Merge branch 'master' into openpyxl-reader

Author: tdamsma

.gitignore

@@ -61,9 +61,11 @@ dist
 .coverage
 coverage.xml
 coverage_html_report
+.mypy_cache
 *.pytest_cache
 # hypothesis test database
 .hypothesis/
+__pycache__
 
 # OS generated files #
 ######################

.travis.yml

@@ -41,7 +41,7 @@ matrix:
 
  - dist: trusty
  env:
- - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36.yaml" PATTERN="((not slow and not network) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
+ - JOB="3.6, coverage" ENV_FILE="ci/deps/travis-36-cov.yaml" PATTERN="((not slow and not network) or (single and db))" PANDAS_TESTING_MODE="deprecate" COVERAGE=true
 
  # In allow_failures
  - dist: trusty
@@ -82,15 +82,10 @@ before_install:
 install:
  - echo "install start"
  - ci/prep_cython_cache.sh
- - ci/install_travis.sh
+ - ci/setup_env.sh
  - ci/submit_cython_cache.sh
  - echo "install done"
 
-before_script:
- - ci/install_db_travis.sh
- - export DISPLAY=":99.0"
- - ci/before_script_travis.sh
-
 script:
  - echo "script start"
  - source activate pandas-dev

LICENSES/SIX

@@ -164,7 +164,7 @@ pip install pandas
 ```
 
 ## Dependencies
-- [NumPy](https://www.numpy.org): 1.12.0 or higher
+- [NumPy](https://www.numpy.org): 1.13.3 or higher
 - [python-dateutil](https://labix.org/python-dateutil): 2.5.0 or higher
 - [pytz](https://pythonhosted.org/pytz): 2015.4 or higher
 

README.md

@@ -13,7 +13,7 @@
  pass
 
 
-class Factorize(object):
+class Factorize:
 
  params = [[True, False], ['int', 'uint', 'float', 'string']]
  param_names = ['sort', 'dtype']
@@ -30,7 +30,7 @@ def time_factorize(self, sort, dtype):
  self.idx.factorize(sort=sort)
 
 
-class FactorizeUnique(object):
+class FactorizeUnique:
 
  params = [[True, False], ['int', 'uint', 'float', 'string']]
  param_names = ['sort', 'dtype']
@@ -48,7 +48,7 @@ def time_factorize(self, sort, dtype):
  self.idx.factorize(sort=sort)
 
 
-class Duplicated(object):
+class Duplicated:
 
  params = [['first', 'last', False], ['int', 'uint', 'float', 'string']]
  param_names = ['keep', 'dtype']
@@ -67,7 +67,7 @@ def time_duplicated(self, keep, dtype):
  self.idx.duplicated(keep=keep)
 
 
-class DuplicatedUniqueIndex(object):
+class DuplicatedUniqueIndex:
 
  params = ['int', 'uint', 'float', 'string']
  param_names = ['dtype']
@@ -86,7 +86,7 @@ def time_duplicated_unique(self, dtype):
  self.idx.duplicated()
 
 
-class Hashing(object):
+class Hashing:
 
  def setup_cache(self):
  N = 10**5
@@ -124,7 +124,7 @@ def time_series_dates(self, df):
  hashing.hash_pandas_object(df['dates'])
 
 
-class Quantile(object):
+class Quantile:
  params = [[0, 0.5, 1],
  ['linear', 'nearest', 'lower', 'higher', 'midpoint'],
  ['float', 'int', 'uint']]

asv_bench/benchmarks/algorithms.py

@@ -6,7 +6,7 @@
  from pandas.util.decorators import cache_readonly
 
 
-class DataFrameAttributes(object):
+class DataFrameAttributes:
 
  def setup(self):
  self.df = DataFrame(np.random.randn(10, 6))
@@ -19,7 +19,7 @@ def time_set_index(self):
  self.df.index = self.cur_index
 
 
-class CacheReadonly(object):
+class CacheReadonly:
 
  def setup(self):
 

asv_bench/benchmarks/attrs_caching.py

@@ -7,7 +7,7 @@
  import pandas.computation.expressions as expr
 
 
-class Ops(object):
+class Ops:
 
  params = [[True, False], ['default', 1]]
  param_names = ['use_numexpr', 'threads']
@@ -38,7 +38,7 @@ def teardown(self, use_numexpr, threads):
  expr.set_numexpr_threads()
 
 
-class Ops2(object):
+class Ops2:
 
  def setup(self):
  N = 10**3
@@ -88,7 +88,7 @@ def time_frame_series_dot(self):
  self.df.dot(self.s)
 
 
-class Timeseries(object):
+class Timeseries:
 
  params = [None, 'US/Eastern']
  param_names = ['tz']
@@ -114,7 +114,7 @@ def time_timestamp_ops_diff_with_shift(self, tz):
  self.s - self.s.shift()
 
 
-class AddOverflowScalar(object):
+class AddOverflowScalar:
 
  params = [1, -1, 0]
  param_names = ['scalar']
@@ -127,7 +127,7 @@ def time_add_overflow_scalar(self, scalar):
  checked_add_with_arr(self.arr, scalar)
 
 
-class AddOverflowArray(object):
+class AddOverflowArray:
 
  def setup(self):
  N = 10**6

asv_bench/benchmarks/binary_ops.py

@@ -12,7 +12,7 @@
  pass
 
 
-class Concat(object):
+class Concat:
 
  def setup(self):
  N = 10**5
@@ -28,7 +28,7 @@ def time_union(self):
  union_categoricals([self.a, self.b])
 
 
-class Constructor(object):
+class Constructor:
 
  def setup(self):
  N = 10**5
@@ -77,7 +77,7 @@ def time_existing_series(self):
  pd.Categorical(self.series)
 
 
-class ValueCounts(object):
+class ValueCounts:
 
  params = [True, False]
  param_names = ['dropna']
@@ -92,7 +92,7 @@ def time_value_counts(self, dropna):
  self.ts.value_counts(dropna=dropna)
 
 
-class Repr(object):
+class Repr:
 
  def setup(self):
  self.sel = pd.Series(['s1234']).astype('category')
@@ -101,7 +101,7 @@ def time_rendering(self):
  str(self.sel)
 
 
-class SetCategories(object):
+class SetCategories:
 
  def setup(self):
  n = 5 * 10**5
@@ -113,7 +113,7 @@ def time_set_categories(self):
  self.ts.cat.set_categories(self.ts.cat.categories[::2])
 
 
-class RemoveCategories(object):
+class RemoveCategories:
 
  def setup(self):
  n = 5 * 10**5
@@ -125,7 +125,7 @@ def time_remove_categories(self):
  self.ts.cat.remove_categories(self.ts.cat.categories[::2])
 
 
-class Rank(object):
+class Rank:
 
  def setup(self):
  N = 10**5
@@ -162,7 +162,7 @@ def time_rank_int_cat_ordered(self):
  self.s_int_cat_ordered.rank()
 
 
-class Isin(object):
+class Isin:
 
  params = ['object', 'int64']
  param_names = ['dtype']
@@ -181,7 +181,7 @@ def time_isin_categorical(self, dtype):
  self.series.isin(self.sample)
 
 
-class IsMonotonic(object):
+class IsMonotonic:
 
  def setup(self):
  N = 1000
@@ -201,7 +201,7 @@ def time_categorical_series_is_monotonic_decreasing(self):
  self.s.is_monotonic_decreasing
 
 
-class Contains(object):
+class Contains:
 
  def setup(self):
  N = 10**5
@@ -216,7 +216,7 @@ def time_categorical_contains(self):
  self.key in self.c
 
 
-class CategoricalSlicing(object):
+class CategoricalSlicing:
 
  params = ['monotonic_incr', 'monotonic_decr', 'non_monotonic']
  param_names = ['index']
@@ -257,7 +257,7 @@ def time_getitem_bool_array(self, index):
  self.data[self.data == self.cat_scalar]
 
 
-class Indexing(object):
+class Indexing:
 
  def setup(self):
  N = 10**5

asv_bench/benchmarks/categoricals.py

@@ -39,7 +39,7 @@ def list_of_lists_with_none(arr):
  return [[i, -i] for i in arr][:-1] + [None]
 
 
-class SeriesConstructors(object):
+class SeriesConstructors:
 
  param_names = ["data_fmt", "with_index", "dtype"]
  params = [[no_change,
@@ -68,7 +68,7 @@ def time_series_constructor(self, data_fmt, with_index, dtype):
  Series(self.data, index=self.index)
 
 
-class SeriesDtypesConstructors(object):
+class SeriesDtypesConstructors:
 
  def setup(self):
  N = 10**4
@@ -90,7 +90,7 @@ def time_dtindex_from_index_with_series(self):
  Index(self.s)
 
 
-class MultiIndexConstructor(object):
+class MultiIndexConstructor:
 
  def setup(self):
  N = 10**4

asv_bench/benchmarks/ctors.py

@@ -12,7 +12,7 @@
 _dtypes = _numpy_dtypes + extension_dtypes
 
 
-class Dtypes(object):
+class Dtypes:
  params = (_dtypes +
  list(map(lambda dt: dt.name, _dtypes)))
  param_names = ['dtype']
@@ -21,7 +21,7 @@ def time_pandas_dtype(self, dtype):
  pandas_dtype(dtype)
 
 
-class DtypesInvalid(object):
+class DtypesInvalid:
  param_names = ['dtype']
  params = ['scalar-string', 'scalar-int', 'list-string', 'array-string']
  data_dict = {'scalar-string': 'foo',