ueshin commented on a change in pull request #32469: URL: https://github.com/apache/spark/pull/32469#discussion_r634683423
########## File path: python/pyspark/pandas/data_type_ops/num_ops.py ########## @@ -0,0 +1,304 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +import numbers +from typing import TYPE_CHECKING, Union + +import numpy as np +from pandas.api.types import CategoricalDtype + +from pyspark.sql import Column, functions as F +from pyspark.sql.types import ( + NumericType, + StringType, + TimestampType, +) + +from pyspark.pandas.base import column_op, IndexOpsMixin, numpy_column_op +from pyspark.pandas.data_type_ops.base import DataTypeOps +from pyspark.pandas.spark import functions as SF + +if TYPE_CHECKING: + from pyspark.pandas.indexes import Index # noqa: F401 (SPARK-34943) + from pyspark.pandas.series import Series # noqa: F401 (SPARK-34943) + + +class NumericOps(DataTypeOps): + """ + The class for binary operations of numeric pandas-on-Spark objects. + """ + + @property + def pretty_name(self) -> str: + return 'numerics' + + def __add__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("string addition can only be applied to string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("addition can not be applied to given types.") + + return column_op(Column.__add__)(left, right) + + def __sub__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("subtraction can not be applied to string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("subtraction can not be applied to given types.") + + return column_op(Column.__sub__)(left, right) + + def __truediv__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("division can not be applied on string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("division can not be applied to given types.") + + def truediv(left, right): + return F.when(F.lit(right != 0) | F.lit(right).isNull(), left.__div__(right)).otherwise( + F.when(F.lit(left == np.inf) | F.lit(left == -np.inf), left).otherwise( + F.lit(np.inf).__div__(left) + ) + ) Review comment: ditto for `__floordiv__`, `__rtruediv__`, and `__rfloordiv__`. ########## File path: python/pyspark/pandas/data_type_ops/num_ops.py ########## @@ -0,0 +1,304 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +import numbers +from typing import TYPE_CHECKING, Union + +import numpy as np +from pandas.api.types import CategoricalDtype + +from pyspark.sql import Column, functions as F +from pyspark.sql.types import ( + NumericType, + StringType, + TimestampType, +) + +from pyspark.pandas.base import column_op, IndexOpsMixin, numpy_column_op +from pyspark.pandas.data_type_ops.base import DataTypeOps +from pyspark.pandas.spark import functions as SF + +if TYPE_CHECKING: + from pyspark.pandas.indexes import Index # noqa: F401 (SPARK-34943) + from pyspark.pandas.series import Series # noqa: F401 (SPARK-34943) + + +class NumericOps(DataTypeOps): + """ + The class for binary operations of numeric pandas-on-Spark objects. + """ + + @property + def pretty_name(self) -> str: + return 'numerics' + + def __add__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("string addition can only be applied to string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("addition can not be applied to given types.") + + return column_op(Column.__add__)(left, right) + + def __sub__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("subtraction can not be applied to string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("subtraction can not be applied to given types.") + + return column_op(Column.__sub__)(left, right) + + def __truediv__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("division can not be applied on string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("division can not be applied to given types.") + + def truediv(left, right): + return F.when(F.lit(right != 0) | F.lit(right).isNull(), left.__div__(right)).otherwise( + F.when(F.lit(left == np.inf) | F.lit(left == -np.inf), left).otherwise( + F.lit(np.inf).__div__(left) + ) + ) Review comment: We can do it in a separate PR, though ########## File path: python/pyspark/pandas/data_type_ops/num_ops.py ########## @@ -0,0 +1,304 @@ +# +# Licensed to the Apache Software Foundation (ASF) under one or more +# contributor license agreements. See the NOTICE file distributed with +# this work for additional information regarding copyright ownership. +# The ASF licenses this file to You under the Apache License, Version 2.0 +# (the "License"); you may not use this file except in compliance with +# the License. You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +# + +import numbers +from typing import TYPE_CHECKING, Union + +import numpy as np +from pandas.api.types import CategoricalDtype + +from pyspark.sql import Column, functions as F +from pyspark.sql.types import ( + NumericType, + StringType, + TimestampType, +) + +from pyspark.pandas.base import column_op, IndexOpsMixin, numpy_column_op +from pyspark.pandas.data_type_ops.base import DataTypeOps +from pyspark.pandas.spark import functions as SF + +if TYPE_CHECKING: + from pyspark.pandas.indexes import Index # noqa: F401 (SPARK-34943) + from pyspark.pandas.series import Series # noqa: F401 (SPARK-34943) + + +class NumericOps(DataTypeOps): + """ + The class for binary operations of numeric pandas-on-Spark objects. + """ + + @property + def pretty_name(self) -> str: + return 'numerics' + + def __add__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("string addition can only be applied to string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("addition can not be applied to given types.") + + return column_op(Column.__add__)(left, right) + + def __sub__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("subtraction can not be applied to string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("subtraction can not be applied to given types.") + + return column_op(Column.__sub__)(left, right) + + def __truediv__(self, left, right) -> Union["Series", "Index"]: + if ( + isinstance(right, IndexOpsMixin) and isinstance(right.spark.data_type, StringType) + ) or isinstance(right, str): + raise TypeError("division can not be applied on string series or literals.") + + if ( + isinstance(right, IndexOpsMixin) + and ( + isinstance(right.dtype, CategoricalDtype) + or (not isinstance(right.spark.data_type, NumericType)) + ) + ) and not isinstance(right, numbers.Number): + raise TypeError("division can not be applied to given types.") + + def truediv(left, right): + return F.when(F.lit(right != 0) | F.lit(right).isNull(), left.__div__(right)).otherwise( + F.when(F.lit(left == np.inf) | F.lit(left == -np.inf), left).otherwise( + F.lit(np.inf).__div__(left) + ) + ) Review comment: I guess we should separate `__truediv__` for `IntegralOps` and `FractionalOps` because this includes some `FractionalOps` specific codes, e.g., `left` will never be `np.inf` in `IntegralOps`. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] --------------------------------------------------------------------- To unsubscribe, e-mail: [email protected] For additional commands, e-mail: [email protected]
