Merge remote-tracking branch 'upstream/master' into round_ambiguous

Author: Matt Roeschke

.coveragerc

@@ -30,12 +30,8 @@ matrix:
     exclude:
       # Exclude the default Python 3.5 build
       - python: 3.5
-    include:
-    - os: osx
-      language: generic
-      env:
-        - JOB="3.5, OSX" ENV_FILE="ci/travis-35-osx.yaml" TEST_ARGS="--skip-slow --skip-network"
 
+    include:
     - dist: trusty
       env:
         - JOB="3.7" ENV_FILE="ci/travis-37.yaml" TEST_ARGS="--skip-slow --skip-network"
@@ -64,7 +60,7 @@ matrix:
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+        - JOB="3.7, NumPy dev" ENV_FILE="ci/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
       addons:
         apt:
           packages:
@@ -79,7 +75,7 @@ matrix:
           - JOB="3.6, slow" ENV_FILE="ci/travis-36-slow.yaml" SLOW=true
       - dist: trusty
         env:
-          - JOB="3.6, NumPy dev" ENV_FILE="ci/travis-36-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
+          - JOB="3.7, NumPy dev" ENV_FILE="ci/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
         addons:
           apt:
             packages:

.travis.yml

@@ -1,7 +1,7 @@
 import warnings
 
 import numpy as np
-from pandas import Series
+from pandas import Series, DataFrame
 import pandas.util.testing as tm
 
 
@@ -12,9 +12,6 @@ class Methods(object):
     def setup(self):
         self.s = Series(tm.makeStringIndex(10**5))
 
-    def time_cat(self):
-        self.s.str.cat(sep=',')
-
     def time_center(self):
         self.s.str.center(100)
 
@@ -87,6 +84,32 @@ def time_repeat(self, repeats):
         self.s.str.repeat(self.repeat)
 
 
+class Cat(object):
+
+    goal_time = 0.2
+    params = ([0, 3], [None, ','], [None, '-'], [0.0, 0.001, 0.15])
+    param_names = ['other_cols', 'sep', 'na_rep', 'na_frac']
+
+    def setup(self, other_cols, sep, na_rep, na_frac):
+        N = 10 ** 5
+        mask_gen = lambda: np.random.choice([True, False], N,
+                                            p=[1 - na_frac, na_frac])
+        self.s = Series(tm.makeStringIndex(N)).where(mask_gen())
+        if other_cols == 0:
+            # str.cat self-concatenates only for others=None
+            self.others = None
+        else:
+            self.others = DataFrame({i: tm.makeStringIndex(N).where(mask_gen())
+                                     for i in range(other_cols)})
+
+    def time_cat(self, other_cols, sep, na_rep, na_frac):
+        # before the concatenation (one caller + other_cols columns), the total
+        # expected fraction of rows containing any NaN is:
+        # reduce(lambda t, _: t + (1 - t) * na_frac, range(other_cols + 1), 0)
+        # for other_cols=3 and na_frac=0.15, this works out to ~48%
+        self.s.str.cat(others=self.others, sep=sep, na_rep=na_rep)
+
+
 class Contains(object):
 
     goal_time = 0.2

appveyor.yml

@@ -0,0 +1,25 @@
+# Adapted from https://github.com/numba/numba/blob/master/azure-pipelines.yml
+jobs:
+# Mac and Linux could potentially use the same template
+# except it isn't clear how to use a different build matrix
+# for each, so for now they are separate
+- template: ci/azure/macos.yml
+  parameters:
+    name: macOS
+    vmImage: xcode9-macos10.13
+# - template: ci/azure/linux.yml
+#   parameters:
+#     name: Linux
+#     vmImage: ubuntu-16.04
+
+# Windows Python 2.7 needs VC 9.0 installed, and not sure
+# how to make that a conditional task, so for now these are
+# separate templates as well
+- template: ci/azure/windows.yml
+  parameters:
+    name: Windows
+    vmImage: vs2017-win2017
+- template: ci/azure/windows-py27.yml
+  parameters:
+    name: WindowsPy27
+    vmImage: vs2017-win2017

asv_bench/benchmarks/strings.py

@@ -0,0 +1,39 @@
+parameters:
+  name: ''
+  vmImage: ''
+
+jobs:
+- job: ${{ parameters.name }}
+  pool:
+    vmImage: ${{ parameters.vmImage }}
+  strategy:
+    maxParallel: 11
+    matrix:
+      py35_np_110:
+        ENV_FILE: ci/azure-macos-35.yml
+        CONDA_PY: "35"
+        CONDA_ENV: pandas
+        TEST_ARGS: "--skip-slow --skip-network"
+
+  steps:
+    - script: |
+        if [ "$(uname)" == "Linux" ]; then sudo apt-get install -y libc6-dev-i386; fi
+        echo "Installing Miniconda"
+        ci/incremental/install_miniconda.sh
+        export PATH=$HOME/miniconda3/bin:$PATH
+        echo "Setting up Conda environment"
+        ci/incremental/setup_conda_environment.sh
+      displayName: 'Before Install'
+    - script: |
+        export PATH=$HOME/miniconda3/bin:$PATH
+        ci/incremental/build.sh
+      displayName: 'Build'
+    - script: |
+        export PATH=$HOME/miniconda3/bin:$PATH
+        ci/script_single.sh
+        ci/script_multi.sh
+        echo "[Test done]"
+      displayName: 'Test'
+    - script: |
+        export PATH=$HOME/miniconda3/bin:$PATH
+        source activate pandas && pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd

azure-pipelines.yml

@@ -0,0 +1,41 @@
+parameters:
+  name: ''
+  vmImage: ''
+
+jobs:
+- job: ${{ parameters.name }}
+  pool:
+    vmImage: ${{ parameters.vmImage }}
+  strategy:
+    maxParallel: 11
+    matrix:
+      py36_np14:
+        ENV_FILE: ci/azure-windows-27.yml
+        CONDA_PY: "27"
+        CONDA_ENV: pandas
+
+  steps:
+    - task: CondaEnvironment@1
+      inputs:
+        updateConda: no
+        packageSpecs: ''
+
+    # Need to install VC 9.0 only for Python 2.7
+    # Once we understand how to do tasks conditional on build matrix variables
+    # we could merge this into azure-windows.yml
+    - powershell: |
+        $wc = New-Object net.webclient
+        $wc.Downloadfile("https://download.microsoft.com/download/7/9/6/796EF2E4-801B-4FC4-AB28-B59FBF6D907B/VCForPython27.msi", "VCForPython27.msi")
+        Start-Process "VCForPython27.msi" /qn -Wait
+      displayName: 'Install VC 9.0'
+
+    - script: |
+        ci\\incremental\\setup_conda_environment.cmd
+      displayName: 'Before Install'
+    - script: |
+        ci\\incremental\\build.cmd
+      displayName: 'Build'
+    - script: |
+        call activate %CONDA_ENV%
+        pytest --skip-slow --skip-network pandas -n 2 -r sxX --strict %*
+      displayName: 'Test'

ci/travis-35-osx.yaml renamed to ci/azure-macos-35.yml

@@ -0,0 +1,32 @@
+parameters:
+  name: ''
+  vmImage: ''
+
+jobs:
+- job: ${{ parameters.name }}
+  pool:
+    vmImage: ${{ parameters.vmImage }}
+  strategy:
+    maxParallel: 11
+    matrix:
+      py36_np14:
+        ENV_FILE: ci/azure-windows-36.yml
+        CONDA_PY: "36"
+        CONDA_ENV: pandas
+
+  steps:
+    - task: CondaEnvironment@1
+      inputs:
+        updateConda: no
+        packageSpecs: ''
+
+    - script: |
+        ci\\incremental\\setup_conda_environment.cmd
+      displayName: 'Before Install'
+    - script: |
+        ci\\incremental\\build.cmd
+      displayName: 'Build'
+    - script: |
+        call activate %CONDA_ENV%
+        pytest --skip-slow --skip-network pandas -n 2 -r sxX --strict %*
+      displayName: 'Test'

ci/appveyor-27.yaml renamed to ci/azure-windows-27.yaml

@@ -21,21 +21,21 @@ if [ "$DOCTEST" ]; then
 
     # DataFrame / Series docstrings
     pytest --doctest-modules -v pandas/core/frame.py \
-        -k"-assign -axes -combine -isin -itertuples -join -nlargest -nsmallest -nunique -pivot_table -quantile -query -reindex -reindex_axis -replace -round -set_index -stack -to_dict -to_stata -transform"
+        -k"-assign -axes -combine -isin -itertuples -join -nlargest -nsmallest -nunique -pivot_table -quantile -query -reindex -reindex_axis -replace -round -set_index -stack -to_dict -to_stata"
 
     if [ $? -ne "0" ]; then
         RET=1
     fi
 
     pytest --doctest-modules -v pandas/core/series.py \
-        -k"-nlargest -nonzero -nsmallest -reindex -searchsorted -to_dict"
+        -k"-nonzero -reindex -searchsorted -to_dict"
 
     if [ $? -ne "0" ]; then
         RET=1
     fi
 
     pytest --doctest-modules -v pandas/core/generic.py \
-        -k"-_set_axis_name -_xs -describe -droplevel -groupby -interpolate -pct_change -pipe -reindex -reindex_axis -resample -sample -to_json -to_xarray -transform -transpose -values -xs"
+        -k"-_set_axis_name -_xs -describe -droplevel -groupby -interpolate -pct_change -pipe -reindex -reindex_axis -resample -sample -to_json -transpose -values -xs"
 
     if [ $? -ne "0" ]; then
         RET=1

ci/appveyor-36.yaml renamed to ci/azure-windows-36.yaml

@@ -0,0 +1,10 @@
+@rem https://github.com/numba/numba/blob/master/buildscripts/incremental/build.cmd
+call activate %CONDA_ENV%
+
+@rem Build numba extensions without silencing compile errors
+python setup.py build_ext -q --inplace
+
+@rem Install pandas locally
+python -m pip install -e .
+
+if %errorlevel% neq 0 exit /b %errorlevel%