def get_indicators(identifiers, data=None, usagedata=None):
ind = {}
ind_ref = {}
# Get the necessary data if we did not get any
if not data:
data = get_indicator_data(identifiers)
if not usagedata:
usagedata = get_usage_data(identifiers)
# Organize the citations with a running index (the citation
# data is already ordered from most to least cited)
citations = [(i + 1, p.citation_num) for i, p in enumerate(data)]
# First the Hirsch index
ind['h'] = max([x[0] for x in citations if x[1] >= x[0]] or [0])
# Next the g index
ind['g'] = max([i for (c, i) in zip(list(np.cumsum([x[1] for
x in citations], axis=0)), [x[0] for x in citations]) if
i**2 <= c] or [0])
# The number of paper with 10 or more citations (i10)
ind['i10'] = len([x for x in citations if x[1] >= 10])
# The number of paper with 100 or more citations (i100)
ind['i100'] = len([x for x in citations if x[1] >= 100])
# The m index is the g index divided by the range of publication years
yrange = datetime.now().year - \
min([int(p.bibcode[:4]) for p in usagedata]) + 1
ind['m'] = float(ind['h']) / float(yrange)
# The read10 index is calculated from current reads for papers published
# in the last 10 years, normalized by number of authors
year = datetime.now().year
Nentries = year - 1996 + 1
ind['read10'] = sum([float(p.reads[-2]) / float(p.author_num)
for p in usagedata if
int(p.bibcode[:4]) > year - 10 and p.reads and
len(p.reads) == Nentries])
# Now all the values for the refereed publications
citations = [(i + 1, n) for i, n in enumerate([p.citation_num for p in
data if p.refereed])]
# First the Hirsch index
ind_ref['h'] = max([x[0] for x in citations if x[1] >= x[0]] or [0])
# Next the g index
ind_ref['g'] = max([i for (c, i) in zip(list(np.cumsum(
[x[1] for x in citations], axis=0)), [x[0] for x in citations]) if
i**2 <= c] or [0])
# The number of paper with 10 or more citations (i10)
ind_ref['i10'] = len([x for x in citations if x[1] >= 10])
# The number of paper with 100 or more citations (i100)
ind_ref['i100'] = len([x for x in citations if x[1] >= 100])
# The m index is the g index divided by the range of publication years
yrange_ref = datetime.now().year - \
min([int(p.bibcode[:4]) for p in usagedata]) + 1
ind_ref['m'] = float(ind_ref['h']) / float(yrange_ref)
# The read10 index is calculated from current reads for papers published
# in the last 10 years, normalized by number of authors
year = datetime.now().year
Nentries = year - 1996 + 1
ind_ref['read10'] = sum([float(p.reads[-1]) / float(p.author_num)
for p in usagedata if p.refereed and
int(p.bibcode[:4]) > year - 10 and
p.reads and len(p.reads) == Nentries])
# Send results back
return ind, ind_ref
def test_get_usage_data(self):
'''Test getting usage data'''
from models import get_usage_data
data = get_usage_data(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_usage_data(self):
'''Test getting usage data'''
from models import get_usage_data
data = get_usage_data(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_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_indicators(identifiers, data=None, usagedata=None):
ind = {}
ind_ref = {}
# Get the necessary data if we did not get any
if not data:
data = get_indicator_data(identifiers)
if not usagedata:
usagedata = get_usage_data(identifiers)
# Organize the citations with a running index (the citation
# data is already ordered from most to least cited)
citations = [(i + 1, p.citation_num) for i, p in enumerate(data)]
# First the Hirsch index
ind['h'] = max([x[0] for x in citations if x[1] >= x[0]] or [0])
# Next the g index
ind['g'] = max([
i for (c, i) in zip(list(np.cumsum([x[1] for x in citations], axis=0)),
[x[0] for x in citations]) if i**2 <= c
] or [0])
# The number of paper with 10 or more citations (i10)
ind['i10'] = len([x for x in citations if x[1] >= 10])
# The number of paper with 100 or more citations (i100)
ind['i100'] = len([x for x in citations if x[1] >= 100])
# The m index is the g index divided by the range of publication years
yrange = datetime.now().year - \
min([int(p.bibcode[:4]) for p in usagedata]) + 1
ind['m'] = float(ind['h']) / float(yrange)
# The read10 index is calculated from current reads for papers published
# in the last 10 years, normalized by number of authors
year = datetime.now().year
Nentries = year - 1996 + 1
ind['read10'] = sum([
float(p.reads[-2]) / float(p.author_num) for p in usagedata
if int(p.bibcode[:4]) > year -
10 and p.reads and len(p.reads) == Nentries
])
# Now all the values for the refereed publications
citations = [
(i + 1, n)
for i, n in enumerate([p.citation_num for p in data if p.refereed])
]
# First the Hirsch index
ind_ref['h'] = max([x[0] for x in citations if x[1] >= x[0]] or [0])
# Next the g index
ind_ref['g'] = max([
i for (c, i) in zip(list(np.cumsum([x[1] for x in citations], axis=0)),
[x[0] for x in citations]) if i**2 <= c
] or [0])
# The number of paper with 10 or more citations (i10)
ind_ref['i10'] = len([x for x in citations if x[1] >= 10])
# The number of paper with 100 or more citations (i100)
ind_ref['i100'] = len([x for x in citations if x[1] >= 100])
# The m index is the g index divided by the range of publication years
yrange_ref = datetime.now().year - \
min([int(p.bibcode[:4]) for p in usagedata]) + 1
ind_ref['m'] = float(ind_ref['h']) / float(yrange_ref)
# The read10 index is calculated from current reads for papers published
# in the last 10 years, normalized by number of authors
year = datetime.now().year
Nentries = year - 1996 + 1
ind_ref['read10'] = sum([
float(p.reads[-1]) / float(p.author_num) for p in usagedata
if p.refereed and int(p.bibcode[:4]) > year -
10 and p.reads and len(p.reads) == Nentries
])
# Send results back
return ind, ind_ref
def get_usage_histograms(identifiers, usage_type='reads', data=None):
uh = {}
# Get necessary data if nothing was provided
if not data:
data = get_usage_data(identifiers)
# Determine the current year (so that we know how many entries to expect
# in usage lists)
year = datetime.now().year
Nentries = year - 1996 + 1
zeros = [[0] * Nentries]
if usage_type == 'reads':
# Get all reads data and sum up the individual lists
usage_data = [
p.reads for p in data if p.reads and len(p.reads) == Nentries
]
usage = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# and also get the normalized reads
usage_data = [
np.array(p.reads) / float(p.author_num) for p in data
if p.reads and len(p.reads) == Nentries
]
usage_norm = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# Do the same for just the refereed publications
usage_data = [
p.reads for p in data
if p.refereed and p.reads and len(p.reads) == Nentries
]
usage_ref = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# and also get the normalized version
usage_data = [
np.array(p.reads) / float(p.author_num) for p in data
if p.refereed and p.reads and len(p.reads) == Nentries
]
usage_ref_norm = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
else:
usage_type = 'downloads'
# Get all downloads data and sum up the individual lists
usage_data = [
p.downloads for p in data
if p.downloads and len(p.downloads) == Nentries
]
usage = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# and also get the normalized version
usage_data = [
np.array(p.downloads) / float(p.author_num) for p in data
if p.downloads and len(p.downloads) == Nentries
]
usage_norm = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# Do the same for just the refereed publications
usage_data = [
p.downloads for p in data
if p.refereed and p.downloads and len(p.downloads) == Nentries
]
usage_ref = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# and also get the normalized version
usage_data = [
np.array(p.downloads) / float(p.author_num) for p in data
if p.refereed and p.downloads and len(p.downloads) == Nentries
]
usage_ref_norm = [
sum(sublist) for sublist in itertools.izip(*usage_data or zeros)
]
# Construct the histograms (index 0 corresponds with year 1996)
uh['all %s' % usage_type] = dict([(1996 + i, v)
for i, v in enumerate(usage)])
uh['all %s normalized' % usage_type] = dict([
(1996 + i, v) for i, v in enumerate(usage_norm)
])
uh['refereed %s' % usage_type] = dict([(1996 + i, v)
for i, v in enumerate(usage_ref)])
uh['refereed %s normalized' % usage_type] = dict([
(1996 + i, v) for i, v in enumerate(usage_ref_norm)
])
return uh
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_usage_histograms(identifiers, usage_type='reads', data=None):
uh = {}
# Get necessary data if nothing was provided
if not data:
data = get_usage_data(identifiers)
# Determine the current year (so that we know how many entries to expect
# in usage lists)
year = datetime.now().year
Nentries = year - 1996 + 1
zeros = [[0] * Nentries]
if usage_type == 'reads':
# Get all reads data and sum up the individual lists
usage_data = [
p.reads for p in data if p.reads and len(p.reads) == Nentries]
usage = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# and also get the normalized reads
usage_data = [np.array(p.reads) / float(p.author_num)
for p in data if p.reads and len(p.reads) == Nentries]
usage_norm = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# Do the same for just the refereed publications
usage_data = [p.reads for p in data if p.refereed and p.reads and
len(p.reads) == Nentries]
usage_ref = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# and also get the normalized version
usage_data = [np.array(p.reads) / float(p.author_num)
for p in data if p.refereed and p.reads and
len(p.reads) == Nentries]
usage_ref_norm = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
else:
usage_type = 'downloads'
# Get all downloads data and sum up the individual lists
usage_data = [
p.downloads for p in data if p.downloads and
len(p.downloads) == Nentries]
usage = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# and also get the normalized version
usage_data = [np.array(p.downloads) / float(p.author_num)
for p in data if p.downloads and
len(p.downloads) == Nentries]
usage_norm = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# Do the same for just the refereed publications
usage_data = [p.downloads for p in data if p.refereed and
p.downloads and len(p.downloads) == Nentries]
usage_ref = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# and also get the normalized version
usage_data = [np.array(p.downloads) / float(p.author_num)
for p in data if p.refereed and p.downloads and
len(p.downloads) == Nentries]
usage_ref_norm = [sum(sublist)
for sublist in itertools.izip(*usage_data or zeros)]
# Construct the histograms (index 0 corresponds with year 1996)
uh['all %s' % usage_type] = dict(
[(1996 + i, v) for i, v in enumerate(usage)])
uh['all %s normalized' % usage_type] = dict(
[(1996 + i, v) for i, v in enumerate(usage_norm)])
uh['refereed %s' % usage_type] = dict(
[(1996 + i, v) for i, v in enumerate(usage_ref)])
uh['refereed %s normalized' % usage_type] = dict(
[(1996 + i, v) for i, v in enumerate(usage_ref_norm)])
return uh
