def __init__(self, term_data, exclusions=[]):
"""Initialize ArticlesAll object.
Parameters
----------
term_data : Articles object
Data for all articles from a given search term.
exclusions : list of str
Words to exclude from the word collections.
"""
# Inherit from the BaseArticles object
BaseArticles.__init__(self, term_data.term)
# Copy over tracking of included IDs & DOIs
self.ids = term_data.ids
self.dois = term_data.dois
# Get counts of authors, journals, years
self.journals = count_elements([journal[0] for journal in term_data.journals])
self.years = count_elements(term_data.years)
self.authors = _count_authors(term_data.authors)
self.first_authors, self.last_authors = _count_end_authors(term_data.authors)
# Convert lists of all words to frequency distributions
exclusions = exclusions + self.term.search + self.term.inclusions
temp_words = [convert_string(words) for words in term_data.words]
self.words = self.create_freq_dist(combine_lists(temp_words), exclusions)
self.keywords = self.create_freq_dist(combine_lists(term_data.keywords), exclusions)
# Initialize summary dictionary
self.summary = dict()
def _count_end_authors(authors):
"""Count first and last authors only.
Parameters
----------
authors : list of list of tuple of (str, str, str, str)
Authors, as (last name, first name, initials, affiliation).
Returns
-------
first_counts, last_counts : collections.Counter
Number of publications for each first and last author.
"""
# Pull out the full name for the first & last author of each article
# Last author is only considered if there is more than 1 author
firsts = [auth[0] for auth in authors]
f_names = [(author[0], author[2]) for author in firsts]
lasts = [auth[-1] for auth in authors if len(auth) > 1]
l_names = [(author[0], author[2]) for author in lasts]
f_counts = count_elements(_fix_author_names(f_names))
l_counts = count_elements(_fix_author_names(l_names))
return f_counts, l_counts
def __init__(self, term_data, exclusions=None):
"""Initialize ArticlesAll object.
Parameters
----------
term_data : Articles
Data for all articles from a given search term.
exclusions : list of str, optional
Words to exclude from the word collections.
Examples
--------
Create an ``ArticlesAll`` object from an :class:`~.Articles` object:
>>> from lisc.data import Articles
>>> articles = Articles('frontal lobe')
>>> articles_all = ArticlesAll(articles)
"""
# Inherit from the BaseArticles object
BaseArticles.__init__(self, term_data.term)
# Copy over tracking of included IDs & DOIs
self.ids = term_data.ids
self.dois = term_data.dois
# Get counts of authors, journals, years
self.journals = count_elements(
[journal[0] for journal in term_data.journals])
self.years = count_elements(term_data.years)
self.authors = _count_authors(term_data.authors)
self.first_authors, self.last_authors = _count_end_authors(
term_data.authors)
# Convert lists of all words to frequency distributions
exclusions = exclusions if exclusions else [] + self.term.search + self.term.inclusions
temp_words = [convert_string(words) for words in term_data.words]
self.words = self.create_freq_dist(combine_lists(temp_words),
exclusions)
self.keywords = self.create_freq_dist(
combine_lists(term_data.keywords), exclusions)
# Initialize summary dictionary
self.summary = dict()
def __init__(self, articles, exclusions=None):
"""Initialize ArticlesAll object.
Parameters
----------
articles : Articles
Data for all articles from a given search term.
exclusions : list of str, optional
Words to exclude from the word collections.
Examples
--------
Create an ``ArticlesAll`` object from an :class:`~.Articles` object:
>>> from lisc.data import Articles
>>> articles = Articles('frontal lobe')
>>> articles_all = ArticlesAll(articles)
"""
# Inherit from the BaseArticles object
BaseArticles.__init__(self, articles.term)
# Process the article data
if not articles.processed:
articles = process_articles(articles)
# Set exclusions, copying input list, if given, and adding current search terms
exclusions = list(set((deepcopy(exclusions) if exclusions else []) + \
[articles.term.label] + articles.term.search + articles.term.inclusions))
# Copy over tracking of included IDs & DOIs
self.ids = articles.ids
self.dois = articles.dois
# Get frequency distributions of years, journals, authors
self.years = count_elements(articles.years)
self.journals = count_elements(articles.journals)
self.first_authors = count_elements(\
auth[0] if auth else None for auth in articles.authors)
self.last_authors = count_elements(\
auth[-1] if auth and len(auth) > 1 else None for auth in articles.authors)
self.authors = count_elements(combine_lists(articles.authors))
# Convert lists of all words to frequency distributions
self.words = count_elements(combine_lists(articles.words), exclusions)
self.keywords = count_elements(combine_lists(articles.keywords),
exclusions)
# Initialize summary dictionary
self.summary = dict()
def _count_authors(authors):
"""Count all authors.
Parameters
----------
authors : list of list of tuple of (str, str, str, str)
Authors, as (last name, first name, initials, affiliation).
Returns
-------
author_counts : collections.Counter
Number of publications per author.
"""
# Reduce author fields to pair of tuples (last name, initials) & count # of publications per author
all_authors = [(author[0], author[2]) for art_authors in authors for author in art_authors]
author_counts = count_elements(_fix_author_names(all_authors))
return author_counts