def run_collection(self,
db='pubmed',
field='TIAB',
api_key=None,
logging=None,
directory=None,
verbose=False):
"""Collect co-occurrence data.
Parameters
----------
db : str, optional, default: 'pubmed'
Which database to access from EUtils.
field : str, optional, default: 'TIAB'
Field to search for term in.
Defaults to 'TIAB', which is Title/Abstract.
api_key : str, optional
An API key for a NCBI account.
logging : {None, 'print', 'store', 'file'}, optional
What kind of logging, if any, to do for requested URLs.
directory : str or SCDB object, optional
Folder or database object specifying the save location.
verbose : bool, optional, default: False
Whether to print out updates.
"""
# Run single list of terms against themselves, in 'square' mode
if not self.terms['B'].has_data:
self.square = True
self.counts, self.terms[
'A'].counts, self.meta_data = collect_counts(
terms_a=self.terms['A'].terms,
inclusions_a=self.terms['A'].inclusions,
exclusions_a=self.terms['A'].exclusions,
db=db,
field=field,
api_key=api_key,
logging=logging,
directory=directory,
verbose=verbose)
# Run two different sets of terms
else:
self.square = False
self.counts, term_counts, self.meta_data = collect_counts(
terms_a=self.terms['A'].terms,
inclusions_a=self.terms['A'].inclusions,
exclusions_a=self.terms['A'].exclusions,
terms_b=self.terms['B'].terms,
inclusions_b=self.terms['B'].inclusions,
exclusions_b=self.terms['B'].exclusions,
db=db,
field=field,
api_key=api_key,
logging=logging,
directory=directory,
verbose=verbose)
self.terms['A'].counts, self.terms['B'].counts = term_counts
###################################################################################################
# Import function to collect data, and helper functions to analyze co-occurrence data
from lisc.collect import collect_counts
from lisc.analysis.counts import compute_normalization, compute_association_index
###################################################################################################
# Set some terms to search for
terms_a = [['protein'], ['gene']]
terms_b = [['heart'], ['lung']]
###################################################################################################
# Collect co-occurrence data across a single list of terms
coocs, term_counts, meta_dat = collect_counts(terms_a, db='pubmed', verbose=True)
###################################################################################################
# Check how many articles were found for each combination
print(coocs)
###################################################################################################
# Print out how many articles found for each term
for term, count in zip(terms_a, term_counts):
print('{:12} : {}'.format(term[0], count))
###################################################################################################
#
# When given a single set of terms, the function collects counts of each term
# Import function to collect data, and helper functions to analyze co-occurrence data
import lisc
from lisc.collect import collect_counts
from lisc.analysis.counts import compute_normalization, compute_association_index
# Set some terms to search for
terms_a = [['Salmonella enterica'], ['Escherichia coli'],['Sus scrofa'],['H**o sapiens'],['Mus musculus']]
# Collect 'counts' (co-occurrence data) - across a single list of terms
coocs, term_counts, meta_dat = collect_counts(terms_a, db='nucleotide', verbose=True)
# Check how many articles were found for each combination
print(coocs)
# Print out how many articles found for each term
for term, count in zip(terms_a, term_counts):
print('{:12} : {}'.format(term[0], count))
def run_collection(self,
db='pubmed',
field='TIAB',
api_key=None,
logging=None,
directory=None,
verbose=False,
**eutils_kwargs):
"""Collect co-occurrence data.
Parameters
----------
db : str, optional, default: 'pubmed'
Which database to access from EUtils.
field : str, optional, default: 'TIAB'
Field to search for term in.
Defaults to 'TIAB', which is Title/Abstract.
api_key : str, optional
An API key for a NCBI account.
logging : {None, 'print', 'store', 'file'}, optional
What kind of logging, if any, to do for requested URLs.
directory : str or SCDB, optional
Folder or database object specifying the save location.
verbose : bool, optional, default: False
Whether to print out updates.
**eutils_kwargs
Additional settings for the EUtils API.
Examples
--------
Collect co-occurrence data from added terms, across one set of terms:
>>> counts = Counts()
>>> counts.add_terms(['frontal lobe', 'temporal lobe', 'parietal lobe', 'occipital lobe'])
>>> counts.run_collection() # doctest: +SKIP
Collect co-occurrence data from added terms, across two sets of terms:
>>> counts = Counts()
>>> counts.add_terms(['frontal lobe', 'temporal lobe', 'parietal lobe', 'occipital lobe'])
>>> counts.add_terms(['attention', 'perception', 'cognition'], dim='B')
>>> counts.run_collection() # doctest: +SKIP
"""
# Run single list of terms against themselves, in 'square' mode
if not self.terms['B'].has_terms:
self.square = True
self.counts, self.terms[
'A'].counts, self.meta_data = collect_counts(
terms_a=self.terms['A'].terms,
inclusions_a=self.terms['A'].inclusions,
exclusions_a=self.terms['A'].exclusions,
labels_a=self.terms['A'].labels,
db=db,
field=field,
api_key=api_key,
logging=logging,
directory=directory,
verbose=verbose,
**eutils_kwargs)
# Run two different sets of terms
else:
self.square = False
self.counts, term_counts, self.meta_data = collect_counts(
terms_a=self.terms['A'].terms,
inclusions_a=self.terms['A'].inclusions,
exclusions_a=self.terms['A'].exclusions,
labels_a=self.terms['A'].labels,
terms_b=self.terms['B'].terms,
inclusions_b=self.terms['B'].inclusions,
exclusions_b=self.terms['B'].exclusions,
labels_b=self.terms['B'].labels,
db=db,
field=field,
api_key=api_key,
logging=logging,
directory=directory,
verbose=verbose,
**eutils_kwargs)
self.terms['A'].counts, self.terms['B'].counts = term_counts