Merge pull request #204 from pandas-dev/master

Sync Fork from Upstream Repo

Author: sthagen

asv_bench/benchmarks/frame_methods.py

@@ -652,7 +652,9 @@ class Rank:
     ]
 
     def setup(self, dtype):
-        self.df = DataFrame(np.random.randn(10000, 10), columns=range(10), dtype=dtype)
+        self.df = DataFrame(
+            np.random.randn(10000, 10).astype(dtype), columns=range(10), dtype=dtype
+        )
 
     def time_rank(self, dtype):
         self.df.rank()

asv_bench/benchmarks/plotting.py

@@ -1,5 +1,9 @@
+import importlib
+import sys
+
 import matplotlib
 import numpy as np
+import pkg_resources
 
 from pandas import (
     DataFrame,
@@ -13,6 +17,8 @@
 except ImportError:
     from pandas.tools.plotting import andrews_curves
 
+from pandas.plotting._core import _get_plot_backend
+
 matplotlib.use("Agg")
 
 
@@ -99,4 +105,28 @@ def time_plot_andrews_curves(self):
         andrews_curves(self.df, "Name")
 
 
+class BackendLoading:
+    repeat = 1
+    number = 1
+    warmup_time = 0
+
+    def setup(self):
+        dist = pkg_resources.get_distribution("pandas")
+        spec = importlib.machinery.ModuleSpec("my_backend", None)
+        mod = importlib.util.module_from_spec(spec)
+        mod.plot = lambda *args, **kwargs: 1
+
+        backends = pkg_resources.get_entry_map("pandas")
+        my_entrypoint = pkg_resources.EntryPoint(
+            "pandas_plotting_backend", mod.__name__, dist=dist
+        )
+        backends["pandas_plotting_backends"][mod.__name__] = my_entrypoint
+        for i in range(10):
+            backends["pandas_plotting_backends"][str(i)] = my_entrypoint
+        sys.modules["my_backend"] = mod
+
+    def time_get_plot_backend(self):
+        _get_plot_backend("my_backend")
+
+
 from .pandas_vb_common import setup  # noqa: F401 isort:skip

doc/source/reference/style.rst

@@ -67,5 +67,6 @@ Style export and import
    Styler.render
    Styler.export
    Styler.use
+   Styler.to_html
    Styler.to_excel
    Styler.to_latex

doc/source/user_guide/options.rst

@@ -487,6 +487,8 @@ styler.sparse.index                     True         "Sparsify" MultiIndex displ
                                                      elements in outer levels within groups).
 styler.sparse.columns                   True         "Sparsify" MultiIndex display for columns
                                                      in Styler output.
+styler.render.max_elements              262144       Maximum number of datapoints that Styler will render
+                                                     trimming either rows, columns or both to fit.
 ======================================= ============ ==================================
 
 

doc/source/whatsnew/v1.2.5.rst

@@ -18,9 +18,11 @@ Fixed regressions
 - Fixed regression in :meth:`DataFrame.sum` and :meth:`DataFrame.prod` when ``min_count`` and ``numeric_only`` are both given (:issue:`41074`)
 - Regression in :func:`read_csv` when using ``memory_map=True`` with an non-UTF8 encoding (:issue:`40986`)
 - Regression in :meth:`DataFrame.replace` and :meth:`Series.replace` when the values to replace is a NumPy float array (:issue:`40371`)
+- Regression in :func:`ExcelFile` when a corrupt file is opened but not closed (:issue:`41778`)
 
 .. ---------------------------------------------------------------------------
 
+
 .. _whatsnew_125.bug_fixes:
 
 Bug fixes

doc/source/whatsnew/v1.3.0.rst

@@ -106,7 +106,8 @@ cdef class IndexEngine:
 
         try:
             return self.mapping.get_item(val)
-        except (TypeError, ValueError):
+        except (TypeError, ValueError, OverflowError):
+            # GH#41775 OverflowError e.g. if we are uint64 and val is -1
             raise KeyError(val)
 
     cdef inline _get_loc_duplicates(self, object val):

pandas/_libs/index.pyx

@@ -31,7 +31,9 @@ cdef class IntervalTree(IntervalMixin):
     we are emulating the IndexEngine interface
     """
     cdef readonly:
-        object left, right, root, dtype
+        ndarray left, right
+        IntervalNode root
+        object dtype
         str closed
         object _is_overlapping, _left_sorter, _right_sorter
 
@@ -203,6 +205,41 @@ cdef sort_values_and_indices(all_values, all_indices, subset):
 # Nodes
 # ----------------------------------------------------------------------
 
+@cython.internal
+cdef class IntervalNode:
+    cdef readonly:
+        int64_t n_elements, n_center, leaf_size
+        bint is_leaf_node
+
+    def __repr__(self) -> str:
+        if self.is_leaf_node:
+            return (
+                f"<{type(self).__name__}: {self.n_elements} elements (terminal)>"
+            )
+        else:
+            n_left = self.left_node.n_elements
+            n_right = self.right_node.n_elements
+            n_center = self.n_elements - n_left - n_right
+            return (
+                f"<{type(self).__name__}: "
+                f"pivot {self.pivot}, {self.n_elements} elements "
+                f"({n_left} left, {n_right} right, {n_center} overlapping)>"
+            )
+
+    def counts(self):
+        """
+        Inspect counts on this node
+        useful for debugging purposes
+        """
+        if self.is_leaf_node:
+            return self.n_elements
+        else:
+            m = len(self.center_left_values)
+            l = self.left_node.counts()
+            r = self.right_node.counts()
+            return (m, (l, r))
+
+
 # we need specialized nodes and leaves to optimize for different dtype and
 # closed values
 
@@ -240,7 +277,7 @@ NODE_CLASSES = {}
 
 
 @cython.internal
-cdef class {{dtype_title}}Closed{{closed_title}}IntervalNode:
+cdef class {{dtype_title}}Closed{{closed_title}}IntervalNode(IntervalNode):
     """Non-terminal node for an IntervalTree
 
     Categorizes intervals by those that fall to the left, those that fall to
@@ -252,8 +289,6 @@ cdef class {{dtype_title}}Closed{{closed_title}}IntervalNode:
         int64_t[:] center_left_indices, center_right_indices, indices
         {{dtype}}_t min_left, max_right
         {{dtype}}_t pivot
-        int64_t n_elements, n_center, leaf_size
-        bint is_leaf_node
 
     def __init__(self,
                  ndarray[{{dtype}}_t, ndim=1] left,
@@ -381,31 +416,6 @@ cdef class {{dtype_title}}Closed{{closed_title}}IntervalNode:
             else:
                 result.extend(self.center_left_indices)
 
-    def __repr__(self) -> str:
-        if self.is_leaf_node:
-            return ('<{{dtype_title}}Closed{{closed_title}}IntervalNode: '
-                    '%s elements (terminal)>' % self.n_elements)
-        else:
-            n_left = self.left_node.n_elements
-            n_right = self.right_node.n_elements
-            n_center = self.n_elements - n_left - n_right
-            return ('<{{dtype_title}}Closed{{closed_title}}IntervalNode: '
-                    'pivot %s, %s elements (%s left, %s right, %s '
-                    'overlapping)>' % (self.pivot, self.n_elements,
-                                       n_left, n_right, n_center))
-
-    def counts(self):
-        """
-        Inspect counts on this node
-        useful for debugging purposes
-        """
-        if self.is_leaf_node:
-            return self.n_elements
-        else:
-            m = len(self.center_left_values)
-            l = self.left_node.counts()
-            r = self.right_node.counts()
-            return (m, (l, r))
 
 NODE_CLASSES['{{dtype}}',
              '{{closed}}'] = {{dtype_title}}Closed{{closed_title}}IntervalNode

pandas/_libs/intervaltree.pxi.in

@@ -73,6 +73,7 @@ def maybe_convert_objects(
     convert_datetime: Literal[False] = ...,
     convert_timedelta: bool = ...,
     convert_period: Literal[False] = ...,
+    convert_interval: Literal[False] = ...,
     convert_to_nullable_integer: Literal[False] = ...,
     dtype_if_all_nat: DtypeObj | None = ...,
 ) -> np.ndarray: ...
@@ -86,6 +87,7 @@ def maybe_convert_objects(
     convert_datetime: bool = ...,
     convert_timedelta: bool = ...,
     convert_period: bool = ...,
+    convert_interval: bool = ...,
     convert_to_nullable_integer: Literal[True] = ...,
     dtype_if_all_nat: DtypeObj | None = ...,
 ) -> ArrayLike: ...
@@ -99,6 +101,7 @@ def maybe_convert_objects(
     convert_datetime: Literal[True] = ...,
     convert_timedelta: bool = ...,
     convert_period: bool = ...,
+    convert_interval: bool = ...,
     convert_to_nullable_integer: bool = ...,
     dtype_if_all_nat: DtypeObj | None = ...,
 ) -> ArrayLike: ...
@@ -112,6 +115,7 @@ def maybe_convert_objects(
     convert_datetime: bool = ...,
     convert_timedelta: bool = ...,
     convert_period: Literal[True] = ...,
+    convert_interval: bool = ...,
     convert_to_nullable_integer: bool = ...,
     dtype_if_all_nat: DtypeObj | None = ...,
 ) -> ArrayLike: ...
@@ -125,6 +129,7 @@ def maybe_convert_objects(
     convert_datetime: bool = ...,
     convert_timedelta: bool = ...,
     convert_period: bool = ...,
+    convert_interval: bool = ...,
     convert_to_nullable_integer: bool = ...,
     dtype_if_all_nat: DtypeObj | None = ...,
 ) -> ArrayLike: ...
@@ -190,11 +195,7 @@ def maybe_indices_to_slice(
     max_len: int,
 ) -> slice | np.ndarray: ...  # np.ndarray[np.uint8]
 
-def clean_index_list(obj: list) -> tuple[
-    list | np.ndarray,  # np.ndarray[object | np.int64 | np.uint64]
-    bool,
-]: ...
-
+def is_all_arraylike(obj: list) -> bool: ...
 
 # -----------------------------------------------------------------
 # Functions which in reality take memoryviews