def test4():
from dazzle.core.dataset import DataSet
from dazzle.core.table import Table
test_dir = os.path.join("/temp", "dazzle-test")
ds = DataSet(test_dir, force_create=True)
t = Table("t", ds, [("a", np.array([np.nan, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, np.nan]))])
ca = t.get_column("a")
print(ca.str_values(format="%.4f"))
def test2():
from dazzle.core.dataset import DataSet
from dazzle.core.table import Table
test_dir = os.path.join("/temp", "dazzle-test")
ds = DataSet(test_dir, force_create=True)
t = Table("t", ds, [("a", np.int)])
ca = t.get_column("a")
#t.append({'a': np.random.randint(10000000, size=5*(10**8)).astype(np.int32)})
print(ca.__dict__)
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 open(data_dir):
"""Open and return an existing DataSet.
Side effect: open each Table in this dataset.
"""
json_file = os.path.join(data_dir, "dataset.json")
if not os.path.exists(json_file):
raise DazzleError("No 'dataset.json' file found in %s" % data_dir)
ds = DataSet(data_dir, mode='open')
with open(json_file, 'rb') as f:
data = json.loads(f.read().decode('ascii'))
params = data["compression_params"]
ds._compression_params = bcolz.cparams(clevel=params["_clevel"], shuffle=params["_shuffle"],
cname=params["_cname"])
for table in data["tables"]:
table = Table(table["name"], ds, [], mode='open')
table._ctable = bcolz.open(table.data_dir)
table._build_columns_from_ctable()
table._dataset._add_table(table)
ds.save()
return ds
def setUp(self):
self.a = [6, 4, 7, 4, 6, 9]
self.test_dir = os.path.join("/temp", "dazzle-test")
self.ds = DataSet(self.test_dir, force_create=True)
self.t = Table("t", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float))], force_create=True)
self.u = Table("u", self.ds, [("a", np.array([1, 2], np.int)), ("b", np.array([1.1, 2.2], np.float))], force_create=True)
def test_copy02(self):
Table.copy("t", self.ds, "/bim/bam")
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
class TestColumn(unittest.TestCase):
def setUp(self):
self.a = [6, 4, 7, 4, 6, 9]
self.test_dir = os.path.join("/temp", "dazzle-test")
ds = DataSet(self.test_dir, force_create=True)
self.t = Table("t", ds, [("a", np.array([1, 3], dtype=np.int8)), ("x", np.array([2, 4], dtype=np.float))], force_create=True)
self.ca = self.t.get_column("a")
@raises(DazzleError)
def test_data_dir01(self):
"""no table associated"""
print(LiteralColumn("a", np.array([], np.int)).data_dir)
def test_data_dir02(self):
self.assertEqual(self.ca.data_dir, os.path.join(self.test_dir, "t", "a"))
@raises(DazzleError)
def test_carray01(self):
"""no table associated"""
print(LiteralColumn("a", np.array([], np.int)).carray)
def test_carray02(self):
assert_array_equal(self.ca.carray[:], [1, 3])
@raises(DazzleError)
def test_init01(self):
LiteralColumn("", [])
@raises(DazzleError)
def test_init02(self):
LiteralColumn("1a", [])
@raises(DazzleError)
def test_init03(self):
LiteralColumn("_a", [])
@raises(DazzleError)
def test_init04(self):
LiteralColumn("a", "XX")
@raises(DazzleError)
def test_init05(self):
LiteralColumn("a", self)
def test_init06(self):
assert_array_equal(self.ca.carray[:], [1, 3])
def test_len01(self):
self.assertEqual(len(self.ca), 2)
def test_position01(self):
self.t.append({'a': self.a, 'x': self.a})
self.assertEqual(self.ca.position, 0)
def test_position02(self):
self.t.append({'a': self.a, 'x': self.a})
self.assertEqual(self.t.get_column("x").position, 1)
def test_getitem01(self):
self.assertEqual(self.ca[0], 1)
def test_getitem02(self):
self.assertEqual(self.ca[1], 3)
@raises(IndexError)
def test_getitem03(self):
self.t.append({'a': self.a, 'x': self.a})
_ = self.ca[10]
def test_getitem04(self):
self.t.append({'a': self.a, 'x': self.a})
assert_array_equal(self.ca[:], self.ca.carray[:])
def test_getitem05(self):
self.t.append({'a': self.a, 'x': self.a})
assert_array_equal(self.ca[0:5], [1, 3, 6, 4, 7])
def test_setitem01(self):
self.ca[0] = 2
self.assertEqual(self.ca[0], 2)
assert_array_equal(self.ca.carray[:], [2, 3])
def test_append01(self):
self.t.append({'a': self.a, 'x': self.a})
self.ca.append(self.a)
assert_array_equal(self.ca.carray[:], [1, 3, 6, 4, 7, 4, 6, 9, 6, 4, 7, 4, 6, 9])
@raises(DazzleError)
def test_rename01(self):
self.t.append({'a': self.a, 'x': self.a})
self.ca.rename("")
@raises(DazzleError)
def test_rename02(self):
self.t.append({'a': self.a, 'x': self.a})
self.ca.rename("x")
def test_rename03(self):
self.ca.rename("b")
self.assertTrue(os.path.exists(os.path.join(self.test_dir, "t", "b")), "'b' dir should exist")
self.assertFalse(os.path.exists(os.path.join(self.test_dir, "t", "a")), "'a' dir should not exist")
self.assertEqual(self.ca.data_dir, os.path.join(self.test_dir, "t", "b"))
self.assertEqual(self.ca._name, "b", "column should be named 'b'")
self.assertEqual(self.t.get_column("b").position, 0, "column should be at position 0")
def test_sum01(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=True), 0.0)
def test_sum02(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=False), 0.0)
def test_sum03(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, 7, 4, 6, 9], np.int))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=True), 36.0)
def test_sum04(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, 7, 4, 6, 9], np.int))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=False), 36.0)
def test_sum05(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=True), 29.0)
def test_sum06(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.sum(skipna=False)))
def test_sum07(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=True), 0.0)
def test_sum08(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.sum(skipna=False)))
def test_sum09(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([3, nan, 2], np.int8))], force_create=True).get_column("a")
self.assertEqual(ca.sum(skipna=True), 5)
def test_sum10(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, 2], np.int8))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.sum(skipna=False)))
def test_sum11(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, nan], np.int8))], force_create=True).get_column("a")
self.assertEqual(ca.sum(skipna=True), 0)
def test_mean01(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.mean(skipna=True)))
def test_mean02(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.mean(skipna=False)))
def test_mean03(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.mean(skipna=True), 6.0)
def test_mean04(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds,[("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.mean(skipna=False), 6.0)
def test_mean05(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
assert_close(ca.mean(skipna=True), 5.0)
def test_mean06(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.mean(skipna=False)))
def test_mean07(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.mean(skipna=True)))
def test_mean08(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.mean(skipna=False)))
def test_min01(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
x = ca.min()
self.assertTrue(ca.isnan(ca.min(skipna=True)))
def test_min02(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=False)))
def test_min03(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.min(skipna=True), 4)
def test_min04(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.min(skipna=False), 4)
def test_min05(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
assert_close(ca.min(skipna=True), 4)
def test_min06(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=False)))
def test_min07(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=True)))
def test_min08(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=False)))
def test_min09(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([3, nan, 2], np.int8))], force_create=True).get_column("a")
self.assertEqual(ca.min(skipna=True), 2)
def test_min10(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, 2], np.int8))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=False)))
def test_min11(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, nan], np.int8))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=False)))
def test_max01(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=True)))
def test_max02(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
def test_max03(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.max(skipna=True), 9)
def test_max04(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.max(skipna=False), 9)
def test_max05(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
assert_close(ca.max(skipna=True), 9)
def test_max06(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
def test_max07(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=True)))
def test_max08(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
def test_max09(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([3, nan, 2], np.int8))], force_create=True).get_column("a")
self.assertEqual(ca.max(skipna=True), 3)
def test_max10(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, 2], np.int8))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
def test_max11(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, nan], np.int8))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
def setUp(self):
self.a = [6, 4, 7, 4, 6, 9]
self.test_dir = os.path.join("/temp", "dazzle-test")
ds = DataSet(self.test_dir, force_create=True)
self.t = Table("t", ds, [("a", np.array([1, 3], dtype=np.int8)), ("x", np.array([2, 4], dtype=np.float))], force_create=True)
self.ca = self.t.get_column("a")
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_sum07(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=True), 0.0)
def test_from_csv02(self):
Table.from_csv("Category", self.ds, "/temp/dazzle-test/dataset.json", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
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_csv01(self):
Table.from_csv("Category", self.ds, "/bim/bam/test.csv", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
def test_copy04(self):
test_dir = os.path.join("/temp/dazzle-test2")
ds2 = DataSet(test_dir, force_create=True)
t = Table.copy("t", ds2, "/temp/dazzle-test/t")
assert_equal_table(t, self.ds.get_table("t"))
def test_copy03(self):
test_dir = os.path.join("/temp/dazzle-test2")
ds2 = DataSet(test_dir, force_create=True)
Table.copy("_", ds2, "/temp/dazzle-test/t")
def test_sum03(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, 7, 4, 6, 9], np.int))], force_create=True).get_column("a")
assert_close(ca.sum(skipna=True), 36.0)
def test_from_dataframe01(self):
df = pd.DataFrame({'a': [1,2], 'b': [3., 4.]})
v = Table.from_dataframe("v", self.ds, df)
self.assertEqual(len(v.ctable), 2)
def test_sum06(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.sum(skipna=False)))
class TestTable(unittest.TestCase):
def assert_string_equal(self, s1, s2):
return self.assertEqual(''.join(s1.split()), ''.join(s2.split()))
def assert_table_content(self, table, to_check):
for check, val in to_check.items():
if check == 'data_dir':
self.assertEqual(table.data_dir, val)
elif check == 'len':
self. assertEqual(len(table.ctable), val)
elif check == 'type':
self. assertEqual(type(table), val)
elif check == 'columns':
index = 0
for col_name, attrs in val:
self.assert_column_content(table, col_name, index, attrs)
index += 1
else:
raise DazzleError("Invalid key: %s" % check)
def assert_column_content(self, table, col_name, index, to_check):
self.assertTrue(isinstance(table._columns[index], LiteralColumn))
col = table._columns[index]
self.assertTrue(col._table == table)
self.assertTrue(col._name == col_name)
self.assertTrue(table.ctable.names[index] == col_name)
bz_col = table.ctable.cols._cols[col_name]
self.assertEqual(col.carray, bz_col)
self.assertTrue(isinstance(bz_col, bcolz.carray))
for check, val in to_check.items():
if check == 'len':
self.assertEqual(bz_col.len, val)
elif check == 'content':
assert_array_equal(bz_col[:], val)
elif check == 'type':
self.assertEqual(col.dtype, val)
else:
raise DazzleError("Invalid key: %s" % check)
def setUp(self):
self.a = [6, 4, 7, 4, 6, 9]
self.test_dir = os.path.join("/temp", "dazzle-test")
self.ds = DataSet(self.test_dir, force_create=True)
self.t = Table("t", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float))], force_create=True)
self.u = Table("u", self.ds, [("a", np.array([1, 2], np.int)), ("b", np.array([1.1, 2.2], np.float))], force_create=True)
def test_init01(self):
self.assert_table_content(self.t, {
'data_dir': os.path.join(self.test_dir, self.t._name),
'len': 0,
'type': Table,
'columns': [('a', {'type': np.int, 'content': []})]})
@raises(DazzleError)
def test_init02(self):
Table("_", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float))], force_create=True)
@raises(DazzleError)
def test_init03(self):
Table("t", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float))], mode='open', force_create=True)
@raises(DazzleError)
def test_init04(self):
Table("t", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float))], force_create=True)
@raises(ValueError)
def test_init05(self):
Table("t", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float))], mode='open')
@raises(ValueError)
def test_init06(self):
Table("t", self.ds, [{"a": np.array([], np.int)}], force_create=True)
@raises(DazzleError)
def test_init07(self):
Table("t", self.ds, [], force_create=True)
@raises(ValueError)
def test_init08(self):
Table("t", self.ds, [("a", 3)], force_create=True)
@raises(ValueError)
def test_init09(self):
Table("t", self.ds, [{"a": np.array([True, False], np.bool)}], force_create=True)
@raises(ValueError)
def test_init10(self):
Table("t", self.ds, ("a", np.array([], np.int)), force_create=True)
@raises(ValueError)
def test_init11(self):
Table("t", self.ds, [("a", np.array([], np.int)), ("b", np.array([], np.float), 'oops')], force_create=True)
@raises(DazzleError)
def test_init11(self):
Table("t", self.ds, [("a", np.array([], np.bool)), ("b", np.array([], np.float))], force_create=True)
def test_init12(self):
v = Table("v", self.ds, [("a", [3])])
self.assert_table_content(v, {
'data_dir': os.path.join(self.test_dir, "v"),
'len': 1,
'type': Table,
'columns': [('a', {'type': np.int, 'content': [3]})]})
def test_dataset01(self):
self.assertEqual(self.ds, self.t.dataset)
@raises(DazzleError)
def test_data_dir01(self):
"""no table associated"""
print(LiteralColumn("a", None).data_dir)
@raises(DazzleError)
def test_copy01(self):
Table.copy("t", self.ds, "/temp/dazzle-test")
@raises(DazzleError)
def test_copy02(self):
Table.copy("t", self.ds, "/bim/bam")
@raises(DazzleError)
def test_copy03(self):
test_dir = os.path.join("/temp/dazzle-test2")
ds2 = DataSet(test_dir, force_create=True)
Table.copy("_", ds2, "/temp/dazzle-test/t")
def test_copy04(self):
test_dir = os.path.join("/temp/dazzle-test2")
ds2 = DataSet(test_dir, force_create=True)
t = Table.copy("t", ds2, "/temp/dazzle-test/t")
assert_equal_table(t, self.ds.get_table("t"))
@raises(FileNotFoundError)
def test_from_csv01(self):
Table.from_csv("Category", self.ds, "/bim/bam/test.csv", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
@raises(ValueError)
def test_from_csv02(self):
Table.from_csv("Category", self.ds, "/temp/dazzle-test/dataset.json", usecols=['CategoryID', 'ParentCategoryID'], verbose=False)
@raises(DazzleError)
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_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_dataframe01(self):
df = pd.DataFrame({'a': [1,2], 'b': [3., 4.]})
v = Table.from_dataframe("v", self.ds, df)
self.assertEqual(len(v.ctable), 2)
def test_get_column01(self):
self.assertTrue(self.t.get_column("x") is None)
def test_get_column02(self):
self.assertEqual(self.t.get_column("a").name, "a")
@raises(ValueError)
def test_remove_column01(self):
self.t.remove_column("x")
def test_remove_column02(self):
self.t.remove_column("a")
self.assertTrue(self.t.get_column("a") is None)
self.assertEqual(self.t.columns[0], self.t.get_column("b"))
self.assertEqual(self.t.ctable.names[0], "b")
def test_to_dataframe01(self):
self.assertEqual(len(self.u.to_dataframe()), 2)
def test_append01(self):
self.t.append({'a': [1,2], 'b': [3., 4.]})
self.assert_table_content(self.t, {
'len': 2,
'columns': [('a', {'content': [1,2]}), ('b', {'content': [3., 4.]})]})
def test_append02(self):
self.t.append({'b': [3., 4.], 'a': [1,2]})
self.assert_table_content(self.t, {
'len': 2,
'columns': [('a', {'content': [1,2]}), ('b', {'content': [3., 4.]})]})
def test_append03(self):
self.t.append({'a': [5.4, 2], 'b': [3., 4.]})
@raises(ValueError)
def test_append04(self):
self.t.append({'a': ["bla", 2], 'b': [3., 4.]})
@raises(ValueError)
def test_append05(self):
self.t.append({'a': [], 'b': [3., 4.]})
@raises(ValueError)
def test_append06(self):
self.t.append({'a': []})
@raises(ValueError)
def test_append05(self):
self.t.append([[], [3., 4.]])
def test_get_item01(self):
self.assertEqual(self.u[0]['a'], 1)
self.assertEqual(self.u[0]['b'], 1.1)
def test_get_item02(self):
assert_array_equal(self.u['a'], np.array([1,2]))
@raises(IndexError)
def test_get_item03(self):
print(self.u[0,1])
def test_get_item04(self):
assert_array_equal(self.u[[0,1]]['a'], np.array([1, 2]))
assert_array_equal(self.u[[0,1]]['b'], np.array([1.1, 2.2]))
def test_get_item05(self):
assert_array_equal(self.u['a'][[0,1]], np.array([1, 2]))
assert_array_equal(self.u['b'][[0,1]], np.array([1.1, 2.2]))
def test_set_item01(self):
self.u[0] = (10, 20.2)
self.assertEqual(self.u[0]['a'], 10)
self.assertEqual(self.u[0]['b'], 20.2)
def test_set_item02(self):
self.u[[0, 1]] = [(10, 20.2), (190, 32.4)]
self.assertEqual(self.u[0]['b'], 20.2)
self.assertEqual(self.u[1]['a'], 190)
# def test_set_item03(self):
# self.u[[0, 1]]['a'] = 40 # makes a copy; u is not modified
# self.assertEqual(self.u[0]['a'], 40)
# def test_set_item04(self):
# self.u[0]['a'] = 14 # makes a copy; u is not modified
# self.assertEqual(self.u[0]['a'], 14)
def test_str01(self):
s = \
"u(a: int32, b: float64)" \
"2 row(s) - compressed: 2.00 MB - comp. ratio: 0.00" \
"+---+-------+" \
"| a | b |" \
"+---+-------+" \
"| 1 | 1.100 |" \
"| 2 | 2.200 |" \
"+---+-------+"
self.assert_string_equal(self.u.__str__(), s)
def test_str02(self):
s = \
"u(a: int32, b: float64)" \
"2 row(s) - compressed: 2.00 MB - comp. ratio: 0.00" \
"+---+-------+" \
"| a | b |" \
"+---+-------+" \
"| 1 | 1.100 |" \
"| 2 | 2.200 |" \
"+---+-------+"
self.assert_string_equal(self.u.__str__(head=20), s)
def test_str03(self):
s = \
"u(a: int32, b: float64)" \
"2 row(s) - compressed: 2.00 MB - comp. ratio: 0.00" \
"+---+-----+" \
"| a | b |" \
"+---+-----+" \
"| 1 | 1.1 |" \
"| 2 | 2.2 |" \
"+---+-----+"
self.u.get_column("b").format = "%.1f"
self.assert_string_equal(self.u.__str__(head=20), s)
def test_head01(self):
s = \
"u(a: int32, b: float64)" \
"2 row(s) - compressed: 2.00 MB - comp. ratio: 0.00" \
"+-----+-------+" \
"| a | b |" \
"+-----+-------+" \
"| 1 | 1.100 |" \
"| ... | ... |" \
"+-----+-------+"
self.assert_string_equal(self.u.head(1), s)
def test_tail01(self):
s = \
"u(a: int32, b: float64)" \
"2 row(s) - compressed: 2.00 MB - comp. ratio: 0.00" \
"+-----+-------+" \
"| a | b |" \
"+-----+-------+" \
"| ... | ... |" \
"| 2 | 2.200 |" \
"+-----+-------+"
self.assert_string_equal(self.u.tail(1), s)
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
@raises(DazzleError)
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_add_join_column(self):
ds = DataSet("/temp/dazzle-test", force_create=True)
t = Table("t", ds, [('a', np.array([10, 2, 3, 5, 4, 7, 1, 8, 6, 9])),
('c', np.array([100, 20, 30, 50, 40, 70, 10, 80, 60, np.nan]))])
a_ref = np.array([1, 5, 4, 5, 6, 4, 1, 1, 9, 7, 8, 4, 5, 5, 2, 2, 8, 5, 4, 20])
u = Table("u", ds, [('a', a_ref), ("y", a_ref * 10)])
u.get_column("a").ref_column = t.get_column("a")
t.rebuild({'a': np.int8, 'c': np.int8})
u.rebuild({'a': np.int8, 'y': np.int16})
u.add_reference_column(u.get_column("a"), t.get_column("a"))
# print(t.head(20))
# print(u.head(30))
u.add_join_column("result", [u.get_column("a_ref"), t.get_column("c")])
#print(u.head(30))
assert np.array_equal(u['result'],
[-128, 10, 50, 40, 50, 60, 40, 10, 10, -128, 70, 80, 40, 50, 50, 20, 20, 80, 50, 40, -128])
def test_sum11(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, nan], np.int8))], force_create=True).get_column("a")
self.assertEqual(ca.sum(skipna=True), 0)
def test_max05(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([6, 4, np.nan, 4, 6, 9], np.float))], force_create=True).get_column("a")
assert_close(ca.max(skipna=True), 9)
def test_min02(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([], np.int))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.min(skipna=False)))
def test_max09(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([3, nan, 2], np.int8))], force_create=True).get_column("a")
self.assertEqual(ca.max(skipna=True), 3)
def test_max04(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", [np.array([6, 4, 7, 4, 6, 9], np.int)])], force_create=True).get_column("a")
assert_close(ca.max(skipna=False), 9)
def test_copy01(self):
Table.copy("t", self.ds, "/temp/dazzle-test")
def test_max08(self):
ds = DataSet(self.test_dir, force_create=True)
ca = Table("t", ds, [("a", np.array([np.nan, np.nan], np.float))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
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_max11(self):
ds = DataSet(self.test_dir, force_create=True)
nan = np.iinfo(np.int8).min
ca = Table("t", ds, [("a", np.array([nan, nan], np.int8))], force_create=True).get_column("a")
self.assertTrue(ca.isnan(ca.max(skipna=False)))
def test_add_join_column(self):
ds = DataSet("/temp/dazzle-test", force_create=True)
t = Table("t", ds, [('a', np.array([10, 2, 3, 5, 4, 7, 1, 8, 6, 9])),
('c', np.array([100, 20, 30, 50, 40, 70, 10, 80, 60, np.nan]))])
a_ref = np.array([1, 5, 4, 5, 6, 4, 1, 1, 9, 7, 8, 4, 5, 5, 2, 2, 8, 5, 4, 20])
u = Table("u", ds, [('a', a_ref), ("y", a_ref * 10)])
u.get_column("a").ref_column = t.get_column("a")
t.rebuild({'a': np.int8, 'c': np.int8})
u.rebuild({'a': np.int8, 'y': np.int16})
u.add_reference_column(u.get_column("a"), t.get_column("a"))
# print(t.head(20))
# print(u.head(30))
u.add_join_column("result", [u.get_column("a_ref"), t.get_column("c")])
#print(u.head(30))
assert np.array_equal(u['result'],
[-128, 10, 50, 40, 50, 60, 40, 10, 10, -128, 70, 80, 40, 50, 50, 20, 20, 80, 50, 40, -128])