def getFiles(args):
tmpRC = metaknowledge.RecordCollection(name = '')
if len(args.files) > 0:
for f in args.files:
path = os.path.abspath(os.path.expanduser(f))
if os.path.exists(path):
tmpRC |= metaknowledge.RecordCollection(path, extension = args.suffix)
else:
raise TypeError(path + " is not an existing file or directory")
if args.name:
tmpRC._repr = args.name
else:
FileNames = [os.path.basename(nm) for nm in args.files]
if len(FileNames) == 1:
tmpRC._repr = "WOS files from: {}".format(FileNames[0])
else:
tmpRC._repr = "WOS files from: {0} and {1}".format(', '.join(FileNames[:-1]), FileNames[-1])
return tmpRC
else:
nflist = input("What files or directorys do you want to extract a network from: ")
paths = [os.path.abspath(os.path.expanduser(f)) for f in nflist.split(' ')]
badPaths = [f for f in paths if not os.path.exists(f)]
if len(badPaths) > 1:
print(', '.join(badPaths[:-1]) + " and " + badPaths[-1] + " are not existing files or directorys")
args.files = []
return getFiles(args)
elif len(badPaths) == 1:
print(badPaths[0] + " is not an existing file or directory")
args.files = []
return getFiles(args)
else:
args.files = paths
return getFiles(args)
def test_directoryRead(self):
self.assertEqual(len(metaknowledge.RecordCollection('.')), 0)
self.assertTrue(
metaknowledge.RecordCollection('metaknowledge/tests/') >= self.RC)
self.assertTrue(
metaknowledge.RecordCollection('metaknowledge/tests/',
extension='.txt') <= self.RC)
def test_bad(self):
self.assertTrue(
metaknowledge.RecordCollection(
'metaknowledge/tests/badFile.isi').bad)
with self.assertRaises(metaknowledge.mkExceptions.RCTypeError):
metaknowledge.RecordCollection('metaknowledge/tests/testFile.isi',
extension='.txt')
self.assertEqual(self.RCbad | self.RC, self.RCbad | self.RC)
self.assertEqual(len(self.RCbad | self.RCbad), 32)
self.assertFalse(self.RCbad == self.RC)
self.assertEqual('metaknowledge/tests/badFile.isi',
self.RCbad.errors.keys().__iter__().__next__())
def test_caching(self):
RC = metaknowledge.RecordCollection("metaknowledge/tests/",
cached=True,
name='testingCache',
extension='testFile.isi')
self.assertTrue(
os.path.isfile(
"metaknowledge/tests/tests.[testFile.isi].mkRecordDirCache"))
accessTime = os.stat("metaknowledge/tests/testFile.isi").st_atime
RC2 = metaknowledge.RecordCollection("metaknowledge/tests/",
cached=True,
name='testingCache',
extension='testFile.isi')
self.assertEqual(accessTime,
os.stat("metaknowledge/tests/testFile.isi").st_atime)
RC.dropBadEntries()
RC2.dropBadEntries()
self.assertEqual(RC, RC2)
os.remove("metaknowledge/tests/tests.[testFile.isi].mkRecordDirCache")
def test_write(self):
fileName = 'OnePaper2.isi'
RC = metaknowledge.RecordCollection('metaknowledge/tests/' + fileName)
RC.writeFile(fileName + '.tmp')
RC.writeFile()
self.assertTrue(
filecmp.cmp('metaknowledge/tests/' + fileName, fileName + '.tmp'))
self.assertTrue(
filecmp.cmp('metaknowledge/tests/' + fileName, RC.name + '.txt'))
os.remove(fileName + '.tmp')
os.remove(RC.name + '.txt')
def test_addRec(self):
l = len(self.RC)
R = self.RC.pop()
self.assertEqual(len(self.RC), l - 1)
self.RC.add(R)
self.assertEqual(len(self.RC), l)
RC2 = metaknowledge.RecordCollection(
"metaknowledge/tests/TwoPaper.isi")
self.RC |= RC2
self.assertEqual(len(self.RC), l + 2)
with self.assertRaises(metaknowledge.CollectionTypeError):
self.RC.add(1)
def test_newOps(self):
l = len(self.RC)
for i in range(10):
self.RCbad.pop()
lb = len(self.RCbad)
RC = metaknowledge.RecordCollection([])
RC.bad = True
RC3 = self.RC | RC
self.assertEqual(self.RC, RC3)
RC4 = RC3 - self.RC
self.assertNotEqual(self.RC, RC4)
RC5 = RC4 ^ self.RC
self.assertEqual(self.RC, RC5)
RC6 = RC5 & self.RCbad
self.assertNotEqual(self.RC, RC6)
def test_equOps(self):
l = len(self.RC)
for i in range(10):
self.RCbad.pop()
lb = len(self.RCbad)
RC = metaknowledge.RecordCollection([])
RC.bad = True
RC |= self.RC
self.assertEqual(self.RC, RC)
RC -= self.RC
self.assertNotEqual(self.RC, RC)
RC ^= self.RC
self.assertEqual(self.RC, RC)
RC &= self.RCbad
self.assertNotEqual(self.RC, RC)
def test_citeFilter(self):
RCmin = self.RC.citeFilter('', reverse=True)
RCmax = self.RC.citeFilter('')
RCanon = self.RC.citeFilter('', 'anonymous')
RC1970 = self.RC.citeFilter(1970, 'year')
RCno1970 = self.RC.citeFilter(1970, 'year', reverse=True)
RCMELLER = self.RC.citeFilter('meller', 'author')
self.assertEqual(len(RCmin), 0)
self.assertEqual(len(RCmax), len(self.RC))
self.assertEqual(len(RCanon), 1)
self.assertEqual(len(RC1970), 15)
self.assertEqual(len(RC1970) + len(RCno1970), len(self.RC))
self.assertEqual(len(RCMELLER), 1)
RCnocite = metaknowledge.RecordCollection(
'metaknowledge/tests/OnePaperNoCites.isi')
self.assertEqual(len(RCnocite.citeFilter('')), 0)
def setUpClass(cls):
cls.sysArgs = sys.argv
cls.RCmain = metaknowledge.RecordCollection("metaknowledge/tests/testFile.isi")
cls.Gmain = cls.RCmain.networkCoAuthor()
def setUp(self):
metaknowledge.VERBOSE_MODE = False
self.RC = metaknowledge.RecordCollection(
"metaknowledge/tests/scopus_testing.csv.scopus")
self.R = self.RC.peek()
def test_create(self):
fileName = 'tempTestFile'
named = argparse.Namespace()
named.name = fileName
unnamed = argparse.Namespace()
unnamed.name = None
with unittest.mock.patch('builtins.print'):
with unittest.mock.patch('builtins.input', new_callable = MockInput) as m:
m.calledVals = ['1']
self.assertTrue(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(named, self.RC))
self.assertEqual(len(m.calledVals), 0)
m.calledVals = ['2']
self.RC.dropBadEntries()
self.assertFalse(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(named, self.RC))
self.assertEqual(os.path.getsize(fileName+ '.txt'), 88160)
self.assertEqual(len(m.calledVals), 0)
m.calledVals = ['3', fileName, 'n', fileName, 'g', 'y']
self.RC.dropBadEntries()
self.assertTrue(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(unnamed, self.RC))
self.assertEqual(os.path.getsize(fileName+ '.txt'), 88160)
os.remove(fileName + '.txt')
self.assertEqual(len(m.calledVals), 0)
m.calledVals = ['4']
self.RC.dropBadEntries()
self.assertFalse(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(named, self.RC))
self.assertEqual(os.path.getsize(fileName+ '.csv'), 86330)
os.remove(fileName + '.csv')
self.assertEqual(len(m.calledVals), 0)
m.calledVals = ['6', 'y']
self.RC.dropBadEntries()
self.assertFalse(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(named, self.RC))
self.assertEqual(os.path.getsize(fileName+ '.csv'), 20123)
os.remove(fileName + '.csv')
self.assertEqual(len(m.calledVals), 0)
with self.assertRaises(KeyboardInterrupt):
#Don't want to mess with these too much
m.calledVals = ['7', '', KeyboardInterrupt]
self.assertFalse(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(named, self.RC))
self.assertEqual(len(m.calledVals), 0)
m.calledVals = ['7', '']
self.assertFalse(metaknowledge.bin.metaknowledgeCLI.getWhatToDo(named, metaknowledge.RecordCollection()))
self.assertEqual(len(m.calledVals), 0)
def test_isCollection(self):
self.assertIsInstance(self.RC, metaknowledge.RecordCollection)
self.assertEqual(str(metaknowledge.RecordCollection()),
"RecordCollection(Empty)")
self.assertTrue(self.RC == self.RC)
def setUp(self):
metaknowledge.VERBOSE_MODE = False
self.RC = metaknowledge.RecordCollection(
"metaknowledge/tests/ProQuest_TestFile.testtxt")
self.R = self.RC.peek()
import metaknowledge as mk
RC = mk.RecordCollection('.')
for i, R in enumerate(RC, start=1):
print('Working on Record number: {}'.format(i), end='\r')
with open("imetrics_tm/{}-{}.txt".format(R.id[:3], R.id[4:]), 'w') as f:
f.write(R.get('AB', ''))
print('\nDone')
# of a GNU General Public License as published by the Free Software Foundation. metaknowledged3
# is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even
# the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License along with metaknowledged3.
# If not, see <http://www.gnu.org/licenses/>.
# *********************************************************************************************
import metaknowledge as mk
import pandas
minYear = 1900 # Specify the minimum year you want to consider
maxYear = 2016 # Specify the maximum year you want to consider
years = range(minYear, maxYear + 1)
RC = mk.RecordCollection(
"/Users/filepath") # Create the RecordCollection you want to analyze
# ***************************
# Create the multiRPYS file
# ***************************
dictionary = {
"CPY": [],
"abs_deviation": [],
"num_cites": [],
"rank": [],
"RPY": []
}
for i in years:
try:
RCyear = RC.yearSplit(i, i)
if len(RCyear) > 0:
def setUp(self):
metaknowledge.VERBOSE_MODE = False
self.RC = metaknowledge.RecordCollection(
"metaknowledge/tests/medline_test.medline")
self.R = self.RC.peek()
import metaknowledge as mk
import networkx as nx
import matplotlib.pyplot as plt
import metaknowledge.contour.plotting as mkv
RC = mk.RecordCollection('./tmp/savedrecs.txt')
CoCitation = RC.networkCoCitation()
print(mk.graphStats(CoCitation, makeString=True))
# print(CoCitation.nodes(data = True)[0])
# print(CoCitation.edges(data = True)[0])
coCiteJournals = RC.networkCoCitation(nodeType='journal', dropNonJournals=True)
print(mk.graphStats(coCiteJournals))
nx.draw_spring(coCiteJournals)
def test_contentType(self):
RC = metaknowledge.RecordCollection('metaknowledge/tests/')
self.assertEqual(
RC._collectedTypes,
{'MedlineRecord', 'WOSRecord', 'ProQuestRecord', 'ScopusRecord'})
self.assertEqual(self.RC._collectedTypes, {'WOSRecord'})
from gensim.models import ldamodel
from gensim.models import CoherenceModel
import re
import pyLDAvis
import pyLDAvis.gensim
import matplotlib.pyplot as plt
get_ipython().run_line_magic('matplotlib', 'inline')
import seaborn as sns
from pprint import pprint
import warnings
warnings.filterwarnings("ignore")
# In[ ]:
# Importing the information science and bibliometrics dataset
RC = mk.RecordCollection("../input/mk/raw_data/imetrics/")
len(RC)
# In[ ]:
RC
# The data is currently stored as a RecordCollection object and must be converted into a dataframe if we want to see its contents. We can do this in two ways: with Pandas or with Metaknowledge's makeDict() function.
# In[ ]:
# Saving the dataset as a csv file
RC.writeCSV("records.csv")
# Reading in the data as a Pandas dataframe
data = pd.read_csv("records.csv")
data.head(3)
def test_fullRead(self):
RC = metaknowledge.RecordCollection("metaknowledge/tests/")
self.assertEqual(len(RC), 1032)
def setUp(self):
metaknowledge.VERBOSE_MODE = False
self.RC = metaknowledge.RecordCollection(
"metaknowledge/tests/testFile.isi")
def setUpClass(cls):
cls.RCmain = metaknowledge.RecordCollection(
"metaknowledge/tests/testFile.isi")
cls.Gmain = cls.RCmain.networkCoCitation()
def setUpClass(cls):
metaknowledge.VERBOSE_MODE = False
cls.RCmain = metaknowledge.RecordCollection(
"metaknowledge/tests/testFile.isi")
cls.RCbadmain = metaknowledge.RecordCollection(
"metaknowledge/tests/badFile.isi")
def test_hash(self):
self.assertNotEqual(hash(self.RC), hash(self.RCbad))
R = self.RC.pop()
RC = metaknowledge.RecordCollection([R])
self.assertEqual(hash(RC), hash(hash(R)))
import metaknowledge as mk
import networkx as Nx
import os
os.chdir("/Users/Yanish/Documents/Fall_2015/Integ_475/final/Integ475Final")
RC = mk.RecordCollection("data/")
coAuth = RC.coAuthNetwork()
Net = RC.coCiteNetwork()
Dat = RC.writeCSV(fname="data/dat.csv")
Net = mk.drop_edges(Net, minWeight=3)
Nx.write_graphml(Net, "networks/net.graphml")
