import pickle
from wikidatasets.processFunctions import get_subclasses, query_wikidata_dump, build_dataset
# change the 4 following values to match your installation
path = '../animals/' # this will contain the files output through the process
dump_path = 'latest-all.json.bz2' # path to the bz2 dump file
n_lines = 56208653 # this can be an upper bound
test_entities = get_subclasses(
'Q16521') # group of one or more organism(s), which a taxonomist
# adjudges to be a unit
query_wikidata_dump(dump_path,
path,
n_lines,
test_entities=test_entities,
collect_labels=False)
labels = pickle.load(open(path + 'labels.pkl', 'rb'))
build_dataset(path, labels)
import pickle
from wikidatasets.processFunctions import get_subclasses, query_wikidata_dump, build_dataset
# change the 4 following values to match your installation
path = '../films/' # this will contain the files output through the process
dump_path = 'latest-all.json.bz2' # path to the bz2 dump file
n_lines = 81933324 # this can be an upper bound
test_entities = get_subclasses(
'Q11424') # sequence of images that give the impression of movement
query_wikidata_dump(dump_path,
path,
n_lines,
test_entities=test_entities,
collect_labels=False)
labels = pickle.load(open(path + 'labels.pkl', 'rb'))
build_dataset(path, labels, dump_date='April 15, 2020')
import pickle
from wikidatasets.processFunctions import get_subclasses, query_wikidata_dump, build_dataset
# change the 4 following values to match your installation
path = '../companies/' # this will contain the files output through the process
dump_path = 'latest-all.json.bz2' # path to the bz2 dump file
n_lines = 56208653 # this can be an upper bound
test_entities = get_subclasses('Q4830453') # organization involved in commercial, industrial, or professional activity
query_wikidata_dump(dump_path, path, n_lines, test_entities=test_entities, collect_labels=False)
labels = pickle.load(open(path + 'labels.pkl', 'rb'))
build_dataset(path, labels)
import pickle
from wikidatasets.processFunctions import get_subclasses, query_wikidata_dump, build_dataset
# change the 4 following values to match your installation
path = '../humans/' # this will contain the files output through the process
dump_path = 'latest-all.json.bz2' # path to the bz2 dump file
n_lines = 81933324 # this can be an upper bound
test_entities = get_subclasses(
'Q5'
) # common name of H**o sapiens, unique extant species of the genus H**o
query_wikidata_dump(dump_path,
path,
n_lines,
test_entities=test_entities,
collect_labels=False)
labels = pickle.load(open(path + 'labels.pkl', 'rb'))
build_dataset(path, labels, dump_date='April 15, 2020')
