Merge pull request #3 from pandas-dev/master

Merge commit

Author: rs2

.gitignore

@@ -106,3 +106,4 @@ doc/build/html/index.html
 doc/tmp.sv
 doc/source/styled.xlsx
 doc/source/templates/
+doc/source/savefig/

.travis.yml

@@ -52,10 +52,6 @@ matrix:
     - dist: trusty
       env:
         - JOB="3.5" TEST_ARGS="--skip-slow --skip-network" COVERAGE=true
-      addons:
-        apt:
-          packages:
-          - xsel
     - dist: trusty
       env:
         - JOB="3.6" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" CONDA_FORGE=true
@@ -66,7 +62,11 @@ matrix:
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="2.7_BUILD_TEST" TEST_ARGS="--skip-slow" BUILD_TEST=true
+        - JOB="3.6_BUILD_TEST" TEST_ARGS="--skip-slow" BUILD_TEST=true
+      addons:
+        apt:
+          packages:
+          - xsel
     # In allow_failures
     - dist: trusty
       env:
@@ -75,17 +75,17 @@ matrix:
     - dist: trusty
       env:
         - JOB="3.6_DOC" DOC=true
-      addons:
-        apt:
-          packages:
-          - xsel
     allow_failures:
       - dist: trusty
         env:
           - JOB="2.7_SLOW" SLOW=true
       - dist: trusty
         env:
-          - JOB="2.7_BUILD_TEST" TEST_ARGS="--skip-slow" BUILD_TEST=true
+          - JOB="3.6_BUILD_TEST" TEST_ARGS="--skip-slow" BUILD_TEST=true
+        addons:
+          apt:
+            packages:
+            - xsel
       - dist: trusty
         env:
           - JOB="3.6_NUMPY_DEV" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate"
@@ -102,8 +102,6 @@ before_install:
   - uname -a
   - git --version
   - git tag
-  - ci/before_install_travis.sh
-  - export DISPLAY=":99.0"
 
 install:
   - echo "install start"
@@ -114,6 +112,8 @@ install:
 
 before_script:
   - ci/install_db_travis.sh
+  - export DISPLAY=":99.0"
+  - ci/before_script_travis.sh
 
 script:
   - echo "script start"

MANIFEST.in

@@ -1,7 +1,7 @@
 include MANIFEST.in
 include LICENSE
 include RELEASE.md
-include README.rst
+include README.md
 include setup.py
 include pyproject.toml
 

Makefile

@@ -12,6 +12,9 @@ clean_pyc:
 build: clean_pyc
 	python setup.py build_ext --inplace
 
+lint-diff:
+	git diff master --name-only -- "*.py" | grep "pandas" | xargs flake8
+
 develop: build
 	-python setup.py develop
 

appveyor.yml

@@ -22,7 +22,7 @@ environment:
       PYTHON_VERSION: "3.6"
       PYTHON_ARCH: "64"
       CONDA_PY: "36"
-      CONDA_NPY: "112"
+      CONDA_NPY: "113"
 
     - CONDA_ROOT: "C:\\Miniconda3_64"
       PYTHON_VERSION: "2.7"
@@ -59,7 +59,7 @@ install:
 
   # install our build environment
   - cmd: conda config --set show_channel_urls true --set always_yes true --set changeps1 false
-  # - cmd: conda update -q conda
+  - cmd: conda update -q conda
   - cmd: conda config --set ssl_verify false
 
   # add the pandas channel *before* defaults to have defaults take priority

asv_bench/benchmarks/categoricals.py

@@ -26,6 +26,9 @@ def setup(self):
         self.datetimes = pd.Series(pd.date_range(
             '1995-01-01 00:00:00', periods=10000, freq='s'))
 
+        self.values_some_nan = list(np.tile(self.categories + [np.nan], N))
+        self.values_all_nan = [np.nan] * len(self.values)
+
     def time_concat(self):
         concat([self.s, self.s])
 
@@ -46,6 +49,12 @@ def time_constructor_datetimes_with_nat(self):
         t.iloc[-1] = pd.NaT
         Categorical(t)
 
+    def time_constructor_with_nan(self):
+        Categorical(self.values_some_nan)
+
+    def time_constructor_all_nan(self):
+        Categorical(self.values_all_nan)
+
 
 class Categoricals2(object):
     goal_time = 0.2

asv_bench/benchmarks/index_object.py

@@ -219,3 +219,22 @@ def time_min(self):
 
     def time_min_trivial(self):
         self.idx_inc.min()
+
+
+class IndexOps(object):
+    goal_time = 0.2
+
+    def setup(self):
+        N = 10000
+        self.ridx = [RangeIndex(i * 100, (i + 1) * 100) for i in range(N)]
+        self.iidx = [idx.astype(int) for idx in self.ridx]
+        self.oidx = [idx.astype(str) for idx in self.iidx]
+
+    def time_concat_range(self):
+        self.ridx[0].append(self.ridx[1:])
+
+    def time_concat_int(self):
+        self.iidx[0].append(self.iidx[1:])
+
+    def time_concat_obj(self):
+        self.oidx[0].append(self.oidx[1:])

asv_bench/benchmarks/indexing.py

@@ -287,3 +287,19 @@ def setup(self):
 
     def time_subset(self):
         self.p.ix[(self.inds, self.inds, self.inds)]
+
+
+class IndexerLookup(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.s = Series(range(10))
+
+    def time_lookup_iloc(self):
+        self.s.iloc
+
+    def time_lookup_ix(self):
+        self.s.ix
+
+    def time_lookup_loc(self):
+        self.s.loc

asv_bench/benchmarks/timedelta.py

@@ -40,3 +40,46 @@ def setup(self):
 
     def test_add_td_ts(self):
         self.td + self.ts
+
+
+class TimedeltaProperties(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.td = Timedelta(days=365, minutes=35, seconds=25, milliseconds=35)
+
+    def time_timedelta_days(self):
+        self.td.days
+
+    def time_timedelta_seconds(self):
+        self.td.seconds
+
+    def time_timedelta_microseconds(self):
+        self.td.microseconds
+
+    def time_timedelta_nanoseconds(self):
+        self.td.nanoseconds
+
+
+class DatetimeAccessor(object):
+    goal_time = 0.2
+
+    def setup(self):
+        self.N = 100000
+        self.series = pd.Series(
+            pd.timedelta_range('1 days', periods=self.N, freq='h')
+        )
+    def time_dt_accessor(self):
+        self.series.dt
+
+    def time_timedelta_dt_accessor_days(self):
+        self.series.dt.days
+
+    def time_timedelta_dt_accessor_seconds(self):
+        self.series.dt.seconds
+
+    def time_timedelta_dt_accessor_microseconds(self):
+        self.series.dt.microseconds
+
+    def time_timedelta_dt_accessor_nanoseconds(self):
+        self.series.dt.nanoseconds

asv_bench/benchmarks/timeseries.py

@@ -346,17 +346,22 @@ class ToDatetime(object):
 
     def setup(self):
         self.rng = date_range(start='1/1/2000', periods=10000, freq='D')
-        self.stringsD = Series((((self.rng.year * 10000) + (self.rng.month * 100)) + self.rng.day), dtype=np.int64).apply(str)
+        self.stringsD = Series(self.rng.strftime('%Y%m%d'))
 
         self.rng = date_range(start='1/1/2000', periods=20000, freq='H')
-        self.strings = [x.strftime('%Y-%m-%d %H:%M:%S') for x in self.rng]
-        self.strings_nosep = [x.strftime('%Y%m%d %H:%M:%S') for x in self.rng]
+        self.strings = self.rng.strftime('%Y-%m-%d %H:%M:%S').tolist()
+        self.strings_nosep = self.rng.strftime('%Y%m%d %H:%M:%S').tolist()
         self.strings_tz_space = [x.strftime('%Y-%m-%d %H:%M:%S') + ' -0800'
                                  for x in self.rng]
 
         self.s = Series((['19MAY11', '19MAY11:00:00:00'] * 100000))
         self.s2 = self.s.str.replace(':\\S+$', '')
 
+        self.unique_numeric_seconds = range(10000)
+        self.dup_numeric_seconds = [1000] * 10000
+        self.dup_string_dates = ['2000-02-11'] * 10000
+        self.dup_string_with_tz = ['2000-02-11 15:00:00-0800'] * 10000
+
     def time_format_YYYYMMDD(self):
         to_datetime(self.stringsD, format='%Y%m%d')
 
@@ -381,6 +386,36 @@ def time_format_exact(self):
     def time_format_no_exact(self):
         to_datetime(self.s, format='%d%b%y', exact=False)
 
+    def time_cache_true_with_unique_seconds_and_unit(self):
+        to_datetime(self.unique_numeric_seconds, unit='s', cache=True)
+
+    def time_cache_false_with_unique_seconds_and_unit(self):
+        to_datetime(self.unique_numeric_seconds, unit='s', cache=False)
+
+    def time_cache_true_with_dup_seconds_and_unit(self):
+        to_datetime(self.dup_numeric_seconds, unit='s', cache=True)
+
+    def time_cache_false_with_dup_seconds_and_unit(self):
+        to_datetime(self.dup_numeric_seconds, unit='s', cache=False)
+
+    def time_cache_true_with_dup_string_dates(self):
+        to_datetime(self.dup_string_dates, cache=True)
+
+    def time_cache_false_with_dup_string_dates(self):
+        to_datetime(self.dup_string_dates, cache=False)
+
+    def time_cache_true_with_dup_string_dates_and_format(self):
+        to_datetime(self.dup_string_dates, format='%Y-%m-%d', cache=True)
+
+    def time_cache_false_with_dup_string_dates_and_format(self):
+        to_datetime(self.dup_string_dates, format='%Y-%m-%d', cache=False)
+
+    def time_cache_true_with_dup_string_tzoffset_dates(self):
+        to_datetime(self.dup_string_with_tz, cache=True)
+
+    def time_cache_false_with_dup_string_tzoffset_dates(self):
+        to_datetime(self.dup_string_with_tz, cache=False)
+
 
 class Offsets(object):
     goal_time = 0.2

ci/before_install_travis.sh renamed to ci/before_script_travis.sh

@@ -4,6 +4,7 @@ echo "inside $0"
 
 if [ "${TRAVIS_OS_NAME}" == "linux" ]; then
    sh -e /etc/init.d/xvfb start
+   sleep 3
 fi
 
 # Never fail because bad things happened here.

ci/environment-dev.yaml

@@ -0,0 +1,14 @@
+name: pandas-dev
+channels:
+  - defaults
+  - conda-forge
+dependencies:
+  - Cython
+  - NumPy
+  - moto
+  - pytest
+  - python-dateutil
+  - python=3
+  - pytz
+  - setuptools
+  - sphinx

ci/install.ps1

@@ -7,7 +7,7 @@ $MINICONDA_URL = "http://repo.continuum.io/miniconda/"
 
 function DownloadMiniconda ($python_version, $platform_suffix) {
     $webclient = New-Object System.Net.WebClient
-    $filename = "Miniconda3-4.3.21-Windows-" + $platform_suffix + ".exe"
+    $filename = "Miniconda3-latest-Windows-" + $platform_suffix + ".exe"
     $url = $MINICONDA_URL + $filename
 
     $basedir = $pwd.Path + "\"
@@ -85,7 +85,7 @@ function UpdateConda ($python_home) {
 
 function main () {
     InstallMiniconda "3.5" $env:PYTHON_ARCH $env:CONDA_ROOT
-    # UpdateConda $env:CONDA_ROOT
+    UpdateConda $env:CONDA_ROOT
     InstallCondaPackages $env:CONDA_ROOT "conda-build jinja2 anaconda-client"
 }
 

ci/install_circle.sh

@@ -10,17 +10,15 @@ echo "[Using clean Miniconda install]"
 rm -rf "$MINICONDA_DIR"
 
 # install miniconda
-# wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -q -O miniconda.sh || exit 1
-# Pin miniconda
-wget https://repo.continuum.io/miniconda/Miniconda2-4.3.21-Linux-x86_64.sh -q -O miniconda.sh || exit 1
+wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -q -O miniconda.sh || exit 1
 bash miniconda.sh -b -p "$MINICONDA_DIR" || exit 1
 
 export PATH="$MINICONDA_DIR/bin:$PATH"
 
 echo "[update conda]"
 conda config --set ssl_verify false || exit 1
 conda config --set always_yes true --set changeps1 false || exit 1
-# conda update -q conda
+conda update -q conda
 
 # add the pandas channel to take priority
 # to add extra packages

ci/install_travis.sh

@@ -34,13 +34,9 @@ fi
 
 # install miniconda
 if [ "${TRAVIS_OS_NAME}" == "osx" ]; then
-    # temporarily pin miniconda
-    # time wget http://repo.continuum.io/miniconda/Miniconda3-latest-MacOSX-x86_64.sh -O miniconda.sh || exit 1
-    time wget https://repo.continuum.io/miniconda/Miniconda2-4.3.21-MacOSX-x86_64.sh -O miniconda.sh || exit 1
+    time wget http://repo.continuum.io/miniconda/Miniconda3-latest-MacOSX-x86_64.sh -q -O miniconda.sh || exit 1
 else
-    # temporarily pin miniconda
-    # time wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh || exit 1
-    time wget https://repo.continuum.io/miniconda/Miniconda2-4.3.21-Linux-x86_64.sh -O miniconda.sh || exit 1
+    time wget http://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -q -O miniconda.sh || exit 1
 fi
 time bash miniconda.sh -b -p "$MINICONDA_DIR" || exit 1
 
@@ -52,7 +48,7 @@ echo
 echo "[update conda]"
 conda config --set ssl_verify false || exit 1
 conda config --set quiet true --set always_yes true --set changeps1 false || exit 1
-# conda update -q conda
+conda update -q conda
 
 echo
 echo "[add channels]"