Merge branch 'master' into orc-reader

Author: jreback

.github/workflows/ci.yml

@@ -8,8 +8,6 @@ on:
 
 env:
   ENV_FILE: environment.yml
-  # TODO: remove export PATH=... in each step once this works
-  # PATH: $HOME/miniconda3/bin:$PATH
 
 jobs:
   checks:
@@ -20,68 +18,61 @@ jobs:
     - name: Checkout
       uses: actions/checkout@v1
 
+    - name: Setting conda path
+      run: echo "::set-env name=PATH::${HOME}/miniconda3/bin:${PATH}"
+
     - name: Looking for unwanted patterns
       run: ci/code_checks.sh patterns
       if: true
 
     - name: Setup environment and build pandas
-      run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
-        ci/setup_env.sh
+      run: ci/setup_env.sh
       if: true
 
     - name: Linting
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh lint
       if: true
 
     - name: Dependencies consistency
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh dependencies
       if: true
 
     - name: Checks on imported code
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh code
       if: true
 
     - name: Running doctests
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh doctests
       if: true
 
     - name: Docstring validation
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh docstrings
       if: true
 
     - name: Typing validation
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         ci/code_checks.sh typing
       if: true
 
     - name: Testing docstring validation script
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         pytest --capture=no --strict scripts
       if: true
 
     - name: Running benchmarks
       run: |
-        export PATH=$HOME/miniconda3/bin:$PATH
         source activate pandas-dev
         cd asv_bench
         asv check -E existing

.travis.yml

@@ -30,11 +30,9 @@ matrix:
       - python: 3.5
 
     include:
-    - dist: bionic
-      # 18.04
-      python: 3.8.0
+    - dist: trusty
       env:
-        - JOB="3.8-dev" PATTERN="(not slow and not network)"
+        - JOB="3.8" ENV_FILE="ci/deps/travis-38.yaml" PATTERN="(not slow and not network)"
 
     - dist: trusty
       env:
@@ -88,7 +86,7 @@ install:
 script:
   - echo "script start"
   - echo "$JOB"
-  - if [ "$JOB" != "3.8-dev" ]; then source activate pandas-dev; fi
+  - source activate pandas-dev
   - ci/run_tests.sh
 
 after_script:

README.md

@@ -164,12 +164,11 @@ pip install pandas
 ```
 
 ## Dependencies
-- [NumPy](https://www.numpy.org): 1.13.3 or higher
-- [python-dateutil](https://labix.org/python-dateutil): 2.5.0 or higher
-- [pytz](https://pythonhosted.org/pytz): 2015.4 or higher
+- [NumPy](https://www.numpy.org)
+- [python-dateutil](https://labix.org/python-dateutil)
+- [pytz](https://pythonhosted.org/pytz)
 
-See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies)
-for recommended and optional dependencies.
+See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies) for minimum supported versions of required, recommended and optional dependencies.
 
 ## Installation from sources
 To install pandas from source you need Cython in addition to the normal

asv_bench/benchmarks/categoricals.py

@@ -14,21 +14,6 @@
         pass
 
 
-class Concat:
-    def setup(self):
-        N = 10 ** 5
-        self.s = pd.Series(list("aabbcd") * N).astype("category")
-
-        self.a = pd.Categorical(list("aabbcd") * N)
-        self.b = pd.Categorical(list("bbcdjk") * N)
-
-    def time_concat(self):
-        pd.concat([self.s, self.s])
-
-    def time_union(self):
-        union_categoricals([self.a, self.b])
-
-
 class Constructor:
     def setup(self):
         N = 10 ** 5
@@ -77,6 +62,33 @@ def time_existing_series(self):
         pd.Categorical(self.series)
 
 
+class CategoricalOps:
+    params = ["__lt__", "__le__", "__eq__", "__ne__", "__ge__", "__gt__"]
+    param_names = ["op"]
+
+    def setup(self, op):
+        N = 10 ** 5
+        self.cat = pd.Categorical(list("aabbcd") * N, ordered=True)
+
+    def time_categorical_op(self, op):
+        getattr(self.cat, op)("b")
+
+
+class Concat:
+    def setup(self):
+        N = 10 ** 5
+        self.s = pd.Series(list("aabbcd") * N).astype("category")
+
+        self.a = pd.Categorical(list("aabbcd") * N)
+        self.b = pd.Categorical(list("bbcdjk") * N)
+
+    def time_concat(self):
+        pd.concat([self.s, self.s])
+
+    def time_union(self):
+        union_categoricals([self.a, self.b])
+
+
 class ValueCounts:
 
     params = [True, False]

asv_bench/benchmarks/timeseries.py

@@ -113,7 +113,7 @@ class InferFreq:
     def setup(self, freq):
         if freq is None:
             self.idx = date_range(start="1/1/1700", freq="D", periods=10000)
-            self.idx.freq = None
+            self.idx._data._freq = None
         else:
             self.idx = date_range(start="1/1/1700", freq=freq, periods=10000)
 

azure-pipelines.yml

@@ -16,95 +16,6 @@ jobs:
     name: Windows
     vmImage: vs2017-win2016
 
-- job: 'Checks'
-  pool:
-    vmImage: ubuntu-16.04
-  timeoutInMinutes: 90
-  steps:
-  - script: |
-      echo '##vso[task.prependpath]$(HOME)/miniconda3/bin'
-      echo '##vso[task.setvariable variable=ENV_FILE]environment.yml'
-      echo '##vso[task.setvariable variable=AZURE]true'
-    displayName: 'Setting environment variables'
-
-  # Do not require a conda environment
-  - script: ci/code_checks.sh patterns
-    displayName: 'Looking for unwanted patterns'
-    condition: true
-
-  - script: |
-      sudo apt-get update
-      sudo apt-get install -y libc6-dev-i386
-      ci/setup_env.sh
-    displayName: 'Setup environment and build pandas'
-    condition: true
-
-  # Do not require pandas
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh lint
-    displayName: 'Linting'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh dependencies
-    displayName: 'Dependencies consistency'
-    condition: true
-
-  # Require pandas
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh code
-    displayName: 'Checks on imported code'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh doctests
-    displayName: 'Running doctests'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh docstrings
-    displayName: 'Docstring validation'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      ci/code_checks.sh typing
-    displayName: 'Typing validation'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      pytest --capture=no --strict scripts
-    displayName: 'Testing docstring validation script'
-    condition: true
-
-  - script: |
-      source activate pandas-dev
-      cd asv_bench
-      asv check -E existing
-      git remote add upstream https://github.com/pandas-dev/pandas.git
-      git fetch upstream
-      if git diff upstream/master --name-only | grep -q "^asv_bench/"; then
-          asv machine --yes
-          ASV_OUTPUT="$(asv dev)"
-          if [[ $(echo "$ASV_OUTPUT" | grep "failed") ]]; then
-              echo "##vso[task.logissue type=error]Benchmarks run with errors"
-              echo "$ASV_OUTPUT"
-              exit 1
-          else
-              echo "Benchmarks run without errors"
-          fi
-      else
-          echo "Benchmarks did not run, no changes detected"
-      fi
-    displayName: 'Running benchmarks'
-    condition: true
-
 - job: 'Web_and_Docs'
   pool:
     vmImage: ubuntu-16.04

ci/azure/posix.yml

@@ -44,16 +44,13 @@ jobs:
           PATTERN: "not slow and not network"
           LOCALE_OVERRIDE: "zh_CN.UTF-8"
 
-        # https://github.com/pandas-dev/pandas/issues/29432
-        # py37_np_dev:
-        #   ENV_FILE: ci/deps/azure-37-numpydev.yaml
-        #   CONDA_PY: "37"
-        #   PATTERN: "not slow and not network"
-        #   TEST_ARGS: "-W error"
-        #   PANDAS_TESTING_MODE: "deprecate"
-        #   EXTRA_APT: "xsel"
-        #   # TODO:
-        #   continueOnError: true
+        py37_np_dev:
+          ENV_FILE: ci/deps/azure-37-numpydev.yaml
+          CONDA_PY: "37"
+          PATTERN: "not slow and not network"
+          TEST_ARGS: "-W error"
+          PANDAS_TESTING_MODE: "deprecate"
+          EXTRA_APT: "xsel"
 
   steps:
     - script: |

ci/azure/windows.yml

@@ -11,49 +11,45 @@ jobs:
       py36_np15:
         ENV_FILE: ci/deps/azure-windows-36.yaml
         CONDA_PY: "36"
+        PATTERN: "not slow and not network"
 
       py37_np141:
         ENV_FILE: ci/deps/azure-windows-37.yaml
         CONDA_PY: "37"
+        PATTERN: "not slow and not network"
 
   steps:
     - powershell: |
         Write-Host "##vso[task.prependpath]$env:CONDA\Scripts"
         Write-Host "##vso[task.prependpath]$HOME/miniconda3/bin"
       displayName: 'Add conda to PATH'
     - script: conda update -q -n base conda
-      displayName: Update conda
-    - script: |
-        call activate
+      displayName: 'Update conda'
+    - bash: |
         conda env create -q --file ci\\deps\\azure-windows-$(CONDA_PY).yaml
       displayName: 'Create anaconda environment'
-    - script: |
-        call activate pandas-dev
-        call conda list
+    - bash: |
+        source activate pandas-dev
+        conda list
         ci\\incremental\\build.cmd
       displayName: 'Build'
-    - script: |
-        call activate pandas-dev
-        pytest -m "not slow and not network" --junitxml=test-data.xml pandas -n 2 -r sxX --strict --durations=10 %*
+    - bash: |
+        source activate pandas-dev
+        ci/run_tests.sh
       displayName: 'Test'
     - task: PublishTestResults@2
       inputs:
         testResultsFiles: 'test-data.xml'
         testRunTitle: 'Windows-$(CONDA_PY)'
     - powershell: |
-        $junitXml = "test-data.xml"
-        $(Get-Content $junitXml | Out-String) -match 'failures="(.*?)"'
-        if ($matches[1] -eq 0)
-        {
+        $(Get-Content "test-data.xml" | Out-String) -match 'failures="(.*?)"'
+        if ($matches[1] -eq 0) {
           Write-Host "No test failures in test-data"
-        }
-        else
-        {
-          # note that this will produce $LASTEXITCODE=1
-          Write-Error "$($matches[1]) tests failed"
+        } else {
+          Write-Error "$($matches[1]) tests failed"  # will produce $LASTEXITCODE=1
         }
       displayName: 'Check for test failures'
-    - script: |
+    - bash: |
         source activate pandas-dev
         python ci/print_skipped.py
       displayName: 'Print skipped tests'