def extract(self, what, df: SeriesOrScalar):
df = convert_to_datetime(df)
if what == "CENTURY":
return da.trunc(df.year / 100)
elif what == "DAY":
return df.day
elif what == "DECADE":
return da.trunc(df.year / 10)
elif what == "DOW":
return (df.dayofweek + 1) % 7
elif what == "DOY":
return df.dayofyear
elif what == "HOUR":
return df.hour
elif what == "MICROSECOND":
return df.microsecond
elif what == "MILLENNIUM":
return da.trunc(df.year / 1000)
elif what == "MILLISECOND":
return da.trunc(1000 * df.microsecond)
elif what == "MINUTE":
return df.minute
elif what == "MONTH":
return df.month
elif what == "QUARTER":
return df.quarter
elif what == "SECOND":
return df.second
elif what == "WEEK":
return df.week
elif what == "YEAR":
return df.year
else:
raise NotImplementedError(f"Extraction of {what} is not (yet) implemented.")
def cast_column_type(df: dd.DataFrame, column_name: str,
expected_type: type) -> dd.DataFrame:
"""
Cast the type of the given column to the expected type,
if they are far "enough" away.
This means, a float will never be converted into a double
or a tinyint into another int - but a string to an integer etc.
"""
current_type = df[column_name].dtype
logger.debug(
f"Column {column_name} has type {current_type}, expecting {expected_type}..."
)
if similar_type(current_type, expected_type):
logger.debug("...not converting.")
return df
current_float = pd.api.types.is_float_dtype(current_type)
expected_integer = pd.api.types.is_integer_dtype(expected_type)
if current_float and expected_integer:
logger.debug("...truncating...")
df[column_name] = da.trunc(df[column_name])
logger.debug(
f"Need to cast {column_name} from {current_type} to {expected_type}")
df[column_name] = df[column_name].astype(expected_type)
return df
def div(self, lhs, rhs):
result = lhs / rhs
lhs_float = pd.api.types.is_float_dtype(lhs)
rhs_float = pd.api.types.is_float_dtype(rhs)
if not lhs_float and not rhs_float:
result = da.trunc(result)
return result
def div(self, lhs, rhs, rex=None):
result = lhs / rhs
output_type = str(rex.getType())
output_type = sql_to_python_type(output_type.upper())
is_float = pd.api.types.is_float_dtype(output_type)
if not is_float:
result = da.trunc(result)
return result
def div(self, lhs, rhs):
result = lhs / rhs
# Specialized code for literals like "1000µs"
# For some reasons, Calcite decides to represent
# 1000µs as 1000µs * 1000 / 1000
# We do not need to truncate in this case
# So far, I did not spot any other occurrence
# of this function.
if isinstance(result, (datetime.timedelta, np.timedelta64)):
return result
else:
return da.trunc(result).astype(np.int64)
def fix_dtype_to_row_type(
dc: DataContainer,
row_type: "org.apache.calcite.rel.type.RelDataType"):
"""
Fix the dtype of the given data container (or: the df within it)
to the data type given as argument.
To prevent unneeded conversions, do only convert if really needed,
e.g. if the two types are "similar" enough, do not convert.
Similarity involves the same general type (int, float, string etc)
but not necessary the size (int64 and int32 are compatible)
or the nullability.
TODO: we should check the nullability of the SQL type
"""
df = dc.df
cc = dc.column_container
field_types = {
int(field.getIndex()): str(field.getType())
for field in row_type.getFieldList()
}
for index, field_type in field_types.items():
expected_type = sql_to_python_type(field_type)
field_name = cc.get_backend_by_frontend_index(index)
current_type = df[field_name].dtype
logger.debug(
f"Column {field_name} has type {current_type}, expecting {expected_type}..."
)
if similar_type(current_type, expected_type):
logger.debug("...not converting.")
continue
current_float = pd.api.types.is_float_dtype(current_type)
expected_integer = pd.api.types.is_integer_dtype(expected_type)
if current_float and expected_integer:
logger.debug("...truncating...")
df[field_name] = da.trunc(df[field_name])
logger.debug(
f"Need to cast {field_name} from {current_type} to {expected_type}"
)
df[field_name] = df[field_name].astype(expected_type)
return DataContainer(df, dc.column_container)
def cast_column_to_type(col: dd.Series, expected_type: str):
"""Cast the given column to the expected type"""
current_type = col.dtype
if similar_type(current_type, expected_type):
logger.debug("...not converting.")
return None
current_float = pd.api.types.is_float_dtype(current_type)
expected_integer = pd.api.types.is_integer_dtype(expected_type)
if current_float and expected_integer:
logger.debug("...truncating...")
# Currently "trunc" can not be applied to NA (the pandas missing value type),
# because NA is a different type. It works with np.NaN though.
# For our use case, that does not matter, as the conversion to integer later
# will convert both NA and np.NaN to NA.
col = da.trunc(col.fillna(value=np.NaN))
logger.debug(f"Need to cast from {current_type} to {expected_type}")
return col.astype(expected_type)
def test_arithmetic():
x = np.arange(5).astype('f4') + 2
y = np.arange(5).astype('i8') + 2
z = np.arange(5).astype('i4') + 2
a = da.from_array(x, chunks=(2,))
b = da.from_array(y, chunks=(2,))
c = da.from_array(z, chunks=(2,))
assert eq(a + b, x + y)
assert eq(a * b, x * y)
assert eq(a - b, x - y)
assert eq(a / b, x / y)
assert eq(b & b, y & y)
assert eq(b | b, y | y)
assert eq(b ^ b, y ^ y)
assert eq(a // b, x // y)
assert eq(a ** b, x ** y)
assert eq(a % b, x % y)
assert eq(a > b, x > y)
assert eq(a < b, x < y)
assert eq(a >= b, x >= y)
assert eq(a <= b, x <= y)
assert eq(a == b, x == y)
assert eq(a != b, x != y)
assert eq(a + 2, x + 2)
assert eq(a * 2, x * 2)
assert eq(a - 2, x - 2)
assert eq(a / 2, x / 2)
assert eq(b & True, y & True)
assert eq(b | True, y | True)
assert eq(b ^ True, y ^ True)
assert eq(a // 2, x // 2)
assert eq(a ** 2, x ** 2)
assert eq(a % 2, x % 2)
assert eq(a > 2, x > 2)
assert eq(a < 2, x < 2)
assert eq(a >= 2, x >= 2)
assert eq(a <= 2, x <= 2)
assert eq(a == 2, x == 2)
assert eq(a != 2, x != 2)
assert eq(2 + b, 2 + y)
assert eq(2 * b, 2 * y)
assert eq(2 - b, 2 - y)
assert eq(2 / b, 2 / y)
assert eq(True & b, True & y)
assert eq(True | b, True | y)
assert eq(True ^ b, True ^ y)
assert eq(2 // b, 2 // y)
assert eq(2 ** b, 2 ** y)
assert eq(2 % b, 2 % y)
assert eq(2 > b, 2 > y)
assert eq(2 < b, 2 < y)
assert eq(2 >= b, 2 >= y)
assert eq(2 <= b, 2 <= y)
assert eq(2 == b, 2 == y)
assert eq(2 != b, 2 != y)
assert eq(-a, -x)
assert eq(abs(a), abs(x))
assert eq(~(a == b), ~(x == y))
assert eq(~(a == b), ~(x == y))
assert eq(da.logaddexp(a, b), np.logaddexp(x, y))
assert eq(da.logaddexp2(a, b), np.logaddexp2(x, y))
assert eq(da.exp(b), np.exp(y))
assert eq(da.log(a), np.log(x))
assert eq(da.log10(a), np.log10(x))
assert eq(da.log1p(a), np.log1p(x))
assert eq(da.expm1(b), np.expm1(y))
assert eq(da.sqrt(a), np.sqrt(x))
assert eq(da.square(a), np.square(x))
assert eq(da.sin(a), np.sin(x))
assert eq(da.cos(b), np.cos(y))
assert eq(da.tan(a), np.tan(x))
assert eq(da.arcsin(b/10), np.arcsin(y/10))
assert eq(da.arccos(b/10), np.arccos(y/10))
assert eq(da.arctan(b/10), np.arctan(y/10))
assert eq(da.arctan2(b*10, a), np.arctan2(y*10, x))
assert eq(da.hypot(b, a), np.hypot(y, x))
assert eq(da.sinh(a), np.sinh(x))
assert eq(da.cosh(b), np.cosh(y))
assert eq(da.tanh(a), np.tanh(x))
assert eq(da.arcsinh(b*10), np.arcsinh(y*10))
assert eq(da.arccosh(b*10), np.arccosh(y*10))
assert eq(da.arctanh(b/10), np.arctanh(y/10))
assert eq(da.deg2rad(a), np.deg2rad(x))
assert eq(da.rad2deg(a), np.rad2deg(x))
assert eq(da.logical_and(a < 1, b < 4), np.logical_and(x < 1, y < 4))
assert eq(da.logical_or(a < 1, b < 4), np.logical_or(x < 1, y < 4))
assert eq(da.logical_xor(a < 1, b < 4), np.logical_xor(x < 1, y < 4))
assert eq(da.logical_not(a < 1), np.logical_not(x < 1))
assert eq(da.maximum(a, 5 - a), np.maximum(a, 5 - a))
assert eq(da.minimum(a, 5 - a), np.minimum(a, 5 - a))
assert eq(da.fmax(a, 5 - a), np.fmax(a, 5 - a))
assert eq(da.fmin(a, 5 - a), np.fmin(a, 5 - a))
assert eq(da.isreal(a + 1j * b), np.isreal(x + 1j * y))
assert eq(da.iscomplex(a + 1j * b), np.iscomplex(x + 1j * y))
assert eq(da.isfinite(a), np.isfinite(x))
assert eq(da.isinf(a), np.isinf(x))
assert eq(da.isnan(a), np.isnan(x))
assert eq(da.signbit(a - 3), np.signbit(x - 3))
assert eq(da.copysign(a - 3, b), np.copysign(x - 3, y))
assert eq(da.nextafter(a - 3, b), np.nextafter(x - 3, y))
assert eq(da.ldexp(c, c), np.ldexp(z, z))
assert eq(da.fmod(a * 12, b), np.fmod(x * 12, y))
assert eq(da.floor(a * 0.5), np.floor(x * 0.5))
assert eq(da.ceil(a), np.ceil(x))
assert eq(da.trunc(a / 2), np.trunc(x / 2))
assert eq(da.degrees(b), np.degrees(y))
assert eq(da.radians(a), np.radians(x))
assert eq(da.rint(a + 0.3), np.rint(x + 0.3))
assert eq(da.fix(a - 2.5), np.fix(x - 2.5))
assert eq(da.angle(a + 1j), np.angle(x + 1j))
assert eq(da.real(a + 1j), np.real(x + 1j))
assert eq((a + 1j).real, np.real(x + 1j))
assert eq(da.imag(a + 1j), np.imag(x + 1j))
assert eq((a + 1j).imag, np.imag(x + 1j))
assert eq(da.conj(a + 1j * b), np.conj(x + 1j * y))
assert eq((a + 1j * b).conj(), (x + 1j * y).conj())
assert eq(da.clip(b, 1, 4), np.clip(y, 1, 4))
assert eq(da.fabs(b), np.fabs(y))
assert eq(da.sign(b - 2), np.sign(y - 2))
l1, l2 = da.frexp(a)
r1, r2 = np.frexp(x)
assert eq(l1, r1)
assert eq(l2, r2)
l1, l2 = da.modf(a)
r1, r2 = np.modf(x)
assert eq(l1, r1)
assert eq(l2, r2)
assert eq(da.around(a, -1), np.around(x, -1))
def test_arithmetic():
x = np.arange(5).astype('f4') + 2
y = np.arange(5).astype('i8') + 2
z = np.arange(5).astype('i4') + 2
a = da.from_array(x, chunks=(2, ))
b = da.from_array(y, chunks=(2, ))
c = da.from_array(z, chunks=(2, ))
assert eq(a + b, x + y)
assert eq(a * b, x * y)
assert eq(a - b, x - y)
assert eq(a / b, x / y)
assert eq(b & b, y & y)
assert eq(b | b, y | y)
assert eq(b ^ b, y ^ y)
assert eq(a // b, x // y)
assert eq(a**b, x**y)
assert eq(a % b, x % y)
assert eq(a > b, x > y)
assert eq(a < b, x < y)
assert eq(a >= b, x >= y)
assert eq(a <= b, x <= y)
assert eq(a == b, x == y)
assert eq(a != b, x != y)
assert eq(a + 2, x + 2)
assert eq(a * 2, x * 2)
assert eq(a - 2, x - 2)
assert eq(a / 2, x / 2)
assert eq(b & True, y & True)
assert eq(b | True, y | True)
assert eq(b ^ True, y ^ True)
assert eq(a // 2, x // 2)
assert eq(a**2, x**2)
assert eq(a % 2, x % 2)
assert eq(a > 2, x > 2)
assert eq(a < 2, x < 2)
assert eq(a >= 2, x >= 2)
assert eq(a <= 2, x <= 2)
assert eq(a == 2, x == 2)
assert eq(a != 2, x != 2)
assert eq(2 + b, 2 + y)
assert eq(2 * b, 2 * y)
assert eq(2 - b, 2 - y)
assert eq(2 / b, 2 / y)
assert eq(True & b, True & y)
assert eq(True | b, True | y)
assert eq(True ^ b, True ^ y)
assert eq(2 // b, 2 // y)
assert eq(2**b, 2**y)
assert eq(2 % b, 2 % y)
assert eq(2 > b, 2 > y)
assert eq(2 < b, 2 < y)
assert eq(2 >= b, 2 >= y)
assert eq(2 <= b, 2 <= y)
assert eq(2 == b, 2 == y)
assert eq(2 != b, 2 != y)
assert eq(-a, -x)
assert eq(abs(a), abs(x))
assert eq(~(a == b), ~(x == y))
assert eq(~(a == b), ~(x == y))
assert eq(da.logaddexp(a, b), np.logaddexp(x, y))
assert eq(da.logaddexp2(a, b), np.logaddexp2(x, y))
assert eq(da.exp(b), np.exp(y))
assert eq(da.log(a), np.log(x))
assert eq(da.log10(a), np.log10(x))
assert eq(da.log1p(a), np.log1p(x))
assert eq(da.expm1(b), np.expm1(y))
assert eq(da.sqrt(a), np.sqrt(x))
assert eq(da.square(a), np.square(x))
assert eq(da.sin(a), np.sin(x))
assert eq(da.cos(b), np.cos(y))
assert eq(da.tan(a), np.tan(x))
assert eq(da.arcsin(b / 10), np.arcsin(y / 10))
assert eq(da.arccos(b / 10), np.arccos(y / 10))
assert eq(da.arctan(b / 10), np.arctan(y / 10))
assert eq(da.arctan2(b * 10, a), np.arctan2(y * 10, x))
assert eq(da.hypot(b, a), np.hypot(y, x))
assert eq(da.sinh(a), np.sinh(x))
assert eq(da.cosh(b), np.cosh(y))
assert eq(da.tanh(a), np.tanh(x))
assert eq(da.arcsinh(b * 10), np.arcsinh(y * 10))
assert eq(da.arccosh(b * 10), np.arccosh(y * 10))
assert eq(da.arctanh(b / 10), np.arctanh(y / 10))
assert eq(da.deg2rad(a), np.deg2rad(x))
assert eq(da.rad2deg(a), np.rad2deg(x))
assert eq(da.logical_and(a < 1, b < 4), np.logical_and(x < 1, y < 4))
assert eq(da.logical_or(a < 1, b < 4), np.logical_or(x < 1, y < 4))
assert eq(da.logical_xor(a < 1, b < 4), np.logical_xor(x < 1, y < 4))
assert eq(da.logical_not(a < 1), np.logical_not(x < 1))
assert eq(da.maximum(a, 5 - a), np.maximum(a, 5 - a))
assert eq(da.minimum(a, 5 - a), np.minimum(a, 5 - a))
assert eq(da.fmax(a, 5 - a), np.fmax(a, 5 - a))
assert eq(da.fmin(a, 5 - a), np.fmin(a, 5 - a))
assert eq(da.isreal(a + 1j * b), np.isreal(x + 1j * y))
assert eq(da.iscomplex(a + 1j * b), np.iscomplex(x + 1j * y))
assert eq(da.isfinite(a), np.isfinite(x))
assert eq(da.isinf(a), np.isinf(x))
assert eq(da.isnan(a), np.isnan(x))
assert eq(da.signbit(a - 3), np.signbit(x - 3))
assert eq(da.copysign(a - 3, b), np.copysign(x - 3, y))
assert eq(da.nextafter(a - 3, b), np.nextafter(x - 3, y))
assert eq(da.ldexp(c, c), np.ldexp(z, z))
assert eq(da.fmod(a * 12, b), np.fmod(x * 12, y))
assert eq(da.floor(a * 0.5), np.floor(x * 0.5))
assert eq(da.ceil(a), np.ceil(x))
assert eq(da.trunc(a / 2), np.trunc(x / 2))
assert eq(da.degrees(b), np.degrees(y))
assert eq(da.radians(a), np.radians(x))
assert eq(da.rint(a + 0.3), np.rint(x + 0.3))
assert eq(da.fix(a - 2.5), np.fix(x - 2.5))
assert eq(da.angle(a + 1j), np.angle(x + 1j))
assert eq(da.real(a + 1j), np.real(x + 1j))
assert eq((a + 1j).real, np.real(x + 1j))
assert eq(da.imag(a + 1j), np.imag(x + 1j))
assert eq((a + 1j).imag, np.imag(x + 1j))
assert eq(da.conj(a + 1j * b), np.conj(x + 1j * y))
assert eq((a + 1j * b).conj(), (x + 1j * y).conj())
assert eq(da.clip(b, 1, 4), np.clip(y, 1, 4))
assert eq(da.fabs(b), np.fabs(y))
assert eq(da.sign(b - 2), np.sign(y - 2))
l1, l2 = da.frexp(a)
r1, r2 = np.frexp(x)
assert eq(l1, r1)
assert eq(l2, r2)
l1, l2 = da.modf(a)
r1, r2 = np.modf(x)
assert eq(l1, r1)
assert eq(l2, r2)
assert eq(da.around(a, -1), np.around(x, -1))
