def test_rebuild01(self):
cat = Table.from_csv("Category", self.ds, os.path.join(AVITO_DATA_DIR, "Category.tsv"), delimiter='\t',
usecols=['CategoryID', 'ParentCategoryID', 'Level'], verbose=False)
cat.rebuild({"CategoryID": np.int8, "Level": np.int8, "ParentCategoryID": np.int8})
self.assertEqual(len(cat[:]), 69)
self.assertEqual(cat['CategoryID'].dtype, np.int8)
self.assertEqual(cat[0]['CategoryID'], -128) # int8.min
self.assertEqual(cat[0]['Level'], -128) # int8.min
self.assertEqual(cat[0]['ParentCategoryID'], -128) # int8.min
def test_rebuild02(self):
cat = Table.from_csv("Category", self.ds, os.path.join(AVITO_DATA_DIR, "Category.tsv"), delimiter='\t',
usecols=['CategoryID', 'ParentCategoryID', 'Level'], verbose=False)
cat.rebuild({"CategoryID": np.uint8, "Level": np.uint8, "ParentCategoryID": np.uint8})
def test_from_csv04(self):
cat = Table.from_csv("Category", self.ds, os.path.join(AVITO_DATA_DIR, "Category.tsv"), delimiter='\t',
usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
self.assertEqual(len(cat.ctable), 68)
self.assertEqual(len(cat.columns), 2)
def test_from_csv03(self):
cat = Table.from_csv("Category", self.ds, os.path.join(AVITO_DATA_DIR, "Category.tsv"), verbose=False)
def test_from_csv02(self):
Table.from_csv("Category", self.ds, "/temp/dazzle-test/dataset.json", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
def test_from_csv01(self):
Table.from_csv("Category", self.ds, "/bim/bam/test.csv", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
def load_dataset():
"""'Raw'-dataset is the result of loading the CSV sources data into dazzle tables, only filtering out data
that we don't want to further process.
The method is programmed in a non-destructive way so as to be able to launch it several times
before getting the job done.
"""
import os
from dazzle.core.dataset import DataSet
if DataSet.exists(raw_dir):
ds = DataSet.open(raw_dir)
else:
ds = DataSet(raw_dir, force_create=True)
# Notes:
# - many of the following attributes should be unsigned int instead of signed int, but numexpr works only on
# signed data.
# - Simlarly to pandas, we use the types required to contain the existing data, not the types we desire to use
if ds.get_table("Category") is None:
t = Table.from_csv("Category", ds, os.path.join(csv_dir, "Category.tsv"), delimiter='\t', chunksize=10**7,
usecols=['CategoryID', 'ParentCategoryID', 'Level'],
dtype={'CategoryID': 'i4', 'ParentCategoryID': 'i1', 'Level': 'i1'})
t = None
# Notice the filter attribute that does not exist in pandas.read_csv(). It makes it possible to skip some rows
# based on a numexpr expression. IsClick == IsClick is true iff IsClick is not na
if ds.get_table("TrainSearchStream") is None:
t = Table.from_csv("TrainSearchStream", ds, os.path.join(csv_dir, "trainSearchStream.tsv"), delimiter='\t', chunksize=10**7,
usecols=['SearchID', 'AdID', 'Position', 'ObjectType', 'HistCTR', 'IsClick'],
dtype={'SearchID':'i4', 'AdID':'i4', 'Position':'i1', 'ObjectType':'i1', 'HistCTR':'f4', 'IsClick':'f1'},
filter='(ObjectType == 3) & (IsClick == IsClick)')
t = None
# We avoid to load the string fields. We will see this problem later with Don
if ds.get_table("AdsInfo") is None:
t = Table.from_csv("AdsInfo", ds, os.path.join(csv_dir, "AdsInfo.tsv"), delimiter='\t', chunksize=10**7,
usecols=['AdID', 'LocationID', 'CategoryID', 'Price', 'IsContext'],
dtype={'AdID':'i4', 'LocationID':'f4', 'CategoryID':'f4', 'Price': 'f4', 'IsContext': 'f1'})
t = None
# We avoid to load the string fields. We will see this problem later with Don
if ds.get_table("SearchInfo") is None:
t = Table.from_csv("SearchInfo", ds, os.path.join(csv_dir, "SearchInfo.tsv"), delimiter='\t', chunksize=10**7,
usecols=['SearchID', 'IPID', 'UserID', 'IsUserLoggedOn', 'LocationID', 'CategoryID'],
dtype={'SearchID':'i4', 'IPID':'i4', 'UserID':'f4', 'IsUserLoggedOn':'f1',
'LocationID':'f4', 'CategoryID':'f4'})
t = None
if ds.get_table("userInfo") is None:
t = Table.from_csv("userInfo", ds, os.path.join(csv_dir, "userInfo.tsv"), delimiter='\t', chunksize=10**7,
usecols=['UserID', 'UserAgentID', 'UserAgentOSID','UserDeviceID', 'UserAgentFamilyID'],
dtype={'UserID':'i4', 'UserAgentID':'i4', 'UserAgentOSID':'i4',
'UserDeviceID':'i4', 'UserAgentFamilyID':'i4'})
t = None
if ds.get_table("Location") is None:
t = Table.from_csv("Location", ds, os.path.join(csv_dir, "Location.tsv"), delimiter='\t', chunksize=10**7,
usecols=['LocationID', 'CityID', 'RegionID'],
dtype={'LocationID': 'i4', 'CityID':'f4', 'RegionID': 'f4'})
t = None
if ds.get_table("PhoneRequestsStream") is None:
t = Table.from_csv("PhoneRequestsStream", ds, os.path.join(csv_dir, "PhoneRequestsStream.tsv"), delimiter='\t', chunksize=10**7,
usecols=['UserID', 'IPID', 'AdID', 'PhoneRequestDate'],
dtype={'UserID':'i4', 'IPID':'i4', 'AdID':'i4', 'PhoneRequestDate': 'object'})
t = None
if ds.get_table("VisitsStream") is None:
t = Table.from_csv("VisitsStream", ds, os.path.join(csv_dir, "VisitsStream.tsv"), delimiter='\t', chunksize=10**7,
usecols=['UserID', 'IPID', 'AdID', 'ViewDate'],
dtype={'UserID':'i4', 'IPID':'i4', 'AdID':'i4', 'ViewDate': 'object'})
t = None
return ds
