CLN: OrderedDict -> Dict (#29923)

Author: alimcmaster1

pandas/core/frame.py

@@ -9,7 +9,7 @@
 labeling information
 """
 import collections
-from collections import OrderedDict, abc
+from collections import abc
 from io import StringIO
 import itertools
 import sys
@@ -8170,10 +8170,10 @@ def isin(self, values):
 
 def _from_nested_dict(data):
     # TODO: this should be seriously cythonized
-    new_data = OrderedDict()
+    new_data = {}
     for index, s in data.items():
         for col, v in s.items():
-            new_data[col] = new_data.get(col, OrderedDict())
+            new_data[col] = new_data.get(col, {})
             new_data[col][index] = v
     return new_data
 

pandas/io/excel/_base.py

@@ -1,5 +1,4 @@
 import abc
-from collections import OrderedDict
 from datetime import date, datetime, timedelta
 from io import BytesIO
 import os
@@ -429,9 +428,9 @@ def parse(
             sheets = [sheet_name]
 
         # handle same-type duplicates.
-        sheets = list(OrderedDict.fromkeys(sheets).keys())
+        sheets = list(dict.fromkeys(sheets).keys())
 
-        output = OrderedDict()
+        output = {}
 
         for asheetname in sheets:
             if verbose:

pandas/io/stata.py

@@ -10,7 +10,6 @@
 http://www.statsmodels.org/devel/
 """
 
-from collections import OrderedDict
 import datetime
 from io import BytesIO
 import os
@@ -1676,7 +1675,7 @@ def read(
                 else:
                     data_formatted.append((col, data[col]))
         if requires_type_conversion:
-            data = DataFrame.from_dict(OrderedDict(data_formatted))
+            data = DataFrame.from_dict(dict(data_formatted))
         del data_formatted
 
         data = self._do_convert_missing(data, convert_missing)
@@ -1715,7 +1714,7 @@ def any_startswith(x: str) -> bool:
                     convert = True
                 retyped_data.append((col, data[col].astype(dtype)))
             if convert:
-                data = DataFrame.from_dict(OrderedDict(retyped_data))
+                data = DataFrame.from_dict(dict(retyped_data))
 
         if index_col is not None:
             data = data.set_index(data.pop(index_col))
@@ -1845,7 +1844,7 @@ def _do_convert_categoricals(
                 cat_converted_data.append((col, cat_data))
             else:
                 cat_converted_data.append((col, data[col]))
-        data = DataFrame.from_dict(OrderedDict(cat_converted_data))
+        data = DataFrame.from_dict(dict(cat_converted_data))
         return data
 
     @property
@@ -2194,7 +2193,7 @@ def _prepare_categoricals(self, data):
                 data_formatted.append((col, values))
             else:
                 data_formatted.append((col, data[col]))
-        return DataFrame.from_dict(OrderedDict(data_formatted))
+        return DataFrame.from_dict(dict(data_formatted))
 
     def _replace_nans(self, data):
         # return data
@@ -2673,7 +2672,7 @@ def __init__(self, df, columns, version=117, byteorder=None):
 
         self.df = df
         self.columns = columns
-        self._gso_table = OrderedDict((("", (0, 0)),))
+        self._gso_table = {"": (0, 0)}
         if byteorder is None:
             byteorder = sys.byteorder
         self._byteorder = _set_endianness(byteorder)
@@ -2703,7 +2702,7 @@ def generate_table(self):
 
         Returns
         -------
-        gso_table : OrderedDict
+        gso_table : dict
             Ordered dictionary using the string found as keys
             and their lookup position (v,o) as values
         gso_df : DataFrame
@@ -2761,7 +2760,7 @@ def generate_blob(self, gso_table):
 
         Parameters
         ----------
-        gso_table : OrderedDict
+        gso_table : dict
             Ordered dictionary (str, vo)
 
         Returns
@@ -2991,7 +2990,7 @@ def _write_map(self):
         the map with 0s.  The second call writes the final map locations when
         all blocks have been written."""
         if self._map is None:
-            self._map = OrderedDict(
+            self._map = dict(
                 (
                     ("stata_data", 0),
                     ("map", self._file.tell()),

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -1,7 +1,6 @@
 """
 test .agg behavior / note that .apply is tested generally in test_groupby.py
 """
-from collections import OrderedDict
 import functools
 
 import numpy as np
@@ -175,18 +174,14 @@ def test_aggregate_str_func(tsframe, groupbyfunc):
     tm.assert_frame_equal(result, expected)
 
     # group frame by function dict
-    result = grouped.agg(
-        OrderedDict([["A", "var"], ["B", "std"], ["C", "mean"], ["D", "sem"]])
-    )
+    result = grouped.agg({"A": "var", "B": "std", "C": "mean", "D": "sem"})
     expected = DataFrame(
-        OrderedDict(
-            [
-                ["A", grouped["A"].var()],
-                ["B", grouped["B"].std()],
-                ["C", grouped["C"].mean()],
-                ["D", grouped["D"].sem()],
-            ]
-        )
+        {
+            "A": grouped["A"].var(),
+            "B": grouped["B"].std(),
+            "C": grouped["C"].mean(),
+            "D": grouped["D"].sem(),
+        }
     )
     tm.assert_frame_equal(result, expected)
 
@@ -261,22 +256,20 @@ def test_multiple_functions_tuples_and_non_tuples(df):
 def test_more_flexible_frame_multi_function(df):
     grouped = df.groupby("A")
 
-    exmean = grouped.agg(OrderedDict([["C", np.mean], ["D", np.mean]]))
-    exstd = grouped.agg(OrderedDict([["C", np.std], ["D", np.std]]))
+    exmean = grouped.agg({"C": np.mean, "D": np.mean})
+    exstd = grouped.agg({"C": np.std, "D": np.std})
 
     expected = concat([exmean, exstd], keys=["mean", "std"], axis=1)
     expected = expected.swaplevel(0, 1, axis=1).sort_index(level=0, axis=1)
 
-    d = OrderedDict([["C", [np.mean, np.std]], ["D", [np.mean, np.std]]])
+    d = {"C": [np.mean, np.std], "D": [np.mean, np.std]}
     result = grouped.aggregate(d)
 
     tm.assert_frame_equal(result, expected)
 
     # be careful
-    result = grouped.aggregate(OrderedDict([["C", np.mean], ["D", [np.mean, np.std]]]))
-    expected = grouped.aggregate(
-        OrderedDict([["C", np.mean], ["D", [np.mean, np.std]]])
-    )
+    result = grouped.aggregate({"C": np.mean, "D": [np.mean, np.std]})
+    expected = grouped.aggregate({"C": np.mean, "D": [np.mean, np.std]})
     tm.assert_frame_equal(result, expected)
 
     def foo(x):
@@ -288,13 +281,11 @@ def bar(x):
     # this uses column selection & renaming
     msg = r"nested renamer is not supported"
     with pytest.raises(SpecificationError, match=msg):
-        d = OrderedDict(
-            [["C", np.mean], ["D", OrderedDict([["foo", np.mean], ["bar", np.std]])]]
-        )
+        d = dict([["C", np.mean], ["D", dict([["foo", np.mean], ["bar", np.std]])]])
         grouped.aggregate(d)
 
     # But without renaming, these functions are OK
-    d = OrderedDict([["C", [np.mean]], ["D", [foo, bar]]])
+    d = {"C": [np.mean], "D": [foo, bar]}
     grouped.aggregate(d)
 
 
@@ -303,26 +294,20 @@ def test_multi_function_flexible_mix(df):
     grouped = df.groupby("A")
 
     # Expected
-    d = OrderedDict(
-        [["C", OrderedDict([["foo", "mean"], ["bar", "std"]])], ["D", {"sum": "sum"}]]
-    )
+    d = {"C": {"foo": "mean", "bar": "std"}, "D": {"sum": "sum"}}
     # this uses column selection & renaming
     msg = r"nested renamer is not supported"
     with pytest.raises(SpecificationError, match=msg):
         grouped.aggregate(d)
 
     # Test 1
-    d = OrderedDict(
-        [["C", OrderedDict([["foo", "mean"], ["bar", "std"]])], ["D", "sum"]]
-    )
+    d = {"C": {"foo": "mean", "bar": "std"}, "D": "sum"}
     # this uses column selection & renaming
     with pytest.raises(SpecificationError, match=msg):
         grouped.aggregate(d)
 
     # Test 2
-    d = OrderedDict(
-        [["C", OrderedDict([["foo", "mean"], ["bar", "std"]])], ["D", ["sum"]]]
-    )
+    d = {"C": {"foo": "mean", "bar": "std"}, "D": "sum"}
     # this uses column selection & renaming
     with pytest.raises(SpecificationError, match=msg):
         grouped.aggregate(d)
@@ -642,9 +627,7 @@ def test_maybe_mangle_lambdas_args(self):
         assert func["A"][0](0, 2, b=3) == (0, 2, 3)
 
     def test_maybe_mangle_lambdas_named(self):
-        func = OrderedDict(
-            [("C", np.mean), ("D", OrderedDict([("foo", np.mean), ("bar", np.mean)]))]
-        )
+        func = {"C": np.mean, "D": {"foo": np.mean, "bar": np.mean}}
         result = _maybe_mangle_lambdas(func)
         assert result == func
 

pandas/tests/groupby/aggregate/test_other.py

@@ -2,7 +2,6 @@
 test all other .agg behavior
 """
 
-from collections import OrderedDict
 import datetime as dt
 from functools import partial
 
@@ -96,8 +95,7 @@ def test_agg_period_index():
     index = period_range(start="1999-01", periods=5, freq="M")
     s1 = Series(np.random.rand(len(index)), index=index)
     s2 = Series(np.random.rand(len(index)), index=index)
-    series = [("s1", s1), ("s2", s2)]
-    df = DataFrame.from_dict(OrderedDict(series))
+    df = DataFrame.from_dict({"s1": s1, "s2": s2})
     grouped = df.groupby(df.index.month)
     list(grouped)
 

pandas/tests/groupby/test_categorical.py

@@ -1,4 +1,3 @@
-from collections import OrderedDict
 from datetime import datetime
 
 import numpy as np
@@ -1204,7 +1203,7 @@ def test_seriesgroupby_observed_apply_dict(df_cat, observed, index, data):
     # GH 24880
     expected = Series(data=data, index=index, name="C")
     result = df_cat.groupby(["A", "B"], observed=observed)["C"].apply(
-        lambda x: OrderedDict([("min", x.min()), ("max", x.max())])
+        lambda x: {"min": x.min(), "max": x.max()}
     )
     tm.assert_series_equal(result, expected)
 

pandas/tests/groupby/test_groupby.py

@@ -1,4 +1,3 @@
-from collections import OrderedDict
 from datetime import datetime
 from decimal import Decimal
 from io import StringIO
@@ -598,7 +597,7 @@ def test_groupby_as_index_agg(df):
     expected = grouped.mean()
     tm.assert_frame_equal(result, expected)
 
-    result2 = grouped.agg(OrderedDict([["C", np.mean], ["D", np.sum]]))
+    result2 = grouped.agg({"C": np.mean, "D": np.sum})
     expected2 = grouped.mean()
     expected2["D"] = grouped.sum()["D"]
     tm.assert_frame_equal(result2, expected2)
@@ -617,7 +616,7 @@ def test_groupby_as_index_agg(df):
     expected = grouped.mean()
     tm.assert_frame_equal(result, expected)
 
-    result2 = grouped.agg(OrderedDict([["C", np.mean], ["D", np.sum]]))
+    result2 = grouped.agg({"C": np.mean, "D": np.sum})
     expected2 = grouped.mean()
     expected2["D"] = grouped.sum()["D"]
     tm.assert_frame_equal(result2, expected2)

pandas/tests/indexes/multi/test_constructor.py

@@ -1,5 +1,3 @@
-from collections import OrderedDict
-
 import numpy as np
 import pytest
 
@@ -654,14 +652,12 @@ def test_from_frame_error(non_frame):
 def test_from_frame_dtype_fidelity():
     # GH 22420
     df = pd.DataFrame(
-        OrderedDict(
-            [
-                ("dates", pd.date_range("19910905", periods=6, tz="US/Eastern")),
-                ("a", [1, 1, 1, 2, 2, 2]),
-                ("b", pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True)),
-                ("c", ["x", "x", "y", "z", "x", "y"]),
-            ]
-        )
+        {
+            "dates": pd.date_range("19910905", periods=6, tz="US/Eastern"),
+            "a": [1, 1, 1, 2, 2, 2],
+            "b": pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True),
+            "c": ["x", "x", "y", "z", "x", "y"],
+        }
     )
     original_dtypes = df.dtypes.to_dict()
 

pandas/tests/indexes/multi/test_conversion.py

@@ -1,5 +1,3 @@
-from collections import OrderedDict
-
 import numpy as np
 import pytest
 
@@ -107,14 +105,12 @@ def test_to_frame_dtype_fidelity():
     original_dtypes = {name: mi.levels[i].dtype for i, name in enumerate(mi.names)}
 
     expected_df = pd.DataFrame(
-        OrderedDict(
-            [
-                ("dates", pd.date_range("19910905", periods=6, tz="US/Eastern")),
-                ("a", [1, 1, 1, 2, 2, 2]),
-                ("b", pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True)),
-                ("c", ["x", "x", "y", "z", "x", "y"]),
-            ]
-        )
+        {
+            "dates": pd.date_range("19910905", periods=6, tz="US/Eastern"),
+            "a": [1, 1, 1, 2, 2, 2],
+            "b": pd.Categorical(["a", "a", "b", "b", "c", "c"], ordered=True),
+            "c": ["x", "x", "y", "z", "x", "y"],
+        }
     )
     df = mi.to_frame(index=False)
     df_dtypes = df.dtypes.to_dict()

pandas/tests/indexes/test_setops.py

@@ -2,7 +2,6 @@
 The tests in this package are to ensure the proper resultant dtypes of
 set operations.
 """
-from collections import OrderedDict
 import itertools as it
 
 import numpy as np
@@ -16,14 +15,12 @@
 from pandas.tests.indexes.conftest import indices_dict
 import pandas.util.testing as tm
 
-COMPATIBLE_INCONSISTENT_PAIRS = OrderedDict(
-    [
-        ((Int64Index, RangeIndex), (tm.makeIntIndex, tm.makeRangeIndex)),
-        ((Float64Index, Int64Index), (tm.makeFloatIndex, tm.makeIntIndex)),
-        ((Float64Index, RangeIndex), (tm.makeFloatIndex, tm.makeIntIndex)),
-        ((Float64Index, UInt64Index), (tm.makeFloatIndex, tm.makeUIntIndex)),
-    ]
-)
+COMPATIBLE_INCONSISTENT_PAIRS = {
+    (Int64Index, RangeIndex): (tm.makeIntIndex, tm.makeRangeIndex),
+    (Float64Index, Int64Index): (tm.makeFloatIndex, tm.makeIntIndex),
+    (Float64Index, RangeIndex): (tm.makeFloatIndex, tm.makeIntIndex),
+    (Float64Index, UInt64Index): (tm.makeFloatIndex, tm.makeUIntIndex),
+}
 
 
 @pytest.fixture(params=it.combinations(indices_dict, 2), ids="-".join)