Merge remote-tracking branch 'pandas-dev/master'

Author: jaehoonhwang

Makefile

@@ -1,4 +1,4 @@
-tseries: pandas/lib.pyx pandas/tslib.pyx pandas/hashtable.pyx
+tseries: pandas/_libs/lib.pyx pandas/_libs/tslib.pyx pandas/_libs/hashtable.pyx
 	python setup.py build_ext --inplace
 
 .PHONY : develop build clean clean_pyc tseries doc
@@ -9,9 +9,6 @@ clean:
 clean_pyc:
 	-find . -name '*.py[co]' -exec rm {} \;
 
-sparse: pandas/src/sparse.pyx
-	python setup.py build_ext --inplace
-
 build: clean_pyc
 	python setup.py build_ext --inplace
 

README.md

@@ -54,7 +54,15 @@
   <td>Conda</td>
   <td>
     <a href="http://pandas.pydata.org">
-    <img src="http://pubbadges.s3-website-us-east-1.amazonaws.com/pkgs-downloads-pandas.png" alt="conda downloads" />
+    <img src="http://pubbadges.s3-website-us-east-1.amazonaws.com/pkgs-downloads-pandas.png" alt="conda default downloads" />
+    </a>
+  </td>
+</tr>
+<tr>
+  <td>Conda-forge</td>
+  <td>
+    <a href="http://pandas.pydata.org">
+    <img src="https://anaconda.org/conda-forge/pandas/badges/downloads.svg" alt="conda-forge downloads" />
     </a>
   </td>
 </tr>

asv_bench/benchmarks/binary_ops.py

@@ -107,4 +107,4 @@ def setup(self):
         self.s = Series(date_range('20010101', periods=self.N, freq='T', tz='US/Eastern'))
         self.ts = self.s[self.halfway]
 
-        self.s2 = Series(date_range('20010101', periods=self.N, freq='s',  tz='US/Eastern'))
+        self.s2 = Series(date_range('20010101', periods=self.N, freq='s',  tz='US/Eastern'))

asv_bench/benchmarks/pandas_vb_common.py

@@ -8,16 +8,22 @@
 import random
 import numpy as np
 import threading
+from importlib import import_module
+
 try:
     from pandas.compat import range
 except ImportError:
     pass
 
 np.random.seed(1234)
-try:
-    import pandas._tseries as lib
-except:
-    import pandas.lib as lib
+
+# try em until it works!
+for imp in ['pandas_tseries', 'pandas.lib', 'pandas._libs.lib']:
+    try:
+        lib = import_module(imp)
+        break
+    except:
+        pass
 
 try:
     Panel = Panel

asv_bench/benchmarks/panel_methods.py

@@ -21,4 +21,4 @@ def time_shift(self):
         self.panel.shift(1)
 
     def time_shift_minor(self):
-        self.panel.shift(1, axis='minor')
+        self.panel.shift(1, axis='minor')

doc/make.py

@@ -197,7 +197,7 @@ def html():
                 print(e)
                 print("Failed to convert %s" % nb)
 
-    if os.system('sphinx-build -P -b html -d build/doctrees '
+    if os.system('sphinx-build -j 2 -P -b html -d build/doctrees '
                  'source build/html'):
         raise SystemExit("Building HTML failed.")
     try:
@@ -222,7 +222,7 @@ def latex():
     check_build()
     if sys.platform != 'win32':
         # LaTeX format.
-        if os.system('sphinx-build -b latex -d build/doctrees '
+        if os.system('sphinx-build -j 2 -b latex -d build/doctrees '
                      'source build/latex'):
             raise SystemExit("Building LaTeX failed.")
         # Produce pdf.
@@ -245,7 +245,7 @@ def latex_forced():
     check_build()
     if sys.platform != 'win32':
         # LaTeX format.
-        if os.system('sphinx-build -b latex -d build/doctrees '
+        if os.system('sphinx-build -j 2 -b latex -d build/doctrees '
                      'source build/latex'):
             raise SystemExit("Building LaTeX failed.")
         # Produce pdf.

doc/source/api.rst

@@ -1237,58 +1237,7 @@ Serialization / IO / Conversion
    Panel.to_frame
    Panel.to_xarray
    Panel.to_clipboard
-
-.. _api.panel4d:
-
-Panel4D
--------
-
-Constructor
-~~~~~~~~~~~
-.. autosummary::
-   :toctree: generated/
-
-   Panel4D
-
-Serialization / IO / Conversion
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-.. autosummary::
-   :toctree: generated/
-
-   Panel4D.to_xarray
-
-Attributes and underlying data
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-**Axes**
-
-  * **labels**: axis 1; each label corresponds to a Panel contained inside
-  * **items**: axis 2; each item corresponds to a DataFrame contained inside
-  * **major_axis**: axis 3; the index (rows) of each of the DataFrames
-  * **minor_axis**: axis 4; the columns of each of the DataFrames
-
-.. autosummary::
-   :toctree: generated/
-
-   Panel4D.values
-   Panel4D.axes
-   Panel4D.ndim
-   Panel4D.size
-   Panel4D.shape
-   Panel4D.dtypes
-   Panel4D.ftypes
-   Panel4D.get_dtype_counts
-   Panel4D.get_ftype_counts
-
-Conversion
-~~~~~~~~~~
-.. autosummary::
-   :toctree: generated/
-
-   Panel4D.astype
-   Panel4D.copy
-   Panel4D.isnull
-   Panel4D.notnull
-
+   
 .. _api.index:
 
 Index

doc/source/install.rst

@@ -23,18 +23,6 @@ Officially Python 2.7, 3.4, 3.5, and 3.6
 Installing pandas
 -----------------
 
-Trying out pandas, no installation required!
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-
-The easiest way to start experimenting with pandas doesn't involve installing
-pandas at all.
-
-`Wakari <https://wakari.io>`__ is a free service that provides a hosted
-`IPython Notebook <http://ipython.org/notebook.html>`__ service in the cloud.
-
-Simply create an account, and have access to pandas from within your brower via
-an `IPython Notebook <http://ipython.org/notebook.html>`__ in a few minutes.
-
 .. _install.anaconda:
 
 Installing pandas with Anaconda

doc/source/io.rst

@@ -3758,7 +3758,7 @@ be data_columns
 
    # on-disk operations
    store.append('df_dc', df_dc, data_columns = ['B', 'C', 'string', 'string2'])
-   store.select('df_dc', [ pd.Term('B>0') ])
+   store.select('df_dc', where='B>0')
 
    # getting creative
    store.select('df_dc', 'B > 0 & C > 0 & string == foo')
@@ -4352,6 +4352,9 @@ HDFStore supports ``Panel4D`` storage.
 .. ipython:: python
    :okwarning:
 
+   wp = pd.Panel(randn(2, 5, 4), items=['Item1', 'Item2'],
+                 major_axis=pd.date_range('1/1/2000', periods=5),
+                 minor_axis=['A', 'B', 'C', 'D'])
    p4d = pd.Panel4D({ 'l1' : wp })
    p4d
    store.append('p4d', p4d)
@@ -4368,8 +4371,7 @@ object). This cannot be changed after table creation.
    :okwarning:
 
    store.append('p4d2', p4d, axes=['labels', 'major_axis', 'minor_axis'])
-   store
-   store.select('p4d2', [ pd.Term('labels=l1'), pd.Term('items=Item1'), pd.Term('minor_axis=A_big_strings') ])
+   store.select('p4d2', where='labels=l1 and items=Item1 and minor_axis=A')
 
 .. ipython:: python
    :suppress:

doc/source/whatsnew/v0.20.0.txt

@@ -484,6 +484,35 @@ New Behavior:
    In [11]: index.memory_usage(deep=True)
    Out[11]: 260
 
+.. _whatsnew_0200.api_breaking.extensions:
+
+Extension Modules Moved
+^^^^^^^^^^^^^^^^^^^^^^^
+
+Some formerly public c/c++/cython extension modules have been moved and/or renamed. These are all removed from the public API.
+If indicated, a deprecation warning will be issued if you reference that module. (:issue:`12588`)
+
+.. csv-table::
+    :header: "Previous Location", "New Location", "Deprecated"
+    :widths: 30, 30, 4
+
+    "pandas.lib", "pandas._libs.lib", "X"
+    "pandas.tslib", "pandas._libs.tslib", "X"
+    "pandas._join", "pandas._libs.join", ""
+    "pandas._period", "pandas._libs.period", ""
+    "pandas.msgpack", "pandas.io.msgpack", ""
+    "pandas.index", "pandas._libs.index", ""
+    "pandas.algos", "pandas._libs.algos", ""
+    "pandas.hashtable", "pandas._libs.hashtable", ""
+    "pandas.json", "pandas.io.json.libjson", "X"
+    "pandas.parser", "pandas.io.libparsers", "X"
+    "pandas.io.sas.saslib", "pandas.io.sas.libsas", ""
+    "pandas._testing", "pandas.util.libtesting", ""
+    "pandas._sparse", "pandas.sparse.libsparse", ""
+    "pandas._hash", "pandas.tools.libhash", ""
+    "pandas._window", "pandas.core.libwindow", ""
+
+
 .. _whatsnew_0200.api_breaking.groupby_describe:
 
 Groupby Describe Formatting
@@ -652,7 +681,7 @@ Bug Fixes
 - Bug in ``Index`` power operations with reversed operands (:issue:`14973`)
 - Bug in ``TimedeltaIndex`` addition where overflow was being allowed without error (:issue:`14816`)
 - Bug in ``TimedeltaIndex`` raising a ``ValueError`` when boolean indexing with ``loc`` (:issue:`14946`)
-- Bug in ``DatetimeIndex.round()`` and ``Timestamp.round()`` floating point accuracy when rounding by milliseconds (:issue: `14440`)
+- Bug in ``DatetimeIndex.round()`` and ``Timestamp.round()`` floating point accuracy when rounding by milliseconds or less (:issue: `14440`, :issue:`15578`)
 - Bug in ``astype()`` where ``inf`` values were incorrectly converted to integers. Now raises error now with ``astype()`` for Series and DataFrames (:issue:`14265`)
 - Bug in ``DataFrame(..).apply(to_numeric)`` when values are of type decimal.Decimal. (:issue:`14827`)
 - Bug in ``describe()`` when passing a numpy array which does not contain the median to the ``percentiles`` keyword argument (:issue:`14908`)
@@ -672,6 +701,10 @@ Bug Fixes
 - Bug in ``Rolling.quantile`` function that caused a segmentation fault when called with a quantile value outside of the range [0, 1] (:issue:`15463`)
 
 
+- Bug in ``SparseSeries.reindex`` on single level with list of length 1 (:issue:`15447`)
+
+
+
 - Bug in the display of ``.info()`` where a qualifier (+) would always be displayed with a ``MultiIndex`` that contains only non-strings (:issue:`15245`)
 
 - Bug in ``.asfreq()``, where frequency was not set for empty ``Series` (:issue:`14320`)
@@ -698,7 +731,7 @@ Bug Fixes
 
 - Bug in ``to_sql`` when writing a DataFrame with numeric index names (:issue:`15404`).
 - Bug in ``Series.iloc`` where a ``Categorical`` object for list-like indexes input was returned, where a ``Series`` was expected. (:issue:`14580`)
-
+- Bug in repr-formatting a ``SparseDataFrame`` after a value was set on (a copy of) one of its series (:issue:`15488`)
 
 
 - Bug in  groupby operations with timedelta64 when passing ``numeric_only=False`` (:issue:`5724`)

pandas/__init__.py

@@ -23,7 +23,9 @@
 from pandas.compat.numpy import *
 
 try:
-    from pandas import hashtable, tslib, lib
+    from pandas._libs import (hashtable as _hashtable,
+                             lib as _lib,
+                             tslib as _tslib)
 except ImportError as e:  # pragma: no cover
     # hack but overkill to use re
     module = str(e).lstrip('cannot import name ')
@@ -52,11 +54,17 @@
 from pandas.tools.util import to_numeric
 from pandas.core.reshape import melt
 from pandas.util.print_versions import show_versions
-
 from pandas.io.api import *
-
 from pandas.util._tester import test
 
+# extension module deprecations
+from pandas.util.depr_module import _DeprecatedModule
+
+json = _DeprecatedModule(deprmod='pandas.json', deprmodto='pandas.io.json.libjson')
+parser = _DeprecatedModule(deprmod='pandas.parser', deprmodto='pandas.io.libparsers')
+lib = _DeprecatedModule(deprmod='pandas.lib', deprmodto='pandas._libs.lib')
+tslib = _DeprecatedModule(deprmod='pandas.tslib', deprmodto='pandas._libs.tslib')
+
 # use the closest tagged version if possible
 from ._version import get_versions
 v = get_versions()

pandas/_libs/__init__.py

@@ -0,0 +1,8 @@
+# flake8: noqa
+
+from .tslib import iNaT, NaT, Timestamp, Timedelta, OutOfBoundsDatetime
+
+# TODO
+# period is directly dependent on tslib and imports python
+# modules, so exposing Period as an alias is currently not possible
+# from period import Period

pandas/algos.pyx renamed to pandas/_libs/algos.pyx

@@ -37,7 +37,7 @@ float64 = np.dtype(np.float64)
 cdef double NaN = <double> np.NaN
 cdef double nan = NaN
 
-cdef extern from "src/headers/math.h":
+cdef extern from "../src/headers/math.h":
     double sqrt(double x) nogil
     double fabs(double) nogil
 
@@ -46,7 +46,7 @@ from util cimport numeric, get_nat
 
 cimport lib
 from lib cimport is_null_datetimelike
-from pandas import lib
+from pandas._libs import lib
 
 cdef int64_t iNaT = get_nat()
 

pandas/src/algos_common_helper.pxi.in renamed to pandas/_libs/algos_common_helper.pxi.in

@@ -433,7 +433,7 @@ def arrmap_{{name}}(ndarray[{{c_type}}] index, object func):
 
     cdef ndarray[object] result = np.empty(length, dtype=np.object_)
 
-    from pandas.lib import maybe_convert_objects
+    from pandas._libs.lib import maybe_convert_objects
 
     for i in range(length):
         result[i] = func(index[i])

pandas/src/algos_groupby_helper.pxi.in renamed to pandas/_libs/algos_groupby_helper.pxi.in

@@ -22,7 +22,7 @@ cdef extern from "numpy/npy_math.h":
 cimport cython
 cimport numpy as cnp
 
-from pandas.lib import checknull
+from pandas._libs.lib import checknull
 
 cnp.import_array()
 cnp.import_ufunc()

pandas/src/algos_rank_helper.pxi.in renamed to pandas/_libs/algos_rank_helper.pxi.in

@@ -17,8 +17,8 @@ import numpy as np
 
 cimport tslib
 from hashtable cimport *
-from pandas import algos, tslib, hashtable as _hash
-from pandas.tslib import Timestamp, Timedelta
+from pandas._libs import tslib, algos, hashtable as _hash
+from pandas._libs.tslib import Timestamp, Timedelta
 
 from datetime cimport (get_datetime64_value, _pydatetime_to_dts,
                        pandas_datetimestruct)

pandas/src/algos_take_helper.pxi.in renamed to pandas/_libs/algos_take_helper.pxi.in

@@ -32,10 +32,10 @@ float64 = np.dtype(np.float64)
 cdef double NaN = <double> np.NaN
 cdef double nan = NaN
 
-from pandas.algos import groupsort_indexer, ensure_platform_int
+from pandas._libs.algos import groupsort_indexer, ensure_platform_int
 from pandas.core.algorithms import take_nd
 
-include "joins_func_helper.pxi"
+include "join_func_helper.pxi"
 
 
 def inner_join(ndarray[int64_t] left, ndarray[int64_t] right,