Merge branch 'master' into duplicate-cut

Author: debnathshoham

.github/workflows/ci.yml

@@ -4,6 +4,7 @@ on:
   push:
     branches:
       - master
+      - 1.3.x
   pull_request:
     branches:
       - master
@@ -23,7 +24,7 @@ jobs:
 
     concurrency:
       group: ${{ github.ref }}-checks
-      cancel-in-progress: true
+      cancel-in-progress: ${{github.event_name == 'pull_request'}}
 
     steps:
     - name: Checkout
@@ -132,15 +133,15 @@ jobs:
         echo "${{ secrets.server_ssh_key }}" > ~/.ssh/id_rsa
         chmod 600 ~/.ssh/id_rsa
         echo "${{ secrets.server_ip }} ecdsa-sha2-nistp256 AAAAE2VjZHNhLXNoYTItbmlzdHAyNTYAAAAIbmlzdHAyNTYAAABBBE1Kkopomm7FHG5enATf7SgnpICZ4W2bw+Ho+afqin+w7sMcrsa0je7sbztFAV8YchDkiBKnWTG4cRT+KZgZCaY=" > ~/.ssh/known_hosts
-      if: github.event_name == 'push'
+      if: ${{github.event_name == 'push' && github.ref == 'refs/heads/master'}}
 
     - name: Upload web
       run: rsync -az --delete --exclude='pandas-docs' --exclude='docs' --exclude='Pandas_Cheat_Sheet*' web/build/ docs@${{ secrets.server_ip }}:/usr/share/nginx/pandas
-      if: github.event_name == 'push'
+      if: ${{github.event_name == 'push' && github.ref == 'refs/heads/master'}}
 
     - name: Upload dev docs
       run: rsync -az --delete doc/build/html/ docs@${{ secrets.server_ip }}:/usr/share/nginx/pandas/pandas-docs/dev
-      if: github.event_name == 'push'
+      if: ${{github.event_name == 'push' && github.ref == 'refs/heads/master'}}
 
     - name: Move docs into site directory
       run: mv doc/build/html web/build/docs

.github/workflows/database.yml

@@ -31,7 +31,7 @@ jobs:
 
     concurrency:
       group: ${{ github.ref }}-${{ matrix.ENV_FILE }}
-      cancel-in-progress: true
+      cancel-in-progress: ${{github.event_name == 'pull_request'}}
 
     services:
       mysql:

.github/workflows/posix.yml

@@ -4,6 +4,7 @@ on:
   push:
     branches:
       - master
+      - 1.3.x
   pull_request:
     branches:
       - master
@@ -45,7 +46,7 @@ jobs:
       TEST_ARGS: ${{ matrix.settings[6] }}
     concurrency:
       group: ${{ github.ref }}-${{ matrix.settings[0] }}
-      cancel-in-progress: true
+      cancel-in-progress: ${{github.event_name == 'pull_request'}}
 
     steps:
     - name: Checkout

.github/workflows/pre-commit.yml

@@ -5,13 +5,14 @@ on:
   push:
     branches:
       - master
+      - 1.3.x
 
 jobs:
   pre-commit:
     runs-on: ubuntu-latest
     concurrency:
       group: ${{ github.ref }}-pre-commit
-      cancel-in-progress: true
+      cancel-in-progress: ${{github.event_name == 'pull_request'}}
     steps:
     - uses: actions/checkout@v2
     - uses: actions/setup-python@v2

.github/workflows/python-dev.yml

@@ -8,6 +8,7 @@ on:
   pull_request:
     branches:
       - master
+      - 1.3.x
     paths-ignore:
       - "doc/**"
 
@@ -25,7 +26,7 @@ jobs:
 
     concurrency:
       group: ${{ github.ref }}-dev
-      cancel-in-progress: true
+      cancel-in-progress: ${{github.event_name == 'pull_request'}}
 
     steps:
     - uses: actions/checkout@v2

.github/workflows/sdist.yml

@@ -4,6 +4,7 @@ on:
   push:
     branches:
       - master
+      - 1.3.x
   pull_request:
     branches:
       - master
@@ -23,6 +24,9 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.8", "3.9"]
+    concurrency:
+      group: ${{github.ref}}-${{matrix.python-version}}-sdist
+      cancel-in-progress: ${{github.event_name == 'pull_request'}}
 
     steps:
     - uses: actions/checkout@v2

.pre-commit-config.yaml

@@ -53,11 +53,11 @@ repos:
         types: [text]
         args: [--append-config=flake8/cython-template.cfg]
 -   repo: https://github.com/PyCQA/isort
-    rev: 5.9.1
+    rev: 5.9.2
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.20.0
+    rev: v2.21.0
     hooks:
     -   id: pyupgrade
         args: [--py38-plus]

asv_bench/benchmarks/algos/isin.py

@@ -1,10 +1,5 @@
 import numpy as np
 
-try:
-    from pandas.compat import np_version_under1p20
-except ImportError:
-    from pandas.compat.numpy import _np_version_under1p20 as np_version_under1p20
-
 from pandas import (
     Categorical,
     NaT,
@@ -283,10 +278,6 @@ class IsInLongSeriesLookUpDominates:
     def setup(self, dtype, MaxNumber, series_type):
         N = 10 ** 7
 
-        # https://github.com/pandas-dev/pandas/issues/39844
-        if not np_version_under1p20 and dtype in ("Int64", "Float64"):
-            raise NotImplementedError
-
         if series_type == "random_hits":
             array = np.random.randint(0, MaxNumber, N)
         if series_type == "random_misses":
@@ -297,7 +288,8 @@ def setup(self, dtype, MaxNumber, series_type):
             array = np.arange(N) + MaxNumber
 
         self.series = Series(array).astype(dtype)
-        self.values = np.arange(MaxNumber).astype(dtype)
+
+        self.values = np.arange(MaxNumber).astype(dtype.lower())
 
     def time_isin(self, dtypes, MaxNumber, series_type):
         self.series.isin(self.values)
@@ -313,16 +305,12 @@ class IsInLongSeriesValuesDominate:
     def setup(self, dtype, series_type):
         N = 10 ** 7
 
-        # https://github.com/pandas-dev/pandas/issues/39844
-        if not np_version_under1p20 and dtype in ("Int64", "Float64"):
-            raise NotImplementedError
-
         if series_type == "random":
             vals = np.random.randint(0, 10 * N, N)
         if series_type == "monotone":
             vals = np.arange(N)
 
-        self.values = vals.astype(dtype)
+        self.values = vals.astype(dtype.lower())
         M = 10 ** 6 + 1
         self.series = Series(np.arange(M)).astype(dtype)
 

asv_bench/benchmarks/frame_methods.py

@@ -232,6 +232,22 @@ def time_to_html_mixed(self):
         self.df2.to_html()
 
 
+class ToDict:
+    params = [["dict", "list", "series", "split", "records", "index"]]
+    param_names = ["orient"]
+
+    def setup(self, orient):
+        data = np.random.randint(0, 1000, size=(10000, 4))
+        self.int_df = DataFrame(data)
+        self.datetimelike_df = self.int_df.astype("timedelta64[ns]")
+
+    def time_to_dict_ints(self, orient):
+        self.int_df.to_dict(orient=orient)
+
+    def time_to_dict_datetimelike(self, orient):
+        self.datetimelike_df.to_dict(orient=orient)
+
+
 class ToNumpy:
     def setup(self):
         N = 10000

asv_bench/benchmarks/io/csv.py

@@ -291,7 +291,8 @@ class ReadCSVFloatPrecision(StringIORewind):
 
     def setup(self, sep, decimal, float_precision):
         floats = [
-            "".join(random.choice(string.digits) for _ in range(28)) for _ in range(15)
+            "".join([random.choice(string.digits) for _ in range(28)])
+            for _ in range(15)
         ]
         rows = sep.join([f"0{decimal}" + "{}"] * 3) + "\n"
         data = rows * 5
@@ -395,7 +396,7 @@ class ReadCSVCachedParseDates(StringIORewind):
     param_names = ["do_cache", "engine"]
 
     def setup(self, do_cache, engine):
-        data = ("\n".join(f"10/{year}" for year in range(2000, 2100)) + "\n") * 10
+        data = ("\n".join([f"10/{year}" for year in range(2000, 2100)]) + "\n") * 10
         self.StringIO_input = StringIO(data)
 
     def time_read_csv_cached(self, do_cache, engine):