Merge pull request #156 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

doc/source/whatsnew/v1.3.0.rst

@@ -423,7 +423,7 @@ Deprecations
 - Using ``.astype`` to convert between ``datetime64[ns]`` dtype and :class:`DatetimeTZDtype` is deprecated and will raise in a future version, use ``obj.tz_localize`` or ``obj.dt.tz_localize`` instead (:issue:`38622`)
 - Deprecated casting ``datetime.date`` objects to ``datetime64`` when used as ``fill_value`` in :meth:`DataFrame.unstack`, :meth:`DataFrame.shift`, :meth:`Series.shift`, and :meth:`DataFrame.reindex`, pass ``pd.Timestamp(dateobj)`` instead (:issue:`39767`)
 - Deprecated :meth:`.Styler.set_na_rep` and :meth:`.Styler.set_precision` in favour of :meth:`.Styler.format` with ``na_rep`` and ``precision`` as existing and new input arguments respectively (:issue:`40134`, :issue:`40425`)
-- Deprecated allowing partial failure in :meth:`Series.transform` and :meth:`DataFrame.transform` when ``func`` is list-like or dict-like; will raise if any function fails on a column in a future version (:issue:`40211`)
+- Deprecated allowing partial failure in :meth:`Series.transform` and :meth:`DataFrame.transform` when ``func`` is list-like or dict-like and raises anything but ``TypeError``; ``func`` raising anything but a ``TypeError`` will raise in a future version (:issue:`40211`)
 - Deprecated support for ``np.ma.mrecords.MaskedRecords`` in the :class:`DataFrame` constructor, pass ``{name: data[name] for name in data.dtype.names}`` instead (:issue:`40363`)
 - Deprecated the use of ``**kwargs`` in :class:`.ExcelWriter`; use the keyword argument ``engine_kwargs`` instead (:issue:`40430`)
 

pandas/_libs/algos.pyx

@@ -490,7 +490,7 @@ def nancorr_kendall(ndarray[float64_t, ndim=2] mat, Py_ssize_t minp=1) -> ndarra
         int64_t total_discordant = 0
         float64_t kendall_tau
         int64_t n_obs
-        const int64_t[:] labels_n
+        const intp_t[:] labels_n
 
     N, K = (<object>mat).shape
 
@@ -499,7 +499,7 @@ def nancorr_kendall(ndarray[float64_t, ndim=2] mat, Py_ssize_t minp=1) -> ndarra
 
     ranked_mat = np.empty((N, K), dtype=np.float64)
     # For compatibility when calling rank_1d
-    labels_n = np.zeros(N, dtype=np.int64)
+    labels_n = np.zeros(N, dtype=np.intp)
 
     for i in range(K):
         ranked_mat[:, i] = rank_1d(mat[:, i], labels_n)
@@ -591,16 +591,17 @@ def validate_limit(nobs: int, limit=None) -> int:
 
 @cython.boundscheck(False)
 @cython.wraparound(False)
-def pad(ndarray[algos_t] old, ndarray[algos_t] new, limit=None):
+def pad(ndarray[algos_t] old, ndarray[algos_t] new, limit=None) -> ndarray:
+    # -> ndarray[intp_t, ndim=1]
     cdef:
         Py_ssize_t i, j, nleft, nright
-        ndarray[int64_t, ndim=1] indexer
+        ndarray[intp_t, ndim=1] indexer
         algos_t cur, next_val
         int lim, fill_count = 0
 
     nleft = len(old)
     nright = len(new)
-    indexer = np.empty(nright, dtype=np.int64)
+    indexer = np.empty(nright, dtype=np.intp)
     indexer[:] = -1
 
     lim = validate_limit(nright, limit)
@@ -737,15 +738,16 @@ D
 @cython.boundscheck(False)
 @cython.wraparound(False)
 def backfill(ndarray[algos_t] old, ndarray[algos_t] new, limit=None) -> ndarray:
+    # -> ndarray[intp_t, ndim=1]
     cdef:
         Py_ssize_t i, j, nleft, nright
-        ndarray[int64_t, ndim=1] indexer
+        ndarray[intp_t, ndim=1] indexer
         algos_t cur, prev
         int lim, fill_count = 0
 
     nleft = len(old)
     nright = len(new)
-    indexer = np.empty(nright, dtype=np.int64)
+    indexer = np.empty(nright, dtype=np.intp)
     indexer[:] = -1
 
     lim = validate_limit(nright, limit)
@@ -959,7 +961,7 @@ ctypedef fused rank_t:
 @cython.boundscheck(False)
 def rank_1d(
     ndarray[rank_t, ndim=1] values,
-    const int64_t[:] labels,
+    const intp_t[:] labels,
     ties_method="average",
     bint ascending=True,
     bint pct=False,
@@ -971,7 +973,8 @@ def rank_1d(
     Parameters
     ----------
     values : array of rank_t values to be ranked
-    labels : array containing unique label for each group, with its ordering
+    labels : np.ndarray[np.intp]
+        Array containing unique label for each group, with its ordering
         matching up to the corresponding record in `values`. If not called
         from a groupby operation, will be an array of 0's
     ties_method : {'average', 'min', 'max', 'first', 'dense'}, default

pandas/_libs/algos_take_helper.pxi.in

@@ -219,8 +219,8 @@ def take_2d_multi_{{name}}_{{dest}}(ndarray[{{c_type_in}}, ndim=2] values,
                                     fill_value=np.nan):
     cdef:
         Py_ssize_t i, j, k, n, idx
-        ndarray[int64_t] idx0 = indexer[0]
-        ndarray[int64_t] idx1 = indexer[1]
+        ndarray[intp_t] idx0 = indexer[0]
+        ndarray[intp_t] idx1 = indexer[1]
         {{c_type_out}} fv
 
     n = len(idx0)