Merge remote-tracking branch 'upstream/master' into remove_tests_multiple

Author: datapythonista

doc/source/whatsnew/v1.0.0.rst

@@ -307,6 +307,7 @@ Other
 - Trying to set the ``display.precision``, ``display.max_rows`` or ``display.max_columns`` using :meth:`set_option` to anything but a ``None`` or a positive int will raise a ``ValueError`` (:issue:`23348`)
 - Using :meth:`DataFrame.replace` with overlapping keys in a nested dictionary will no longer raise, now matching the behavior of a flat dictionary (:issue:`27660`)
 - :meth:`DataFrame.to_csv` and :meth:`Series.to_csv` now support dicts as ``compression`` argument with key ``'method'`` being the compression method and others as additional compression options when the compression method is ``'zip'``. (:issue:`26023`)
+- Bug in :meth:`Series.diff` where a boolean series would incorrectly raise a ``TypeError`` (:issue:`17294`)
 - :meth:`Series.append` will no longer raise a ``TypeError`` when passed a tuple of ``Series`` (:issue:`28410`)
 
 .. _whatsnew_1000.contributors:

pandas/core/algorithms.py

@@ -1910,6 +1910,7 @@ def diff(arr, n: int, axis: int = 0):
     dtype = arr.dtype
 
     is_timedelta = False
+    is_bool = False
     if needs_i8_conversion(arr):
         dtype = np.float64
         arr = arr.view("i8")
@@ -1918,6 +1919,7 @@ def diff(arr, n: int, axis: int = 0):
 
     elif is_bool_dtype(dtype):
         dtype = np.object_
+        is_bool = True
 
     elif is_integer_dtype(dtype):
         dtype = np.float64
@@ -1959,6 +1961,8 @@ def diff(arr, n: int, axis: int = 0):
             result = res - lag
             result[mask] = na
             out_arr[res_indexer] = result
+        elif is_bool:
+            out_arr[res_indexer] = arr[res_indexer] ^ arr[lag_indexer]
         else:
             out_arr[res_indexer] = arr[res_indexer] - arr[lag_indexer]
 

pandas/core/arrays/interval.py

@@ -259,7 +259,7 @@ def _from_factorized(cls, values, original):
     closed : {'left', 'right', 'both', 'neither'}, default 'right'
         Whether the intervals are closed on the left-side, right-side, both
         or neither.
-    copy : boolean, default False
+    copy : bool, default False
         copy the data
     dtype : dtype or None, default None
         If None, dtype will be inferred
@@ -315,7 +315,7 @@ def from_breaks(cls, breaks, closed="right", copy=False, dtype=None):
         closed : {'left', 'right', 'both', 'neither'}, default 'right'
             Whether the intervals are closed on the left-side, right-side, both
             or neither.
-        copy : boolean, default False
+        copy : bool, default False
             Copy the data.
         dtype : dtype, optional
             If None, dtype will be inferred.
@@ -387,7 +387,7 @@ def from_arrays(cls, left, right, closed="right", copy=False, dtype=None):
     closed : {'left', 'right', 'both', 'neither'}, default 'right'
         Whether the intervals are closed on the left-side, right-side, both
         or neither.
-    copy : boolean, default False
+    copy : bool, default False
         by-default copy the data, this is compat only and ignored
     dtype : dtype or None, default None
         If None, dtype will be inferred
@@ -811,7 +811,7 @@ def value_counts(self, dropna=True):
 
         Parameters
         ----------
-        dropna : boolean, default True
+        dropna : bool, default True
             Don't include counts of NaN.
 
         Returns

pandas/core/dtypes/cast.py

@@ -339,7 +339,7 @@ def maybe_promote(dtype, fill_value=np.nan):
     # if we passed an array here, determine the fill value by dtype
     if isinstance(fill_value, np.ndarray):
         if issubclass(fill_value.dtype.type, (np.datetime64, np.timedelta64)):
-            fill_value = iNaT
+            fill_value = fill_value.dtype.type("NaT", "ns")
         else:
 
             # we need to change to object type as our
@@ -350,9 +350,14 @@ def maybe_promote(dtype, fill_value=np.nan):
 
     # returns tuple of (dtype, fill_value)
     if issubclass(dtype.type, np.datetime64):
-        fill_value = tslibs.Timestamp(fill_value).value
+        fill_value = tslibs.Timestamp(fill_value).to_datetime64()
     elif issubclass(dtype.type, np.timedelta64):
-        fill_value = tslibs.Timedelta(fill_value).value
+        fv = tslibs.Timedelta(fill_value)
+        if fv is NaT:
+            # NaT has no `to_timedelta6` method
+            fill_value = np.timedelta64("NaT", "ns")
+        else:
+            fill_value = fv.to_timedelta64()
     elif is_datetime64tz_dtype(dtype):
         if isna(fill_value):
             fill_value = NaT
@@ -393,7 +398,7 @@ def maybe_promote(dtype, fill_value=np.nan):
             dtype = np.float64
             fill_value = np.nan
         elif is_datetime_or_timedelta_dtype(dtype):
-            fill_value = iNaT
+            fill_value = dtype.type("NaT", "ns")
         else:
             dtype = np.object_
             fill_value = np.nan

pandas/core/frame.py

@@ -304,7 +304,7 @@ class DataFrame(NDFrame):
     Parameters
     ----------
     data : ndarray (structured or homogeneous), Iterable, dict, or DataFrame
-        Dict can contain Series, arrays, constants, or list-like objects
+        Dict can contain Series, arrays, constants, or list-like objects.
 
         .. versionchanged:: 0.23.0
            If data is a dict, column order follows insertion-order for
@@ -316,14 +316,14 @@ class DataFrame(NDFrame):
 
     index : Index or array-like
         Index to use for resulting frame. Will default to RangeIndex if
-        no indexing information part of input data and no index provided
+        no indexing information part of input data and no index provided.
     columns : Index or array-like
         Column labels to use for resulting frame. Will default to
-        RangeIndex (0, 1, 2, ..., n) if no column labels are provided
+        RangeIndex (0, 1, 2, ..., n) if no column labels are provided.
     dtype : dtype, default None
-        Data type to force. Only a single dtype is allowed. If None, infer
+        Data type to force. Only a single dtype is allowed. If None, infer.
     copy : bool, default False
-        Copy data from inputs. Only affects DataFrame / 2d ndarray input
+        Copy data from inputs. Only affects DataFrame / 2d ndarray input.
 
     See Also
     --------
@@ -1544,20 +1544,20 @@ def from_records(
         data : ndarray (structured dtype), list of tuples, dict, or DataFrame
         index : str, list of fields, array-like
             Field of array to use as the index, alternately a specific set of
-            input labels to use
+            input labels to use.
         exclude : sequence, default None
-            Columns or fields to exclude
+            Columns or fields to exclude.
         columns : sequence, default None
             Column names to use. If the passed data do not have names
             associated with them, this argument provides names for the
             columns. Otherwise this argument indicates the order of the columns
             in the result (any names not found in the data will become all-NA
-            columns)
+            columns).
         coerce_float : bool, default False
             Attempt to convert values of non-string, non-numeric objects (like
-            decimal.Decimal) to floating point, useful for SQL result sets
+            decimal.Decimal) to floating point, useful for SQL result sets.
         nrows : int, default None
-            Number of rows to read if data is an iterator
+            Number of rows to read if data is an iterator.
 
         Returns
         -------
@@ -2118,8 +2118,8 @@ def to_parquet(
             .. versionadded:: 0.24.0
 
         partition_cols : list, optional, default None
-            Column names by which to partition the dataset
-            Columns are partitioned in the order they are given
+            Column names by which to partition the dataset.
+            Columns are partitioned in the order they are given.
 
             .. versionadded:: 0.24.0
 
@@ -3460,9 +3460,9 @@ def insert(self, loc, column, value, allow_duplicates=False):
         Parameters
         ----------
         loc : int
-            Insertion index. Must verify 0 <= loc <= len(columns)
+            Insertion index. Must verify 0 <= loc <= len(columns).
         column : str, number, or hashable object
-            label of the inserted column
+            Label of the inserted column.
         value : int, Series, or array-like
         allow_duplicates : bool, optional
         """
@@ -3681,9 +3681,9 @@ def lookup(self, row_labels, col_labels):
         Parameters
         ----------
         row_labels : sequence
-            The row labels to use for lookup
+            The row labels to use for lookup.
         col_labels : sequence
-            The column labels to use for lookup
+            The column labels to use for lookup.
 
         Returns
         -------
@@ -4770,14 +4770,14 @@ def drop_duplicates(self, subset=None, keep="first", inplace=False):
         ----------
         subset : column label or sequence of labels, optional
             Only consider certain columns for identifying duplicates, by
-            default use all of the columns
+            default use all of the columns.
         keep : {'first', 'last', False}, default 'first'
             Determines which duplicates (if any) to keep.
             - ``first`` : Drop duplicates except for the first occurrence.
             - ``last`` : Drop duplicates except for the last occurrence.
             - False : Drop all duplicates.
         inplace : bool, default False
-            Whether to drop duplicates in place or to return a copy
+            Whether to drop duplicates in place or to return a copy.
 
         Returns
         -------
@@ -4805,7 +4805,7 @@ def duplicated(self, subset=None, keep="first"):
         ----------
         subset : column label or sequence of labels, optional
             Only consider certain columns for identifying duplicates, by
-            default use all of the columns
+            default use all of the columns.
         keep : {'first', 'last', False}, default 'first'
             Determines which duplicates (if any) to mark.
 
@@ -6233,9 +6233,9 @@ def unstack(self, level=-1, fill_value=None):
         Parameters
         ----------
         level : int, str, or list of these, default -1 (last level)
-            Level(s) of index to unstack, can pass level name
+            Level(s) of index to unstack, can pass level name.
         fill_value : int, string or dict
-            Replace NaN with this value if the unstack produces missing values
+            Replace NaN with this value if the unstack produces missing values.
 
         Returns
         -------
@@ -7368,7 +7368,8 @@ def corr(self, method="pearson", min_periods=1):
             * callable: callable with input two 1d ndarrays
                 and returning a float. Note that the returned matrix from corr
                 will have 1 along the diagonals and will be symmetric
-                regardless of the callable's behavior
+                regardless of the callable's behavior.
+
                 .. versionadded:: 0.24.0
 
         min_periods : int, optional
@@ -7572,7 +7573,7 @@ def corrwith(self, other, axis=0, drop=False, method="pearson"):
             * kendall : Kendall Tau correlation coefficient
             * spearman : Spearman rank correlation
             * callable: callable with input two 1d ndarrays
-                and returning a float
+                and returning a float.
 
             .. versionadded:: 0.24.0
 
@@ -7948,7 +7949,7 @@ def idxmin(self, axis=0, skipna=True):
         ----------
         axis : {0 or 'index', 1 or 'columns'}, default 0
             The axis to use. 0 or 'index' for row-wise, 1 or 'columns' for column-wise
-        skipna : boolean, default True
+        skipna : bool, default True
             Exclude NA/null values. If an entire row/column is NA, the result
             will be NA.
 
@@ -7985,7 +7986,7 @@ def idxmax(self, axis=0, skipna=True):
         ----------
         axis : {0 or 'index', 1 or 'columns'}, default 0
             The axis to use. 0 or 'index' for row-wise, 1 or 'columns' for column-wise
-        skipna : boolean, default True
+        skipna : bool, default True
             Exclude NA/null values. If an entire row/column is NA, the result
             will be NA.
 
@@ -8037,7 +8038,8 @@ def mode(self, axis=0, numeric_only=False, dropna=True):
             The axis to iterate over while searching for the mode:
 
             * 0 or 'index' : get mode of each column
-            * 1 or 'columns' : get mode of each row
+            * 1 or 'columns' : get mode of each row.
+
         numeric_only : bool, default False
             If True, only apply to numeric columns.
         dropna : bool, default True

pandas/core/groupby/generic.py

@@ -709,7 +709,7 @@ def filter(self, func, dropna=True, *args, **kwargs):
         f : function
             Function to apply to each subframe. Should return True or False.
         dropna : Drop groups that do not pass the filter. True by default;
-            if False, groups that evaluate False are filled with NaNs.
+            If False, groups that evaluate False are filled with NaNs.
 
         Returns
         -------