def test_new_table(self):
jobj1 = JArrayList()
jobj1.add(1)
jobj1.add(-1)
jobj2 = JArrayList()
jobj2.add(2)
jobj2.add(-2)
cols = [
bool_col(name="Boolean", data=[True, False]),
byte_col(name="Byte", data=(1, -1)),
char_col(name="Char", data='-1'),
short_col(name="Short", data=[1, -1]),
int_col(name="Int", data=[1, -1]),
long_col(name="Long", data=[1, -1]),
long_col(name="NPLong", data=np.array([1, -1], dtype=np.int8)),
float_col(name="Float", data=[1.01, -1.01]),
double_col(name="Double", data=[1.01, -1.01]),
string_col(name="String", data=["foo", "bar"]),
datetime_col(name="Datetime",
data=[dtypes.DateTime(1),
dtypes.DateTime(-1)]),
pyobj_col(name="PyObj",
data=[CustomClass(1, "1"),
CustomClass(-1, "-1")]),
pyobj_col(name="PyObj1", data=[[1, 2, 3],
CustomClass(-1, "-1")]),
pyobj_col(name="PyObj2", data=[False, 'False']),
jobj_col(name="JObj", data=[jobj1, jobj2]),
]
t = new_table(cols=cols)
self.assertEqual(t.size, 2)
def setUp(self):
j_array_list1 = j_array_list([1, -1])
j_array_list2 = j_array_list([2, -2])
input_cols = [
bool_col(name="Boolean", data=[True, False]),
byte_col(name="Byte", data=(1, -1)),
char_col(name="Char", data='-1'),
short_col(name="Short", data=[1, -1]),
int_col(name="Int_", data=[1, -1]),
long_col(name="Long_", data=[1, NULL_LONG]),
long_col(name="NPLong", data=np.array([1, -1], dtype=np.int8)),
float_col(name="Float_", data=[1.01, -1.01]),
double_col(name="Double_", data=[1.01, -1.01]),
string_col(name="String", data=["foo", "bar"]),
datetime_col(name="Datetime",
data=[dtypes.DateTime(1),
dtypes.DateTime(-1)]),
pyobj_col(name="PyObj",
data=[CustomClass(1, "1"),
CustomClass(-1, "-1")]),
pyobj_col(name="PyObj1", data=[[1, 2, 3],
CustomClass(-1, "-1")]),
pyobj_col(name="PyObj2", data=[False, 'False']),
jobj_col(name="JObj", data=[j_array_list1, j_array_list2]),
]
self.test_table = new_table(cols=input_cols)
def setUp(self):
j_array_list1 = j_array_list([1, -1])
j_array_list2 = j_array_list([2, -2])
input_cols = [
bool_col(name="Boolean", data=[True, False]),
byte_col(name="Byte", data=(1, -1)),
char_col(name="Char", data='-1'),
short_col(name="Short", data=[1, -1]),
int_col(name="Int", data=[1, -1]),
long_col(name="Long", data=[1, NULL_LONG]),
long_col(name="NPLong", data=np.array([1, -1], dtype=np.int8)),
float_col(name="Float", data=[1.01, -1.01]),
double_col(name="Double", data=[1.01, -1.01]),
string_col(name="String", data=["foo", "bar"]),
datetime_col(name="Datetime",
data=[dtypes.DateTime(1),
dtypes.DateTime(-1)]),
pyobj_col(name="PyObj",
data=[CustomClass(1, "1"),
CustomClass(-1, "-1")]),
pyobj_col(name="PyObj1", data=[[1, 2, 3],
CustomClass(-1, "-1")]),
pyobj_col(name="PyObj2", data=[False, 'False']),
jobj_col(name="JObj", data=[j_array_list1, j_array_list2]),
]
self.test_table = new_table(cols=input_cols)
self.np_array_dict = {
'Boolean':
np.array([True, False]),
'Byte':
np.array([1, -1], dtype=np.int8),
'Char':
np.array('-1', dtype=np.int16),
'Short':
np.array([1, -1], dtype=np.int16),
'Int':
np.array([1, -1], dtype=np.int32),
'Long':
np.array([1, NULL_LONG], dtype=np.int64),
"NPLong":
np.array([1, -1], dtype=np.int8),
"Float":
np.array([1.01, -1.01], dtype=np.float32),
"Double":
np.array([1.01, -1.01]),
"String":
np.array(["foo", "bar"], dtype=np.string_),
"Datetime":
np.array([1, -1], dtype=np.dtype("datetime64[ns]")),
"PyObj":
np.array([CustomClass(1, "1"),
CustomClass(-1, "-1")]),
"PyObj1":
np.array([[1, 2, 3], CustomClass(-1, "-1")], dtype=np.object_),
"PyObj2":
np.array([False, 'False'], dtype=np.object_),
"JObj":
np.array([j_array_list1, j_array_list2]),
}
def test_get_constituent(self):
keys = [917, 167]
self.assertIsNotNone(self.partitioned_table.get_constituent(keys))
from deephaven.column import string_col, int_col, double_col
houses = new_table([
string_col("HomeType", [
"Colonial", "Contemporary", "Contemporary", "Condo",
"Colonial", "Apartment"
]),
int_col("HouseNumber", [1, 3, 4, 15, 4, 9]),
string_col("StreetName", [
"Test Drive", "Test Drive", "Test Drive", "Deephaven Road",
"Community Circle", "Community Circle"
]),
int_col("SquareFeet", [2251, 1914, 4266, 1280, 3433, 981]),
int_col("Price",
[450000, 400000, 1250000, 300000, 600000, 275000]),
double_col("LotSizeAcres", [0.41, 0.26, 1.88, 0.11, 0.95, 0.10])
])
houses_by_type = houses.partition_by("HomeType")
colonial_homes = houses_by_type.get_constituent("Colonial")
self.assertIsNotNone(colonial_homes)
def table_helper():
columns = [
string_col('Symbol', ['MSFT', 'GOOG', 'AAPL', 'AAPL']),
string_col('Side', ['B', 'B', 'S', 'B']),
int_col('Qty', [200, 100, 300, 50]),
double_col('Price', [210.0, 310.5, 411.0, 411.5])
]
t = new_table(cols=columns)
return t
def test_simple_spec(self):
"""
Check a simple Kafka subscription creates the right table.
"""
t = new_table(cols=[double_col('Price', [10.0, 10.5, 11.0, 11.5])])
cleanup = pk.produce(t, {'bootstrap.servers': 'redpanda:29092'},
'orders',
key_spec=KeyValueSpec.IGNORE,
value_spec=pk.simple_spec('Price'))
self.assertIsNotNone(cleanup)
cleanup()
def test_array_column(self):
strings = ["Str1", "Str1", "Str2", "Str2"]
doubles = [1.0, 2.0, 4.0, 8.0]
test_table = new_table([
string_col("StringColumn", strings),
double_col("Decimals", doubles)
])
test_table = test_table.group_by(["StringColumn"])
self.assertIsNone(test_table.columns[0].component_type)
self.assertEqual(test_table.columns[1].component_type, dtypes.double)
def test_vector_column(self):
strings = ["Str1", "Str1", "Str2", "Str2", "Str2"]
doubles = [1.0, 2.0, 4.0, 8.0, 16.0]
test_table = new_table(
[string_col("String", strings),
double_col("Doubles", doubles)])
test_table = test_table.group_by(["String"])
df = to_pandas(test_table, cols=["String", "Doubles"])
self.assertEqual(df['String'].dtype, np.object_)
self.assertEqual(df['Doubles'].dtype, np.object_)
double_series = df['Doubles']
self.assertEqual([1.0, 2.0], list(double_series[0].toArray()))
self.assertEqual([4.0, 8.0, 16.0], list(double_series[1].toArray()))
def test_to_table(self):
input_cols = [
bool_col(name="Boolean", data=[True, False]),
byte_col(name="Byte", data=(1, -1)),
char_col(name="Char", data='-1'),
short_col(name="Short", data=[1, -1]),
int_col(name="Int", data=[1, -1]),
long_col(name="Long", data=[1, NULL_LONG]),
long_col(name="NPLong", data=np.array([1, -1], dtype=np.int8)),
float_col(name="Float", data=[1.01, -1.01]),
double_col(name="Double", data=[1.01, -1.01]),
]
test_table = new_table(cols=input_cols)
df = to_pandas(test_table)
table_from_df = to_table(df)
self.assert_table_equals(table_from_df, test_table)
def test_round_trip_with_nulls(self):
# Note that no two-way conversion for those types
# j_array_list = dtypes.ArrayList([1, -1])
# bool_col(name="Boolean", data=[True, None])]
# string_col(name="String", data=["foo", None]),
# jobj_col(name="JObj", data=[j_array_list, None]),
input_cols = [
byte_col(name="Byte", data=(1, NULL_BYTE)),
char_col(name="Char", data='-1'),
short_col(name="Short", data=[1, NULL_SHORT]),
int_col(name="Int_", data=[1, NULL_INT]),
long_col(name="Long_", data=[1, NULL_LONG]),
float_col(name="Float_", data=[1.01, np.nan]),
double_col(name="Double_", data=[1.01, np.nan]),
datetime_col(name="Datetime", data=[dtypes.DateTime(1), None]),
pyobj_col(name="PyObj", data=[CustomClass(1, "1"), None]),
]
test_table = new_table(cols=input_cols)
df = to_pandas(test_table)
self.assertEqual(len(df.columns), len(test_table.columns))
self.assertEqual(df.size, 2 * len(test_table.columns))
test_table2 = to_table(df)
self.assert_table_equals(test_table2, test_table)
def test_column_error(self):
jobj = j_array_list([1, -1])
with self.assertRaises(DHError) as cm:
bool_input_col = bool_col(name="Boolean", data=[True, 'abc'])
self.assertNotIn("bool_input_col", dir())
with self.assertRaises(DHError) as cm:
_ = byte_col(name="Byte", data=[1, 'abc'])
with self.assertRaises(DHError) as cm:
_ = char_col(name="Char", data=[jobj])
with self.assertRaises(DHError) as cm:
_ = short_col(name="Short", data=[1, 'abc'])
with self.assertRaises(DHError) as cm:
_ = int_col(name="Int", data=[1, [1, 2]])
with self.assertRaises(DHError) as cm:
_ = long_col(name="Long", data=[1, float('inf')])
with self.assertRaises(DHError) as cm:
_ = float_col(name="Float", data=[1.01, 'NaN'])
with self.assertRaises(DHError) as cm:
_ = double_col(name="Double", data=[1.01, jobj])
with self.assertRaises(DHError) as cm:
_ = string_col(name="String", data=[1, -1.01])
with self.assertRaises(DHError) as cm:
_ = datetime_col(name="Datetime",
data=[dtypes.DateTime(round(time.time())), False])
with self.assertRaises(DHError) as cm:
_ = jobj_col(name="JObj", data=[jobj, CustomClass(-1, "-1")])