_piecewise_lineardf,
args=(colx, coly)).reset_index().rename(columns=newname_dict)
def longterm_impact(pub2ref_df, colgroupby = 'CitedPublicationId', coldate='CitingYear', show_progress=True):
"""
This function calculates the longterm scientific impact as introduced in :cite:`Wang2013longterm`.
Following equation (3) from [w]:
c_(t) = m * (e^{lam * PHI()})
"""
pub2ref_df = pub2ref_df.copy()
if 'Year' in coldate:
pub2ref_df['DateDelta'] = pub2ref_df.groupby(colgroupby, sort=False)[coldate].transform(lambda x: x-x.min())
elif 'Date' in coldate:
pub2ref_df['DateDelta'] = pub2ref_df.groupby(colgroupby, sort=False)[coldate].transform(lambda x: x-x.min()) / np.timedelta64(1,'D')
else:
print("Column Date Error")
pub2ref_df = pub2ref_df.loc[pub2ref_df['DateDelta'] > 0]
pub2ref_df.sort_values(by=['DateDelta'], inplace=True)
newname_dict = zip2dict(list(range(4)), ['lam', 'mu', 'sig', 'm' ])
return pub2ref_df.groupby(colgroupby, sort=False).apply(_fit_predicted_citations).reset_index().rename(columns = newname_dict)
def author_endyear(pub2author_df = None, colgroupby = 'AuthorId', datecol = 'Year', show_progress=False):
"""
Calculate the year of last publication for each author.
Parameters
----------
pub2author_df : DataFrame, default None, Optional
A DataFrame with the author2publication information.
colgroupby : str, default 'AuthorId', Optional
The DataFrame column with Author Ids. If None then the database 'AuthorId' is used.
datecol : str, default 'Year', Optional
The DataFrame column with Date information. If None then the database 'Year' is used.
Returns
-------
DataFrame
Productivity DataFrame with 2 columns: 'AuthorId', 'CareerLength'
"""
newname_dict = zip2dict([str(datecol), '0'], ['EndYear']*2)
return pub2author_df.groupby(colgroupby)[datecol].max().to_frame().reset_index().rename(columns=newname_dict)