def generate_data(cls):
"""
get statistics for a list of values and associated weights:
mean, median, normalized values
"""
cls.pre_process()
#
values = map(lambda a: a[0], cls.data)
weights = map(lambda a: a[1], cls.data)
refereed_values = map(lambda a: a[0], cls.refereed_data)
refereed_weights = map(lambda a: a[1], cls.refereed_data)
# get number of entries
cls.number_of_entries = len(values)
# get number of refereed entries
cls.number_of_refereed_entries = len(refereed_values)
# get normalized value
cls.normalized_value = vector_product(values, weights)
# get refereed normalized value
cls.refereed_normalized_value = vector_product(refereed_values,
refereed_weights)
# get mean value of values
cls.mean_value = mean(values)
# get mean value of refereed values
cls.refereed_mean_value = mean(refereed_values)
# get median value of values
cls.median_value = median(values)
# get median value of refereed values
cls.refereed_median_value = median(refereed_values)
# get total of values
cls.total_value = sum(values)
# get total of refereed values
cls.refereed_total_value = sum(refereed_values)
# record results
cls.post_process()
def generate_data(cls):
"""
get statistics for a list of values and associated weights:
mean, median, normalized values
"""
cls.pre_process()
#
values = map(lambda a: a[0], cls.data)
weights= map(lambda a: a[1], cls.data)
refereed_values = map(lambda a: a[0], cls.refereed_data)
refereed_weights= map(lambda a: a[1], cls.refereed_data)
# get number of entries
cls.number_of_entries = len(values)
# get number of refereed entries
cls.number_of_refereed_entries = len(refereed_values)
# get normalized value
cls.normalized_value = float('%.1f' % round(vector_product(values,weights), 1))
# get refereed normalized value
cls.refereed_normalized_value = float('%.1f' % round(vector_product(refereed_values,refereed_weights), 1))
# get mean value of values
cls.mean_value = float('%.1f' % round(mean(values), 1))
# get mean value of refereed values
cls.refereed_mean_value = float('%.1f' % round(mean(refereed_values), 1))
# get median value of values
cls.median_value = float('%.1f' % round(median(values), 1))
# get median value of refereed values
cls.refereed_median_value = float('%.1f' % round(median(refereed_values), 1))
# get total of values
cls.total_value = sum(values)
# get total of refereed values
cls.refereed_total_value = sum(refereed_values)
# record results
cls.post_process()
def generate_data(cls):
cls.pre_process()
# array with citations, descending order
citations = cls.citations
citations.sort()
citations.reverse()
# first calclate the Hirsch and g indices
rank = 1
N = 0
h = 0
g = 0
for cite in citations:
N += cite
r2 = rank*rank
if r2 <= N:
g = rank
h += min(1, cite/rank)
rank += 1
# the e-index
try:
e = sqrt(sum(citations[:h]) - h*h)
except:
e = 'NA'
# Get the number of self-citations
try:
number_of_self_citations = sum(map(lambda a: a['number_of_self_citations'], cls.metrics_data))
except:
number_of_self_citations = 0
# get the Tori index
rn_citations = map(lambda a: a['rn_citations'], cls.metrics_data)
auth_nums = map(lambda a: 1.0/float(a['author_num']), cls.metrics_data)
tori = vector_product(rn_citations,auth_nums)
try:
read10_reads = map(lambda a: a[7][-2], cls.reads10data)
read10_auths = map(lambda a: 1.0/float(a[4]), cls.reads10data)
read10 = vector_product(read10_reads, read10_auths)
except:
read10 = 0
try:
riq = int(1000.0*sqrt(float(tori))/float(cls.time_span))
except:
riq = "NA"
cls.h_index = h
cls.g_index = g
cls.m_index = float('%.1f' % round(float(h)/float(cls.time_span), 2))
cls.i10_index = len(filter(lambda a: a >= 10, citations))
cls.i100_index= len(filter(lambda a: a >= 100, citations))
cls.e_index = float('%.1f' % round(e,1))
cls.tori = float('%.1f' % round(tori,1))
cls.riq = float('%.1f' % round(riq,1))
cls.read10 = int(round(read10))
cls.number_of_self_citations = number_of_self_citations
cls.post_process()
def generate_data(cls):
"""
Get time series
"""
today = datetime.today()
bibcodes = map(lambda a: a[0], cls.attributes)
years = map(lambda a: int(a[:4]), bibcodes)
minYear = min(years)
maxYear = today.year
cls.series = {}
cls.pre_process()
for year in range(minYear, maxYear+1):
if year < 1996:
read10 = 0
else:
threshold = year - 10
year_index = year - 1996
if year == maxYear:
year_index -= 1
reads10data = filter(lambda a: len(a[7]) > 0 and int(a[0][:4]) > threshold, cls.attributes)
try:
read10_reads = map(lambda a: a[7][year_index], reads10data)
read10_auths = map(lambda a: 1.0/float(a[4]), reads10data)
read10 = vector_product(read10_reads, read10_auths)
except:
read10 = 0
tori = sum([value for d in cls.metrics_data for (yr,value) in d['rn_citations_hist'].items() if int(yr) <= year])
new_list = get_subset(cls.attributes,year)
new_list = sort_list_of_lists(new_list,2)
citations = map(lambda a: a[2], new_list)
# first calclate the Hirsch and g indices
rank = 1
N = 0
h = 0
g = 0
for cite in citations:
N += cite
r2 = rank*rank
if r2 <= N:
g = rank
h += min(1, cite/rank)
rank += 1
TimeSpan = year - minYear + 1
i10 = len(filter(lambda a: a >= 10, citations))
i100= len(filter(lambda a: a >= 100, citations))
m = float(h)/float(TimeSpan)
roq = int(1000.0*math.sqrt(float(tori))/float(TimeSpan))
indices = "%s:%s:%s:%s:%s:%s:%s:%s" % (h,g,i10,tori,m,roq,i100,int(round(read10)*0.1))
cls.series[str(year)] = indices
cls.post_process()
