merge master

Author: vaibhavhrt

.gitignore

@@ -66,6 +66,9 @@ coverage_html_report
 # hypothesis test database
 .hypothesis/
 __pycache__
+# pytest-monkeytype
+monkeytype.sqlite3
+
 
 # OS generated files #
 ######################

.travis.yml

@@ -1,4 +1,3 @@
-sudo: false
 language: python
 python: 3.5
 

Makefile

@@ -1,5 +1,7 @@
 .PHONY : develop build clean clean_pyc doc lint-diff black
 
+all: develop
+
 clean:
 	-python setup.py clean
 

asv_bench/benchmarks/index_cached_properties.py

@@ -0,0 +1,75 @@
+import pandas as pd
+
+
+class IndexCache:
+    number = 1
+    repeat = (3, 100, 20)
+
+    params = [
+        [
+            "DatetimeIndex",
+            "Float64Index",
+            "IntervalIndex",
+            "Int64Index",
+            "MultiIndex",
+            "PeriodIndex",
+            "RangeIndex",
+            "TimedeltaIndex",
+            "UInt64Index",
+        ]
+    ]
+    param_names = ["index_type"]
+
+    def setup(self, index_type):
+        N = 10 ** 5
+        if index_type == "MultiIndex":
+            self.idx = pd.MultiIndex.from_product(
+                [pd.date_range("1/1/2000", freq="T", periods=N // 2), ["a", "b"]]
+            )
+        elif index_type == "DatetimeIndex":
+            self.idx = pd.date_range("1/1/2000", freq="T", periods=N)
+        elif index_type == "Int64Index":
+            self.idx = pd.Index(range(N))
+        elif index_type == "PeriodIndex":
+            self.idx = pd.period_range("1/1/2000", freq="T", periods=N)
+        elif index_type == "RangeIndex":
+            self.idx = pd.RangeIndex(start=0, stop=N)
+        elif index_type == "IntervalIndex":
+            self.idx = pd.IntervalIndex.from_arrays(range(N), range(1, N + 1))
+        elif index_type == "TimedeltaIndex":
+            self.idx = pd.TimedeltaIndex(range(N))
+        elif index_type == "Float64Index":
+            self.idx = pd.Float64Index(range(N))
+        elif index_type == "UInt64Index":
+            self.idx = pd.UInt64Index(range(N))
+        else:
+            raise ValueError
+        assert len(self.idx) == N
+        self.idx._cache = {}
+
+    def time_values(self, index_type):
+        self.idx._values
+
+    def time_shape(self, index_type):
+        self.idx.shape
+
+    def time_is_monotonic(self, index_type):
+        self.idx.is_monotonic
+
+    def time_is_monotonic_decreasing(self, index_type):
+        self.idx.is_monotonic_decreasing
+
+    def time_is_monotonic_increasing(self, index_type):
+        self.idx.is_monotonic_increasing
+
+    def time_is_unique(self, index_type):
+        self.idx.is_unique
+
+    def time_engine(self, index_type):
+        self.idx._engine
+
+    def time_inferred_type(self, index_type):
+        self.idx.inferred_type
+
+    def time_is_all_dates(self, index_type):
+        self.idx.is_all_dates

asv_bench/benchmarks/io/parsers.py

@@ -10,7 +10,7 @@
     pass
 
 
-class DoesStringLookLikeDatetime(object):
+class DoesStringLookLikeDatetime:
 
     params = (["2Q2005", "0.0", "10000"],)
     param_names = ["value"]
@@ -23,7 +23,7 @@ def time_check_datetimes(self, value):
             _does_string_look_like_datetime(obj)
 
 
-class ConcatDateCols(object):
+class ConcatDateCols:
 
     params = ([1234567890, "AAAA"], [1, 2])
     param_names = ["value", "dim"]

asv_bench/benchmarks/reshape.py

@@ -240,4 +240,17 @@ def time_qcut_datetime(self, bins):
         pd.qcut(self.datetime_series, bins)
 
 
+class Explode:
+    param_names = ["n_rows", "max_list_length"]
+    params = [[100, 1000, 10000], [3, 5, 10]]
+
+    def setup(self, n_rows, max_list_length):
+
+        data = [np.arange(np.random.randint(max_list_length)) for _ in range(n_rows)]
+        self.series = pd.Series(data)
+
+    def time_explode(self, n_rows, max_list_length):
+        self.series.explode()
+
+
 from .pandas_vb_common import setup  # noqa: F401

asv_bench/benchmarks/series_methods.py

@@ -219,7 +219,7 @@ def time_series_datetimeindex_repr(self):
         getattr(self.s, "a", None)
 
 
-class All(object):
+class All:
 
     params = [[10 ** 3, 10 ** 6], ["fast", "slow"]]
     param_names = ["N", "case"]
@@ -232,7 +232,7 @@ def time_all(self, N, case):
         self.s.all()
 
 
-class Any(object):
+class Any:
 
     params = [[10 ** 3, 10 ** 6], ["fast", "slow"]]
     param_names = ["N", "case"]
@@ -245,7 +245,7 @@ def time_any(self, N, case):
         self.s.any()
 
 
-class NanOps(object):
+class NanOps:
 
     params = [
         [

asv_bench/benchmarks/timeseries.py

@@ -293,7 +293,7 @@ def time_format_YYYYMMDD(self):
         to_datetime(self.stringsD, format="%Y%m%d")
 
 
-class ToDatetimeCacheSmallCount(object):
+class ToDatetimeCacheSmallCount:
 
     params = ([True, False], [50, 500, 5000, 100000])
     param_names = ["cache", "count"]

ci/code_checks.sh

@@ -156,7 +156,7 @@ if [[ -z "$CHECK" || "$CHECK" == "patterns" ]]; then
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for python2 new-style classes and for empty parentheses' ; echo $MSG
-    invgrep -R --include="*.py" --include="*.pyx" -E "class\s\S*\((object)?\):" pandas scripts
+    invgrep -R --include="*.py" --include="*.pyx" -E "class\s\S*\((object)?\):" pandas asv_bench/benchmarks scripts
     RET=$(($RET + $?)) ; echo $MSG "DONE"
 
     MSG='Check for backticks incorrectly rendering because of missing spaces' ; echo $MSG

ci/deps/travis-36-cov.yaml

@@ -39,7 +39,7 @@ dependencies:
   - xlsxwriter
   - xlwt
   # universal
-  - pytest>=4.0.2
+  - pytest
   - pytest-xdist
   - pytest-cov
   - pytest-mock

doc/source/development/contributing.rst

@@ -288,7 +288,7 @@ complex changes to the documentation as well.
 Some other important things to know about the docs:
 
 * The *pandas* documentation consists of two parts: the docstrings in the code
-  itself and the docs in this folder ``pandas/doc/``.
+  itself and the docs in this folder ``doc/``.
 
   The docstrings provide a clear explanation of the usage of the individual
   functions, while the documentation in this folder consists of tutorial-like
@@ -404,11 +404,11 @@ Building the documentation
 ~~~~~~~~~~~~~~~~~~~~~~~~~~
 
 So how do you build the docs? Navigate to your local
-``pandas/doc/`` directory in the console and run::
+``doc/`` directory in the console and run::
 
     python make.py html
 
-Then you can find the HTML output in the folder ``pandas/doc/build/html/``.
+Then you can find the HTML output in the folder ``doc/build/html/``.
 
 The first time you build the docs, it will take quite a while because it has to run
 all the code examples and build all the generated docstring pages. In subsequent
@@ -448,7 +448,7 @@ You can also specify to use multiple cores to speed up the documentation build::
 Open the following file in a web browser to see the full documentation you
 just built::
 
-    pandas/docs/build/html/index.html
+    doc/build/html/index.html
 
 And you'll have the satisfaction of seeing your new and improved documentation!
 

doc/source/getting_started/basics.rst

@@ -1422,8 +1422,6 @@ The :meth:`~DataFrame.rename` method also provides an ``inplace`` named
 parameter that is by default ``False`` and copies the underlying data. Pass
 ``inplace=True`` to rename the data in place.
 
-.. versionadded:: 0.18.0
-
 Finally, :meth:`~Series.rename` also accepts a scalar or list-like
 for altering the ``Series.name`` attribute.
 
@@ -2063,8 +2061,6 @@ Convert a subset of columns to a specified type using :meth:`~DataFrame.astype`.
    dft
    dft.dtypes
 
-.. versionadded:: 0.19.0
-
 Convert certain columns to a specific dtype by passing a dict to :meth:`~DataFrame.astype`.
 
 .. ipython:: python

doc/source/getting_started/dsintro.rst

@@ -251,8 +251,6 @@ Series can also have a ``name`` attribute:
 The Series ``name`` will be assigned automatically in many cases, in particular
 when taking 1D slices of DataFrame as you will see below.
 
-.. versionadded:: 0.18.0
-
 You can rename a Series with the :meth:`pandas.Series.rename` method.
 
 .. ipython:: python

doc/source/reference/frame.rst

@@ -239,6 +239,7 @@ Reshaping, sorting, transposing
    DataFrame.unstack
    DataFrame.swapaxes
    DataFrame.melt
+   DataFrame.explode
    DataFrame.squeeze
    DataFrame.to_xarray
    DataFrame.T

doc/source/reference/series.rst

@@ -245,6 +245,7 @@ Reshaping, sorting
    Series.sort_index
    Series.swaplevel
    Series.unstack
+   Series.explode
    Series.searchsorted
    Series.ravel
    Series.repeat
@@ -590,4 +591,3 @@ Sparse
 
    SparseSeries.to_coo
    SparseSeries.from_coo
-

doc/source/user_guide/advanced.rst

@@ -810,15 +810,10 @@ values **not** in the categories, similarly to how you can reindex **any** panda
 Int64Index and RangeIndex
 ~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. warning::
-
-   Indexing on an integer-based Index with floats has been clarified in 0.18.0, for a summary of the changes, see :ref:`here <whatsnew_0180.float_indexers>`.
-
-:class:`Int64Index` is a fundamental basic index in pandas.
-This is an immutable array implementing an ordered, sliceable set.
-Prior to 0.18.0, the ``Int64Index`` would provide the default index for all ``NDFrame`` objects.
+:class:`Int64Index` is a fundamental basic index in pandas. This is an immutable array
+implementing an ordered, sliceable set.
 
-:class:`RangeIndex` is a sub-class of ``Int64Index`` added in version 0.18.0, now providing the default index for all ``NDFrame`` objects.
+:class:`RangeIndex` is a sub-class of ``Int64Index``  that provides the default index for all ``NDFrame`` objects.
 ``RangeIndex`` is an optimized version of ``Int64Index`` that can represent a monotonic ordered set. These are analogous to Python `range types <https://docs.python.org/3/library/stdtypes.html#typesseq-range>`__.
 
 .. _indexing.float64index:
@@ -880,16 +875,6 @@ In non-float indexes, slicing using floats will raise a ``TypeError``.
    In [1]: pd.Series(range(5))[3.5:4.5]
    TypeError: the slice start [3.5] is not a proper indexer for this index type (Int64Index)
 
-.. warning::
-
-   Using a scalar float indexer for ``.iloc`` has been removed in 0.18.0, so the following will raise a ``TypeError``:
-
-   .. code-block:: ipython
-
-      In [3]: pd.Series(range(5)).iloc[3.0]
-      TypeError: cannot do positional indexing on <class 'pandas.indexes.range.RangeIndex'> with these indexers [3.0] of <type 'float'>
-
-
 Here is a typical use-case for using this type of indexing. Imagine that you have a somewhat
 irregular timedelta-like indexing scheme, but the data is recorded as floats. This could, for
 example, be millisecond offsets.

doc/source/user_guide/categorical.rst

@@ -834,8 +834,6 @@ See also the section on :ref:`merge dtypes<merging.dtypes>` for notes about pres
 Unioning
 ~~~~~~~~
 
-.. versionadded:: 0.19.0
-
 If you want to combine categoricals that do not necessarily have the same
 categories, the :func:`~pandas.api.types.union_categoricals` function will
 combine a list-like of categoricals. The new categories will be the union of

doc/source/user_guide/computation.rst

@@ -408,9 +408,7 @@ For some windowing functions, additional parameters must be specified:
 Time-aware rolling
 ~~~~~~~~~~~~~~~~~~
 
-.. versionadded:: 0.19.0
-
-New in version 0.19.0 are the ability to pass an offset (or convertible) to a ``.rolling()`` method and have it produce
+It is possible to pass an offset (or convertible) to a ``.rolling()`` method and have it produce
 variable sized windows based on the passed time window. For each time point, this includes all preceding values occurring
 within the indicated time delta.
 
@@ -893,10 +891,9 @@ Therefore, there is an assumption that :math:`x_0` is not an ordinary value
 but rather an exponentially weighted moment of the infinite series up to that
 point.
 
-One must have :math:`0 < \alpha \leq 1`, and while since version 0.18.0
-it has been possible to pass :math:`\alpha` directly, it's often easier
-to think about either the **span**, **center of mass (com)** or **half-life**
-of an EW moment:
+One must have :math:`0 < \alpha \leq 1`, and while it is possible to pass
+:math:`\alpha` directly, it's often easier to think about either the
+**span**, **center  of mass (com)** or **half-life** of an EW moment:
 
 .. math::
 

doc/source/user_guide/enhancingperf.rst

@@ -601,8 +601,6 @@ This allows for *formulaic evaluation*.  The assignment target can be a
 new column name or an existing column name, and it must be a valid Python
 identifier.
 
-.. versionadded:: 0.18.0
-
 The ``inplace`` keyword determines whether this assignment will performed
 on the original ``DataFrame`` or return a copy with the new column.
 
@@ -630,8 +628,6 @@ new or modified columns is returned and the original frame is unchanged.
    df.eval('e = a - c', inplace=False)
    df
 
-.. versionadded:: 0.18.0
-
 As a convenience, multiple assignments can be performed by using a
 multi-line string.
 
@@ -652,9 +648,7 @@ The equivalent in standard Python would be
    df['a'] = 1
    df
 
-.. versionadded:: 0.18.0
-
-The ``query`` method gained the ``inplace`` keyword which determines
+The ``query`` method has a ``inplace`` keyword which determines
 whether the query modifies the original frame.
 
 .. ipython:: python

doc/source/user_guide/groupby.rst

@@ -827,13 +827,10 @@ and that the transformed data contains no NAs.
 
 .. _groupby.transform.window_resample:
 
-New syntax to window and resample operations
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-.. versionadded:: 0.18.1
+Window and resample operations
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-Working with the resample, expanding or rolling operations on the groupby
-level used to require the application of helper functions. However,
-now it is possible to use ``resample()``, ``expanding()`` and
+It is possible to use ``resample()``, ``expanding()`` and
 ``rolling()`` as methods on groupbys.
 
 The example below will apply the ``rolling()`` method on the samples of