Merge branch 'master' of https://github.com/pandas-dev/pandas into tslibs-conversion11

Author: jbrockmendel

ci/lint.sh

@@ -9,7 +9,7 @@ RET=0
 if [ "$LINT" ]; then
 
     # pandas/_libs/src is C code, so no need to search there.
-    echo "Linting  *.py"
+    echo "Linting *.py"
     flake8 pandas --filename=*.py --exclude pandas/_libs/src
     if [ $? -ne "0" ]; then
         RET=1
@@ -38,10 +38,20 @@ if [ "$LINT" ]; then
         if [ $? -ne "0" ]; then
             RET=1
         fi
-
     done
     echo "Linting *.pxi.in DONE"
 
+    echo "Linting *.pxd"
+    for path in '_libs'
+    do
+        echo "linting -> pandas/$path"
+        flake8 pandas/$path --filename=*.pxd --select=E501,E302,E203,E111,E114,E221,E303,E231,E126,F403
+        if [ $? -ne "0" ]; then
+            RET=1
+        fi
+    done
+    echo "Linting *.pxd DONE"
+
     # readability/casting: Warnings about C casting instead of C++ casting
     # runtime/int: Warnings about using C number types instead of C++ ones
     # build/include_subdir: Warnings about prefacing included header files with directory

doc/source/api.rst

@@ -1822,7 +1822,7 @@ Interval
 Properties
 ~~~~~~~~~~
 .. autosummary::
-    :toctree generated/
+    :toctree: generated/
 
     Interval.closed
     Interval.closed_left
@@ -1843,7 +1843,7 @@ Timedelta
 Properties
 ~~~~~~~~~~
 .. autosummary::
-    :toctree generated/
+    :toctree: generated/
 
     Timedelta.asm8
     Timedelta.components
@@ -1860,7 +1860,7 @@ Properties
 Methods
 ~~~~~~~
 .. autosummary::
-    :toctree generated/
+    :toctree: generated/
 
     Timedelta.ceil
     Timedelta.floor

doc/source/computation.rst

@@ -670,6 +670,7 @@ columns of a ``DataFrame``:
 
 .. ipython:: python
    :okexcept:
+   :okwarning:
 
    r.agg({'A' : np.sum,
           'B' : lambda x: np.std(x, ddof=1)})

doc/source/conf.py

@@ -358,13 +358,12 @@
 # latex_use_modindex = True
 
 
-# Example configuration for intersphinx: refer to the Python standard library.
 intersphinx_mapping = {
     'statsmodels': ('http://www.statsmodels.org/devel/', None),
     'matplotlib': ('http://matplotlib.org/', None),
-    'python': ('http://docs.python.org/3', None),
-    'numpy': ('http://docs.scipy.org/doc/numpy', None),
-    'scipy': ('http://docs.scipy.org/doc/scipy/reference', None),
+    'python': ('https://docs.python.org/3/', None),
+    'numpy': ('https://docs.scipy.org/doc/numpy/', None),
+    'scipy': ('https://docs.scipy.org/doc/scipy/reference/', None),
     'py': ('https://pylib.readthedocs.io/en/latest/', None)
 }
 import glob
@@ -573,6 +572,15 @@ def remove_flags_docstring(app, what, name, obj, options, lines):
     if what == "attribute" and name.endswith(".flags"):
         del lines[:]
 
+
+suppress_warnings = [
+    # We "overwrite" autosummary with our PandasAutosummary, but
+    # still want the regular autosummary setup to run. So we just
+    # suppress this warning.
+    'app.add_directive'
+]
+
+
 def setup(app):
     app.connect("autodoc-process-docstring", remove_flags_docstring)
     app.add_autodocumenter(AccessorDocumenter)

doc/source/contributing.rst

@@ -60,7 +60,7 @@ Bug reports must:
 
 The issue will then show up to the *pandas* community and be open to comments/ideas from others.
 
-.. _contributing.github
+.. _contributing.github:
 
 Working with the code
 =====================

doc/source/io.rst

@@ -115,7 +115,7 @@ header : int or list of ints, default ``'infer'``
 names : array-like, default ``None``
   List of column names to use. If file contains no header row, then you should
   explicitly pass ``header=None``. Duplicates in this list will cause
-    a ``UserWarning`` to be issued.
+  a ``UserWarning`` to be issued.
 index_col :  int or sequence or ``False``, default ``None``
   Column to use as the row labels of the DataFrame. If a sequence is given, a
   MultiIndex is used. If you have a malformed file with delimiters at the end of

doc/source/whatsnew/v0.15.2.txt

@@ -163,7 +163,7 @@ Other enhancements:
      p.all()
 
 - Added support for ``utcfromtimestamp()``, ``fromtimestamp()``, and ``combine()`` on `Timestamp` class (:issue:`5351`).
-- Added Google Analytics (`pandas.io.ga`) basic documentation (:issue:`8835`). See `here<http://pandas.pydata.org/pandas-docs/version/0.15.2/remote_data.html#remote-data-ga>`__.
+- Added Google Analytics (`pandas.io.ga`) basic documentation (:issue:`8835`). See `here <http://pandas.pydata.org/pandas-docs/version/0.15.2/remote_data.html#remote-data-ga>`__.
 - ``Timedelta`` arithmetic returns ``NotImplemented`` in unknown cases, allowing extensions by custom classes (:issue:`8813`).
 - ``Timedelta`` now supports arithemtic with ``numpy.ndarray`` objects of the appropriate dtype (numpy 1.8 or newer only) (:issue:`8884`).
 - Added ``Timedelta.to_timedelta64()`` method to the public API (:issue:`8884`).

doc/source/whatsnew/v0.19.0.txt

@@ -216,6 +216,7 @@ contained the values ``[0, 3]``.
 **New behavior**:
 
 .. ipython:: python
+   :okwarning:
 
    pd.read_csv(StringIO(data), names=names)
 

doc/source/whatsnew/v0.20.0.txt

@@ -1375,6 +1375,7 @@ Convert to a MultiIndex DataFrame
 Convert to an xarray DataArray
 
 .. ipython:: python
+   :okwarning:
 
    p.to_xarray()
 

pandas/_libs/period.pyx

@@ -967,7 +967,7 @@ cdef class _Period(object):
     def strftime(self, fmt):
         """
         Returns the string representation of the :class:`Period`, depending
-        on the selected :keyword:`format`. :keyword:`format` must be a string
+        on the selected ``fmt``. ``fmt`` must be a string
         containing one or several directives.  The method recognizes the same
         directives as the :func:`time.strftime` function of the standard Python
         distribution, as well as the specific additional directives ``%f``,

pandas/_libs/src/datetime.pxd

@@ -44,8 +44,9 @@ cdef extern from "datetime/np_datetime.h":
         npy_int64 year
         npy_int32 month, day, hour, min, sec, us, ps, as
 
-    npy_datetime pandas_datetimestruct_to_datetime(PANDAS_DATETIMEUNIT fr,
-                                                   pandas_datetimestruct *d) nogil
+    npy_datetime pandas_datetimestruct_to_datetime(
+        PANDAS_DATETIMEUNIT fr, pandas_datetimestruct *d) nogil
+
     void pandas_datetime_to_datetimestruct(npy_datetime val,
                                            PANDAS_DATETIMEUNIT fr,
                                            pandas_datetimestruct *result) nogil
@@ -58,12 +59,12 @@ cdef extern from "datetime/np_datetime.h":
 cdef extern from "datetime/np_datetime_strings.h":
 
     int parse_iso_8601_datetime(char *str, int len, PANDAS_DATETIMEUNIT unit,
-                                NPY_CASTING casting, pandas_datetimestruct *out,
+                                NPY_CASTING casting,
+                                pandas_datetimestruct *out,
                                 int *out_local, int *out_tzoffset,
                                 PANDAS_DATETIMEUNIT *out_bestunit,
                                 npy_bool *out_special)
 
-
 cdef inline int _string_to_dts(object val, pandas_datetimestruct* dts,
                            int* out_local, int* out_tzoffset) except? -1:
     cdef int result
@@ -89,5 +90,6 @@ cdef inline int _cstring_to_dts(char *val, int length,
 
     result = parse_iso_8601_datetime(val, length, PANDAS_FR_ns,
                                      NPY_UNSAFE_CASTING,
-                                     dts, out_local, out_tzoffset, &out_bestunit, &special)
+                                     dts, out_local, out_tzoffset,
+                                     &out_bestunit, &special)
     return result

pandas/_libs/src/numpy.pxd

@@ -152,7 +152,8 @@ cdef extern from "numpy/arrayobject.h":
 
     npy_intp NPY_MAX_ELSIZE
 
-    ctypedef void (*PyArray_VectorUnaryFunc)(void *, void *, npy_intp, void *,  void *)
+    ctypedef void (*PyArray_VectorUnaryFunc)(
+        void *, void *, npy_intp, void *,  void *)
 
     ctypedef class numpy.dtype [object PyArray_Descr]:
         # Use PyDataType_* macros when possible, however there are no macros
@@ -225,7 +226,9 @@ cdef extern from "numpy/arrayobject.h":
             if copy_shape:
                 # Allocate new buffer for strides and shape info.
                 # This is allocated as one block, strides first.
-                info.strides = <Py_ssize_t*>stdlib.malloc(sizeof(Py_ssize_t) * <size_t>ndim * 2)
+                info.strides = <Py_ssize_t*>stdlib.malloc(
+                    sizeof(Py_ssize_t) * <size_t>ndim * 2)
+                
                 info.shape = info.strides + ndim
                 for i in range(ndim):
                     info.strides[i] = PyArray_STRIDES(self)[i]
@@ -275,7 +278,8 @@ cdef extern from "numpy/arrayobject.h":
                 elif t == NPY_CLONGDOUBLE: f = "Zg"
                 elif t == NPY_OBJECT:      f = "O"
                 else:
-                    raise ValueError(u"unknown dtype code in numpy.pxd (%d)" % t)
+                    raise ValueError(
+                        u"unknown dtype code in numpy.pxd (%d)" % t)
                 info.format = f
                 return
             else:
@@ -294,7 +298,6 @@ cdef extern from "numpy/arrayobject.h":
                 stdlib.free(info.strides)
                 # info.shape was stored after info.strides in the same block
 
-
     ctypedef signed char      npy_bool
 
     ctypedef signed char      npy_byte
@@ -462,7 +465,6 @@ cdef extern from "numpy/arrayobject.h":
     bint PyArray_ISBEHAVED(ndarray)
     bint PyArray_ISBEHAVED_RO(ndarray)
 
-
     bint PyDataType_ISNOTSWAPPED(dtype)
     bint PyDataType_ISBYTESWAPPED(dtype)
 
@@ -475,7 +477,6 @@ cdef extern from "numpy/arrayobject.h":
     # bint PyArray_HasArrayInterfaceType(object, dtype, object, object&)
     # bint PyArray_HasArrayInterface(op, out)
 
-
     bint PyArray_IsZeroDim(object)
     # Cannot be supported due to ## ## in macro:
     # bint PyArray_IsScalar(object, verbatim work)
@@ -502,24 +503,28 @@ cdef extern from "numpy/arrayobject.h":
     unsigned char PyArray_EquivArrTypes(ndarray a1, ndarray a2)
     bint PyArray_EquivByteorders(int b1, int b2)
     object PyArray_SimpleNew(int nd, npy_intp* dims, int typenum)
-    object PyArray_SimpleNewFromData(int nd, npy_intp* dims, int typenum, void* data)
+    object PyArray_SimpleNewFromData(int nd, npy_intp* dims,
+                                     int typenum, void* data)
     #object PyArray_SimpleNewFromDescr(int nd, npy_intp* dims, dtype descr)
     object PyArray_ToScalar(void* data, ndarray arr)
 
     void* PyArray_GETPTR1(ndarray m, npy_intp i)
     void* PyArray_GETPTR2(ndarray m, npy_intp i, npy_intp j)
     void* PyArray_GETPTR3(ndarray m, npy_intp i, npy_intp j, npy_intp k)
-    void* PyArray_GETPTR4(ndarray m, npy_intp i, npy_intp j, npy_intp k, npy_intp l)
+    void* PyArray_GETPTR4(ndarray m, npy_intp i,
+                          npy_intp j, npy_intp k, npy_intp l)
 
     void PyArray_XDECREF_ERR(ndarray)
     # Cannot be supported due to out arg
     # void PyArray_DESCR_REPLACE(descr)
 
-
     object PyArray_Copy(ndarray)
-    object PyArray_FromObject(object op, int type, int min_depth, int max_depth)
-    object PyArray_ContiguousFromObject(object op, int type, int min_depth, int max_depth)
-    object PyArray_CopyFromObject(object op, int type, int min_depth, int max_depth)
+    object PyArray_FromObject(object op, int type,
+                              int min_depth, int max_depth)
+    object PyArray_ContiguousFromObject(object op, int type,
+                                        int min_depth, int max_depth)
+    object PyArray_CopyFromObject(object op, int type,
+                                  int min_depth, int max_depth)
 
     object PyArray_Cast(ndarray mp, int type_num)
     object PyArray_Take(ndarray ap, object items, int axis)
@@ -598,8 +603,8 @@ cdef extern from "numpy/arrayobject.h":
     object PyArray_Dumps (object, int)
     int PyArray_ValidType (int)
     void PyArray_UpdateFlags (ndarray, int)
-    object PyArray_New (type, int, npy_intp *, int, npy_intp *, void *, int, int, object)
-    #object PyArray_NewFromDescr (type, dtype, int, npy_intp *, npy_intp *, void *, int, object)
+    object PyArray_New (type, int, npy_intp *, int, npy_intp *,
+                        void *, int, int, object)
     #dtype PyArray_DescrNew (dtype)
     dtype PyArray_DescrNewFromType (int)
     double PyArray_GetPriority (object, double)
@@ -611,7 +616,8 @@ cdef extern from "numpy/arrayobject.h":
     int PyArray_Broadcast (broadcast)
     void PyArray_FillObjectArray (ndarray, object)
     int PyArray_FillWithScalar (ndarray, object)
-    npy_bool PyArray_CheckStrides (int, int, npy_intp, npy_intp, npy_intp *, npy_intp *)
+    npy_bool PyArray_CheckStrides (
+        int, int, npy_intp, npy_intp, npy_intp *, npy_intp *)
     dtype PyArray_DescrNewByteorder (dtype, char)
     object PyArray_IterAllButAxis (object, int *)
     #object PyArray_CheckFromAny (object, dtype, int, int, int, object)
@@ -782,9 +788,11 @@ cdef inline object PyArray_MultiIterNew4(a, b, c, d):
     return PyArray_MultiIterNew(4, <void*>a, <void*>b, <void*>c, <void*> d)
 
 cdef inline object PyArray_MultiIterNew5(a, b, c, d, e):
-    return PyArray_MultiIterNew(5, <void*>a, <void*>b, <void*>c, <void*> d, <void*> e)
+    return PyArray_MultiIterNew(5, <void*>a, <void*>b,
+                                <void*>c, <void*> d, <void*> e)
 
-cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset) except NULL:
+cdef inline char* _util_dtypestring(dtype descr, char* f,
+                                    char* end, int* offset) except NULL:
     # Recursive utility function used in __getbuffer__ to get format
     # string. The new location in the format string is returned.
 
@@ -800,7 +808,8 @@ cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset
         child, new_offset = fields
 
         if (end - f) - (new_offset - offset[0]) < 15:
-            raise RuntimeError(u"Format string allocated too short, see comment in numpy.pxd")
+            raise RuntimeError(
+                u"Format string allocated too short, see comment in numpy.pxd")
 
         if ((child.byteorder == '>' and little_endian) or
             (child.byteorder == '<' and not little_endian)):
@@ -860,7 +869,8 @@ cdef inline char* _util_dtypestring(dtype descr, char* f, char* end, int* offset
 
 cdef extern from "numpy/ufuncobject.h":
 
-    ctypedef void (*PyUFuncGenericFunction) (char **, npy_intp *, npy_intp *, void *)
+    ctypedef void (*PyUFuncGenericFunction) (char **, npy_intp *,
+                                             npy_intp *, void *)
 
     ctypedef extern class numpy.ufunc [object PyUFuncObject]:
         cdef:
@@ -968,14 +978,14 @@ cdef extern from "numpy/ufuncobject.h":
 
 
 cdef inline void set_array_base(ndarray arr, object base):
-     cdef PyObject* baseptr
-     if base is None:
-         baseptr = NULL
-     else:
-         Py_INCREF(base) # important to do this before decref below!
-         baseptr = <PyObject*>base
-     Py_XDECREF(arr.base)
-     arr.base = baseptr
+    cdef PyObject* baseptr
+    if base is None:
+        baseptr = NULL
+    else:
+        Py_INCREF(base) # important to do this before decref below!
+        baseptr = <PyObject*>base
+    Py_XDECREF(arr.base)
+    arr.base = baseptr
 
 cdef inline object get_array_base(ndarray arr):
     if arr.base is NULL:

pandas/_libs/src/util.pxd

@@ -115,7 +115,8 @@ cdef inline bint _checknull_old(object val):
     cdef double INF = <double> np.inf
     cdef double NEGINF = -INF
     try:
-        return val is None or (cpython.PyFloat_Check(val) and (val != val or val == INF or val == NEGINF))
+        return val is None or (cpython.PyFloat_Check(val) and
+                               (val != val or val == INF or val == NEGINF))
     except ValueError:
         return False