def get_citation_histograms(identifiers, data=None):
ch = {}
current_year = datetime.now().year
# Get necessary data if nothing was provided
if not data:
data = get_citations(identifiers)
if len(data) == 0:
data = get_citations(identifiers, no_zero=False)
years = [int(p.bibcode[:4]) for p in data]
# First gather all necessary data
# refereed -> refereed
rr_data = [([int(c[:4]) for c in p.refereed_citations],
1.0 / float(p.author_num)) for p in data if p.refereed]
# refereed -> non-refereed
rn_data = [([int(c[:4]) for c in p.citations if c in p.refereed_citations],
1.0 / float(p.author_num)) for p in data if not p.refereed]
# non-refereed -> refereed
nr_data = [([int(c[:4]) for c in list(set(p.citations).difference(
set(p.refereed_citations)))], 1.0 / float(p.author_num)) for
p in data if p.refereed]
# non-refereed -> non-refereed
nn_data = [([int(c[:4]) for c in p.citations if
c not in p.refereed_citations],
1.0 / float(p.author_num)) for p in data if not p.refereed]
# First construct the regular histograms
rr_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in rr_data])))
rn_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in rn_data])))
nr_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in nr_data])))
nn_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in nn_data])))
# Get the earliest citation
try:
min_year = min(
rr_hist.keys() + rn_hist.keys() + nr_hist.keys() + nn_hist.keys())
nullhist = [(y, 0) for y in range(min_year, current_year + 1)]
except:
nullhist = [(y, 0) for y in range(min(years), current_year + 1)]
# Now create the histograms with zeroes for year without values
ch['refereed to refereed'] = merge_dictionaries(dict(nullhist), rr_hist)
ch['refereed to nonrefereed'] = merge_dictionaries(dict(nullhist), rn_hist)
ch['nonrefereed to refereed'] = merge_dictionaries(dict(nullhist), nr_hist)
ch['nonrefereed to nonrefereed'] = merge_dictionaries(
dict(nullhist), nn_hist)
min_year = min(ch['refereed to refereed'].keys() +
ch['refereed to nonrefereed'].keys() +
ch['nonrefereed to refereed'].keys() +
ch['nonrefereed to nonrefereed'].keys())
nullhist = [(y, 0) for y in range(min_year, current_year + 1)]
# Normalized histograms need a different approach
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in rr_data]))
ch['refereed to refereed normalized'] = get_norm_histo(nullhist + tmp)
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in rn_data]))
ch['refereed to nonrefereed normalized'] = get_norm_histo(nullhist + tmp)
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in nr_data]))
ch['nonrefereed to refereed normalized'] = get_norm_histo(nullhist + tmp)
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in nn_data]))
ch['nonrefereed to nonrefereed normalized'] = get_norm_histo(
nullhist + tmp)
return ch
def test_get_citations(self):
'''Test getting citations'''
from models import get_citations
data = get_citations(testset)
# The most important thing here is to test that it is a list
# of MetricsModel instances
self.assertEqual(isinstance(data, list), True)
self.assertTrue(False not in
[x.__class__.__name__ == 'MetricsModel' for x in data])
def test_get_citations(self):
'''Test getting citations'''
from models import get_citations
data = get_citations(testset)
# The most important thing here is to test that it is a list
# of MetricsModel instances
self.assertEqual(isinstance(data, list), True)
self.assertTrue(
False not in [x.__class__.__name__ == 'MetricsModel' for
x in data])
def get_selfcitations(identifiers, bibcodes):
data = get_citations(identifiers)
# record the actual self-citations so that we can use that
# information later on in the calculation of the Tori
try:
selfcits = [(set(p.citations).intersection(set(bibcodes)), p.refereed)
for p in data]
except:
selfcits = [([], False)]
Nself = sum([len(c[0]) for c in selfcits])
Nself_refereed = sum([len(c[0]) * c[1] for c in selfcits])
Nciting = len(set(itertools.chain(*[p.citations for p in data])))
Nciting_ref = len(
set(itertools.chain(*[p.citations for p in data if p.refereed])))
return data, selfcits, Nself, Nself_refereed, Nciting, Nciting_ref
def get_selfcitations(identifiers, bibcodes):
data = get_citations(identifiers)
# record the actual self-citations so that we can use that
# information later on in the calculation of the Tori
try:
selfcits = [
(set(p.citations).intersection(set(bibcodes)), p.refereed)
for p in data]
except:
selfcits = [([], False)]
Nself = sum([len(c[0]) for c in selfcits])
Nself_refereed = sum([len(c[0]) * c[1] for c in selfcits])
Nciting = len(set(itertools.chain(*[p.citations for p in data])))
Nciting_ref = len(
set(itertools.chain(*[p.citations for p in data if p.refereed])))
return data, selfcits, Nself, Nself_refereed, Nciting, Nciting_ref
def get_time_series(identifiers,
bibcodes,
data=None,
usagedata=None,
tori_data=None,
include_tori=True,
self_cits=None):
series = {}
i10 = {}
i100 = {}
h = {}
g = {}
r10 = {}
tori = {}
# Get data if nothing was supplied
if not data:
data = get_citations(identifiers)
if not usagedata:
usagedata = get_usage_data(identifiers)
if not self_cits and include_tori:
self_cits = get_selfcitations(identifiers, bibcodes)[1]
self_citations = set((itertools.chain(*[x[0] for x in self_cits])))
if not tori_data and include_tori:
tdata = get_tori_data(identifiers)
tori_data = [
p for p in list(
itertools.chain(
*[p.rn_citation_data for p in tdata
if p.rn_citation_data]))
if p['bibcode'] not in self_citations and 'pubyear' in p
]
# Determine the year range
Nentries = datetime.now().year - 1996 + 1
years = [int(b[:4]) for b in bibcodes]
yrange = range(min(years), datetime.now().year + 1)
d0 = date(datetime.now().year, 1, 1)
d1 = date(datetime.now().year, datetime.now().month, datetime.now().day)
d2 = date(datetime.now().year, 12, 31)
delta = (d1 - d0).days + 1
ndays = (d2 - d0).days + 1
try:
r10_corr = float(ndays) / float(delta)
except:
r10_corr = 1.0
for year in yrange:
biblist = [b for b in bibcodes if int(b[:4]) <= year]
citations = sorted([
len([int(c[:4]) for c in p.citations if int(c[:4]) <= year])
for p in data if p.bibcode in biblist
],
reverse=True)
if year < 1996:
r10[year] = 0.0
else:
idx = year - 1996
r10[year] = sum([
float(p.reads[idx]) / float(p.author_num) for p in usagedata
if p.bibcode in biblist and int(p.bibcode[:4]) > year -
10 and p.reads and len(p.reads) == Nentries
])
try:
h[year] = max([i for i, n in enumerate(citations) if i <= n])
g[year] = max([
i for i, n in enumerate(np.cumsum(citations, axis=0))
if i**2 <= n
])
except:
h[year] = 0
g[year] = 0
i10[year] = len([c for c in citations if c >= 10])
i100[year] = len([c for c in citations if c >= 100])
if include_tori:
tori[year] = np.sum(
np.array([
r['auth_norm'] * r['ref_norm'] for r in tori_data
if r['pubyear'] <= year and r['cityear'] <= year
]))
r10[datetime.now().year] = r10[datetime.now().year] * r10_corr
series['i10'] = i10
series['i100'] = i100
series['h'] = h
series['g'] = g
series['read10'] = r10
if include_tori:
series['tori'] = tori
return series
def get_citation_histograms(identifiers, data=None):
ch = {}
current_year = datetime.now().year
# Get necessary data if nothing was provided
if not data:
data = get_citations(identifiers)
if len(data) == 0:
data = get_citations(identifiers, no_zero=False)
years = [int(p.bibcode[:4]) for p in data]
# First gather all necessary data
# refereed -> refereed
rr_data = [([int(c[:4])
for c in p.refereed_citations], 1.0 / float(p.author_num))
for p in data if p.refereed]
# refereed -> non-refereed
rn_data = [([int(c[:4]) for c in p.citations
if c in p.refereed_citations], 1.0 / float(p.author_num))
for p in data if not p.refereed]
# non-refereed -> refereed
nr_data = [([
int(c[:4])
for c in list(set(p.citations).difference(set(p.refereed_citations)))
], 1.0 / float(p.author_num)) for p in data if p.refereed]
# non-refereed -> non-refereed
nn_data = [
([int(c[:4]) for c in p.citations
if c not in p.refereed_citations], 1.0 / float(p.author_num))
for p in data if not p.refereed
]
# First construct the regular histograms
rr_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in rr_data])))
rn_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in rn_data])))
nr_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in nr_data])))
nn_hist = cy.frequencies(list(itertools.chain(*[d[0] for d in nn_data])))
# Get the earliest citation
try:
min_year = min(rr_hist.keys() + rn_hist.keys() + nr_hist.keys() +
nn_hist.keys())
nullhist = [(y, 0) for y in range(min_year, current_year + 1)]
except:
nullhist = [(y, 0) for y in range(min(years), current_year + 1)]
# Now create the histograms with zeroes for year without values
ch['refereed to refereed'] = merge_dictionaries(dict(nullhist), rr_hist)
ch['refereed to nonrefereed'] = merge_dictionaries(dict(nullhist), rn_hist)
ch['nonrefereed to refereed'] = merge_dictionaries(dict(nullhist), nr_hist)
ch['nonrefereed to nonrefereed'] = merge_dictionaries(
dict(nullhist), nn_hist)
min_year = min(ch['refereed to refereed'].keys() +
ch['refereed to nonrefereed'].keys() +
ch['nonrefereed to refereed'].keys() +
ch['nonrefereed to nonrefereed'].keys())
nullhist = [(y, 0) for y in range(min_year, current_year + 1)]
# Normalized histograms need a different approach
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in rr_data]))
ch['refereed to refereed normalized'] = get_norm_histo(nullhist + tmp)
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in rn_data]))
ch['refereed to nonrefereed normalized'] = get_norm_histo(nullhist + tmp)
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in nr_data]))
ch['nonrefereed to refereed normalized'] = get_norm_histo(nullhist + tmp)
tmp = list(itertools.chain(*[[(d, x[1]) for d in x[0]] for x in nn_data]))
ch['nonrefereed to nonrefereed normalized'] = get_norm_histo(nullhist +
tmp)
return ch
def get_time_series(identifiers, bibcodes, data=None, usagedata=None,
tori_data=None, include_tori=True, self_cits=None):
series = {}
i10 = {}
i100 = {}
h = {}
g = {}
r10 = {}
tori = {}
# Get data if nothing was supplied
if not data:
data = get_citations(identifiers)
if not usagedata:
usagedata = get_usage_data(identifiers)
if not self_cits and include_tori:
self_cits = get_selfcitations(identifiers, bibcodes)[1]
self_citations = set((itertools.chain(*[x[0] for x in self_cits])))
if not tori_data and include_tori:
tdata = get_tori_data(identifiers)
tori_data = [p for p in list(itertools.chain(
*[p.rn_citation_data for p in tdata if p.rn_citation_data])) if
p['bibcode'] not in self_citations and 'pubyear' in p]
# Determine the year range
Nentries = datetime.now().year - 1996 + 1
years = [int(b[:4]) for b in bibcodes]
yrange = range(min(years), datetime.now().year + 1)
d0 = date(datetime.now().year, 1, 1)
d1 = date(datetime.now().year, datetime.now().month, datetime.now().day)
d2 = date(datetime.now().year, 12, 31)
delta = (d1 - d0).days + 1
ndays = (d2 - d0).days + 1
try:
r10_corr = float(ndays)/float(delta)
except:
r10_corr = 1.0
for year in yrange:
biblist = [b for b in bibcodes if int(b[:4]) <= year]
citations = sorted([len([int(c[:4]) for c in p.citations if int(
c[:4]) <= year]) for p in data if
p.bibcode in biblist], reverse=True)
if year < 1996:
r10[year] = 0.0
else:
idx = year - 1996
r10[year] = sum([float(p.reads[idx]) / float(p.author_num) for
p in usagedata if p.bibcode in biblist and int(
p.bibcode[:4]) > year - 10 and p.reads and
len(p.reads) == Nentries])
try:
h[year] = max([i for i, n in enumerate(citations) if i <= n])
g[year] = max(
[i for i, n in enumerate(np.cumsum(citations, axis=0)) if
i**2 <= n])
except:
h[year] = 0
g[year] = 0
i10[year] = len([c for c in citations if c >= 10])
i100[year] = len([c for c in citations if c >= 100])
if include_tori:
tori[year] = np.sum(np.array([r['auth_norm'] * r['ref_norm'] for
r in tori_data if
r['pubyear'] <= year and
r['cityear'] <= year]))
r10[datetime.now().year] = r10[datetime.now().year] * r10_corr
series['i10'] = i10
series['i100'] = i100
series['h'] = h
series['g'] = g
series['read10'] = r10
if include_tori:
series['tori'] = tori
return series
