Merge remote-tracking branch 'upstream/master' into pd.array

Author: TomAugspurger

.circleci/config.yml

@@ -34,5 +34,5 @@ jobs:
           command: |
             export PATH="$MINICONDA_DIR/bin:$PATH"
             source activate pandas-dev
-            echo "pytest --strict --durations=10 --color=no --junitxml=$CIRCLE_TEST_REPORTS/reports/junit.xml --skip-slow --skip-network pandas"
-            pytest       --strict --durations=10 --color=no --junitxml=$CIRCLE_TEST_REPORTS/reports/junit.xml --skip-slow --skip-network pandas
+            echo "pytest -m "not slow and not network" --strict --durations=10 --color=no --junitxml=$CIRCLE_TEST_REPORTS/reports/junit.xml pandas"
+            pytest       -m "not slow and not network" --strict --durations=10 --color=no --junitxml=$CIRCLE_TEST_REPORTS/reports/junit.xml pandas

.travis.yml

@@ -34,28 +34,28 @@ matrix:
     include:
     - dist: trusty
       env:
-        - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" TEST_ARGS="--skip-slow --skip-network"
+        - JOB="3.7" ENV_FILE="ci/deps/travis-37.yaml" PATTERN="not slow and not network"
 
     - dist: trusty
       env:
-        - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/deps/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" SLOW=true
+        - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/deps/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" PATTERN="slow"
       addons:
         apt:
           packages:
           - language-pack-zh-hans
     - dist: trusty
       env:
-        - JOB="2.7" ENV_FILE="ci/deps/travis-27.yaml" TEST_ARGS="--skip-slow"
+        - JOB="2.7" ENV_FILE="ci/deps/travis-27.yaml" PATTERN="not slow"
       addons:
         apt:
           packages:
           - python-gtk2
     - dist: trusty
       env:
-        - JOB="3.6, lint, coverage" ENV_FILE="ci/deps/travis-36.yaml" TEST_ARGS="--skip-slow --skip-network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true LINT=true
+        - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36.yaml" PATTERN="not slow and not network" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
     - dist: trusty
       env:
-        - JOB="3.7, NumPy dev" ENV_FILE="ci/deps/travis-37-numpydev.yaml" TEST_ARGS="--skip-slow --skip-network -W error" PANDAS_TESTING_MODE="deprecate"
+        - JOB="3.7, NumPy dev" ENV_FILE="ci/deps/travis-37-numpydev.yaml" PATTERN="not slow and not network" TEST_ARGS="-W error" PANDAS_TESTING_MODE="deprecate"
       addons:
         apt:
           packages:
@@ -64,7 +64,7 @@ matrix:
     # In allow_failures
     - dist: trusty
       env:
-        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" SLOW=true
+        - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow"
 
     # In allow_failures
     - dist: trusty
@@ -73,7 +73,7 @@ matrix:
     allow_failures:
       - dist: trusty
         env:
-          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" SLOW=true
+          - JOB="3.6, slow" ENV_FILE="ci/deps/travis-36-slow.yaml" PATTERN="slow"
       - dist: trusty
         env:
           - JOB="3.6, doc" ENV_FILE="ci/deps/travis-36-doc.yaml" DOC=true
@@ -107,20 +107,15 @@ script:
   - echo "script start"
   - source activate pandas-dev
   - ci/run_build_docs.sh
-  - ci/script_single.sh
-  - ci/script_multi.sh
-  - ci/code_checks.sh
-
-after_success:
-  -  ci/upload_coverage.sh
+  - ci/run_tests.sh
 
 after_script:
   - echo "after_script start"
   - source activate pandas-dev && pushd /tmp && python -c "import pandas; pandas.show_versions();" && popd
   - if [ -e test-data-single.xml ]; then
-    ci/print_skipped.py test-data-single.xml;
+        ci/print_skipped.py test-data-single.xml;
     fi
   - if [ -e test-data-multiple.xml ]; then
-    ci/print_skipped.py test-data-multiple.xml;
+        ci/print_skipped.py test-data-multiple.xml;
     fi
   - echo "after_script done"

LICENSES/MUSL_LICENSE

@@ -0,0 +1,132 @@
+musl as a whole is licensed under the following standard MIT license:
+
+----------------------------------------------------------------------
+Copyright © 2005-2014 Rich Felker, et al.
+
+Permission is hereby granted, free of charge, to any person obtaining
+a copy of this software and associated documentation files (the
+"Software"), to deal in the Software without restriction, including
+without limitation the rights to use, copy, modify, merge, publish,
+distribute, sublicense, and/or sell copies of the Software, and to
+permit persons to whom the Software is furnished to do so, subject to
+the following conditions:
+
+The above copyright notice and this permission notice shall be
+included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.
+IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY
+CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
+TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
+SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
+----------------------------------------------------------------------
+
+Authors/contributors include:
+
+Anthony G. Basile
+Arvid Picciani
+Bobby Bingham
+Boris Brezillon
+Brent Cook
+Chris Spiegel
+Clément Vasseur
+Emil Renner Berthing
+Hiltjo Posthuma
+Isaac Dunham
+Jens Gustedt
+Jeremy Huntwork
+John Spencer
+Justin Cormack
+Luca Barbato
+Luka Perkov
+M Farkas-Dyck (Strake)
+Michael Forney
+Nicholas J. Kain
+orc
+Pascal Cuoq
+Pierre Carrier
+Rich Felker
+Richard Pennington
+sin
+Solar Designer
+Stefan Kristiansson
+Szabolcs Nagy
+Timo Teräs
+Valentin Ochs
+William Haddon
+
+Portions of this software are derived from third-party works licensed
+under terms compatible with the above MIT license:
+
+The TRE regular expression implementation (src/regex/reg* and
+src/regex/tre*) is Copyright © 2001-2008 Ville Laurikari and licensed
+under a 2-clause BSD license (license text in the source files). The
+included version has been heavily modified by Rich Felker in 2012, in
+the interests of size, simplicity, and namespace cleanliness.
+
+Much of the math library code (src/math/* and src/complex/*) is
+Copyright © 1993,2004 Sun Microsystems or
+Copyright © 2003-2011 David Schultz or
+Copyright © 2003-2009 Steven G. Kargl or
+Copyright © 2003-2009 Bruce D. Evans or
+Copyright © 2008 Stephen L. Moshier
+and labelled as such in comments in the individual source files. All
+have been licensed under extremely permissive terms.
+
+The ARM memcpy code (src/string/armel/memcpy.s) is Copyright © 2008
+The Android Open Source Project and is licensed under a two-clause BSD
+license. It was taken from Bionic libc, used on Android.
+
+The implementation of DES for crypt (src/misc/crypt_des.c) is
+Copyright © 1994 David Burren. It is licensed under a BSD license.
+
+The implementation of blowfish crypt (src/misc/crypt_blowfish.c) was
+originally written by Solar Designer and placed into the public
+domain. The code also comes with a fallback permissive license for use
+in jurisdictions that may not recognize the public domain.
+
+The smoothsort implementation (src/stdlib/qsort.c) is Copyright © 2011
+Valentin Ochs and is licensed under an MIT-style license.
+
+The BSD PRNG implementation (src/prng/random.c) and XSI search API
+(src/search/*.c) functions are Copyright © 2011 Szabolcs Nagy and
+licensed under following terms: "Permission to use, copy, modify,
+and/or distribute this code for any purpose with or without fee is
+hereby granted. There is no warranty."
+
+The x86_64 port was written by Nicholas J. Kain. Several files (crt)
+were released into the public domain; others are licensed under the
+standard MIT license terms at the top of this file. See individual
+files for their copyright status.
+
+The mips and microblaze ports were originally written by Richard
+Pennington for use in the ellcc project. The original code was adapted
+by Rich Felker for build system and code conventions during upstream
+integration. It is licensed under the standard MIT terms.
+
+The powerpc port was also originally written by Richard Pennington,
+and later supplemented and integrated by John Spencer. It is licensed
+under the standard MIT terms.
+
+All other files which have no copyright comments are original works
+produced specifically for use as part of this library, written either
+by Rich Felker, the main author of the library, or by one or more
+contibutors listed above. Details on authorship of individual files
+can be found in the git version control history of the project. The
+omission of copyright and license comments in each file is in the
+interest of source tree size.
+
+All public header files (include/* and arch/*/bits/*) should be
+treated as Public Domain as they intentionally contain no content
+which can be covered by copyright. Some source modules may fall in
+this category as well. If you believe that a file is so trivial that
+it should be in the Public Domain, please contact the authors and
+request an explicit statement releasing it from copyright.
+
+The following files are trivial, believed not to be copyrightable in
+the first place, and hereby explicitly released to the Public Domain:
+
+All public headers: include/*, arch/*/bits/*
+Startup files: crt/*

asv_bench/benchmarks/algorithms.py

@@ -1,10 +1,11 @@
-import warnings
 from importlib import import_module
 
 import numpy as np
+
 import pandas as pd
 from pandas.util import testing as tm
 
+
 for imp in ['pandas.util', 'pandas.tools.hashing']:
     try:
         hashing = import_module(imp)
@@ -73,10 +74,6 @@ def setup(self):
         self.uniques = tm.makeStringIndex(1000).values
         self.all = self.uniques.repeat(10)
 
-    def time_match_string(self):
-        with warnings.catch_warnings(record=True):
-            pd.match(self.all, self.uniques)
-
 
 class Hashing(object):
 

asv_bench/benchmarks/categoricals.py

@@ -46,6 +46,8 @@ def setup(self):
         self.values_some_nan = list(np.tile(self.categories + [np.nan], N))
         self.values_all_nan = [np.nan] * len(self.values)
         self.values_all_int8 = np.ones(N, 'int8')
+        self.categorical = pd.Categorical(self.values, self.categories)
+        self.series = pd.Series(self.categorical)
 
     def time_regular(self):
         pd.Categorical(self.values, self.categories)
@@ -68,6 +70,12 @@ def time_all_nan(self):
     def time_from_codes_all_int8(self):
         pd.Categorical.from_codes(self.values_all_int8, self.categories)
 
+    def time_existing_categorical(self):
+        pd.Categorical(self.categorical)
+
+    def time_existing_series(self):
+        pd.Categorical(self.series)
+
 
 class ValueCounts(object):
 

asv_bench/benchmarks/frame_methods.py

@@ -1,10 +1,10 @@
 import string
-import warnings
 
 import numpy as np
+
+from pandas import (
+    DataFrame, MultiIndex, NaT, Series, date_range, isnull, period_range)
 import pandas.util.testing as tm
-from pandas import (DataFrame, Series, MultiIndex, date_range, period_range,
-                    isnull, NaT)
 
 
 class GetNumericData(object):
@@ -13,8 +13,7 @@ def setup(self):
         self.df = DataFrame(np.random.randn(10000, 25))
         self.df['foo'] = 'bar'
         self.df['bar'] = 'baz'
-        with warnings.catch_warnings(record=True):
-            self.df = self.df.consolidate()
+        self.df = self.df._consolidate()
 
     def time_frame_get_numeric_data(self):
         self.df._get_numeric_data()
@@ -62,9 +61,6 @@ def time_reindex_axis1(self):
     def time_reindex_both_axes(self):
         self.df.reindex(index=self.idx, columns=self.idx)
 
-    def time_reindex_both_axes_ix(self):
-        self.df.ix[self.idx, self.idx]
-
     def time_reindex_upcast(self):
         self.df2.reindex(np.random.permutation(range(1200)))
 

asv_bench/benchmarks/groupby.py

@@ -1,11 +1,13 @@
-import warnings
-from string import ascii_letters
-from itertools import product
 from functools import partial
+from itertools import product
+from string import ascii_letters
+import warnings
 
 import numpy as np
-from pandas import (DataFrame, Series, MultiIndex, date_range, period_range,
-                    TimeGrouper, Categorical, Timestamp)
+
+from pandas import (
+    Categorical, DataFrame, MultiIndex, Series, TimeGrouper, Timestamp,
+    date_range, period_range)
 import pandas.util.testing as tm
 
 
@@ -210,7 +212,7 @@ def time_multi_int_nunique(self, df):
 
 class AggFunctions(object):
 
-    def setup_cache():
+    def setup_cache(self):
         N = 10**5
         fac1 = np.array(['A', 'B', 'C'], dtype='O')
         fac2 = np.array(['one', 'two'], dtype='O')
@@ -471,8 +473,8 @@ def setup(self):
         n1 = 400
         n2 = 250
         index = MultiIndex(levels=[np.arange(n1), tm.makeStringIndex(n2)],
-                           labels=[np.repeat(range(n1), n2).tolist(),
-                                   list(range(n2)) * n1],
+                           codes=[np.repeat(range(n1), n2).tolist(),
+                                  list(range(n2)) * n1],
                            names=['lev1', 'lev2'])
         arr = np.random.randn(n1 * n2, 3)
         arr[::10000, 0] = np.nan

asv_bench/benchmarks/join_merge.py

@@ -23,11 +23,7 @@ def setup(self):
         self.mdf1['obj1'] = 'bar'
         self.mdf1['obj2'] = 'bar'
         self.mdf1['int1'] = 5
-        try:
-            with warnings.catch_warnings(record=True):
-                self.mdf1.consolidate(inplace=True)
-        except (AttributeError, TypeError):
-            pass
+        self.mdf1 = self.mdf1._consolidate()
         self.mdf2 = self.mdf1.copy()
         self.mdf2.index = self.df2.index
 
@@ -119,16 +115,16 @@ class Join(object):
     def setup(self, sort):
         level1 = tm.makeStringIndex(10).values
         level2 = tm.makeStringIndex(1000).values
-        label1 = np.arange(10).repeat(1000)
-        label2 = np.tile(np.arange(1000), 10)
+        codes1 = np.arange(10).repeat(1000)
+        codes2 = np.tile(np.arange(1000), 10)
         index2 = MultiIndex(levels=[level1, level2],
-                            labels=[label1, label2])
+                            codes=[codes1, codes2])
         self.df_multi = DataFrame(np.random.randn(len(index2), 4),
                                   index=index2,
                                   columns=['A', 'B', 'C', 'D'])
 
-        self.key1 = np.tile(level1.take(label1), 10)
-        self.key2 = np.tile(level2.take(label2), 10)
+        self.key1 = np.tile(level1.take(codes1), 10)
+        self.key2 = np.tile(level2.take(codes2), 10)
         self.df = DataFrame({'data1': np.random.randn(100000),
                              'data2': np.random.randn(100000),
                              'key1': self.key1,

asv_bench/benchmarks/multiindex_object.py

@@ -79,8 +79,8 @@ def setup(self):
         levels = [np.arange(n),
                   tm.makeStringIndex(n).values,
                   1000 + np.arange(n)]
-        labels = [np.random.choice(n, (k * n)) for lev in levels]
-        self.mi = MultiIndex(levels=levels, labels=labels)
+        codes = [np.random.choice(n, (k * n)) for lev in levels]
+        self.mi = MultiIndex(levels=levels, codes=codes)
 
     def time_duplicated(self):
         self.mi.duplicated()

asv_bench/benchmarks/period.py

@@ -43,13 +43,17 @@ class PeriodIndexConstructor(object):
     def setup(self, freq):
         self.rng = date_range('1985', periods=1000)
         self.rng2 = date_range('1985', periods=1000).to_pydatetime()
+        self.ints = list(range(2000, 3000))
 
     def time_from_date_range(self, freq):
         PeriodIndex(self.rng, freq=freq)
 
     def time_from_pydatetime(self, freq):
         PeriodIndex(self.rng2, freq=freq)
 
+    def time_from_ints(self, freq):
+        PeriodIndex(self.ints, freq=freq)
+
 
 class DataFramePeriodColumn(object):