FIX-#2596: Revert fix for binary ops

Signed-off-by: Igoshev, Yaroslav <[email protected]>

Author: YarShev

asv_bench/asv.conf.json

@@ -2,57 +2,65 @@
     // The version of the config file format.  Do not change, unless
     // you know what you are doing.
     "version": 1,
+
     // The name of the project being benchmarked
     "project": "modin",
+
     // The project's homepage
     "project_url": "https://modin.readthedocs.io/",
+
     // The URL or local path of the source code repository for the
     // project being benchmarked
     "repo": "..",
+
     // The Python project's subdirectory in your repo.  If missing or
     // the empty string, the project is assumed to be located at the root
     // of the repository.
     // "repo_subdir": "",
+
     // Customizable commands for building, installing, and
     // uninstalling the project. See asv.conf.json documentation.
     //
-    "install_command": [
-        "in-dir={env_dir} python -mpip install {wheel_file}[ray]"
-    ],
+    "install_command": ["in-dir={env_dir} python -mpip install {wheel_file}[ray]"],
     // "uninstall_command": ["return-code=any python -mpip uninstall -y {project}"],
     // "build_command": [
     //     "python setup.py build",
     //     "PIP_NO_BUILD_ISOLATION=false python -mpip wheel --no-deps --no-index -w {build_cache_dir} {build_dir}"
     // ],
+
     // List of branches to benchmark. If not provided, defaults to "master"
     // (for git) or "default" (for mercurial).
     // "branches": ["master"], // for git
     // "branches": ["default"],    // for mercurial
+
     // The DVCS being used.  If not set, it will be automatically
     // determined from "repo" by looking at the protocol in the URL
     // (if remote), or by looking for special directories, such as
     // ".git" (if local).
     // "dvcs": "git",
+
     // The tool to use to create environments.  May be "conda",
     // "virtualenv" or other value depending on the plugins in use.
     // If missing or the empty string, the tool will be automatically
     // determined by looking for tools on the PATH environment
     // variable.
     "environment_type": "conda",
+
     // timeout in seconds for installing any dependencies in environment
     // defaults to 10 min
     //"install_timeout": 600,
+
     // the base URL to show a commit for the project.
     "show_commit_url": "https://github.com/modin-project/modin/commit/",
+
     // The Pythons you'd like to test against.  If not provided, defaults
     // to the current version of Python used to run `asv`.
     // "pythons": ["3.7"],
+
     // The list of conda channel names to be searched for benchmark
     // dependency packages in the specified order
-    "conda_channels": [
-        "conda-forge",
-        "defaults"
-    ],
+    "conda_channels": ["conda-forge", "defaults"],
+
     // The matrix of dependencies to test.  Each key is the name of a
     // package (in PyPI) and the values are version numbers.  An empty
     // list or empty string indicates to just test against the default
@@ -98,24 +106,31 @@
     //     // additional env if run on windows+conda
     //     {"platform": "win32", "environment_type": "conda", "python": "2.7", "libpython": ""},
     // ],
+
     // The directory (relative to the current directory) that benchmarks are
     // stored in.  If not provided, defaults to "benchmarks"
     // "benchmark_dir": "benchmarks",
+
     // The directory (relative to the current directory) to cache the Python
     // environments in.  If not provided, defaults to "env"
     "env_dir": ".asv/env",
+
     // The directory (relative to the current directory) that raw benchmark
     // results are stored in.  If not provided, defaults to "results".
     "results_dir": ".asv/results",
+
     // The directory (relative to the current directory) that the html tree
     // should be written to.  If not provided, defaults to "html".
     "html_dir": ".asv/html",
+
     // The number of characters to retain in the commit hashes.
     // "hash_length": 8,
+
     // `asv` will cache results of the recent builds in each
     // environment, making them faster to install next time.  This is
     // the number of builds to keep, per environment.
     // "build_cache_size": 2,
+
     // The commits after which the regression search in `asv publish`
     // should start looking for regressions. Dictionary whose keys are
     // regexps matching to benchmark names, and values corresponding to
@@ -128,6 +143,7 @@
     //    "some_benchmark": "352cdf",  // Consider regressions only after this commit
     //    "another_benchmark": null,   // Skip regression detection altogether
     // },
+
     // The thresholds for relative change in results, after which `asv
     // publish` starts reporting regressions. Dictionary of the same
     // form as in ``regressions_first_commits``, with values
@@ -138,4 +154,4 @@
     //    "some_benchmark": 0.01,     // Threshold of 1%
     //    "another_benchmark": 0.5,   // Threshold of 50%
     // },
-}
+}

modin/data_management/functions/binary_function.py

@@ -24,7 +24,6 @@ def caller(query_compiler, other, *args, **kwargs):
             axis = kwargs.get("axis", 0)
             broadcast = kwargs.pop("broadcast", False)
             join_type = call_kwds.get("join_type", "outer")
-            squeeze_self = kwargs.pop("squeeze_self", None)
             if isinstance(other, type(query_compiler)):
                 if broadcast:
                     assert (
@@ -55,37 +54,11 @@ def caller(query_compiler, other, *args, **kwargs):
                     )
             else:
                 if isinstance(other, (list, np.ndarray, pandas.Series)):
-                    if len(query_compiler.columns) == 1:
-
-                        def _apply_func(df):
-                            result = func(
-                                df.squeeze(axis=1) if squeeze_self else df,
-                                other,
-                                *args,
-                                **kwargs
-                            )
-                            return pandas.DataFrame(result)
-
-                        apply_func = _apply_func
-                        build_mapreduce_func = False
-                    else:
-
-                        def _apply_func(df):
-                            return func(
-                                df.squeeze(axis=1) if squeeze_self else df,
-                                other,
-                                *args,
-                                **kwargs
-                            )
-
-                        apply_func = _apply_func
-                        build_mapreduce_func = True
                     new_modin_frame = query_compiler._modin_frame._apply_full_axis(
                         axis,
-                        apply_func,
+                        lambda df: func(df, other, *args, **kwargs),
                         new_index=query_compiler.index,
                         new_columns=query_compiler.columns,
-                        build_mapreduce_func=build_mapreduce_func,
                     )
                 else:
                     new_modin_frame = query_compiler._modin_frame._map(

modin/engines/base/frame/data.py

@@ -1272,7 +1272,6 @@ def _apply_full_axis(
         new_index=None,
         new_columns=None,
         dtypes=None,
-        build_mapreduce_func=True,
     ):
         """
         Perform a function across an entire axis.
@@ -1310,7 +1309,6 @@ def _apply_full_axis(
             new_columns=new_columns,
             dtypes=dtypes,
             other=None,
-            build_mapreduce_func=build_mapreduce_func,
         )
 
     def _apply_full_axis_select_indices(
@@ -1645,7 +1643,6 @@ def broadcast_apply_full_axis(
         apply_indices=None,
         enumerate_partitions=False,
         dtypes=None,
-        build_mapreduce_func=True,
     ):
         """Broadcast partitions of other dataframe partitions and apply a function along full axis.
 
@@ -1691,9 +1688,7 @@ def broadcast_apply_full_axis(
             axis=axis,
             left=self._partitions,
             right=other,
-            apply_func=self._build_mapreduce_func(axis, func)
-            if build_mapreduce_func
-            else func,
+            apply_func=self._build_mapreduce_func(axis, func),
             apply_indices=apply_indices,
             enumerate_partitions=enumerate_partitions,
             keep_partitioning=True,

modin/pandas/series.py

@@ -142,12 +142,16 @@ def __radd__(self, left):
         return self.add(left)
 
     def __and__(self, other):
+        if isinstance(other, (list, np.ndarray, pandas.Series)):
+            return self._default_to_pandas(pandas.Series.__and__, other)
         new_self, new_other = self._prepare_inter_op(other)
-        return new_self._binary_op("__and__", new_other, axis=0, squeeze_self=True)
+        return super(Series, new_self).__and__(new_other)
 
     def __rand__(self, other):
+        if isinstance(other, (list, np.ndarray, pandas.Series)):
+            return self._default_to_pandas(pandas.Series.__rand__, other)
         new_self, new_other = self._prepare_inter_op(other)
-        return self._binary_op("__rand__", other, axis=0, squeeze_self=True)
+        return super(Series, new_self).__rand__(new_other)
 
     def __array__(self, dtype=None):
         return super(Series, self).__array__(dtype).flatten()
@@ -215,20 +219,28 @@ def __rmul__(self, left):
         return self.rmul(left)
 
     def __or__(self, other):
+        if isinstance(other, (list, np.ndarray, pandas.Series)):
+            return self._default_to_pandas(pandas.Series.__or__, other)
         new_self, new_other = self._prepare_inter_op(other)
-        return new_self._binary_op("__or__", new_other, axis=0, squeeze_self=True)
+        return super(Series, new_self).__or__(new_other)
 
     def __ror__(self, other):
+        if isinstance(other, (list, np.ndarray, pandas.Series)):
+            return self._default_to_pandas(pandas.Series.__ror__, other)
         new_self, new_other = self._prepare_inter_op(other)
-        return self._binary_op("__ror__", other, axis=0, squeeze_self=True)
+        return super(Series, new_self).__ror__(new_other)
 
     def __xor__(self, other):
+        if isinstance(other, (list, np.ndarray, pandas.Series)):
+            return self._default_to_pandas(pandas.Series.__xor__, other)
         new_self, new_other = self._prepare_inter_op(other)
-        return new_self._binary_op("__xor__", new_other, axis=0, squeeze_self=True)
+        return super(Series, new_self).__xor__(new_other)
 
     def __rxor__(self, other):
+        if isinstance(other, (list, np.ndarray, pandas.Series)):
+            return self._default_to_pandas(pandas.Series.__rxor__, other)
         new_self, new_other = self._prepare_inter_op(other)
-        return new_self._binary_op("__rxor__", new_other, axis=0, squeeze_self=True)
+        return super(Series, new_self).__rxor__(new_other)
 
     def __pow__(self, right):
         return self.pow(right)