Merge remote-tracking branch 'upstream/master' into bisect

Author: simonjayhawkins

.github/workflows/ci.yml

@@ -37,12 +37,6 @@ jobs:
         ci/code_checks.sh lint
       if: always()
 
-    - name: Dependencies consistency
-      run: |
-        source activate pandas-dev
-        ci/code_checks.sh dependencies
-      if: always()
-
     - name: Checks on imported code
       run: |
         source activate pandas-dev

.pre-commit-config.yaml

@@ -9,24 +9,23 @@ repos:
     -   id: flake8
         additional_dependencies: [flake8-comprehensions>=3.1.0]
     -   id: flake8
-        name: flake8-pyx
-        files: \.(pyx|pxd)$
-        types:
-          - file
+        name: flake8 (cython)
+        types: [cython]
         args: [--append-config=flake8/cython.cfg]
     -   id: flake8
-        name: flake8-pxd
+        name: flake8 (cython template)
         files: \.pxi\.in$
         types:
           - file
         args: [--append-config=flake8/cython-template.cfg]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.6.0
+    rev: 5.6.3
     hooks:
     -   id: isort
-        exclude: ^pandas/__init__\.py$|^pandas/core/api\.py$
-        files: '.pxd$|.py$'
-        types: [file]
+        name: isort (python)
+    -   id: isort
+        name: isort (cython)
+        types: [cython]
 -   repo: https://github.com/asottile/pyupgrade
     rev: v2.7.2
     hooks:
@@ -46,6 +45,60 @@ repos:
         files: ^(environment.yml|requirements-dev.txt)$
         pass_filenames: false
         additional_dependencies: [pyyaml]
+    -   id: flake8-rst
+        name: flake8-rst
+        description: Run flake8 on code snippets in docstrings or RST files
+        language: python
+        entry: flake8-rst
+        types: [rst]
+        args: [--filename=*.rst]
+        additional_dependencies: [flake8-rst==0.7.0, flake8==3.7.9]
+    -   id: incorrect-sphinx-directives
+        name: Check for incorrect Sphinx directives
+        language: pygrep
+        entry: |
+            (?x)
+            # Check for cases of e.g. .. warning: instead of .. warning::
+            \.\.\ (
+                autosummary|contents|currentmodule|deprecated|
+                function|image|important|include|ipython|literalinclude|
+                math|module|note|raw|seealso|toctree|versionadded|
+                versionchanged|warning
+            ):[^:]
+        files: \.(py|pyx|rst)$
+    -   id: non-standard-imports
+        name: Check for non-standard imports
+        language: pygrep
+        entry: |
+            (?x)
+            # Check for imports from pandas.core.common instead of `import pandas.core.common as com`
+            from\ pandas\.core\.common\ import|
+            from\ pandas\.core\ import\ common|
+
+            # Check for imports from collections.abc instead of `from collections import abc`
+            from\ collections\.abc\ import|
+
+            from\ numpy\ import\ nan
+        types: [python]
+    -   id: non-standard-imports-in-tests
+        name: Check for non-standard imports in test suite
+        language: pygrep
+        entry: |
+            (?x)
+            # Check for imports from pandas._testing instead of `import pandas._testing as tm`
+            from\ pandas\._testing\ import|
+            from\ pandas\ import\ _testing\ as\ tm|
+
+            # No direct imports from conftest
+            conftest\ import|
+            import\ conftest
+        types: [python]
+        files: ^pandas/tests/
+    -   id: incorrect-code-directives
+        name: Check for incorrect code block or IPython directives
+        language: pygrep
+        entry: (\.\. code-block ::|\.\. ipython ::)
+        files: \.(py|pyx|rst)$
 -   repo: https://github.com/asottile/yesqa
     rev: v1.2.2
     hooks:
@@ -54,4 +107,6 @@ repos:
     rev: v3.2.0
     hooks:
     -   id: end-of-file-fixer
-        exclude: '.html$|^LICENSES/|.csv$|.txt$|.svg$|.py$'
+        exclude: ^LICENSES/|\.(html|csv|txt|svg|py)$
+    -   id: trailing-whitespace
+        exclude: \.(html|svg)$

asv_bench/benchmarks/groupby.py

@@ -358,6 +358,26 @@ def time_category_size(self):
         self.draws.groupby(self.cats).size()
 
 
+class FillNA:
+    def setup(self):
+        N = 100
+        self.df = DataFrame(
+            {"group": [1] * N + [2] * N, "value": [np.nan, 1.0] * N}
+        ).set_index("group")
+
+    def time_df_ffill(self):
+        self.df.groupby("group").fillna(method="ffill")
+
+    def time_df_bfill(self):
+        self.df.groupby("group").fillna(method="bfill")
+
+    def time_srs_ffill(self):
+        self.df.groupby("group")["value"].fillna(method="ffill")
+
+    def time_srs_bfill(self):
+        self.df.groupby("group")["value"].fillna(method="bfill")
+
+
 class GroupByMethods:
 
     param_names = ["dtype", "method", "application"]

asv_bench/benchmarks/io/pickle.py

@@ -24,5 +24,11 @@ def time_read_pickle(self):
     def time_write_pickle(self):
         self.df.to_pickle(self.fname)
 
+    def peakmem_read_pickle(self):
+        read_pickle(self.fname)
+
+    def peakmem_write_pickle(self):
+        self.df.to_pickle(self.fname)
+
 
 from ..pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/rolling.py

@@ -76,12 +76,21 @@ class ExpandingMethods:
 
     def setup(self, constructor, dtype, method):
         N = 10 ** 5
+        N_groupby = 100
         arr = (100 * np.random.random(N)).astype(dtype)
         self.expanding = getattr(pd, constructor)(arr).expanding()
+        self.expanding_groupby = (
+            pd.DataFrame({"A": arr[:N_groupby], "B": range(N_groupby)})
+            .groupby("B")
+            .expanding()
+        )
 
     def time_expanding(self, constructor, dtype, method):
         getattr(self.expanding, method)()
 
+    def time_expanding_groupby(self, constructor, dtype, method):
+        getattr(self.expanding_groupby, method)()
+
 
 class EWMMethods:
 

asv_bench/benchmarks/timeseries.py

@@ -3,7 +3,14 @@
 import dateutil
 import numpy as np
 
-from pandas import DataFrame, Series, date_range, period_range, to_datetime
+from pandas import (
+    DataFrame,
+    Series,
+    date_range,
+    period_range,
+    timedelta_range,
+    to_datetime,
+)
 
 from pandas.tseries.frequencies import infer_freq
 
@@ -121,12 +128,15 @@ def time_convert(self):
 
 class Iteration:
 
-    params = [date_range, period_range]
+    params = [date_range, period_range, timedelta_range]
     param_names = ["time_index"]
 
     def setup(self, time_index):
         N = 10 ** 6
-        self.idx = time_index(start="20140101", freq="T", periods=N)
+        if time_index is timedelta_range:
+            self.idx = time_index(start=0, freq="T", periods=N)
+        else:
+            self.idx = time_index(start="20140101", freq="T", periods=N)
         self.exit = 10000
 
     def time_iter(self, time_index):