Fixed comment for pandas.unique

.github/workflows/ci.yml

@@ -6,7 +6,7 @@ on:
   pull_request:
     branches:
       - master
-      - 1.1.x
+      - 1.2.x
 
 env:
   ENV_FILE: environment.yml
@@ -64,7 +64,7 @@ jobs:
     - name: Testing docstring validation script
       run: |
         source activate pandas-dev
-        pytest --capture=no --strict scripts
+        pytest --capture=no --strict-markers scripts
       if: always()
 
     - name: Running benchmarks

.github/workflows/database.yml

@@ -0,0 +1,186 @@
+name: Database
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+    branches:
+      - master
+      - 1.2.x
+
+env:
+  PYTEST_WORKERS: "auto"
+  PANDAS_CI: 1
+  PATTERN: ((not slow and not network and not clipboard) or (single and db))
+
+jobs:
+  Linux_py37_locale:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+
+    env:
+      ENV_FILE: ci/deps/actions-37-locale.yaml
+      LOCALE_OVERRIDE: zh_CN.UTF-8
+
+    services:
+      mysql:
+        image: mysql
+        env:
+          MYSQL_ALLOW_EMPTY_PASSWORD: yes
+          MYSQL_DATABASE: pandas
+        options: >-
+          --health-cmd "mysqladmin ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          - 3306:3306
+
+      postgres:
+        image: postgres
+        env:
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: postgres
+          POSTGRES_DB: pandas
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          - 5432:5432
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v1
+
+    - name: Cache conda
+      uses: actions/cache@v1
+      env:
+        CACHE_NUMBER: 0
+      with:
+        path: ~/conda_pkgs_dir
+        key: ${{ runner.os }}-conda-${{ env.CACHE_NUMBER }}-${{
+          hashFiles('${{ env.ENV_FILE }}') }}
+
+    - 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: |
+        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: Test
+      run: ci/run_tests.sh
+      if: always()
+
+    - name: Build Version
+      run: pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd
+
+    - name: Publish test results
+      uses: actions/upload-artifact@master
+      with:
+        name: Test results
+        path: test-data.xml
+      if: failure()
+
+    - name: Print skipped tests
+      run: python ci/print_skipped.py
+
+  Linux_py37_cov:
+    runs-on: ubuntu-latest
+    defaults:
+      run:
+        shell: bash -l {0}
+
+    env:
+      ENV_FILE: ci/deps/actions-37-cov.yaml
+      PANDAS_TESTING_MODE: deprecate
+      COVERAGE: true
+
+    services:
+      mysql:
+        image: mysql
+        env:
+          MYSQL_ALLOW_EMPTY_PASSWORD: yes
+          MYSQL_DATABASE: pandas
+        options: >-
+          --health-cmd "mysqladmin ping"
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          - 3306:3306
+
+      postgres:
+        image: postgres
+        env:
+          POSTGRES_USER: postgres
+          POSTGRES_PASSWORD: postgres
+          POSTGRES_DB: pandas
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+          --health-retries 5
+        ports:
+          - 5432:5432
+
+    steps:
+    - name: Checkout
+      uses: actions/checkout@v1
+
+    - name: Cache conda
+      uses: actions/cache@v1
+      env:
+        CACHE_NUMBER: 0
+      with:
+        path: ~/conda_pkgs_dir
+        key: ${{ runner.os }}-conda-${{ env.CACHE_NUMBER }}-${{
+          hashFiles('${{ env.ENV_FILE }}') }}
+
+    - 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: |
+        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: Test
+      run: ci/run_tests.sh
+      if: always()
+
+    - name: Build Version
+      run: pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd
+
+    - name: Publish test results
+      uses: actions/upload-artifact@master
+      with:
+        name: Test results
+        path: test-data.xml
+      if: failure()
+
+    - name: Print skipped tests
+      run: python ci/print_skipped.py

.pre-commit-config.yaml

@@ -144,6 +144,11 @@ repos:
             \#\ type:\s?ignore(?!\[)
         language: pygrep
         types: [python]
+    -   id: np-bool
+        name: Check for use of np.bool instead of np.bool_
+        entry: np\.bool[^_8]
+        language: pygrep
+        types_or: [python, cython, rst]
     -   id: no-os-remove
         name: Check code for instances of os.remove
         entry: os\.remove

.travis.yml

@@ -16,13 +16,13 @@ services:
 # travis cache --delete inside the project directory from the travis command line client
 # The cache directories will be deleted if anything in ci/ changes in a commit
 cache:
+  apt: true
   ccache: true
   directories:
     - $HOME/.cache # cython cache
 
 env:
   global:
-    - PYTEST_WORKERS="auto"
     # create a github personal access token
     # cd pandas-dev/pandas
     # travis encrypt 'PANDAS_GH_TOKEN=personal_access_token' -r pandas-dev/pandas
@@ -35,31 +35,10 @@ matrix:
   fast_finish: true
 
   include:
-    - env:
-      - JOB="3.8, slow" ENV_FILE="ci/deps/travis-38-slow.yaml" PATTERN="slow" SQL="1"
-      services:
-        - mysql
-        - postgresql
-
-    - env:
-        - JOB="3.7, locale" ENV_FILE="ci/deps/travis-37-locale.yaml" PATTERN="((not slow and not network and not clipboard) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
-      services:
-        - mysql
-        - postgresql
-
     - arch: arm64
       env:
         - JOB="3.7, arm64" PYTEST_WORKERS=1 ENV_FILE="ci/deps/travis-37-arm64.yaml" PATTERN="(not slow and not network and not clipboard and not arm_slow)"
 
-    - env:
-        # Enabling Deprecations when running tests
-        # PANDAS_TESTING_MODE="deprecate" causes DeprecationWarning messages to be displayed in the logs
-        # See pandas/_testing.py for more details.
-        - JOB="3.7, coverage" ENV_FILE="ci/deps/travis-37-cov.yaml" PATTERN="((not slow and not network and not clipboard) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true SQL="1"
-      services:
-        - mysql
-        - postgresql
-
   allow_failures:
     # Moved to allowed_failures 2020-09-29 due to timeouts https://github.com/pandas-dev/pandas/issues/36719
     - arch: arm64

asv_bench/benchmarks/algorithms.py

@@ -5,7 +5,6 @@
 from pandas._libs import lib
 
 import pandas as pd
-from pandas.core.algorithms import make_duplicates_of_left_unique_in_right
 
 from .pandas_vb_common import tm
 
@@ -175,15 +174,4 @@ def time_argsort(self, N):
         self.array.argsort()
 
 
-class RemoveDuplicates:
-    def setup(self):
-        N = 10 ** 5
-        na = np.arange(int(N / 2))
-        self.left = np.concatenate([na[: int(N / 4)], na[: int(N / 4)]])
-        self.right = np.concatenate([na, na])
-
-    def time_make_duplicates_of_left_unique_in_right(self):
-        make_duplicates_of_left_unique_in_right(self.left, self.right)
-
-
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

asv_bench/benchmarks/groupby.py

@@ -625,7 +625,7 @@ class TransformBools:
     def setup(self):
         N = 120000
         transition_points = np.sort(np.random.choice(np.arange(N), 1400))
-        transitions = np.zeros(N, dtype=np.bool)
+        transitions = np.zeros(N, dtype=np.bool_)
         transitions[transition_points] = True
         self.g = transitions.cumsum()
         self.df = DataFrame({"signal": np.random.rand(N)})

asv_bench/benchmarks/io/excel.py

@@ -40,7 +40,7 @@ def time_write_excel(self, engine):
 
 class ReadExcel:
 
-    params = ["xlrd", "openpyxl", "odf"]
+    params = ["openpyxl", "odf"]
     param_names = ["engine"]
     fname_excel = "spreadsheet.xlsx"
     fname_odf = "spreadsheet.ods"

azure-pipelines.yml

@@ -1,11 +1,11 @@
 # Adapted from https://github.com/numba/numba/blob/master/azure-pipelines.yml
 trigger:
 - master
-- 1.1.x
+- 1.2.x
 
 pr:
 - master
-- 1.1.x
+- 1.2.x
 
 variables:
   PYTEST_WORKERS: auto

ci/azure/posix.yml

@@ -43,6 +43,11 @@ jobs:
           CONDA_PY: "38"
           PATTERN: "not slow and not network and not clipboard"
 
+        py38_slow:
+          ENV_FILE: ci/deps/azure-38-slow.yaml
+          CONDA_PY: "38"
+          PATTERN: "slow"
+
         py38_locale:
           ENV_FILE: ci/deps/azure-38-locale.yaml
           CONDA_PY: "38"

ci/deps/travis-37-cov.yaml → ci/deps/actions-37-cov.yaml

@@ -15,7 +15,7 @@ dependencies:
   - beautifulsoup4
   - botocore>=1.11
   - dask
-  - fastparquet>=0.3.2
+  - fastparquet>=0.4.0
   - fsspec>=0.7.4
   - gcsfs>=0.6.0
   - geopandas
@@ -43,7 +43,7 @@ dependencies:
   - sqlalchemy
   - statsmodels
   - xarray
-  - xlrd
+  - xlrd<2.0
   - xlsxwriter
   - xlwt
   - pip

ci/deps/travis-37-locale.yaml → ci/deps/actions-37-locale.yaml

@@ -1,6 +1,5 @@
 name: pandas-dev
 channels:
-  - defaults
   - conda-forge
 dependencies:
   - python=3.7.*
@@ -12,15 +11,15 @@ dependencies:
   - hypothesis>=3.58.0
 
   # required
-  - numpy
+  - numpy<1.20  # GH#39541 compat for pyarrow<3
   - python-dateutil
   - pytz
 
   # optional
   - beautifulsoup4
-  - blosc=1.15.0
+  - blosc=1.17.0
   - python-blosc
-  - fastparquet=0.3.2
+  - fastparquet=0.4.0
   - html5lib
   - ipython
   - jinja2
@@ -31,17 +30,17 @@ dependencies:
   - openpyxl
   - pandas-gbq
   - google-cloud-bigquery>=1.27.2 # GH 36436
-  - pyarrow>=0.17
+  - pyarrow=0.17 # GH 38803
   - pytables>=3.5.1
   - scipy
   - xarray=0.12.3
-  - xlrd
+  - xlrd<2.0
   - xlsxwriter
   - xlwt
   - moto
   - flask
 
   # sql
   - psycopg2=2.7
-  - pymysql=0.7.11
+  - pymysql=0.8.1
   - sqlalchemy=1.3.0