Merge remote-tracking branch 'upstream/main' into 7023_error_bars

Author: thetestspecimen

Dockerfile

@@ -11,4 +11,5 @@ RUN apt-get install -y libhdf5-dev libgles2-mesa-dev
 RUN python -m pip install --upgrade pip
 COPY requirements-dev.txt /tmp
 RUN python -m pip install -r /tmp/requirements-dev.txt
+RUN git config --global --add safe.directory /home/pandas
 CMD ["/bin/bash"]

asv_bench/benchmarks/timeseries.py

@@ -183,7 +183,7 @@ def setup(self):
         self.dt_ts = Series(5, rng3, dtype="datetime64[ns]")
 
     def time_resample(self):
-        self.dt_ts.resample("1S").last()
+        self.dt_ts.resample("1s").last()
 
 
 class AsOf:

doc/source/development/maintaining.rst

@@ -151,15 +151,15 @@ and then run::
     git bisect start
     git bisect good v1.4.0
     git bisect bad v1.5.0
-    git bisect run bash -c "python setup.py build_ext -j 4; python t.py"
+    git bisect run bash -c "python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true; python t.py"
 
 This finds the first commit that changed the behavior. The C extensions have to be
 rebuilt at every step, so the search can take a while.
 
 Exit bisect and rebuild the current version::
 
     git bisect reset
-    python setup.py build_ext -j 4
+    python -m pip install -ve . --no-build-isolation --config-settings editable-verbose=true
 
 Report your findings under the corresponding issue and ping the commit author to get
 their input.

doc/source/user_guide/timeseries.rst

@@ -1468,11 +1468,16 @@ or some other non-observed day.  Defined observance rules are:
     :header: "Rule", "Description"
     :widths: 15, 70
 
+    "next_workday", "move Saturday and Sunday to Monday"
+    "previous_workday", "move Saturday and Sunday to Friday"
     "nearest_workday", "move Saturday to Friday and Sunday to Monday"
+    "before_nearest_workday", "apply ``nearest_workday`` and then move to previous workday before that day"
+    "after_nearest_workday", "apply ``nearest_workday`` and then move to next workday after that day"
     "sunday_to_monday", "move Sunday to following Monday"
     "next_monday_or_tuesday", "move Saturday to Monday and Sunday/Monday to Tuesday"
     "previous_friday", move Saturday and Sunday to previous Friday"
     "next_monday", "move Saturday and Sunday to following Monday"
+    "weekend_to_monday", "same as ``next_monday``"
 
 An example of how holidays and holiday calendars are defined:
 

doc/source/whatsnew/v3.0.0.rst

@@ -208,6 +208,8 @@ Removal of prior version deprecations/changes
 - Enforced deprecation of string ``A`` denoting frequency in :class:`YearEnd` and strings ``A-DEC``, ``A-JAN``, etc. denoting annual frequencies with various fiscal year ends (:issue:`57699`)
 - Enforced deprecation of string ``BAS`` denoting frequency in :class:`BYearBegin` and strings ``BAS-DEC``, ``BAS-JAN``, etc. denoting annual frequencies with various fiscal year starts (:issue:`57793`)
 - Enforced deprecation of string ``BA`` denoting frequency in :class:`BYearEnd` and strings ``BA-DEC``, ``BA-JAN``, etc. denoting annual frequencies with various fiscal year ends (:issue:`57793`)
+- Enforced deprecation of strings ``T``, ``L``, ``U``, and ``N`` denoting frequencies in :class:`Minute`, :class:`Second`, :class:`Milli`, :class:`Micro`, :class:`Nano` (:issue:`57627`)
+- Enforced deprecation of strings ``T``, ``L``, ``U``, and ``N`` denoting units in :class:`Timedelta` (:issue:`57627`)
 - Enforced deprecation of the behavior of :func:`concat` when ``len(keys) != len(objs)`` would truncate to the shorter of the two. Now this raises a ``ValueError`` (:issue:`43485`)
 - Enforced silent-downcasting deprecation for :ref:`all relevant methods <whatsnew_220.silent_downcasting>` (:issue:`54710`)
 - In :meth:`DataFrame.stack`, the default value of ``future_stack`` is now ``True``; specifying ``False`` will raise a ``FutureWarning`` (:issue:`55448`)

pandas/__init__.py

@@ -28,7 +28,8 @@
     raise ImportError(
         f"C extension: {_module} not built. If you want to import "
         "pandas from the source directory, you may need to run "
-        "'python setup.py build_ext' to build the C extensions first."
+        "'python -m pip install -ve . --no-build-isolation --config-settings "
+        "editable-verbose=true' to build the C extensions first."
     ) from _err
 
 from pandas._config import (

pandas/_libs/hashtable.pxd

@@ -183,7 +183,7 @@ cdef class Int64Vector(Vector):
     cdef Int64VectorData data
     cdef ndarray ao
 
-    cdef resize(self)
+    cdef resize(self, Py_ssize_t new_size)
     cpdef ndarray to_array(self)
     cdef void append(self, int64_t x) noexcept
     cdef extend(self, int64_t[:] x)

pandas/_libs/hashtable.pyx

@@ -7,6 +7,7 @@ from libc.stdlib cimport (
     free,
     malloc,
 )
+from libc.string cimport memcpy
 
 import numpy as np
 

pandas/_libs/hashtable_class_helper.pxi.in

@@ -163,8 +163,9 @@ ctypedef fused vector_data:
     Complex64VectorData
     StringVectorData
 
-cdef bint needs_resize(vector_data *data) noexcept nogil:
-    return data.size == data.capacity
+
+cdef bint needs_resize(Py_ssize_t nelems, Py_ssize_t capacity) noexcept nogil:
+    return nelems >= capacity
 
 # ----------------------------------------------------------------------
 # Vector
@@ -214,8 +215,8 @@ cdef class {{name}}Vector(Vector):
         self.ao = np.empty(self.data.capacity, dtype=np.{{dtype}})
         self.data.data = <{{c_type}}*>self.ao.data
 
-    cdef resize(self):
-        self.data.capacity = max(self.data.capacity * 4, _INIT_VEC_CAP)
+    cdef resize(self, Py_ssize_t new_size):
+        self.data.capacity = max(new_size, _INIT_VEC_CAP)
         self.ao.resize(self.data.capacity, refcheck=False)
         self.data.data = <{{c_type}}*>self.ao.data
 
@@ -234,17 +235,28 @@ cdef class {{name}}Vector(Vector):
 
     cdef void append(self, {{c_type}} x) noexcept:
 
-        if needs_resize(&self.data):
+        if needs_resize(self.data.size, self.data.capacity):
             if self.external_view_exists:
                 raise ValueError("external reference but "
                                  "Vector.resize() needed")
-            self.resize()
+            self.resize(self.data.capacity * 4)
 
         append_data_{{dtype}}(&self.data, x)
 
     cdef extend(self, const {{c_type}}[:] x):
-        for i in range(len(x)):
-            self.append(x[i])
+        cdef Py_ssize_t x_size = len(x)
+        if x_size == 0:
+            return
+
+        cdef Py_ssize_t needed_size = self.data.size + x_size
+        if needs_resize(needed_size, self.data.capacity):
+            if self.external_view_exists:
+                raise ValueError("external reference but "
+                                 "Vector.resize() needed")
+            self.resize(needed_size)
+
+        memcpy(self.data.data + self.data.size, &x[0], x_size * sizeof({{c_type}}))
+        self.data.size = needed_size
 
 {{endfor}}
 
@@ -260,7 +272,7 @@ cdef class StringVector(Vector):
         if self.data.data is NULL:
             raise MemoryError()
 
-    cdef resize(self):
+    cdef resize(self, Py_ssize_t new_size):
         cdef:
             char **orig_data
             Py_ssize_t i, orig_capacity
@@ -297,8 +309,8 @@ cdef class StringVector(Vector):
 
     cdef void append(self, char *x) noexcept:
 
-        if needs_resize(&self.data):
-            self.resize()
+        if needs_resize(self.data.size, self.data.capacity):
+            self.resize(self.data.capacity * 4)
 
         append_data_string(&self.data, x)
 
@@ -684,18 +696,18 @@ cdef class {{name}}HashTable(HashTable):
                             continue
 
                         seen_na = True
-                        if needs_resize(ud):
+                        if needs_resize(ud.size, ud.capacity):
                             with gil:
                                 if uniques.external_view_exists:
                                     raise ValueError("external reference to "
                                                      "uniques held, but "
                                                      "Vector.resize() needed")
-                                uniques.resize()
+                                uniques.resize(uniques.data.capacity * 4)
                                 if result_mask.external_view_exists:
                                     raise ValueError("external reference to "
                                                      "result_mask held, but "
                                                      "Vector.resize() needed")
-                                result_mask.resize()
+                                result_mask.resize(result_mask.data.capacity * 4)
                         append_data_{{dtype}}(ud, val)
                         append_data_uint8(rmd, 1)
                         continue
@@ -706,19 +718,19 @@ cdef class {{name}}HashTable(HashTable):
                     # k hasn't been seen yet
                     k = kh_put_{{dtype}}(self.table, val, &ret)
 
-                    if needs_resize(ud):
+                    if needs_resize(ud.size, ud.capacity):
                         with gil:
                             if uniques.external_view_exists:
                                 raise ValueError("external reference to "
                                                  "uniques held, but "
                                                  "Vector.resize() needed")
-                            uniques.resize()
+                            uniques.resize(uniques.data.capacity * 4)
                             if use_result_mask:
                                 if result_mask.external_view_exists:
                                     raise ValueError("external reference to "
                                                      "result_mask held, but "
                                                      "Vector.resize() needed")
-                                result_mask.resize()
+                                result_mask.resize(result_mask.data.capacity * 4)
                     append_data_{{dtype}}(ud, val)
                     if use_result_mask:
                         append_data_uint8(rmd, 0)
@@ -849,9 +861,9 @@ cdef class {{name}}HashTable(HashTable):
                     k = kh_put_{{dtype}}(self.table, val, &ret)
                     self.table.vals[k] = count
 
-                    if needs_resize(ud):
+                    if needs_resize(ud.size, ud.capacity):
                         with gil:
-                            uniques.resize()
+                            uniques.resize(uniques.data.capacity * 4)
                     append_data_{{dtype}}(ud, val)
                     labels[i] = count
                     count += 1

pandas/_libs/hashtable_func_helper.pxi.in

@@ -480,9 +480,9 @@ def _unique_label_indices_{{dtype}}(const {{c_type}}[:] labels) -> ndarray:
         for i in range(n):
             kh_put_{{ttype}}(table, labels[i], &ret)
             if ret != 0:
-                if needs_resize(ud):
+                if needs_resize(ud.size, ud.capacity):
                     with gil:
-                        idx.resize()
+                        idx.resize(idx.data.capacity * 4)
                 append_data_{{ttype}}(ud, i)
 
     kh_destroy_{{ttype}}(table)