DEPR: lookup, append (#49481)

* DEPR: lookup, append

* update docs, fix tests

* rm test_append files

* update tests

* fix doc

* remove asvs

Author: jbrockmendel

asv_bench/benchmarks/frame_methods.py

@@ -28,26 +28,6 @@ def time_frame_get_numeric_data(self):
         self.df._get_numeric_data()
 
 
-class Lookup:
-    def setup(self):
-        self.df = DataFrame(np.random.randn(10000, 8), columns=list("abcdefgh"))
-        self.df["foo"] = "bar"
-        self.row_labels = list(self.df.index[::10])[:900]
-        self.col_labels = list(self.df.columns) * 100
-        self.row_labels_all = np.array(
-            list(self.df.index) * len(self.df.columns), dtype="object"
-        )
-        self.col_labels_all = np.array(
-            list(self.df.columns) * len(self.df.index), dtype="object"
-        )
-
-    def time_frame_fancy_lookup(self):
-        self.df.lookup(self.row_labels, self.col_labels)
-
-    def time_frame_fancy_lookup_all(self):
-        self.df.lookup(self.row_labels_all, self.col_labels_all)
-
-
 class Reindex:
     def setup(self):
         N = 10**3

asv_bench/benchmarks/join_merge.py

@@ -22,26 +22,6 @@
     from pandas import ordered_merge as merge_ordered
 
 
-class Append:
-    def setup(self):
-        self.df1 = DataFrame(np.random.randn(10000, 4), columns=["A", "B", "C", "D"])
-        self.df2 = self.df1.copy()
-        self.df2.index = np.arange(10000, 20000)
-        self.mdf1 = self.df1.copy()
-        self.mdf1["obj1"] = "bar"
-        self.mdf1["obj2"] = "bar"
-        self.mdf1["int1"] = 5
-        self.mdf1 = self.mdf1._consolidate()
-        self.mdf2 = self.mdf1.copy()
-        self.mdf2.index = self.df2.index
-
-    def time_append_homogenous(self):
-        self.df1.append(self.df2)
-
-    def time_append_mixed(self):
-        self.mdf1.append(self.mdf2)
-
-
 class Concat:
 
     params = [0, 1]

doc/redirects.csv

@@ -315,7 +315,6 @@ generated/pandas.DataFrame.aggregate,../reference/api/pandas.DataFrame.aggregate
 generated/pandas.DataFrame.align,../reference/api/pandas.DataFrame.align
 generated/pandas.DataFrame.all,../reference/api/pandas.DataFrame.all
 generated/pandas.DataFrame.any,../reference/api/pandas.DataFrame.any
-generated/pandas.DataFrame.append,../reference/api/pandas.DataFrame.append
 generated/pandas.DataFrame.apply,../reference/api/pandas.DataFrame.apply
 generated/pandas.DataFrame.applymap,../reference/api/pandas.DataFrame.applymap
 generated/pandas.DataFrame.as_blocks,../reference/api/pandas.DataFrame.as_blocks
@@ -408,7 +407,6 @@ generated/pandas.DataFrame.last,../reference/api/pandas.DataFrame.last
 generated/pandas.DataFrame.last_valid_index,../reference/api/pandas.DataFrame.last_valid_index
 generated/pandas.DataFrame.le,../reference/api/pandas.DataFrame.le
 generated/pandas.DataFrame.loc,../reference/api/pandas.DataFrame.loc
-generated/pandas.DataFrame.lookup,../reference/api/pandas.DataFrame.lookup
 generated/pandas.DataFrame.lt,../reference/api/pandas.DataFrame.lt
 generated/pandas.DataFrame.mask,../reference/api/pandas.DataFrame.mask
 generated/pandas.DataFrame.max,../reference/api/pandas.DataFrame.max
@@ -917,7 +915,6 @@ generated/pandas.Series.aggregate,../reference/api/pandas.Series.aggregate
 generated/pandas.Series.align,../reference/api/pandas.Series.align
 generated/pandas.Series.all,../reference/api/pandas.Series.all
 generated/pandas.Series.any,../reference/api/pandas.Series.any
-generated/pandas.Series.append,../reference/api/pandas.Series.append
 generated/pandas.Series.apply,../reference/api/pandas.Series.apply
 generated/pandas.Series.argmax,../reference/api/pandas.Series.argmax
 generated/pandas.Series.argmin,../reference/api/pandas.Series.argmin

doc/source/reference/frame.rst

@@ -66,7 +66,6 @@ Indexing, iteration
    DataFrame.keys
    DataFrame.iterrows
    DataFrame.itertuples
-   DataFrame.lookup
    DataFrame.pop
    DataFrame.tail
    DataFrame.xs
@@ -250,7 +249,6 @@ Combining / comparing / joining / merging
 .. autosummary::
    :toctree: api/
 
-   DataFrame.append
    DataFrame.assign
    DataFrame.compare
    DataFrame.join

doc/source/reference/series.rst

@@ -247,7 +247,6 @@ Combining / comparing / joining / merging
 .. autosummary::
    :toctree: api/
 
-   Series.append
    Series.compare
    Series.update
 

doc/source/user_guide/indexing.rst

@@ -1559,7 +1559,7 @@ For instance:
     df.reindex(cols, axis=1).to_numpy()[np.arange(len(df)), idx]
 
 Formerly this could be achieved with the dedicated ``DataFrame.lookup`` method
-which was deprecated in version 1.2.0.
+which was deprecated in version 1.2.0 and removed in version 2.0.0.
 
 .. _indexing.class:
 

doc/source/whatsnew/v2.0.0.rst

@@ -267,6 +267,9 @@ Removal of prior version deprecations/changes
 - Enforced deprecation changing behavior when passing ``datetime64[ns]`` dtype data and timezone-aware dtype to :class:`Series`, interpreting the values as wall-times instead of UTC times, matching :class:`DatetimeIndex` behavior (:issue:`41662`)
 - Removed deprecated :meth:`DataFrame._AXIS_NUMBERS`, :meth:`DataFrame._AXIS_NAMES`, :meth:`Series._AXIS_NUMBERS`, :meth:`Series._AXIS_NAMES` (:issue:`33637`)
 - Removed deprecated :meth:`Index.to_native_types`, use ``obj.astype(str)`` instead (:issue:`36418`)
+- Removed deprecated :meth:`Series.iteritems`, :meth:`DataFrame.iteritems`, use ``obj.items`` instead (:issue:`45321`)
+- Removed deprecated :meth:`DataFrame.lookup` (:issue:`35224`)
+- Removed deprecated :meth:`Series.append`, :meth:`DataFrame.append`, use :func:`concat` instead (:issue:`35407`)
 - Removed deprecated :meth:`Series.iteritems`, :meth:`DataFrame.iteritems` and :meth:`HDFStore.iteritems` use ``obj.items`` instead (:issue:`45321`)
 - Removed deprecated :meth:`DatetimeIndex.union_many` (:issue:`45018`)
 - Removed deprecated ``weekofyear`` and ``week`` attributes of :class:`DatetimeArray`, :class:`DatetimeIndex` and ``dt`` accessor in favor of ``isocalendar().week`` (:issue:`33595`)

pandas/core/frame.py

@@ -4870,69 +4870,6 @@ def _series(self):
             for idx, item in enumerate(self.columns)
         }
 
-    def lookup(
-        self, row_labels: Sequence[IndexLabel], col_labels: Sequence[IndexLabel]
-    ) -> np.ndarray:
-        """
-        Label-based "fancy indexing" function for DataFrame.
-
-        .. deprecated:: 1.2.0
-            DataFrame.lookup is deprecated,
-            use pandas.factorize and NumPy indexing instead.
-            For further details see
-            :ref:`Looking up values by index/column labels <indexing.lookup>`.
-
-        Given equal-length arrays of row and column labels, return an
-        array of the values corresponding to each (row, col) pair.
-
-        Parameters
-        ----------
-        row_labels : sequence
-            The row labels to use for lookup.
-        col_labels : sequence
-            The column labels to use for lookup.
-
-        Returns
-        -------
-        numpy.ndarray
-            The found values.
-        """
-        msg = (
-            "The 'lookup' method is deprecated and will be "
-            "removed in a future version. "
-            "You can use DataFrame.melt and DataFrame.loc "
-            "as a substitute."
-        )
-        warnings.warn(msg, FutureWarning, stacklevel=find_stack_level())
-
-        n = len(row_labels)
-        if n != len(col_labels):
-            raise ValueError("Row labels must have same size as column labels")
-        if not (self.index.is_unique and self.columns.is_unique):
-            # GH#33041
-            raise ValueError("DataFrame.lookup requires unique index and columns")
-
-        thresh = 1000
-        if not self._is_mixed_type or n > thresh:
-            values = self.values
-            ridx = self.index.get_indexer(row_labels)
-            cidx = self.columns.get_indexer(col_labels)
-            if (ridx == -1).any():
-                raise KeyError("One or more row labels was not found")
-            if (cidx == -1).any():
-                raise KeyError("One or more column labels was not found")
-            flat_index = ridx * len(self.columns) + cidx
-            result = values.flat[flat_index]
-        else:
-            result = np.empty(n, dtype="O")
-            for i, (r, c) in enumerate(zip(row_labels, col_labels)):
-                result[i] = self._get_value(r, c)
-
-        if is_object_dtype(result):
-            result = lib.maybe_convert_objects(result)
-
-        return result
-
     # ----------------------------------------------------------------------
     # Reindexing and alignment
 
@@ -9560,118 +9497,6 @@ def infer(x):
     # ----------------------------------------------------------------------
     # Merging / joining methods
 
-    def append(
-        self,
-        other,
-        ignore_index: bool = False,
-        verify_integrity: bool = False,
-        sort: bool = False,
-    ) -> DataFrame:
-        """
-        Append rows of `other` to the end of caller, returning a new object.
-
-        .. deprecated:: 1.4.0
-            Use :func:`concat` instead. For further details see
-            :ref:`whatsnew_140.deprecations.frame_series_append`
-
-        Columns in `other` that are not in the caller are added as new columns.
-
-        Parameters
-        ----------
-        other : DataFrame or Series/dict-like object, or list of these
-            The data to append.
-        ignore_index : bool, default False
-            If True, the resulting axis will be labeled 0, 1, …, n - 1.
-        verify_integrity : bool, default False
-            If True, raise ValueError on creating index with duplicates.
-        sort : bool, default False
-            Sort columns if the columns of `self` and `other` are not aligned.
-
-            .. versionchanged:: 1.0.0
-
-                Changed to not sort by default.
-
-        Returns
-        -------
-        DataFrame
-            A new DataFrame consisting of the rows of caller and the rows of `other`.
-
-        See Also
-        --------
-        concat : General function to concatenate DataFrame or Series objects.
-
-        Notes
-        -----
-        If a list of dict/series is passed and the keys are all contained in
-        the DataFrame's index, the order of the columns in the resulting
-        DataFrame will be unchanged.
-
-        Iteratively appending rows to a DataFrame can be more computationally
-        intensive than a single concatenate. A better solution is to append
-        those rows to a list and then concatenate the list with the original
-        DataFrame all at once.
-
-        Examples
-        --------
-        >>> df = pd.DataFrame([[1, 2], [3, 4]], columns=list('AB'), index=['x', 'y'])
-        >>> df
-           A  B
-        x  1  2
-        y  3  4
-        >>> df2 = pd.DataFrame([[5, 6], [7, 8]], columns=list('AB'), index=['x', 'y'])
-        >>> df.append(df2)
-           A  B
-        x  1  2
-        y  3  4
-        x  5  6
-        y  7  8
-
-        With `ignore_index` set to True:
-
-        >>> df.append(df2, ignore_index=True)
-           A  B
-        0  1  2
-        1  3  4
-        2  5  6
-        3  7  8
-
-        The following, while not recommended methods for generating DataFrames,
-        show two ways to generate a DataFrame from multiple data sources.
-
-        Less efficient:
-
-        >>> df = pd.DataFrame(columns=['A'])
-        >>> for i in range(5):
-        ...     df = df.append({'A': i}, ignore_index=True)
-        >>> df
-           A
-        0  0
-        1  1
-        2  2
-        3  3
-        4  4
-
-        More efficient:
-
-        >>> pd.concat([pd.DataFrame([i], columns=['A']) for i in range(5)],
-        ...           ignore_index=True)
-           A
-        0  0
-        1  1
-        2  2
-        3  3
-        4  4
-        """
-        warnings.warn(
-            "The frame.append method is deprecated "
-            "and will be removed from pandas in a future version. "
-            "Use pandas.concat instead.",
-            FutureWarning,
-            stacklevel=find_stack_level(),
-        )
-
-        return self._append(other, ignore_index, verify_integrity, sort)
-
     def _append(
         self,
         other,