Merge branch 'main' into groupby_cat_unobserved

Author: rhshadrach

.github/workflows/32-bit-linux.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/code-checks.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
 
 env:
   ENV_FILE: environment.yml
@@ -88,7 +86,7 @@ jobs:
         echo "PYTHONPATH=$PYTHONPATH" >> $GITHUB_ENV
       if: ${{ steps.build.outcome == 'success' && always() }}
 
-    - name: Typing
+    - name: Typing + pylint
       uses: pre-commit/[email protected]
       with:
         extra_args: --hook-stage manual --all-files

.github/workflows/docbuild-and-upload.yml

@@ -5,14 +5,12 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     tags:
       - '*'
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
 
 env:
   ENV_FILE: environment.yml

.github/workflows/macos-windows.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/python-dev.yml

@@ -25,12 +25,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.github/workflows/sdist.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     types: [labeled, opened, synchronize, reopened]
     paths-ignore:
       - "doc/**"

.github/workflows/ubuntu.yml

@@ -5,12 +5,10 @@ on:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
   pull_request:
     branches:
       - main
       - 1.5.x
-      - 1.4.x
     paths-ignore:
       - "doc/**"
 

.pre-commit-config.yaml

@@ -18,16 +18,16 @@ repos:
         pass_filenames: true
         require_serial: false
 -   repo: https://github.com/python/black
-    rev: 22.8.0
+    rev: 22.10.0
     hooks:
     -   id: black
 -   repo: https://github.com/codespell-project/codespell
-    rev: v2.2.1
+    rev: v2.2.2
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
 -   repo: https://github.com/MarcoGorelli/cython-lint
-    rev: v0.1.8
+    rev: v0.2.1
     hooks:
     -   id: cython-lint
 -   repo: https://github.com/pre-commit/pre-commit-hooks
@@ -60,15 +60,16 @@ repos:
         - flake8-bugbear==22.7.1
         - pandas-dev-flaker==0.5.0
 -   repo: https://github.com/pycqa/pylint
-    rev: v2.15.3
+    rev: v2.15.5
     hooks:
     -   id: pylint
+        stages: [manual]
 -   repo: https://github.com/PyCQA/isort
     rev: 5.10.1
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.38.2
+    rev: v3.2.0
     hooks:
     -   id: pyupgrade
         args: [--py38-plus]
@@ -83,7 +84,7 @@ repos:
         types: [text]  # overwrite types: [rst]
         types_or: [python, rst]
 -   repo: https://github.com/sphinx-contrib/sphinx-lint
-    rev: v0.6.1
+    rev: v0.6.7
     hooks:
     - id: sphinx-lint
 -   repo: https://github.com/asottile/yesqa

asv_bench/benchmarks/attrs_caching.py

@@ -15,7 +15,7 @@ def setup(self):
         self.cur_index = self.df.index
 
     def time_get_index(self):
-        self.foo = self.df.index
+        self.df.index
 
     def time_set_index(self):
         self.df.index = self.cur_index

asv_bench/benchmarks/frame_methods.py

@@ -28,26 +28,6 @@ def time_frame_get_numeric_data(self):
         self.df._get_numeric_data()
 
 
-class Lookup:
-    def setup(self):
-        self.df = DataFrame(np.random.randn(10000, 8), columns=list("abcdefgh"))
-        self.df["foo"] = "bar"
-        self.row_labels = list(self.df.index[::10])[:900]
-        self.col_labels = list(self.df.columns) * 100
-        self.row_labels_all = np.array(
-            list(self.df.index) * len(self.df.columns), dtype="object"
-        )
-        self.col_labels_all = np.array(
-            list(self.df.columns) * len(self.df.index), dtype="object"
-        )
-
-    def time_frame_fancy_lookup(self):
-        self.df.lookup(self.row_labels, self.col_labels)
-
-    def time_frame_fancy_lookup_all(self):
-        self.df.lookup(self.row_labels_all, self.col_labels_all)
-
-
 class Reindex:
     def setup(self):
         N = 10**3

asv_bench/benchmarks/index_cached_properties.py

@@ -70,6 +70,3 @@ def time_engine(self, index_type):
 
     def time_inferred_type(self, index_type):
         self.idx.inferred_type
-
-    def time_is_all_dates(self, index_type):
-        self.idx.is_all_dates

asv_bench/benchmarks/inference.py

@@ -223,7 +223,7 @@ class ToDatetimeFormat:
     def setup(self):
         N = 100000
         self.s = Series(["19MAY11", "19MAY11:00:00:00"] * N)
-        self.s2 = self.s.str.replace(":\\S+$", "")
+        self.s2 = self.s.str.replace(":\\S+$", "", regex=True)
 
         self.same_offset = ["10/11/2018 00:00:00.045-07:00"] * N
         self.diff_offset = [

asv_bench/benchmarks/io/hdf.py

@@ -43,7 +43,7 @@ def setup(self):
             np.random.randn(N, 100), index=date_range("1/1/2000", periods=N)
         )
         self.df_dc = DataFrame(
-            np.random.randn(N, 10), columns=["C%03d" % i for i in range(10)]
+            np.random.randn(N, 10), columns=[f"C{i:03d}" for i in range(10)]
         )
 
         self.fname = "__test__.h5"

asv_bench/benchmarks/join_merge.py

@@ -22,26 +22,6 @@
     from pandas import ordered_merge as merge_ordered
 
 
-class Append:
-    def setup(self):
-        self.df1 = DataFrame(np.random.randn(10000, 4), columns=["A", "B", "C", "D"])
-        self.df2 = self.df1.copy()
-        self.df2.index = np.arange(10000, 20000)
-        self.mdf1 = self.df1.copy()
-        self.mdf1["obj1"] = "bar"
-        self.mdf1["obj2"] = "bar"
-        self.mdf1["int1"] = 5
-        self.mdf1 = self.mdf1._consolidate()
-        self.mdf2 = self.mdf1.copy()
-        self.mdf2.index = self.df2.index
-
-    def time_append_homogenous(self):
-        self.df1.append(self.df2)
-
-    def time_append_mixed(self):
-        self.mdf1.append(self.mdf2)
-
-
 class Concat:
 
     params = [0, 1]

asv_bench/benchmarks/tslibs/timestamp.py

@@ -50,62 +50,58 @@ def time_from_pd_timestamp(self):
 
 
 class TimestampProperties:
-    _freqs = [None, "B"]
-    params = [_tzs, _freqs]
-    param_names = ["tz", "freq"]
+    params = [_tzs]
+    param_names = ["tz"]
 
-    def setup(self, tz, freq):
-        self.ts = Timestamp("2017-08-25 08:16:14", tzinfo=tz, freq=freq)
+    def setup(self, tz):
+        self.ts = Timestamp("2017-08-25 08:16:14", tzinfo=tz)
 
-    def time_tz(self, tz, freq):
+    def time_tz(self, tz):
         self.ts.tz
 
-    def time_dayofweek(self, tz, freq):
+    def time_dayofweek(self, tz):
         self.ts.dayofweek
 
-    def time_dayofyear(self, tz, freq):
+    def time_dayofyear(self, tz):
         self.ts.dayofyear
 
-    def time_week(self, tz, freq):
+    def time_week(self, tz):
         self.ts.week
 
-    def time_quarter(self, tz, freq):
+    def time_quarter(self, tz):
         self.ts.quarter
 
-    def time_days_in_month(self, tz, freq):
+    def time_days_in_month(self, tz):
         self.ts.days_in_month
 
-    def time_freqstr(self, tz, freq):
-        self.ts.freqstr
-
-    def time_is_month_start(self, tz, freq):
+    def time_is_month_start(self, tz):
         self.ts.is_month_start
 
-    def time_is_month_end(self, tz, freq):
+    def time_is_month_end(self, tz):
         self.ts.is_month_end
 
-    def time_is_quarter_start(self, tz, freq):
+    def time_is_quarter_start(self, tz):
         self.ts.is_quarter_start
 
-    def time_is_quarter_end(self, tz, freq):
+    def time_is_quarter_end(self, tz):
         self.ts.is_quarter_end
 
-    def time_is_year_start(self, tz, freq):
+    def time_is_year_start(self, tz):
         self.ts.is_year_start
 
-    def time_is_year_end(self, tz, freq):
+    def time_is_year_end(self, tz):
         self.ts.is_year_end
 
-    def time_is_leap_year(self, tz, freq):
+    def time_is_leap_year(self, tz):
         self.ts.is_leap_year
 
-    def time_microsecond(self, tz, freq):
+    def time_microsecond(self, tz):
         self.ts.microsecond
 
-    def time_month_name(self, tz, freq):
+    def time_month_name(self, tz):
         self.ts.month_name()
 
-    def time_weekday_name(self, tz, freq):
+    def time_weekday_name(self, tz):
         self.ts.day_name()
 
 

ci/deps/actions-38-minimum_versions.yaml

@@ -32,7 +32,7 @@ dependencies:
   - gcsfs=2021.07.0
   - jinja2=3.0.0
   - lxml=4.6.3
-  - matplotlib=3.6.0
+  - matplotlib=3.6.1
   - numba=0.53.1
   - numexpr=2.7.3
   - odfpy=1.4.1

ci/fix_wheels.py

@@ -4,7 +4,12 @@
 import zipfile
 
 try:
-    _, wheel_path, dest_dir = sys.argv
+    if len(sys.argv) != 3:
+        raise ValueError(
+            "User must pass the path to the wheel and the destination directory."
+        )
+    wheel_path = sys.argv[1]
+    dest_dir = sys.argv[2]
     # Figure out whether we are building on 32 or 64 bit python
     is_32 = sys.maxsize <= 2**32
     PYTHON_ARCH = "x86" if is_32 else "x64"
@@ -50,5 +55,4 @@
 if not success:
     os.remove(repaired_wheel_path)
     raise exception
-else:
-    print(f"Successfully repaired wheel was written to {repaired_wheel_path}")
+print(f"Successfully repaired wheel was written to {repaired_wheel_path}")

doc/make.py

@@ -259,8 +259,7 @@ def latex(self, force=False):
                     "You should check the file "
                     '"build/latex/pandas.pdf" for problems.'
                 )
-            else:
-                self._run_os("make")
+            self._run_os("make")
             return ret_code
 
     def latex_forced(self):