Merge remote-tracking branch 'upstream/master' into issue_26186_tick_label

Author: nrebena

.binstar.yml

@@ -8,15 +8,16 @@ on:
 
 env:
   ENV_FILE: environment.yml
-  # TODO: remove export PATH=... in each step once this works
-  # PATH: $HOME/miniconda3/bin:$PATH
 
 jobs:
   checks:
     name: Checks
     runs-on: ubuntu-latest
     steps:
 
+    - name: Setting conda path
+      run: echo "::add-path::${HOME}/miniconda3/bin"
+
     - name: Checkout
       uses: actions/checkout@v1
 
@@ -25,79 +26,72 @@ jobs:
       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
         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 "$ASV_OUTPUT"
+            asv dev | sed "/failed$/ s/^/##[error]/" | tee benchmarks.log
+            if grep "failed" benchmarks.log > /dev/null ; then
                 exit 1
-            else
-                echo "Benchmarks run without errors"
             fi
         else
             echo "Benchmarks did not run, no changes detected"
         fi
       if: true
+
+    - name: Publish benchmarks artifact
+      uses: actions/upload-artifact@master
+      with:
+        name: Benchmarks log
+        path: asv_bench/benchmarks.log
+      if: failure()

.github/workflows/ci.yml

@@ -30,31 +30,34 @@ matrix:
       - python: 3.5
 
     include:
-    - dist: trusty
-      env:
+    - env:
         - JOB="3.8" ENV_FILE="ci/deps/travis-38.yaml" PATTERN="(not slow and not network)"
 
-    - dist: trusty
-      env:
+    - env:
         - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network)"
 
-    - dist: trusty
-      env:
-        - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="((not slow and not network) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8"
+    - env:
+        - JOB="3.6, locale" ENV_FILE="ci/deps/travis-36-locale.yaml" PATTERN="((not slow and not network) or (single and db))" LOCALE_OVERRIDE="zh_CN.UTF-8" SQL="1"
+      services:
+        - mysql
+        - postgresql
 
-    - dist: trusty
-      env:
-        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36-cov.yaml" PATTERN="((not slow and not network) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
+    - env:
+        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36-cov.yaml" PATTERN="((not slow and not network) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true SQL="1"
+      services:
+        - mysql
+        - postgresql
 
     # In allow_failures
-    - dist: trusty
-      env:
-        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow"
+    - env:
+        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow" SQL="1"
+      services:
+        - mysql
+        - postgresql
 
     allow_failures:
-      - dist: trusty
-        env:
-          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow"
+      - env:
+          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow" SQL="1"
 
 before_install:
   - echo "before_install"

.travis.yml

@@ -20,7 +20,6 @@ global-exclude *.gz
 global-exclude *.h5
 global-exclude *.html
 global-exclude *.json
-global-exclude *.msgpack
 global-exclude *.pickle
 global-exclude *.png
 global-exclude *.pyc

LICENSES/MSGPACK_LICENSE

@@ -124,7 +124,7 @@ Here are just a few of the things that pandas does well:
     and saving/loading data from the ultrafast [**HDF5 format**][hdfstore]
   - [**Time series**][timeseries]-specific functionality: date range
     generation and frequency conversion, moving window statistics,
-    moving window linear regressions, date shifting and lagging, etc.
+    date shifting and lagging.
 
 
    [missing-data]: https://pandas.pydata.org/pandas-docs/stable/missing_data.html#working-with-missing-data
@@ -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

LICENSES/MSGPACK_NUMPY_LICENSE

@@ -0,0 +1,23 @@
+import numpy as np
+
+import pandas as pd
+
+
+class BooleanArray:
+    def setup(self):
+        self.values_bool = np.array([True, False, True, False])
+        self.values_float = np.array([1.0, 0.0, 1.0, 0.0])
+        self.values_integer = np.array([1, 0, 1, 0])
+        self.values_integer_like = [1, 0, 1, 0]
+
+    def time_from_bool_array(self):
+        pd.array(self.values_bool, dtype="boolean")
+
+    def time_from_integer_array(self):
+        pd.array(self.values_integer, dtype="boolean")
+
+    def time_from_integer_like(self):
+        pd.array(self.values_integer_like, dtype="boolean")
+
+    def time_from_float_array(self):
+        pd.array(self.values_float, dtype="boolean")

MANIFEST.in

@@ -1,3 +1,5 @@
+import operator
+
 import numpy as np
 
 from pandas import DataFrame, Series, date_range
@@ -9,6 +11,36 @@
     import pandas.computation.expressions as expr
 
 
+class IntFrameWithScalar:
+    params = [
+        [np.float64, np.int64],
+        [2, 3.0, np.int32(4), np.float64(5)],
+        [
+            operator.add,
+            operator.sub,
+            operator.mul,
+            operator.truediv,
+            operator.floordiv,
+            operator.pow,
+            operator.mod,
+            operator.eq,
+            operator.ne,
+            operator.gt,
+            operator.ge,
+            operator.lt,
+            operator.le,
+        ],
+    ]
+    param_names = ["dtype", "scalar", "op"]
+
+    def setup(self, dtype, scalar, op):
+        arr = np.random.randn(20000, 100)
+        self.df = DataFrame(arr.astype(dtype))
+
+    def time_frame_op_with_scalar(self, dtype, scalar, op):
+        op(self.df, scalar)
+
+
 class Ops:
 
     params = [[True, False], ["default", 1]]

README.md

@@ -0,0 +1,32 @@
+import numpy as np
+
+import pandas as pd
+
+
+class TimeLogicalOps:
+    def setup(self):
+        N = 10_000
+        left, right, lmask, rmask = np.random.randint(0, 2, size=(4, N)).astype("bool")
+        self.left = pd.arrays.BooleanArray(left, lmask)
+        self.right = pd.arrays.BooleanArray(right, rmask)
+
+    def time_or_scalar(self):
+        self.left | True
+        self.left | False
+
+    def time_or_array(self):
+        self.left | self.right
+
+    def time_and_scalar(self):
+        self.left & True
+        self.left & False
+
+    def time_and_array(self):
+        self.left & self.right
+
+    def time_xor_scalar(self):
+        self.left ^ True
+        self.left ^ False
+
+    def time_xor_array(self):
+        self.left ^ self.right