Merge branch 'master' into mypy/arraylike

Author: ivanovmg

.github/ISSUE_TEMPLATE/documentation_improvement.md

@@ -9,7 +9,7 @@ labels: "Docs, Needs Triage"
 
 #### Location of the documentation
 
-[this should provide the location of the documentation, e.g. "pandas.read_csv" or the URL of the documentation, e.g. "https://dev.pandas.io/docs/reference/api/pandas.read_csv.html"]
+[this should provide the location of the documentation, e.g. "pandas.read_csv" or the URL of the documentation, e.g. "https://pandas.pydata.org/docs/reference/api/pandas.read_csv.html"]
 
 **Note**: You can check the latest versions of the docs on `master` [here](https://pandas.pydata.org/docs/dev/).
 

.github/workflows/ci.yml

@@ -2,74 +2,81 @@ name: CI
 
 on:
   push:
-    branches: master
+    branches: [master]
   pull_request:
     branches:
       - master
       - 1.2.x
 
 env:
   ENV_FILE: environment.yml
+  PANDAS_CI: 1
 
 jobs:
   checks:
     name: Checks
     runs-on: ubuntu-latest
-    steps:
-
-    - name: Setting conda path
-      run: echo "${HOME}/miniconda3/bin" >> $GITHUB_PATH
+    defaults:
+      run:
+        shell: bash -l {0}
 
+    steps:
     - name: Checkout
       uses: actions/checkout@v1
 
     - name: Looking for unwanted patterns
       run: ci/code_checks.sh patterns
       if: always()
 
-    - name: Setup environment and build pandas
-      run: ci/setup_env.sh
-      if: always()
+    - name: Cache conda
+      uses: actions/cache@v2
+      with:
+        path: ~/conda_pkgs_dir
+        key: ${{ runner.os }}-conda-${{ hashFiles('${{ env.ENV_FILE }}') }}
 
-    - name: Linting
+    - uses: conda-incubator/setup-miniconda@v2
+      with:
+        activate-environment: pandas-dev
+        channel-priority: strict
+        environment-file: ${{ env.ENV_FILE }}
+        use-only-tar-bz2: true
+
+    - name: Environment Detail
       run: |
-        source activate pandas-dev
-        ci/code_checks.sh lint
+        conda info
+        conda list
+
+    - name: Build Pandas
+      run: |
+        python setup.py build_ext -j 2
+        python -m pip install -e . --no-build-isolation --no-use-pep517
+
+    - name: Linting
+      run: ci/code_checks.sh lint
       if: always()
 
     - name: Checks on imported code
-      run: |
-        source activate pandas-dev
-        ci/code_checks.sh code
+      run: ci/code_checks.sh code
       if: always()
 
     - name: Running doctests
-      run: |
-        source activate pandas-dev
-        ci/code_checks.sh doctests
+      run: ci/code_checks.sh doctests
       if: always()
 
     - name: Docstring validation
-      run: |
-        source activate pandas-dev
-        ci/code_checks.sh docstrings
+      run: ci/code_checks.sh docstrings
       if: always()
 
     - name: Typing validation
-      run: |
-        source activate pandas-dev
-        ci/code_checks.sh typing
+      run: ci/code_checks.sh typing
       if: always()
 
     - name: Testing docstring validation script
-      run: |
-        source activate pandas-dev
-        pytest --capture=no --strict-markers scripts
+      run: pytest --capture=no --strict-markers scripts
       if: always()
 
     - name: Running benchmarks
       run: |
-        source activate pandas-dev
         cd asv_bench
         asv check -E existing
         git remote add upstream https://github.com/pandas-dev/pandas.git
@@ -106,7 +113,6 @@ jobs:
       run: |
         source activate pandas-dev
         python web/pandas_web.py web/pandas --target-path=web/build
-
     - name: Build documentation
       run: |
         source activate pandas-dev
@@ -132,3 +138,22 @@ jobs:
     - name: Upload dev docs
       run: rsync -az --delete doc/build/html/ docs@${{ secrets.server_ip }}:/usr/share/nginx/pandas/pandas-docs/dev
       if: github.event_name == 'push'
+
+  data_manager:
+    name: Test experimental data manager
+    runs-on: ubuntu-latest
+    steps:
+
+    - name: Setting conda path
+      run: echo "${HOME}/miniconda3/bin" >> $GITHUB_PATH
+
+    - name: Checkout
+      uses: actions/checkout@v1
+
+    - name: Setup environment and build pandas
+      run: ci/setup_env.sh
+
+    - name: Run tests
+      run: |
+        source activate pandas-dev
+        pytest pandas/tests/frame/methods --array-manager

.github/workflows/comment_bot.yml

@@ -29,7 +29,7 @@ jobs:
       - name: Install-pre-commit
         run: python -m pip install --upgrade pre-commit
       - name: Run pre-commit
-        run: pre-commit run --all-files || (exit 0)
+        run: pre-commit run --from-ref=origin/master --to-ref=HEAD --all-files || (exit 0)
       - name: Commit results
         run: |
           git config user.name "$(git log -1 --pretty=format:%an)"

.pre-commit-config.yaml

@@ -24,12 +24,12 @@ repos:
     hooks:
     -   id: isort
 -   repo: https://github.com/asottile/pyupgrade
-    rev: v2.7.4
+    rev: v2.10.0
     hooks:
     -   id: pyupgrade
-        args: [--py37-plus]
+        args: [--py37-plus, --keep-runtime-typing]
 -   repo: https://github.com/pre-commit/pygrep-hooks
-    rev: v1.7.0
+    rev: v1.7.1
     hooks:
       - id: rst-backticks
       - id: rst-directive-colons
@@ -60,11 +60,11 @@ repos:
         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|
+            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\ collections\.abc\ import
 
     -   id: non-standard-numpy.random-related-imports
         name: Check for non-standard numpy.random-related imports excluding pandas/_testing.py
@@ -73,24 +73,24 @@ repos:
         entry: |
             (?x)
             # Check for imports from np.random.<method> instead of `from numpy import random` or `from numpy.random import <method>`
-            from\ numpy\ import\ random|
-            from\ numpy.random\ import
+            from\ numpy\ import\ random
+            |from\ numpy.random\ import
         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|
+            from\ pandas\._testing\ import
+            |from\ pandas\ import\ _testing\ as\ tm
 
             # No direct imports from conftest
-            conftest\ import|
-            import\ conftest
+            |conftest\ import
+            |import\ conftest
 
             # Check for use of pandas.testing instead of tm
-            pd\.testing\.
+            |pd\.testing\.
         types: [python]
         files: ^pandas/tests/
     -   id: incorrect-code-directives
@@ -127,6 +127,12 @@ repos:
         types: [python]
         files: ^pandas/tests/
         exclude: ^pandas/tests/extension/
+    -   id: unwanted-patters-pytest-xfail
+        name: Check for use of pytest.xfail
+        entry: pytest\.xfail
+        language: pygrep
+        types: [python]
+        files: ^pandas/tests/
     -   id: inconsistent-namespace-usage
         name: 'Check for inconsistent use of pandas namespace in tests'
         entry: python scripts/check_for_inconsistent_pandas_namespace.py
@@ -135,7 +141,7 @@ repos:
         files: ^pandas/tests/
     -   id: FrameOrSeriesUnion
         name: Check for use of Union[Series, DataFrame] instead of FrameOrSeriesUnion alias
-        entry: Union\[.*(Series.*DataFrame|DataFrame.*Series).*\]
+        entry: Union\[.*(Series,.*DataFrame|DataFrame,.*Series).*\]
         language: pygrep
         types: [python]
         exclude: ^pandas/_typing\.py$
@@ -145,11 +151,11 @@ repos:
         language: pygrep
         types_or: [python, cython]
     -   id: unwanted-typing
-        name: Check for use of comment-based annotation syntax and missing error codes
+        name: Check for outdated annotation syntax and missing error codes
         entry: |
             (?x)
-            \#\ type:\ (?!ignore)|
-            \#\ type:\s?ignore(?!\[)
+            \#\ type:\ (?!ignore)
+            |\#\ type:\s?ignore(?!\[)
         language: pygrep
         types: [python]
     -   id: np-bool
@@ -165,9 +171,15 @@ repos:
         files: ^pandas/tests/
         exclude: |
             (?x)^
-            pandas/tests/io/excel/test_writers\.py|
-            pandas/tests/io/pytables/common\.py|
-            pandas/tests/io/pytables/test_store\.py$
+            pandas/tests/io/excel/test_writers\.py
+            |pandas/tests/io/pytables/common\.py
+            |pandas/tests/io/pytables/test_store\.py$
+    -   id: no-pandas-api-types
+        name: Check code for instances of pd.api.types
+        entry: (pd|pandas)\.api\.types\.
+        language: pygrep
+        types: [python]
+        files: ^pandas/tests/
 -   repo: https://github.com/asottile/yesqa
     rev: v1.2.2
     hooks:
@@ -183,4 +195,14 @@ repos:
     hooks:
     -   id: codespell
         types_or: [python, rst, markdown]
-        files: ^pandas/core/
+        files: ^pandas/
+        exclude: ^pandas/tests/
+-   repo: https://github.com/MarcoGorelli/no-string-hints
+    rev: v0.1.7
+    hooks:
+    -   id: no-string-hints
+-   repo: https://github.com/MarcoGorelli/abs-imports
+    rev: v0.1.2
+    hooks:
+    -   id: abs-imports
+        files: ^pandas/

README.md

@@ -1,5 +1,5 @@
 <div align="center">
-  <img src="https://dev.pandas.io/static/img/pandas.svg"><br>
+  <img src="https://pandas.pydata.org/static/img/pandas.svg"><br>
 </div>
 
 -----------------

asv_bench/benchmarks/categoricals.py

@@ -118,12 +118,29 @@ def setup(self):
         self.a = pd.Categorical(list("aabbcd") * N)
         self.b = pd.Categorical(list("bbcdjk") * N)
 
+        self.idx_a = pd.CategoricalIndex(range(N), range(N))
+        self.idx_b = pd.CategoricalIndex(range(N + 1), range(N + 1))
+        self.df_a = pd.DataFrame(range(N), columns=["a"], index=self.idx_a)
+        self.df_b = pd.DataFrame(range(N + 1), columns=["a"], index=self.idx_b)
+
     def time_concat(self):
         pd.concat([self.s, self.s])
 
     def time_union(self):
         union_categoricals([self.a, self.b])
 
+    def time_append_overlapping_index(self):
+        self.idx_a.append(self.idx_a)
+
+    def time_append_non_overlapping_index(self):
+        self.idx_a.append(self.idx_b)
+
+    def time_concat_overlapping_index(self):
+        pd.concat([self.df_a, self.df_a])
+
+    def time_concat_non_overlapping_index(self):
+        pd.concat([self.df_a, self.df_b])
+
 
 class ValueCounts:
 
@@ -306,7 +323,7 @@ def time_get_loc(self):
         self.index.get_loc(self.category)
 
     def time_shallow_copy(self):
-        self.index._shallow_copy()
+        self.index._view()
 
     def time_align(self):
         pd.DataFrame({"a": self.series, "b": self.series[:500]})

asv_bench/benchmarks/dtypes.py

@@ -2,9 +2,10 @@
 
 import numpy as np
 
+import pandas as pd
 from pandas import DataFrame
 import pandas._testing as tm
-from pandas.api.types import pandas_dtype
+from pandas.api.types import is_extension_array_dtype, pandas_dtype
 
 from .pandas_vb_common import (
     datetime_dtypes,
@@ -119,4 +120,16 @@ def time_select_dtype_string_exclude(self, dtype):
         self.df_string.select_dtypes(exclude=dtype)
 
 
+class CheckDtypes:
+    def setup(self):
+        self.ext_dtype = pd.Int64Dtype()
+        self.np_dtype = np.dtype("int64")
+
+    def time_is_extension_array_dtype_true(self):
+        is_extension_array_dtype(self.ext_dtype)
+
+    def time_is_extension_array_dtype_false(self):
+        is_extension_array_dtype(self.np_dtype)
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/gil.py

@@ -1,7 +1,7 @@
 import numpy as np
 
 from pandas import DataFrame, Series, date_range, factorize, read_csv
-from pandas.core.algorithms import take_1d
+from pandas.core.algorithms import take_nd
 
 from .pandas_vb_common import tm
 
@@ -110,7 +110,7 @@ def setup(self, dtype):
 
         @test_parallel(num_threads=2)
         def parallel_take1d():
-            take_1d(df["col"].values, indexer)
+            take_nd(df["col"].values, indexer)
 
         self.parallel_take1d = parallel_take1d