Merge branch 'master' of https://github.com/pandas-dev/pandas into di…

…v_zero2

ci/requirements-3.6_WIN.run

@@ -12,5 +12,6 @@ numexpr
 pytables
 matplotlib
 blosc
+thrift=0.10*
 fastparquet
 pyarrow

doc/source/developer.rst

@@ -153,7 +153,7 @@ Libraries can use the decorators
 pandas objects. All of these follow a similar convention: you decorate a class, providing the name of attribute to add. The
 class's `__init__` method gets the object being decorated. For example:
 
-.. ipython:: python
+.. code-block:: python
 
    @pd.api.extensions.register_dataframe_accessor("geo")
    class GeoAccessor(object):

doc/source/whatsnew/v0.23.0.txt

@@ -482,6 +482,7 @@ Timezones
 - :func:`Timestamp.replace` will now handle Daylight Savings transitions gracefully (:issue:`18319`)
 - Bug in tz-aware :class:`DatetimeIndex` where addition/subtraction with a :class:`TimedeltaIndex` or array with ``dtype='timedelta64[ns]'`` was incorrect (:issue:`17558`)
 - Bug in :func:`DatetimeIndex.insert` where inserting ``NaT`` into a timezone-aware index incorrectly raised (:issue:`16357`)
+- Bug in the :class:`DataFrame` constructor, where tz-aware Datetimeindex and a given column name will result in an empty ``DataFrame`` (:issue:`19157`)
 
 Offsets
 ^^^^^^^
@@ -540,6 +541,8 @@ I/O
 - Bug in :func:`DataFrame.to_latex()` where pairs of braces meant to serve as invisible placeholders were escaped (:issue:`18667`)
 - Bug in :func:`read_json` where large numeric values were causing an ``OverflowError`` (:issue:`18842`)
 - Bug in :func:`DataFrame.to_parquet` where an exception was raised if the write destination is S3 (:issue:`19134`)
+- :class:`Interval` now supported in :func:`DataFrame.to_excel` for all Excel file types (:issue:`19242`)
+- :class:`Timedelta` now supported in :func:`DataFrame.to_excel` for xls file type (:issue:`19242`, :issue:`9155`)
 -
 
 Plotting
@@ -563,7 +566,7 @@ Groupby/Resample/Rolling
 Sparse
 ^^^^^^
 
--
+- Bug in which creating a ``SparseDataFrame`` from a dense ``Series`` or an unsupported type raised an uncontrolled exception (:issue:`19374`)
 -
 -
 

pandas/_libs/algos.pyx

@@ -1,39 +1,34 @@
 # cython: profile=False
 
-cimport numpy as np
-import numpy as np
-
 cimport cython
 from cython cimport Py_ssize_t
 
-np.import_array()
-
-cdef float64_t FP_ERR = 1e-13
-
-cimport util
-
 from libc.stdlib cimport malloc, free
 from libc.string cimport memmove
+from libc.math cimport fabs, sqrt
 
+import numpy as np
+cimport numpy as cnp
 from numpy cimport (ndarray,
                     NPY_INT64, NPY_UINT64, NPY_INT32, NPY_INT16, NPY_INT8,
                     NPY_FLOAT32, NPY_FLOAT64,
                     NPY_OBJECT,
                     int8_t, int16_t, int32_t, int64_t, uint8_t, uint16_t,
                     uint32_t, uint64_t, float32_t, float64_t,
                     double_t)
+cnp.import_array()
 
 
-cdef double NaN = <double> np.NaN
-cdef double nan = NaN
-
-from libc.math cimport fabs, sqrt
-
-# this is our util.pxd
+cimport util
 from util cimport numeric, get_nat
 
 import missing
 
+cdef float64_t FP_ERR = 1e-13
+
+cdef double NaN = <double> np.NaN
+cdef double nan = NaN
+
 cdef int64_t iNaT = get_nat()
 
 cdef:

pandas/_libs/algos_rank_helper.pxi.in

@@ -50,7 +50,7 @@ def rank_1d_{{dtype}}(object in_arr, ties_method='average', ascending=True,
 
         ndarray[float64_t] ranks
         ndarray[int64_t] argsorted
-        ndarray[np.uint8_t, cast=True] sorted_mask
+        ndarray[uint8_t, cast=True] sorted_mask
 
         {{if dtype == 'uint64'}}
         {{ctype}} val

pandas/_libs/hashtable.pyx

@@ -1,6 +1,22 @@
 # cython: profile=False
 
-from cpython cimport PyObject, Py_INCREF, PyList_Check, PyTuple_Check
+cimport cython
+
+from cpython cimport (PyObject, Py_INCREF, PyList_Check, PyTuple_Check,
+                      PyMem_Malloc, PyMem_Realloc, PyMem_Free,
+                      PyString_Check, PyBytes_Check,
+                      PyUnicode_Check)
+
+from libc.stdlib cimport malloc, free
+
+import numpy as np
+cimport numpy as cnp
+from numpy cimport ndarray, uint8_t, uint32_t
+cnp.import_array()
+
+cdef extern from "numpy/npy_math.h":
+    double NAN "NPY_NAN"
+
 
 from khash cimport (
     khiter_t,
@@ -23,29 +39,13 @@ from khash cimport (
     kh_put_pymap, kh_resize_pymap)
 
 
-from numpy cimport ndarray, uint8_t, uint32_t
-
-from libc.stdlib cimport malloc, free
-from cpython cimport (PyMem_Malloc, PyMem_Realloc, PyMem_Free,
-                      PyString_Check, PyBytes_Check,
-                      PyUnicode_Check)
-
 from util cimport _checknan
 cimport util
 
-import numpy as np
-nan = np.nan
-
-cdef extern from "numpy/npy_math.h":
-    double NAN "NPY_NAN"
-
-cimport cython
-cimport numpy as cnp
-
 from missing cimport checknull
 
-cnp.import_array()
-cnp.import_ufunc()
+
+nan = np.nan
 
 cdef int64_t iNaT = util.get_nat()
 _SIZE_HINT_LIMIT = (1 << 20) + 7

pandas/_libs/index.pyx

@@ -1,17 +1,23 @@
 # cython: profile=False
+from datetime import datetime, timedelta, date
 
-from numpy cimport (ndarray, float64_t, int32_t, int64_t, uint8_t, uint64_t,
-                    NPY_DATETIME, NPY_TIMEDELTA)
 cimport cython
 
-cimport numpy as cnp
+from cpython cimport PyTuple_Check, PyList_Check
+from cpython.slice cimport PySlice_Check
 
+import numpy as np
+cimport numpy as cnp
+from numpy cimport ndarray, float64_t, int32_t, int64_t, uint8_t, uint64_t
 cnp.import_array()
-cnp.import_ufunc()
 
-cimport util
+cdef extern from "numpy/arrayobject.h":
+    # These can be cimported directly from numpy in cython>=0.27.3
+    cdef enum NPY_TYPES:
+        NPY_DATETIME
+        NPY_TIMEDELTA
 
-import numpy as np
+cimport util
 
 from tslibs.conversion cimport maybe_datetimelike_to_i8
 
@@ -20,10 +26,6 @@ from hashtable cimport HashTable
 from pandas._libs import algos, hashtable as _hash
 from pandas._libs.tslibs import period as periodlib
 from pandas._libs.tslib import Timestamp, Timedelta
-from datetime import datetime, timedelta, date
-
-from cpython cimport PyTuple_Check, PyList_Check
-from cpython.slice cimport PySlice_Check
 
 cdef int64_t iNaT = util.get_nat()
 

pandas/_libs/internals.pyx

@@ -10,7 +10,6 @@ cdef extern from "Python.h":
     Py_ssize_t PY_SSIZE_T_MAX
 
 import numpy as np
-cimport numpy as np
 from numpy cimport int64_t
 
 cdef extern from "compat_helper.h":

pandas/_libs/interval.pyx

@@ -1,4 +1,4 @@
-cimport numpy as np
+cimport numpy as cnp
 import numpy as np
 
 cimport util

pandas/_libs/join.pyx

@@ -1,16 +1,15 @@
 # cython: profile=False
 
-cimport numpy as np
-import numpy as np
-
 cimport cython
 from cython cimport Py_ssize_t
 
-np.import_array()
-
+import numpy as np
+cimport numpy as cnp
 from numpy cimport (ndarray,
                     int8_t, int16_t, int32_t, int64_t, uint8_t, uint16_t,
                     uint32_t, uint64_t, float32_t, float64_t)
+cnp.import_array()
+
 
 cdef double NaN = <double> np.NaN
 cdef double nan = NaN

pandas/_libs/lib.pyx

@@ -5,17 +5,15 @@ cimport cython
 from cython cimport Py_ssize_t
 
 import numpy as np
-cimport numpy as np
+cimport numpy as cnp
 from numpy cimport (ndarray, PyArray_NDIM, PyArray_GETITEM,
                     PyArray_ITER_DATA, PyArray_ITER_NEXT, PyArray_IterNew,
                     flatiter, NPY_OBJECT,
                     int64_t,
                     float32_t, float64_t,
                     uint8_t, uint64_t,
                     complex128_t)
-# initialize numpy
-np.import_array()
-np.import_ufunc()
+cnp.import_array()
 
 from cpython cimport (Py_INCREF, PyTuple_SET_ITEM,
                       PyList_Check, PyFloat_Check,
@@ -95,7 +93,7 @@ cpdef bint is_scalar(object val):
 
     """
 
-    return (np.PyArray_IsAnyScalar(val)
+    return (cnp.PyArray_IsAnyScalar(val)
             # As of numpy-1.9, PyArray_IsAnyScalar misses bytearrays on Py3.
             or PyBytes_Check(val)
             # We differ from numpy (as of 1.10), which claims that None is
@@ -710,7 +708,7 @@ def clean_index_list(list obj):
 
     for i in range(n):
         v = obj[i]
-        if not (PyList_Check(v) or np.PyArray_Check(v) or hasattr(v, '_data')):
+        if not (PyList_Check(v) or util.is_array(v) or hasattr(v, '_data')):
             all_arrays = 0
             break
 

pandas/_libs/missing.pyx

@@ -7,9 +7,9 @@ cimport cython
 from cython cimport Py_ssize_t
 
 import numpy as np
-cimport numpy as np
+cimport numpy as cnp
 from numpy cimport ndarray, int64_t, uint8_t
-np.import_array()
+cnp.import_array()
 
 cimport util
 

pandas/_libs/reduction.pyx

@@ -8,13 +8,13 @@ from cpython cimport Py_INCREF
 from libc.stdlib cimport malloc, free
 
 import numpy as np
-cimport numpy as np
+cimport numpy as cnp
 from numpy cimport (ndarray,
                     int64_t,
                     PyArray_SETITEM,
                     PyArray_ITER_NEXT, PyArray_ITER_DATA, PyArray_IterNew,
                     flatiter)
-np.import_array()
+cnp.import_array()
 
 cimport util
 from lib import maybe_convert_objects

pandas/_libs/reshape.pyx

@@ -1,16 +1,15 @@
 # cython: profile=False
 
-cimport numpy as np
-import numpy as np
-
 cimport cython
 from cython cimport Py_ssize_t
 
-np.import_array()
-
+import numpy as np
+cimport numpy as cnp
 from numpy cimport (ndarray,
                     int8_t, int16_t, int32_t, int64_t, uint8_t, uint16_t,
                     uint32_t, uint64_t, float32_t, float64_t)
+cnp.import_array()
+
 
 cdef double NaN = <double> np.NaN
 cdef double nan = NaN

pandas/_libs/skiplist.pyx

@@ -8,20 +8,20 @@
 
 from libc.math cimport log
 
+import numpy as np
+cimport numpy as cnp
+from numpy cimport double_t
+cnp.import_array()
+
+
 # MSVC does not have log2!
 
 cdef double Log2(double x):
     return log(x) / log(2.)
 
-cimport numpy as np
-import numpy as np
-from numpy cimport double_t
 
 from random import random
 
-# initialize numpy
-np.import_array()
-
 # TODO: optimize this, make less messy
 
 cdef class Node:

pandas/_libs/sparse.pyx

@@ -1,12 +1,15 @@
-from numpy cimport (ndarray, uint8_t, int64_t, int32_t, int16_t, int8_t,
-                    float64_t, float32_t)
-cimport numpy as np
+# -*- coding: utf-8 -*-
+import operator
+import sys
 
 cimport cython
 
 import numpy as np
-import operator
-import sys
+cimport numpy as cnp
+from numpy cimport (ndarray, uint8_t, int64_t, int32_t, int16_t, int8_t,
+                    float64_t, float32_t)
+cnp.import_array()
+
 
 from distutils.version import LooseVersion
 
@@ -15,8 +18,6 @@ _np_version = np.version.short_version
 _np_version_under1p10 = LooseVersion(_np_version) < LooseVersion('1.10')
 _np_version_under1p11 = LooseVersion(_np_version) < LooseVersion('1.11')
 
-np.import_array()
-np.import_ufunc()
 
 # -----------------------------------------------------------------------------
 # Preamble stuff