Merge branch 'master' into integer-array-from-bool

Author: vladserkoff

.travis.yml

@@ -1,6 +1,5 @@
 sudo: false
 language: python
-# Default Python version is usually 2.7
 python: 3.5
 
 # To turn off cached cython files and compiler cache
@@ -36,14 +35,6 @@ matrix:
       env:
         - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="(not slow and not network)"
 
-    - dist: trusty
-      env:
-        - JOB="2.7" ENV_FILE="ci/deps/travis-27.yaml" PATTERN="(not slow or (single and db))"
-      addons:
-        apt:
-          packages:
-          - python-gtk2
-
     - 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"

README.md

@@ -26,8 +26,9 @@
   <td>Package Status</td>
   <td>
 		<a href="https://pypi.org/project/pandas/">
-		<img src="https://img.shields.io/pypi/status/pandas.svg" alt="status" /></td>
+		<img src="https://img.shields.io/pypi/status/pandas.svg" alt="status" />
 		</a>
+  </td>
 </tr>
 <tr>
   <td>License</td>
@@ -73,8 +74,8 @@
 	<td>Gitter</td>
 	<td>
 		<a href="https://gitter.im/pydata/pandas">
-		<img src="https://badges.gitter.im/Join%20Chat.svg"
-	</a>
+		<img src="https://badges.gitter.im/Join%20Chat.svg" />
+		</a>
 	</td>
 </tr>
 </table>
@@ -165,7 +166,7 @@ pip install pandas
 ## Dependencies
 - [NumPy](https://www.numpy.org): 1.12.0 or higher
 - [python-dateutil](https://labix.org/python-dateutil): 2.5.0 or higher
-- [pytz](https://pythonhosted.org/pytz): 2011k or higher
+- [pytz](https://pythonhosted.org/pytz): 2015.4 or higher
 
 See the [full installation instructions](https://pandas.pydata.org/pandas-docs/stable/install.html#dependencies)
 for recommended and optional dependencies.

asv_bench/benchmarks/groupby.py

@@ -14,7 +14,7 @@
 method_blacklist = {
     'object': {'median', 'prod', 'sem', 'cumsum', 'sum', 'cummin', 'mean',
                'max', 'skew', 'cumprod', 'cummax', 'rank', 'pct_change', 'min',
-               'var', 'mad', 'describe', 'std'},
+               'var', 'mad', 'describe', 'std', 'quantile'},
     'datetime': {'median', 'prod', 'sem', 'cumsum', 'sum', 'mean', 'skew',
                  'cumprod', 'cummax', 'pct_change', 'var', 'mad', 'describe',
                  'std'}
@@ -316,8 +316,9 @@ class GroupByMethods(object):
               ['all', 'any', 'bfill', 'count', 'cumcount', 'cummax', 'cummin',
                'cumprod', 'cumsum', 'describe', 'ffill', 'first', 'head',
                'last', 'mad', 'max', 'min', 'median', 'mean', 'nunique',
-               'pct_change', 'prod', 'rank', 'sem', 'shift', 'size', 'skew',
-               'std', 'sum', 'tail', 'unique', 'value_counts', 'var'],
+               'pct_change', 'prod', 'quantile', 'rank', 'sem', 'shift',
+               'size', 'skew', 'std', 'sum', 'tail', 'unique', 'value_counts',
+               'var'],
               ['direct', 'transformation']]
 
     def setup(self, dtype, method, application):

asv_bench/benchmarks/indexing.py

@@ -2,7 +2,7 @@
 
 import numpy as np
 import pandas.util.testing as tm
-from pandas import (Series, DataFrame, Panel, MultiIndex,
+from pandas import (Series, DataFrame, MultiIndex,
                     Int64Index, UInt64Index, Float64Index,
                     IntervalIndex, CategoricalIndex,
                     IndexSlice, concat, date_range)
@@ -277,18 +277,6 @@ def time_get_indexer_list(self, index):
         self.data.get_indexer(self.cat_list)
 
 
-class PanelIndexing(object):
-
-    def setup(self):
-        with warnings.catch_warnings(record=True):
-            self.p = Panel(np.random.randn(100, 100, 100))
-            self.inds = range(0, 100, 10)
-
-    def time_subset(self):
-        with warnings.catch_warnings(record=True):
-            self.p.ix[(self.inds, self.inds, self.inds)]
-
-
 class MethodLookup(object):
 
     def setup_cache(self):

asv_bench/benchmarks/io/hdf.py

@@ -1,7 +1,5 @@
-import warnings
-
 import numpy as np
-from pandas import DataFrame, Panel, date_range, HDFStore, read_hdf
+from pandas import DataFrame, date_range, HDFStore, read_hdf
 import pandas.util.testing as tm
 
 from ..pandas_vb_common import BaseIO
@@ -99,31 +97,6 @@ def time_store_info(self):
         self.store.info()
 
 
-class HDFStorePanel(BaseIO):
-
-    def setup(self):
-        self.fname = '__test__.h5'
-        with warnings.catch_warnings(record=True):
-            self.p = Panel(np.random.randn(20, 1000, 25),
-                           items=['Item%03d' % i for i in range(20)],
-                           major_axis=date_range('1/1/2000', periods=1000),
-                           minor_axis=['E%03d' % i for i in range(25)])
-            self.store = HDFStore(self.fname)
-            self.store.append('p1', self.p)
-
-    def teardown(self):
-        self.store.close()
-        self.remove(self.fname)
-
-    def time_read_store_table_panel(self):
-        with warnings.catch_warnings(record=True):
-            self.store.select('p1')
-
-    def time_write_store_table_panel(self):
-        with warnings.catch_warnings(record=True):
-            self.store.append('p2', self.p)
-
-
 class HDF(BaseIO):
 
     params = ['table', 'fixed']

asv_bench/benchmarks/join_merge.py

@@ -1,9 +1,8 @@
-import warnings
 import string
 
 import numpy as np
 import pandas.util.testing as tm
-from pandas import (DataFrame, Series, Panel, MultiIndex,
+from pandas import (DataFrame, Series, MultiIndex,
                     date_range, concat, merge, merge_asof)
 
 try:
@@ -66,31 +65,6 @@ def time_concat_mixed_ndims(self, axis):
         concat(self.mixed_ndims, axis=axis)
 
 
-class ConcatPanels(object):
-
-    params = ([0, 1, 2], [True, False])
-    param_names = ['axis', 'ignore_index']
-
-    def setup(self, axis, ignore_index):
-        with warnings.catch_warnings(record=True):
-            panel_c = Panel(np.zeros((10000, 200, 2),
-                                     dtype=np.float32,
-                                     order='C'))
-            self.panels_c = [panel_c] * 20
-            panel_f = Panel(np.zeros((10000, 200, 2),
-                            dtype=np.float32,
-                            order='F'))
-            self.panels_f = [panel_f] * 20
-
-    def time_c_ordered(self, axis, ignore_index):
-        with warnings.catch_warnings(record=True):
-            concat(self.panels_c, axis=axis, ignore_index=ignore_index)
-
-    def time_f_ordered(self, axis, ignore_index):
-        with warnings.catch_warnings(record=True):
-            concat(self.panels_f, axis=axis, ignore_index=ignore_index)
-
-
 class ConcatDataFrames(object):
 
     params = ([0, 1], [True, False])

asv_bench/benchmarks/panel_ctor.py

@@ -124,6 +124,25 @@ def time_dropna(self, dtype):
         self.s.dropna()
 
 
+class SearchSorted(object):
+
+    goal_time = 0.2
+    params = ['int8', 'int16', 'int32', 'int64',
+              'uint8', 'uint16', 'uint32', 'uint64',
+              'float16', 'float32', 'float64',
+              'str']
+    param_names = ['dtype']
+
+    def setup(self, dtype):
+        N = 10**5
+        data = np.array([1] * N + [2] * N + [3] * N).astype(dtype)
+        self.s = Series(data)
+
+    def time_searchsorted(self, dtype):
+        key = '2' if dtype == 'str' else 2
+        self.s.searchsorted(key)
+
+
 class Map(object):
 
     params = ['dict', 'Series']

asv_bench/benchmarks/panel_methods.py

@@ -10,7 +10,6 @@ jobs:
     name: Linux
     vmImage: ubuntu-16.04
 
-# Windows Python 2.7 needs VC 9.0 installed, handled in the template
 - template: ci/azure/windows.yml
   parameters:
     name: Windows
@@ -104,7 +103,7 @@ jobs:
       if git diff upstream/master --name-only | grep -q "^asv_bench/"; then
           cd asv_bench
           asv machine --yes
-          ASV_OUTPUT="$(asv run --quick --show-stderr --python=same --launch-method=spawn)"
+          ASV_OUTPUT="$(asv dev)"
           if [[ $(echo "$ASV_OUTPUT" | grep "failed") ]]; then
               echo "##vso[task.logissue type=error]Benchmarks run with errors"
               echo "$ASV_OUTPUT"

asv_bench/benchmarks/series_methods.py

@@ -9,24 +9,12 @@ jobs:
   strategy:
     matrix:
       ${{ if eq(parameters.name, 'macOS') }}:
-        py35_np_120:
+        py35_macos:
           ENV_FILE: ci/deps/azure-macos-35.yaml
           CONDA_PY: "35"
           PATTERN: "not slow and not network"
 
       ${{ if eq(parameters.name, 'Linux') }}:
-        py27_np_120:
-          ENV_FILE: ci/deps/azure-27-compat.yaml
-          CONDA_PY: "27"
-          PATTERN: "not slow and not network"
-
-        py27_locale_slow_old_np:
-          ENV_FILE: ci/deps/azure-27-locale.yaml
-          CONDA_PY: "27"
-          PATTERN: "slow"
-          LOCALE_OVERRIDE: "zh_CN.UTF-8"
-          EXTRA_APT: "language-pack-zh-hans"
-
         py36_locale_slow:
           ENV_FILE: ci/deps/azure-36-locale_slow.yaml
           CONDA_PY: "36"

azure-pipelines.yml

@@ -12,23 +12,12 @@ jobs:
         ENV_FILE: ci/deps/azure-windows-36.yaml
         CONDA_PY: "36"
 
-      py27_np121:
-        ENV_FILE: ci/deps/azure-windows-27.yaml
-        CONDA_PY: "27"
-
   steps:
     - task: CondaEnvironment@1
       inputs:
         updateConda: no
         packageSpecs: ''
 
-    - 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 only for Python 2.7'
-      condition: eq(variables.CONDA_PY, '27')
-
     - script: |
         ci\\incremental\\setup_conda_environment.cmd
       displayName: 'Before Install'

ci/azure/posix.yml

@@ -241,8 +241,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
-    MSG='Validate docstrings (GL06, GL07, GL09, SS04, PR03, PR05, PR10, EX04, RT04, SS05, SA05)' ; echo $MSG
-    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR05,EX04,RT04,SS05,SA05
+    MSG='Validate docstrings (GL03, GL06, GL07, GL09, SS04, SS05, PR03, PR04, PR05, PR10, EX04, RT04, RT05, SA05)' ; echo $MSG
+    $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL03,GL06,GL07,GL09,SS04,SS05,PR03,PR04,PR05,PR10,EX04,RT04,RT05,SA05
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi