def find_cites(author):
"""
Find and return all necessary components for plotting the data set.
Returned values:
1. year_dict: a dictionary keyed by years with values of the citations that occured in that year
2. start_year: an integer that holds the year the first citation occured, used for calculating
points to plot
3. lifetime_cites: an integer holding the total amount of cites the author has in the present
day, used to scale the final data set
This definition first grabs a list of all the papers written by the author. From there,
it iterates through the list, pulling the citations of each paper and incrementing the
appropriate year in the year_dict dictionary for that citations year.
Next, it iterates through the year ditionary to fill in values for missing years, setting them
to zero. It also calculates the lifetime cites during this iteration.
"""
print "# Author:", author
papers = get_realauthor_data(author, 'bibrec_id')
year_dict = {}
lifetime_cites = 0
for paper in papers:
cites = get_cited_by(int(paper[1]))
# print papers[i][1], cites
for cite in cites:
fieldvalues_yearlist = get_fieldvalues(cite, '269__C')
if len(fieldvalues_yearlist) > 0:
year = year_re.search(fieldvalues_yearlist[0])
if year:
if int(year.group()) not in year_dict:
year_dict[int(year.group())] = 1
else:
year_dict[int(year.group())] += 1
# print year.group()
if len(year_dict) > 0:
start_year = min(year_dict.keys())
end_year = max(year_dict.keys())
for i in range(start_year, end_year + 1):
if i not in year_dict:
year_dict[i] = 0
lifetime_cites += year_dict[i]
else:
print "# Author has no citations"
# print year_dict
return year_dict, start_year, float(lifetime_cites)
def find_citesb(author):
"""
This defition plays the same role as the above defition of a similar name. However,
it creates a different dictionary, as this definition is used only when the user
wants to plot citations that occured in the past five years from papers published
in the past five years only.
The year dictionary in rather keyed by year of paper published. The values of the
keys are then another dictionary that holds years as the keys (of citations)
with the values as the number of citations.
Ex: {paper year: {citation year, count}}
All other return values are the same, with the addition of 'end_year', which
is an integer denoting the final year the author had a paper cited.
"""
print "# Author:", author
papers = get_realauthor_data(author, 'bibrec_id')
year_dict = {}
# print papers, "Papers"
# print 'Number of papers:', len(papers)
lifetime_cites = 0
end_year = 0
for paper in papers:
paper_yearlist = get_fieldvalues(int(paper[1]), '269__C')
# print paper_yearlist, "Paper year list"
# print paper[1]
if len(paper_yearlist) > 0:
paper_year_match = year_re.search(paper_yearlist[0])
if paper_year_match:
paper_year = int(paper_year_match.group())
# print paper_year
cites = get_cited_by(int(paper[1]))
# print cites
for cite in cites:
fieldvalues_yearlist = get_fieldvalues(cite, '269__C')
if len(fieldvalues_yearlist) > 0:
cite_year_match = year_re.search(fieldvalues_yearlist[0])
if cite_year_match:
cite_year = int(cite_year_match.group())
if cite_year > end_year:
end_year = cite_year
# print "Years:", paper_year, cite_year
if paper_year not in year_dict:
year_dict[paper_year] = {cite_year: 1}
elif cite_year not in year_dict[paper_year]:
year_dict[paper_year][cite_year] = 1
else:
year_dict[paper_year][cite_year] += 1
if len(year_dict) > 0:
start_year = min(year_dict.keys())
for i in year_dict:
for j in year_dict[i]:
lifetime_cites += year_dict[i][j]
else:
print "# Author has no citations"
# print year_dict
return year_dict, start_year, end_year, float(lifetime_cites)