def setUp(self):
data_file = os.path.abspath(
os.path.dirname(__file__) + os.path.sep +
"../../") + '/example/yelp_3000.pkl'
self.localdata = LocalData(data_file, 'pkl', "row['business_id']",
["row['name']"],
["row['name']", "row['full_address']"])
def test_sota_sampler(self):
local_file = os.path.abspath(os.path.dirname(__file__) + os.path.sep + "../../") + '/pkl_example/yelp_3000.pkl'
localdata = LocalData(local_file, 'pkl', "business_id", ["name"], ["name", "full_address"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
sampler.sota_sampler(query_pool=initQueries, api=self.yelp, match_term=localdata.getQueryList(), top_k=300,
adjustment=1, samplenum=1)
self.yelp.getSession().close()
assert True
def setUp(self):
search_term = 'q'
parameters = {'h': 1000}
self.dblp = PublApi(delay=5, search_term=search_term, **parameters)
localdata_file = os.path.abspath(
os.path.dirname(__file__) + os.path.sep +
"../../") + '/example/dblp_10000.pkl'
localdata = LocalData(localdata_file, 'pkl', "row['key']",
["row['title']"], ["row['title']"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
self.initQueries = initQueries
class LocaldataTestCase(unittest.TestCase):
def setUp(self):
data_file = os.path.abspath(os.path.dirname(__file__) + os.path.sep + "../../") + '/yelp_example/yelp_3000_AZ.csv'
self.localdata = LocalData(data_file, 'csv', "business_id", ["name"],
["name", "full_address"])
def tearDown(self):
self.localdata = None
def test_loadLocalData(self):
self.localdata.setlocalData(None, None, None)
self.localdata.read_csv()
localdata_ids, localdata_query, localdata_er = self.localdata.getlocalData()
assert len(localdata_ids) == 3000
def setUp(self):
search_term = 'q'
parameters = {'h': 1000}
self.dblp = PublApi(top_k=1000,
delay=5,
search_term=search_term,
**parameters)
localdata_file = os.path.abspath(
os.path.dirname(__file__) + os.path.sep +
"../../") + '/csv_example/dblp_sample.csv'
localdata = LocalData(localdata_file, 'csv', "key", ["title"],
["title"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
self.initQueries = initQueries
class LocaldataTestCase(unittest.TestCase):
def setUp(self):
data_file = os.path.abspath(
os.path.dirname(__file__) + os.path.sep +
"../../") + '/example/yelp_3000.pkl'
self.localdata = LocalData(data_file, 'pkl', "row['business_id']",
["row['name']"],
["row['name']", "row['full_address']"])
def tearDown(self):
self.localdata = None
def test_loadLocalData(self):
self.localdata.setlocalData(None, None, None)
self.localdata.read_pickle()
localdata_ids, localdata_query, localdata_er = self.localdata.getlocalData(
)
assert len(localdata_ids) == 3000
result_file.csv
match_file.pkl
match_file.csv
enriched_file.pkl
enriched_file.csv
"""
sample_file = 'dblp_sample.csv'
localdata_file = 'dblp_3881.csv'
result_dir = 'dblp_result'
sampledata = SampleData(sample_ratio=0.5,
samplepath=sample_file,
filetype='csv',
uniqueid="key",
querylist=["title"])
localdata = LocalData(localpath=localdata_file,
filetype='csv',
uniqueid="ID",
querylist=['title'],
matchlist=['title'])
hiddendata = HiddenData(result_dir=result_dir,
uniqueid="info.key",
matchlist=["info.title"])
budget = 20
smartcrawl.smartCrawl(budget, dblp, sampledata, localdata, hiddendata)
"""
pool_thre = 2
jaccard_thre = 0.85
threads = 4
smartcrawl.smartCrawl(budget, dblp, sampledata, localdata, hiddendata, pool_thre, jaccard_thre, threads)
"""
yelp = SearchApi(client_id=client_id, client_secret=client_secret, top_k=300, delay=5, search_term=search_term,
**parameters)
"""
\yelp_sample_AZ.pkl
yelp_3000_AZ.csv
yelp_result\\result_file.pkl
result_file.csv
match_file.pkl
match_file.csv
enriched_file.pkl
enriched_file.csv
"""
sample_file = 'yelp_sample_AZ.pkl'
localdata_file = 'yelp_3000_AZ.csv'
result_dir = 'yelp_result'
sampledata = SampleData(sample_ratio=0.5, samplepath=sample_file, filetype='pkl', uniqueid="business_id", querylist=["name"])
localdata = LocalData(localpath=localdata_file, filetype='csv', uniqueid="business_id",
querylist=["name"],
matchlist=["name", "full_address"])
hiddendata = HiddenData(result_dir=result_dir, uniqueid="id",
matchlist=["name", "location.display_address.*"])
budget = 20
smartcrawl.smartCrawl(budget, yelp, sampledata, localdata, hiddendata)
"""
pool_thre = 2
jaccard_thre = 0.85
threads = 4
smartcrawl.smartCrawl(budget, yelp, sampledata, localdata, hiddendata, pool_thre, jaccard_thre, threads)
"""
def setUp(self):
data_file = os.path.abspath(os.path.dirname(__file__) + os.path.sep + "../../") + '/yelp_example/yelp_3000_AZ.csv'
self.localdata = LocalData(data_file, 'csv', "business_id", ["name"],
["name", "full_address"])
from deeperlib.api.yelp.searchapi import SearchApi
from deeperlib.core import utils
from deeperlib.data_processing.local_data import LocalData
from deeperlib.estimator import sampler
# ==== Sota-Sampler Yelp ====
client_id = "kCe2YbZePXsPnC204ZrXoQ"
client_secret = "s9KnvEEQW7jaA2wlrBi4X2fnDQ0F7asdklXVvJUidWp8i50ov24E8EjkHX2AUhoL"
search_term = 'term'
parameters = {'limit': 50, 'location': 'AZ'}
yelp = SearchApi(client_id=client_id,
client_secret=client_secret,
top_k=300,
delay=5,
search_term=search_term,
**parameters)
local_file = 'yelp_3000.pkl'
localdata = LocalData(local_file, 'pkl', "row['business_id']", ["row['name']"],
["row['name']", "row['full_address']"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
sampler.sota_sampler(query_pool=initQueries,
api=yelp,
match_term=localdata.getQueryList(),
top_k=300,
adjustment=1)
yelp.getSession().close()
from deeperlib.api.yelp.searchapi import SearchApi
from deeperlib.core import utils
from deeperlib.data_processing.local_data import LocalData
from deeperlib.estimator import sampler
# ==== Sota-Sampler Yelp ====
client_id = "kCe2YbZePXsPnC204ZrXoQ"
client_secret = "s9KnvEEQW7jaA2wlrBi4X2fnDQ0F7asdklXVvJUidWp8i50ov24E8EjkHX2AUhoL"
search_term = 'term'
parameters = {'limit': 50, 'location': 'AZ'}
yelp = SearchApi(client_id=client_id,
client_secret=client_secret,
top_k=300,
delay=5,
search_term=search_term,
**parameters)
local_file = 'yelp_3000.pkl'
localdata = LocalData(local_file, 'pkl', "business_id", ["name"],
["name", "full_address"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
sampler.sota_sampler(query_pool=initQueries,
api=yelp,
match_term=localdata.getQueryList(),
top_k=300,
adjustment=1)
yelp.getSession().close()
from deeperlib.api.dblp.publapi import PublApi
from deeperlib.core import utils
from deeperlib.data_processing.local_data import LocalData
from deeperlib.estimator import aggregation
# ==== Sota-Estimator Dblp ====
search_term = 'q'
parameters = {'h': 1000}
dblp = PublApi(delay=5, search_term=search_term, **parameters)
localdata_file = 'dblp_10000'
localdata = LocalData(localdata_file, 'pkl', "row['key']", ["row['title']"],
["row['title']"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
aggregation.sota_estimator(query_pool=initQueries,
api=dblp,
match_term=["row['info']['title']"],
uniqueid="row['info']['key']",
query_num=1)
# ==== Stratified-Estimator Dblp ====
dblp = PublApi(delay=5, search_term=search_term, **parameters)
aggregation.stratified_estimator(query_pool=initQueries,
api=dblp,
match_term=["row['info']['title']"],
candidate_rate=0.2,
query_num=100)
dblp.getSession().close()
from deeperlib.api.dblp.publapi import PublApi
from deeperlib.core import utils
from deeperlib.data_processing.local_data import LocalData
from deeperlib.estimator import aggregation
# ==== Sota-Estimator Dblp ====
search_term = 'q'
parameters = {'h': 1000}
dblp = PublApi(top_k=1000, delay=5, search_term=search_term, **parameters)
localdata_file = 'dblp_sample.csv'
localdata = LocalData(localdata_file, 'csv', "key", ["title"], ["title"])
localdata_ids, localdata_query, localdata_er = localdata.getlocalData()
initQueries = utils.queryGene(localdata_query, 2)
aggregation.sota_estimator(query_pool=initQueries,
api=dblp,
match_term=["info.title"],
uniqueid="info.key",
query_num=1)
# ==== Stratified-Estimator Dblp ====
aggregation.stratified_estimator(query_pool=initQueries,
api=dblp,
match_term=["info.title"],
candidate_rate=0.2,
query_num=100)
dblp.getSession().close()
format The result format of the search. Recognized values are "xml", xml ...?q=test&format=json
"json", and "jsonp".
h Maximum number of search results (hits) to return. For bandwidth 30 ...?q=test&h=100
reasons, this number is capped at 1000.
f The first hit in the numbered sequence of search results
(starting with 0) to return. In combination with the h parameter, 0 ...?q=test&h=100&f=300
this parameter can be used for pagination of search results.
c Maximum number of completion terms (see below) to return. For 10 ...?q=test&c=0
bandwidth reasons, this number is capped at 1000.
"""
search_term = 'q'
parameters = {'h': 1000}
dblp = PublApi(delay=5, search_term=search_term, **parameters)
"""
\dblp_sample.pkl
dblp_10000.pkl
dblp_result\\result_file.pkl
result_file.csv
match_file.pkl
match_file.csv
"""
sample_file = 'dblp_sample.pkl'
localdata_file = 'dblp_10000.pkl'
result_dir = 'dblp_result'
sampledata = SampleData(samplepath=sample_file, filetype='pkl', uniqueid="row['key']", querylist=["row['title']"])
localdata = LocalData(localpath=localdata_file, filetype='pkl', uniqueid="row['key']", querylist=["row['title']"],
matchlist=["row['title']"])
hiddendata = HiddenData(result_dir=result_dir, uniqueid="row['info']['key']", matchlist=["row['info']['title']"])
smartcrawl.smartCrawl(top_k, count, pool_thre, jaccard_thre, threads, budget, dblp, sampledata, localdata, hiddendata)
yelp_result\\result_file.pkl
result_file.csv
match_file.pkl
match_file.csv
"""
sample_file = 'yelp_sample.pkl'
localdata_file = 'yelp_3000.pkl'
result_dir = 'yelp_result'
sampledata = SampleData(samplepath=sample_file,
filetype='pkl',
uniqueid="row['id']",
querylist=["row['name']"])
"""
localdata = LocalData(localpath=localdata_file, filetype='pkl', uniqueid="row['business_id']",
querylist=["row['name']"],
matchlist=["row['name']", "row['full_address']"])
hiddendata = HiddenData(result_dir=result_dir, uniqueid="row['id']",
matchlist=["row['name']", "' '.join(row['location']['display_address'])"])
"""
localdata = LocalData(localpath='yelp_5882.csv',
filetype='csv',
uniqueid='ID',
querylist=['NAME'],
matchlist=['NAME', 'ADDRESS'])
hiddendata = HiddenData(
result_dir=result_dir,
uniqueid="row['id']",
matchlist=["row['name']", "' '.join(row['location']['display_address'])"])
smartcrawl.smartCrawl(top_k, count, pool_thre, jaccard_thre, threads, budget,
yelp, sampledata, localdata, hiddendata)