Merge branch 'master' into to_stata_docstring

Author: ryankarlos

.circleci/config.yml

@@ -1,10 +1,6 @@
 version: 2
 jobs:
-
-  # --------------------------------------------------------------------------
-  # 1. py36_locale
-  # --------------------------------------------------------------------------
-  py36_locale:
+  build:
     docker:
       - image: continuumio/miniconda:latest
       # databases configuration
@@ -34,9 +30,3 @@ jobs:
       - run:
           name: test
           command: ./ci/circle/run_circle.sh  --skip-slow --skip-network
-
-workflows:
-  version: 2
-  build_and_test:
-    jobs:
-      - py36_locale

.gitignore

@@ -109,6 +109,5 @@ doc/build/html/index.html
 # Windows specific leftover:
 doc/tmp.sv
 doc/source/styled.xlsx
-doc/source/templates/
 env/
 doc/source/savefig/

.pep8speaks.yml

@@ -13,7 +13,6 @@ pycodestyle:
         - W503,  # line break before binary operator
         - W504,  # line break after binary operator
         - E402,  # module level import not at top of file
-        - E722,  # do not use bare except
         - E731,  # do not assign a lambda expression, use a def
         - C406,  # Unnecessary list literal - rewrite as a dict literal.
         - C408,  # Unnecessary dict call - rewrite as a literal.

.travis.yml

@@ -23,7 +23,7 @@ env:
 
 git:
     # for cloning
-    depth: 1000
+    depth: 1500
 
 matrix:
     fast_finish: true

asv_bench/benchmarks/timeseries.py

@@ -1,5 +1,6 @@
 from datetime import timedelta
 
+import dateutil
 import numpy as np
 from pandas import to_datetime, date_range, Series, DataFrame, period_range
 from pandas.tseries.frequencies import infer_freq
@@ -57,7 +58,10 @@ def time_to_pydatetime(self, index_type):
 
 class TzLocalize(object):
 
-    def setup(self):
+    params = [None, 'US/Eastern', 'UTC', dateutil.tz.tzutc()]
+    param_names = 'tz'
+
+    def setup(self, tz):
         dst_rng = date_range(start='10/29/2000 1:00:00',
                              end='10/29/2000 1:59:59', freq='S')
         self.index = date_range(start='10/29/2000',
@@ -68,8 +72,8 @@ def setup(self):
                                                   end='10/29/2000 3:00:00',
                                                   freq='S'))
 
-    def time_infer_dst(self):
-        self.index.tz_localize('US/Eastern', ambiguous='infer')
+    def time_infer_dst(self, tz):
+        self.index.tz_localize(tz, ambiguous='infer')
 
 
 class ResetIndex(object):
@@ -377,15 +381,35 @@ def time_dup_string_tzoffset_dates(self, cache):
 
 class DatetimeAccessor(object):
 
-    def setup(self):
+    params = [None, 'US/Eastern', 'UTC', dateutil.tz.tzutc()]
+    param_names = 'tz'
+
+    def setup(self, tz):
         N = 100000
-        self.series = Series(date_range(start='1/1/2000', periods=N, freq='T'))
+        self.series = Series(
+            date_range(start='1/1/2000', periods=N, freq='T', tz=tz)
+        )
 
-    def time_dt_accessor(self):
+    def time_dt_accessor(self, tz):
         self.series.dt
 
-    def time_dt_accessor_normalize(self):
+    def time_dt_accessor_normalize(self, tz):
         self.series.dt.normalize()
 
+    def time_dt_accessor_month_name(self, tz):
+        self.series.dt.month_name()
+
+    def time_dt_accessor_day_name(self, tz):
+        self.series.dt.day_name()
+
+    def time_dt_accessor_time(self, tz):
+        self.series.dt.time
+
+    def time_dt_accessor_date(self, tz):
+        self.series.dt.date
+
+    def time_dt_accessor_year(self, tz):
+        self.series.dt.year
+
 
 from .pandas_vb_common import setup  # noqa: F401

asv_bench/benchmarks/timestamp.py

@@ -2,6 +2,7 @@
 
 from pandas import Timestamp
 import pytz
+import dateutil
 
 
 class TimestampConstruction(object):
@@ -29,7 +30,8 @@ def time_fromtimestamp(self):
 
 
 class TimestampProperties(object):
-    _tzs = [None, pytz.timezone('Europe/Amsterdam')]
+    _tzs = [None, pytz.timezone('Europe/Amsterdam'), pytz.UTC,
+            dateutil.tz.tzutc()]
     _freqs = [None, 'B']
     params = [_tzs, _freqs]
     param_names = ['tz', 'freq']
@@ -87,7 +89,8 @@ def time_microsecond(self, tz, freq):
 
 
 class TimestampOps(object):
-    params = [None, 'US/Eastern']
+    params = [None, 'US/Eastern', pytz.UTC,
+              dateutil.tz.tzutc()]
     param_names = ['tz']
 
     def setup(self, tz):
@@ -102,6 +105,17 @@ def time_replace_None(self, tz):
     def time_to_pydatetime(self, tz):
         self.ts.to_pydatetime()
 
+    def time_normalize(self, tz):
+        self.ts.normalize()
+
+    def time_tz_convert(self, tz):
+        if self.ts.tz is not None:
+            self.ts.tz_convert(tz)
+
+    def time_tz_localize(self, tz):
+        if self.ts.tz is None:
+            self.ts.tz_localize(tz)
+
 
 class TimestampAcrossDst(object):
     def setup(self):

ci/build_docs.sh

@@ -5,7 +5,7 @@ if [ "${TRAVIS_OS_NAME}" != "linux" ]; then
    exit 0
 fi
 
-cd "$TRAVIS_BUILD_DIR"
+cd "$TRAVIS_BUILD_DIR"/doc
 echo "inside $0"
 
 if [ "$DOC" ]; then
@@ -14,10 +14,6 @@ if [ "$DOC" ]; then
 
     source activate pandas
 
-    mv "$TRAVIS_BUILD_DIR"/doc /tmp
-    mv "$TRAVIS_BUILD_DIR/LICENSE" /tmp  # included in the docs.
-    cd /tmp/doc
-
     echo ###############################
     echo # Log file for the doc build  #
     echo ###############################
@@ -29,7 +25,7 @@ if [ "$DOC" ]; then
     echo # Create and send docs #
     echo ########################
 
-    cd /tmp/doc/build/html
+    cd build/html
     git config --global user.email "[email protected]"
     git config --global user.name "pandas-docs-bot"
 

ci/code_checks.sh

@@ -9,16 +9,19 @@
 # In the future we may want to add the validation of docstrings and other checks here.
 #
 # Usage:
-#   $ ./ci/code_checks.sh             # run all checks
-#   $ ./ci/code_checks.sh lint        # run linting only
-#   $ ./ci/code_checks.sh patterns    # check for patterns that should not exist
-#   $ ./ci/code_checks.sh doctests    # run doctests
+#   $ ./ci/code_checks.sh               # run all checks
+#   $ ./ci/code_checks.sh lint          # run linting only
+#   $ ./ci/code_checks.sh patterns      # check for patterns that should not exist
+#   $ ./ci/code_checks.sh doctests      # run doctests
+#   $ ./ci/code_checks.sh dependencies  # check that dependencies are consistent
 
 echo "inside $0"
 [[ $LINT ]] || { echo "NOT Linting. To lint use: LINT=true $0 $1"; exit 0; }
-[[ -z "$1" || "$1" == "lint" || "$1" == "patterns" || "$1" == "doctests" ]] || { echo "Unknown command $1. Usage: $0 [lint|patterns|doctests]"; exit 9999; }
+[[ -z "$1" || "$1" == "lint" || "$1" == "patterns" || "$1" == "doctests" || "$1" == "dependencies"  ]] \
+    || { echo "Unknown command $1. Usage: $0 [lint|patterns|doctests|dependencies]"; exit 9999; }
 
 source activate pandas
+BASE_DIR="$(dirname $0)/.."
 RET=0
 CHECK=$1
 
@@ -44,6 +47,13 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     flake8 pandas/_libs --filename=*.pxi.in,*.pxd --select=E501,E302,E203,E111,E114,E221,E303,E231,E126,F403
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    echo "flake8-rst --version"
+    flake8-rst --version
+
+    MSG='Linting code-blocks in .rst documentation' ; echo $MSG
+    flake8-rst doc/source --filename=*.rst
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     # Check that cython casting is of the form `<type>obj` as opposed to `<type> obj`;
     # it doesn't make a difference, but we want to be internally consistent.
     # Note: this grep pattern is (intended to be) equivalent to the python
@@ -64,6 +74,9 @@ if [[ -z "$CHECK" || "$CHECK" == "lint" ]]; then
     cpplint --quiet --extensions=c,h --headers=h --recursive --filter=-readability/casting,-runtime/int,-build/include_subdir pandas/_libs/src/*.h pandas/_libs/src/parser pandas/_libs/ujson pandas/_libs/tslibs/src/datetime
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    echo "isort --version-number"
+    isort --version-number
+
     # Imports - Check formatting using isort see setup.cfg for settings
     MSG='Check import format using isort ' ; echo $MSG
     isort --recursive --check-only pandas
@@ -109,6 +122,10 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     ! grep -R --include="*.py" --include="*.pyx" --include="*.rst" -E "\.\. (autosummary|contents|currentmodule|deprecated|function|image|important|include|ipython|literalinclude|math|module|note|raw|seealso|toctree|versionadded|versionchanged|warning):[^:]" ./pandas ./doc/source
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
+    MSG='Check that the deprecated `assert_raises_regex` is not used (`pytest.raises(match=pattern)` should be used instead)' ; echo $MSG
+    ! grep -R --exclude=*.pyc --exclude=testing.py --exclude=test_testing.py assert_raises_regex pandas
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+
     MSG='Check for modules that pandas should not import' ; echo $MSG
     python -c "
 import sys
@@ -141,7 +158,7 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
     MSG='Doctests generic.py' ; echo $MSG
     pytest -q --doctest-modules pandas/core/generic.py \
-        -k"-_set_axis_name -_xs -describe -droplevel -groupby -interpolate -pct_change -pipe -reindex -reindex_axis -resample -to_json -transpose -values -xs"
+        -k"-_set_axis_name -_xs -describe -droplevel -groupby -interpolate -pct_change -pipe -reindex -reindex_axis -to_json -transpose -values -xs"
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Doctests top-level reshaping functions' ; echo $MSG
@@ -162,4 +179,11 @@ if [[ -z "$CHECK" || "$CHECK" == "doctests" ]]; then
 
 fi
 
+### DEPENDENCIES ###
+if [[ -z "$CHECK" || "$CHECK" == "dependencies" ]]; then
+    MSG='Check that requirements-dev.txt has been generated from environment.yml' ; echo $MSG
+    $BASE_DIR/scripts/generate_pip_deps_from_conda.py --compare
+    RET=$(($RET + $?)) ; echo $MSG "DONE"
+fi
+
 exit $RET

ci/deps/azure-27-compat.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytz=2013b
   - scipy=0.18.1
   - sqlalchemy=0.7.8
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-27-locale.yaml

@@ -16,7 +16,7 @@ dependencies:
   - pytz=2013b
   - scipy
   - sqlalchemy=0.8.1
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-27.yaml

@@ -35,7 +35,7 @@ dependencies:
   - scipy
   - sqlalchemy=0.9.6
   - xarray=0.9.6
-  - xlrd=0.9.2
+  - xlrd=1.0.0
   - xlsxwriter=0.5.2
   - xlwt=0.7.5
   # universal

ci/deps/travis-36-doc.yaml

@@ -8,10 +8,11 @@ dependencies:
   - bottleneck
   - cython>=0.28.2
   - fastparquet
+  - gitpython
   - html5lib
   - hypothesis>=3.58.0
   - ipykernel
-  - ipython==6.5.0
+  - ipython
   - ipywidgets
   - lxml
   - matplotlib

ci/deps/travis-36.yaml

@@ -9,6 +9,7 @@ dependencies:
   - fastparquet
   - flake8>=3.5
   - flake8-comprehensions
+  - flake8-rst=0.4.2
   - gcsfs
   - geopandas
   - html5lib

ci/environment-dev.yaml

@@ -126,7 +126,12 @@ def _process_single_doc(self, single_doc):
             self.single_doc = 'api'
         elif os.path.exists(os.path.join(SOURCE_PATH, single_doc)):
             self.single_doc_type = 'rst'
-            self.single_doc = os.path.splitext(os.path.basename(single_doc))[0]
+
+            if 'whatsnew' in single_doc:
+                basename = single_doc
+            else:
+                basename = os.path.basename(single_doc)
+            self.single_doc = os.path.splitext(basename)[0]
         elif os.path.exists(
                 os.path.join(SOURCE_PATH, '{}.rst'.format(single_doc))):
             self.single_doc_type = 'rst'