TST/CLN: replace %s formatting syntax with .format in tests (#27324)

Author: simonjayhawkins

pandas/tests/arrays/categorical/test_dtypes.py

@@ -92,20 +92,22 @@ def test_codes_dtypes(self):
         result = Categorical(["foo", "bar", "baz"])
         assert result.codes.dtype == "int8"
 
-        result = Categorical(["foo%05d" % i for i in range(400)])
+        result = Categorical(["foo{i:05d}".format(i=i) for i in range(400)])
         assert result.codes.dtype == "int16"
 
-        result = Categorical(["foo%05d" % i for i in range(40000)])
+        result = Categorical(["foo{i:05d}".format(i=i) for i in range(40000)])
         assert result.codes.dtype == "int32"
 
         # adding cats
         result = Categorical(["foo", "bar", "baz"])
         assert result.codes.dtype == "int8"
-        result = result.add_categories(["foo%05d" % i for i in range(400)])
+        result = result.add_categories(["foo{i:05d}".format(i=i) for i in range(400)])
         assert result.codes.dtype == "int16"
 
         # removing cats
-        result = result.remove_categories(["foo%05d" % i for i in range(300)])
+        result = result.remove_categories(
+            ["foo{i:05d}".format(i=i) for i in range(300)]
+        )
         assert result.codes.dtype == "int8"
 
     @pytest.mark.parametrize("ordered", [True, False])

pandas/tests/arrays/sparse/test_libsparse.py

@@ -596,6 +596,6 @@ def _check_case(xloc, xlen, yloc, ylen, eloc, elen):
 
     @pytest.mark.parametrize("opname", ["add", "sub", "mul", "truediv", "floordiv"])
     def test_op(self, opname):
-        sparse_op = getattr(splib, "sparse_%s_float64" % opname)
+        sparse_op = getattr(splib, "sparse_{opname}_float64".format(opname=opname))
         python_op = getattr(operator, opname)
         self._op_tests(sparse_op, python_op)

pandas/tests/computation/test_eval.py

@@ -736,16 +736,16 @@ def test_float_truncation(self):
 
         df = pd.DataFrame({"A": [1000000000.0009, 1000000000.0011, 1000000000.0015]})
         cutoff = 1000000000.0006
-        result = df.query("A < %.4f" % cutoff)
+        result = df.query("A < {cutoff:.4f}".format(cutoff=cutoff))
         assert result.empty
 
         cutoff = 1000000000.0010
-        result = df.query("A > %.4f" % cutoff)
+        result = df.query("A > {cutoff:.4f}".format(cutoff=cutoff))
         expected = df.loc[[1, 2], :]
         tm.assert_frame_equal(expected, result)
 
         exact = 1000000000.0011
-        result = df.query("A == %.4f" % exact)
+        result = df.query("A == {exact:.4f}".format(exact=exact))
         expected = df.loc[[1], :]
         tm.assert_frame_equal(expected, result)
 

pandas/tests/dtypes/test_inference.py

@@ -1349,7 +1349,7 @@ def test_is_scalar_pandas_containers(self):
 
 def test_datetimeindex_from_empty_datetime64_array():
     for unit in ["ms", "us", "ns"]:
-        idx = DatetimeIndex(np.array([], dtype="datetime64[%s]" % unit))
+        idx = DatetimeIndex(np.array([], dtype="datetime64[{unit}]".format(unit=unit)))
         assert len(idx) == 0
 
 

pandas/tests/frame/test_alter_axes.py

@@ -342,7 +342,7 @@ def __init__(self, name, color):
                 self.color = color
 
             def __str__(self):
-                return "<Thing %r>" % (self.name,)
+                return "<Thing {self.name!r}>".format(self=self)
 
             # necessary for pretty KeyError
             __repr__ = __str__
@@ -419,7 +419,7 @@ def __init__(self, name, color):
                 self.color = color
 
             def __str__(self):
-                return "<Thing %r>" % (self.name,)
+                return "<Thing {self.name!r}>".format(self=self)
 
         thing1 = Thing("One", "red")
         thing2 = Thing("Two", "blue")

pandas/tests/frame/test_api.py

@@ -74,19 +74,19 @@ def test_get_value(self, float_frame):
 
     def test_add_prefix_suffix(self, float_frame):
         with_prefix = float_frame.add_prefix("foo#")
-        expected = pd.Index(["foo#%s" % c for c in float_frame.columns])
+        expected = pd.Index(["foo#{c}".format(c=c) for c in float_frame.columns])
         tm.assert_index_equal(with_prefix.columns, expected)
 
         with_suffix = float_frame.add_suffix("#foo")
-        expected = pd.Index(["%s#foo" % c for c in float_frame.columns])
+        expected = pd.Index(["{c}#foo".format(c=c) for c in float_frame.columns])
         tm.assert_index_equal(with_suffix.columns, expected)
 
         with_pct_prefix = float_frame.add_prefix("%")
-        expected = pd.Index(["%{}".format(c) for c in float_frame.columns])
+        expected = pd.Index(["%{c}".format(c=c) for c in float_frame.columns])
         tm.assert_index_equal(with_pct_prefix.columns, expected)
 
         with_pct_suffix = float_frame.add_suffix("%")
-        expected = pd.Index(["{}%".format(c) for c in float_frame.columns])
+        expected = pd.Index(["{c}%".format(c=c) for c in float_frame.columns])
         tm.assert_index_equal(with_pct_suffix.columns, expected)
 
     def test_get_axis(self, float_frame):

pandas/tests/frame/test_constructors.py

@@ -264,7 +264,7 @@ def test_constructor_ordereddict(self):
         nitems = 100
         nums = list(range(nitems))
         random.shuffle(nums)
-        expected = ["A%d" % i for i in nums]
+        expected = ["A{i:d}".format(i=i) for i in nums]
         df = DataFrame(OrderedDict(zip(expected, [[0]] * nitems)))
         assert expected == list(df.columns)
 

pandas/tests/frame/test_query_eval.py

@@ -453,7 +453,9 @@ def test_date_query_with_non_date(self):
 
         for op in ["<", ">", "<=", ">="]:
             with pytest.raises(TypeError):
-                df.query("dates %s nondate" % op, parser=parser, engine=engine)
+                df.query(
+                    "dates {op} nondate".format(op=op), parser=parser, engine=engine
+                )
 
     def test_query_syntax_error(self):
         engine, parser = self.engine, self.parser
@@ -688,7 +690,7 @@ def test_inf(self):
         ops = "==", "!="
         d = dict(zip(ops, (operator.eq, operator.ne)))
         for op, f in d.items():
-            q = "a %s inf" % op
+            q = "a {op} inf".format(op=op)
             expected = df[f(df.a, np.inf)]
             result = df.query(q, engine=self.engine, parser=self.parser)
             assert_frame_equal(result, expected)

pandas/tests/frame/test_repr_info.py

@@ -285,7 +285,7 @@ def test_info_shows_column_dtypes(self):
         df.info(buf=buf)
         res = buf.getvalue()
         for i, dtype in enumerate(dtypes):
-            name = "%d    %d non-null %s" % (i, n, dtype)
+            name = "{i:d}    {n:d} non-null {dtype}".format(i=i, n=n, dtype=dtype)
             assert name in res
 
     def test_info_max_cols(self):

pandas/tests/frame/test_timeseries.py

@@ -223,7 +223,7 @@ def test_frame_append_datetime64_col_other_units(self):
         ns_dtype = np.dtype("M8[ns]")
 
         for unit in units:
-            dtype = np.dtype("M8[%s]" % unit)
+            dtype = np.dtype("M8[{unit}]".format(unit=unit))
             vals = np.arange(n, dtype=np.int64).view(dtype)
 
             df = DataFrame({"ints": np.arange(n)}, index=np.arange(n))
@@ -239,7 +239,7 @@ def test_frame_append_datetime64_col_other_units(self):
         df["dates"] = np.arange(n, dtype=np.int64).view(ns_dtype)
 
         for unit in units:
-            dtype = np.dtype("M8[%s]" % unit)
+            dtype = np.dtype("M8[{unit}]".format(unit=unit))
             vals = np.arange(n, dtype=np.int64).view(dtype)
 
             tmp = df.copy()

pandas/tests/frame/test_to_csv.py

@@ -718,7 +718,7 @@ def test_to_csv_withcommas(self):
 
     def test_to_csv_mixed(self):
         def create_cols(name):
-            return ["%s%03d" % (name, i) for i in range(5)]
+            return ["{name}{i:03d}".format(name=name, i=i) for i in range(5)]
 
         df_float = DataFrame(
             np.random.randn(100, 5), dtype="float64", columns=create_cols("float")

pandas/tests/groupby/aggregate/test_other.py

@@ -473,7 +473,8 @@ def test_agg_timezone_round_trip():
     assert result3 == ts
 
     dates = [
-        pd.Timestamp("2016-01-0%d 12:00:00" % i, tz="US/Pacific") for i in range(1, 5)
+        pd.Timestamp("2016-01-0{i:d} 12:00:00".format(i=i), tz="US/Pacific")
+        for i in range(1, 5)
     ]
     df = pd.DataFrame({"A": ["a", "b"] * 2, "B": dates})
     grouped = df.groupby("A")

pandas/tests/groupby/test_apply.py

@@ -265,7 +265,7 @@ def desc3(group):
         result = group.describe()
 
         # names are different
-        result.index.name = "stat_%d" % len(group)
+        result.index.name = "stat_{:d}".format(len(group))
 
         result = result[: len(group)]
         # weirdo

pandas/tests/groupby/test_bin_groupby.py

@@ -95,7 +95,7 @@ def _check(dtype):
         counts = np.zeros(len(out), dtype=np.int64)
         labels = ensure_int64(np.repeat(np.arange(3), np.diff(np.r_[0, bins])))
 
-        func = getattr(groupby, "group_ohlc_%s" % dtype)
+        func = getattr(groupby, "group_ohlc_{dtype}".format(dtype=dtype))
         func(out, counts, obj[:, None], labels)
 
         def _ohlc(group):

pandas/tests/groupby/test_counting.py

@@ -197,8 +197,11 @@ def test_ngroup_respects_groupby_order(self):
     @pytest.mark.parametrize(
         "datetimelike",
         [
-            [Timestamp("2016-05-%02d 20:09:25+00:00" % i) for i in range(1, 4)],
-            [Timestamp("2016-05-%02d 20:09:25" % i) for i in range(1, 4)],
+            [
+                Timestamp("2016-05-{i:02d} 20:09:25+00:00".format(i=i))
+                for i in range(1, 4)
+            ],
+            [Timestamp("2016-05-{i:02d} 20:09:25".format(i=i)) for i in range(1, 4)],
             [Timedelta(x, unit="h") for x in range(1, 4)],
             [Period(freq="2W", year=2017, month=x) for x in range(1, 4)],
         ],

pandas/tests/indexes/datetimelike.py

@@ -36,15 +36,15 @@ def test_str(self):
         # test the string repr
         idx = self.create_index()
         idx.name = "foo"
-        assert not "length=%s" % len(idx) in str(idx)
+        assert not "length={}".format(len(idx)) in str(idx)
         assert "'foo'" in str(idx)
         assert idx.__class__.__name__ in str(idx)
 
         if hasattr(idx, "tz"):
             if idx.tz is not None:
                 assert idx.tz in str(idx)
         if hasattr(idx, "freq"):
-            assert "freq='%s'" % idx.freqstr in str(idx)
+            assert "freq='{idx.freqstr}'".format(idx=idx) in str(idx)
 
     def test_view(self):
         i = self.create_index()

pandas/tests/indexes/datetimes/test_datetime.py

@@ -90,7 +90,7 @@ def test_week_of_month_frequency(self):
     def test_hash_error(self):
         index = date_range("20010101", periods=10)
         with pytest.raises(
-            TypeError, match=("unhashable type: %r" % type(index).__name__)
+            TypeError, match=("unhashable type: {0.__name__!r}".format(type(index)))
         ):
             hash(index)
 

pandas/tests/indexes/multi/test_integrity.py

@@ -253,7 +253,9 @@ def test_rangeindex_fallback_coercion_bug():
 
 def test_hash_error(indices):
     index = indices
-    with pytest.raises(TypeError, match=("unhashable type: %r" % type(index).__name__)):
+    with pytest.raises(
+        TypeError, match=("unhashable type: {0.__name__!r}".format(type(index)))
+    ):
         hash(indices)
 
 

pandas/tests/indexes/period/test_construction.py

@@ -363,7 +363,7 @@ def test_constructor_year_and_quarter(self):
         year = pd.Series([2001, 2002, 2003])
         quarter = year - 2000
         idx = PeriodIndex(year=year, quarter=quarter)
-        strs = ["%dQ%d" % t for t in zip(quarter, year)]
+        strs = ["{t[0]:d}Q{t[1]:d}".format(t=t) for t in zip(quarter, year)]
         lops = list(map(Period, strs))
         p = PeriodIndex(lops)
         tm.assert_index_equal(p, idx)

pandas/tests/indexes/period/test_tools.py

@@ -161,7 +161,7 @@ def test_dti_to_period(self):
     @pytest.mark.parametrize("month", MONTHS)
     def test_to_period_quarterly(self, month):
         # make sure we can make the round trip
-        freq = "Q-%s" % month
+        freq = "Q-{month}".format(month=month)
         rng = period_range("1989Q3", "1991Q3", freq=freq)
         stamps = rng.to_timestamp()
         result = stamps.to_period(freq)

pandas/tests/indexes/test_common.py

@@ -163,7 +163,7 @@ def test_dtype_str(self, indices):
     def test_hash_error(self, indices):
         index = indices
         with pytest.raises(
-            TypeError, match=("unhashable type: %r" % type(index).__name__)
+            TypeError, match=("unhashable type: {0.__name__!r}".format(type(index)))
         ):
             hash(indices)
 

pandas/tests/indexes/timedeltas/test_timedelta.py

@@ -239,7 +239,7 @@ def test_pickle(self):
     def test_hash_error(self):
         index = timedelta_range("1 days", periods=10)
         with pytest.raises(
-            TypeError, match=("unhashable type: %r" % type(index).__name__)
+            TypeError, match=("unhashable type: {0.__name__!r}".format(type(index)))
         ):
             hash(index)
 

pandas/tests/indexing/common.py

@@ -16,7 +16,7 @@
 
 
 def _mklbl(prefix, n):
-    return ["%s%s" % (prefix, i) for i in range(n)]
+    return ["{prefix}{i}".format(prefix=prefix, i=i) for i in range(n)]
 
 
 def _axify(obj, key, axis):
@@ -105,7 +105,7 @@ def setup_method(self, method):
 
             d = dict()
             for t in self._typs:
-                d[t] = getattr(self, "%s_%s" % (o, t), None)
+                d[t] = getattr(self, "{o}_{t}".format(o=o, t=t), None)
 
             setattr(self, o, d)
 
@@ -247,7 +247,7 @@ def _print(result, error=None):
                 # if we are in fails, the ok, otherwise raise it
                 if fails is not None:
                     if isinstance(detail, fails):
-                        result = "ok (%s)" % type(detail).__name__
+                        result = "ok ({0.__name__})".format(type(detail))
                         _print(result)
                         return
 

pandas/tests/indexing/test_iloc.py

@@ -729,7 +729,9 @@ def test_iloc_mask(self):
                     r = expected.get(key)
                     if r != ans:
                         raise AssertionError(
-                            "[%s] does not match [%s], received [%s]" % (key, ans, r)
+                            "[{key}] does not match [{ans}], received [{r}]".format(
+                                key=key, ans=ans, r=r
+                            )
                         )
 
     def test_iloc_non_unique_indexing(self):

pandas/tests/indexing/test_ix.py

@@ -292,8 +292,8 @@ def test_ix_slicing_strings(self):
     def test_ix_setitem_out_of_bounds_axis_0(self):
         df = DataFrame(
             np.random.randn(2, 5),
-            index=["row%s" % i for i in range(2)],
-            columns=["col%s" % i for i in range(5)],
+            index=["row{i}".format(i=i) for i in range(2)],
+            columns=["col{i}".format(i=i) for i in range(5)],
         )
         with catch_warnings(record=True):
             msg = "cannot set by positional indexing with enlargement"
@@ -303,8 +303,8 @@ def test_ix_setitem_out_of_bounds_axis_0(self):
     def test_ix_setitem_out_of_bounds_axis_1(self):
         df = DataFrame(
             np.random.randn(5, 2),
-            index=["row%s" % i for i in range(5)],
-            columns=["col%s" % i for i in range(2)],
+            index=["row{i}".format(i=i) for i in range(5)],
+            columns=["col{i}".format(i=i) for i in range(2)],
         )
         with catch_warnings(record=True):
             msg = "cannot set by positional indexing with enlargement"

pandas/tests/internals/test_internals.py

@@ -110,7 +110,9 @@ def create_block(typestr, placement, item_shape=None, num_offset=0):
     elif typestr in ("complex", "c16", "c8"):
         values = 1.0j * (mat.astype(typestr) + num_offset)
     elif typestr in ("object", "string", "O"):
-        values = np.reshape(["A%d" % i for i in mat.ravel() + num_offset], shape)
+        values = np.reshape(
+            ["A{i:d}".format(i=i) for i in mat.ravel() + num_offset], shape
+        )
     elif typestr in ("b", "bool"):
         values = np.ones(shape, dtype=np.bool_)
     elif typestr in ("datetime", "dt", "M8[ns]"):

pandas/tests/io/excel/test_readers.py

@@ -537,7 +537,7 @@ def test_read_from_file_url(self, read_ext, datapath):
             # fails on some systems
             import platform
 
-            pytest.skip("failing on %s" % " ".join(platform.uname()).strip())
+            pytest.skip("failing on {}".format(" ".join(platform.uname()).strip()))
 
         tm.assert_frame_equal(url_table, local_table)
 

pandas/tests/io/excel/test_style.py

@@ -108,7 +108,7 @@ def custom_converter(css):
         for col1, col2 in zip(wb["frame"].columns, wb["styled"].columns):
             assert len(col1) == len(col2)
             for cell1, cell2 in zip(col1, col2):
-                ref = "%s%d" % (cell2.column, cell2.row)
+                ref = "{cell2.column}{cell2.row:d}".format(cell2=cell2)
                 # XXX: this isn't as strong a test as ideal; we should
                 #      confirm that differences are exclusive
                 if ref == "B2":
@@ -156,7 +156,7 @@ def custom_converter(css):
         for col1, col2 in zip(wb["frame"].columns, wb["custom"].columns):
             assert len(col1) == len(col2)
             for cell1, cell2 in zip(col1, col2):
-                ref = "%s%d" % (cell2.column, cell2.row)
+                ref = "{cell2.column}{cell2.row:d}".format(cell2=cell2)
                 if ref in ("B2", "C3", "D4", "B5", "C6", "D7", "B8", "B9"):
                     assert not cell1.font.bold
                     assert cell2.font.bold

pandas/tests/io/formats/test_style.py

@@ -362,7 +362,7 @@ def color_negative_red(val):
             strings, black otherwise.
             """
             color = "red" if val < 0 else "black"
-            return "color: %s" % color
+            return "color: {color}".format(color=color)
 
         dic = {
             ("a", "d"): [-1.12, 2.11],