Merge remote-tracking branch 'upstream/master' into issue-23334-attrs-to-eval

Author: gasparia405

Makefile

@@ -23,4 +23,3 @@ doc:
 cd doc; \
 python make.py clean; \
 python make.py html
-python make.py spellcheck

asv_bench/benchmarks/__init__.py

@@ -0,0 +1 @@
+"""Pandas benchmarks."""

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/series_methods.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']

ci/code_checks.sh

@@ -93,7 +93,7 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
  # this particular codebase (e.g. src/headers, src/klib, src/msgpack). However,
  # we can lint all header files since they aren't "generated" like C files are.
  MSG='Linting .c and .h' ; echo $MSG
- cpplint --quiet --extensions=c,h --headers=h --recursive --filter=-readability/casting,-runtime/int,-build/include_subdir pandas/_libs/src/*.h pandas/_libs/src/parser pandas/_libs/ujson pandas/_libs/tslibs/src/datetime
+ cpplint --quiet --extensions=c,h --headers=h --recursive --filter=-readability/casting,-runtime/int,-build/include_subdir pandas/_libs/src/*.h pandas/_libs/src/parser pandas/_libs/ujson pandas/_libs/tslibs/src/datetime pandas/io/msgpack pandas/_libs/*.cpp pandas/util
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 
  echo "isort --version-number"
@@ -174,9 +174,10 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
  MSG='Check that no file in the repo contains tailing whitespaces' ; echo $MSG
  set -o pipefail
  if [[ "$AZURE" == "true" ]]; then
- ! grep -n --exclude="*.svg" -RI "\s$" * | awk -F ":" '{print "##vso[task.logissue type=error;sourcepath=" $1 ";linenumber=" $2 ";] Tailing whitespaces found: " $3}'
+ # we exclude all c/cpp files as the c/cpp files of pandas code base are tested when Linting .c and .h files
+ ! grep -n '--exclude=*.'{svg,c,cpp,html} -RI "\s$" * | awk -F ":" '{print "##vso[task.logissue type=error;sourcepath=" $1 ";linenumber=" $2 ";] Tailing whitespaces found: " $3}'
  else
- ! grep -n --exclude="*.svg" -RI "\s$" * | awk -F ":" '{print $1 ":" $2 ":Tailing whitespaces found: " $3}'
+ ! grep -n '--exclude=*.'{svg,c,cpp,html}  -RI "\s$" * | awk -F ":" '{print $1 ":" $2 ":Tailing whitespaces found: " $3}'
  fi
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 fi
@@ -206,7 +207,7 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
  MSG='Doctests frame.py' ; echo $MSG
  pytest -q --doctest-modules pandas/core/frame.py \
- -k"-axes -combine -itertuples -join -pivot_table -query -reindex -reindex_axis -round"
+ -k" -itertuples -join -reindex -reindex_axis -round"
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 
  MSG='Doctests series.py' ; echo $MSG
@@ -240,8 +241,8 @@ fi
 ### DOCSTRINGS ###
 if [[ -z "$CHECK" || "$CHECK" == "docstrings" ]]; then
 
- MSG='Validate docstrings (GL06, GL07, GL09, SS04, PR03, PR05, EX04)' ; echo $MSG
- $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR05,EX04
+ MSG='Validate docstrings (GL06, GL07, GL09, SS04, PR03, PR05, PR10, EX04, RT04, RT05, SS05, SA05)' ; echo $MSG
+ $BASE_DIR/scripts/validate_docstrings.py --format=azure --errors=GL06,GL07,GL09,SS04,PR03,PR04,PR05,EX04,RT04,RT05,SS05,SA05
  RET=$(($RET + $?)) ; echo $MSG "DONE"
 
 fi

ci/deps/azure-27-compat.yaml

@@ -20,6 +20,8 @@ dependencies:
  # universal
  - pytest
  - pytest-xdist
+ - pytest-mock
+ - isort
  - pip:
  - html5lib==1.0b2
  - beautifulsoup4==4.2.1

ci/deps/azure-27-locale.yaml

@@ -22,7 +22,9 @@ dependencies:
  # universal
  - pytest
  - pytest-xdist
+ - pytest-mock
  - hypothesis>=3.58.0
+ - isort
  - pip:
  - html5lib==1.0b2
  - beautifulsoup4==4.2.1

ci/deps/azure-36-locale_slow.yaml

@@ -28,6 +28,8 @@ dependencies:
  # universal
  - pytest
  - pytest-xdist
+ - pytest-mock
  - moto
+ - isort
  - pip:
  - hypothesis>=3.58.0

ci/deps/azure-37-locale.yaml

@@ -27,6 +27,8 @@ dependencies:
  # universal
  - pytest
  - pytest-xdist
+ - pytest-mock
+ - isort
  - pip:
  - hypothesis>=3.58.0
  - moto # latest moto in conda-forge fails with 3.7, move to conda dependencies when this is fixed

ci/deps/azure-37-numpydev.yaml

@@ -8,7 +8,9 @@ dependencies:
  # universal
  - pytest
  - pytest-xdist
+ - pytest-mock
  - hypothesis>=3.58.0
+ - isort
  - pip:
  - "git+git://github.com/dateutil/dateutil.git"
  - "-f https://7933911d6844c6c53a7d-47bd50c35cd79bd838daf386af554a83.ssl.cf2.rackcdn.com"