Merge branch 'master' into replace_object

Author: peterpanmj

.travis.yml

@@ -35,6 +35,11 @@ matrix:
       language: generic
       env:
         - JOB="3.5, OSX" ENV_FILE="ci/travis-35-osx.yaml" TEST_ARGS="--skip-slow --skip-network"
+
+    - dist: trusty
+      env:
+        - JOB="3.7" ENV_FILE="ci/travis-37.yaml" TEST_ARGS="--skip-slow --skip-network"
+
     - dist: trusty
       env:
         - JOB="2.7, locale, slow, old NumPy" ENV_FILE="ci/travis-27-locale.yaml" LOCALE_OVERRIDE="zh_CN.UTF-8" SLOW=true

MANIFEST.in

@@ -3,27 +3,39 @@ include LICENSE
 include RELEASE.md
 include README.md
 include setup.py
-include pyproject.toml
 
 graft doc
 prune doc/build
 
+graft LICENSES
+
 graft pandas
 
-global-exclude *.so
-global-exclude *.pyd
+global-exclude *.bz2
+global-exclude *.csv
+global-exclude *.dta
+global-exclude *.gz
+global-exclude *.h5
+global-exclude *.html
+global-exclude *.json
+global-exclude *.msgpack
+global-exclude *.pickle
+global-exclude *.png
 global-exclude *.pyc
+global-exclude *.pyd
+global-exclude *.sas7bdat
+global-exclude *.so
+global-exclude *.xls
+global-exclude *.xlsm
+global-exclude *.xlsx
+global-exclude *.xpt
+global-exclude *.xz
+global-exclude *.zip
 global-exclude *~
-global-exclude \#*
-global-exclude .git*
 global-exclude .DS_Store
-global-exclude *.png
+global-exclude .git*
+global-exclude \#*
 
-# include examples/data/*
-# recursive-include examples *.py
-# recursive-include doc/source *
-# recursive-include doc/sphinxext *
-# recursive-include LICENSES *
 include versioneer.py
 include pandas/_version.py
 include pandas/io/formats/templates/*.tpl

asv_bench/benchmarks/categoricals.py

@@ -193,3 +193,55 @@ def time_categorical_series_is_monotonic_increasing(self):
 
     def time_categorical_series_is_monotonic_decreasing(self):
         self.s.is_monotonic_decreasing
+
+
+class Contains(object):
+
+    goal_time = 0.2
+
+    def setup(self):
+        N = 10**5
+        self.ci = tm.makeCategoricalIndex(N)
+        self.c = self.ci.values
+        self.key = self.ci.categories[0]
+
+    def time_categorical_index_contains(self):
+        self.key in self.ci
+
+    def time_categorical_contains(self):
+        self.key in self.c
+
+
+class CategoricalSlicing(object):
+
+    goal_time = 0.2
+    params = ['monotonic_incr', 'monotonic_decr', 'non_monotonic']
+    param_names = ['index']
+
+    def setup(self, index):
+        N = 10**6
+        values = list('a' * N + 'b' * N + 'c' * N)
+        indices = {
+            'monotonic_incr': pd.Categorical(values),
+            'monotonic_decr': pd.Categorical(reversed(values)),
+            'non_monotonic': pd.Categorical(list('abc' * N))}
+        self.data = indices[index]
+
+        self.scalar = 10000
+        self.list = list(range(10000))
+        self.cat_scalar = 'b'
+
+    def time_getitem_scalar(self, index):
+        self.data[self.scalar]
+
+    def time_getitem_slice(self, index):
+        self.data[:self.scalar]
+
+    def time_getitem_list_like(self, index):
+        self.data[[self.scalar]]
+
+    def time_getitem_list(self, index):
+        self.data[self.list]
+
+    def time_getitem_bool_array(self, index):
+        self.data[self.data == self.cat_scalar]

asv_bench/benchmarks/frame_methods.py

@@ -501,7 +501,7 @@ def time_info(self):
 class NSort(object):
 
     goal_time = 0.2
-    params = ['first', 'last']
+    params = ['first', 'last', 'all']
     param_names = ['keep']
 
     def setup(self, keep):

asv_bench/benchmarks/groupby.py

@@ -5,7 +5,7 @@
 
 import numpy as np
 from pandas import (DataFrame, Series, MultiIndex, date_range, period_range,
-                    TimeGrouper, Categorical)
+                    TimeGrouper, Categorical, Timestamp)
 import pandas.util.testing as tm
 
 from .pandas_vb_common import setup  # noqa
@@ -385,6 +385,25 @@ def time_dtype_as_field(self, dtype, method, application):
         self.as_field_method()
 
 
+class RankWithTies(object):
+    # GH 21237
+    goal_time = 0.2
+    param_names = ['dtype', 'tie_method']
+    params = [['float64', 'float32', 'int64', 'datetime64'],
+              ['first', 'average', 'dense', 'min', 'max']]
+
+    def setup(self, dtype, tie_method):
+        N = 10**4
+        if dtype == 'datetime64':
+            data = np.array([Timestamp("2011/01/01")] * N, dtype=dtype)
+        else:
+            data = np.array([1] * N, dtype=dtype)
+        self.df = DataFrame({'values': data, 'key': ['foo'] * N})
+
+    def time_rank_ties(self, dtype, tie_method):
+        self.df.groupby('key').rank(method=tie_method)
+
+
 class Float32(object):
     # GH 13335
     goal_time = 0.2

asv_bench/benchmarks/indexing.py

@@ -3,7 +3,8 @@
 import numpy as np
 import pandas.util.testing as tm
 from pandas import (Series, DataFrame, MultiIndex, Int64Index, Float64Index,
-                    IntervalIndex, IndexSlice, concat, date_range)
+                    IntervalIndex, CategoricalIndex,
+                    IndexSlice, concat, date_range)
 from .pandas_vb_common import setup, Panel  # noqa
 
 
@@ -230,6 +231,49 @@ def time_loc_list(self, monotonic):
         monotonic.loc[80000:]
 
 
+class CategoricalIndexIndexing(object):
+
+    goal_time = 0.2
+    params = ['monotonic_incr', 'monotonic_decr', 'non_monotonic']
+    param_names = ['index']
+
+    def setup(self, index):
+        N = 10**5
+        values = list('a' * N + 'b' * N + 'c' * N)
+        indices = {
+            'monotonic_incr': CategoricalIndex(values),
+            'monotonic_decr': CategoricalIndex(reversed(values)),
+            'non_monotonic': CategoricalIndex(list('abc' * N))}
+        self.data = indices[index]
+
+        self.int_scalar = 10000
+        self.int_list = list(range(10000))
+
+        self.cat_scalar = 'b'
+        self.cat_list = ['a', 'c']
+
+    def time_getitem_scalar(self, index):
+        self.data[self.int_scalar]
+
+    def time_getitem_slice(self, index):
+        self.data[:self.int_scalar]
+
+    def time_getitem_list_like(self, index):
+        self.data[[self.int_scalar]]
+
+    def time_getitem_list(self, index):
+        self.data[self.int_list]
+
+    def time_getitem_bool_array(self, index):
+        self.data[self.data == self.cat_scalar]
+
+    def time_get_loc_scalar(self, index):
+        self.data.get_loc(self.cat_scalar)
+
+    def time_get_indexer_list(self, index):
+        self.data.get_indexer(self.cat_list)
+
+
 class PanelIndexing(object):
 
     goal_time = 0.2

asv_bench/benchmarks/period.py

@@ -64,6 +64,11 @@ def setup(self):
     def time_setitem_period_column(self):
         self.df['col'] = self.rng
 
+    def time_set_index(self):
+        # GH#21582 limited by comparisons of Period objects
+        self.df['col2'] = self.rng
+        self.df.set_index('col2', append=True)
+
 
 class Algorithms(object):
 

asv_bench/benchmarks/series_methods.py

@@ -41,7 +41,7 @@ def time_isin(self, dtypes):
 class NSort(object):
 
     goal_time = 0.2
-    params = ['last', 'first']
+    params = ['first', 'last', 'all']
     param_names = ['keep']
 
     def setup(self, keep):

ci/appveyor-27.yaml

@@ -6,6 +6,7 @@ dependencies:
   - beautifulsoup4
   - bottleneck
   - dateutil
+  - gcsfs
   - html5lib
   - jinja2=2.8
   - lxml
@@ -23,7 +24,7 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - cython
+  - cython>=0.28.2
   - pytest
   - pytest-xdist
   - moto

ci/appveyor-36.yaml

@@ -22,6 +22,6 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - cython
+  - cython>=0.28.2
   - pytest
   - pytest-xdist