CLN: Remove redundant int() calls

Author: eumiro

asv_bench/benchmarks/arithmetic.py

@@ -122,18 +122,18 @@ def setup(self, op):
         n_rows = 500
 
         # construct dataframe with 2 blocks
-        arr1 = np.random.randn(n_rows, int(n_cols / 2)).astype("f8")
-        arr2 = np.random.randn(n_rows, int(n_cols / 2)).astype("f4")
+        arr1 = np.random.randn(n_rows, n_cols // 2).astype("f8")
+        arr2 = np.random.randn(n_rows, n_cols // 2).astype("f4")
         df = pd.concat(
             [pd.DataFrame(arr1), pd.DataFrame(arr2)], axis=1, ignore_index=True
         )
         # should already be the case, but just to be sure
         df._consolidate_inplace()
 
         # TODO: GH#33198 the setting here shoudlnt need two steps
-        arr1 = np.random.randn(n_rows, int(n_cols / 4)).astype("f8")
-        arr2 = np.random.randn(n_rows, int(n_cols / 2)).astype("i8")
-        arr3 = np.random.randn(n_rows, int(n_cols / 4)).astype("f8")
+        arr1 = np.random.randn(n_rows, n_cols // 4).astype("f8")
+        arr2 = np.random.randn(n_rows, n_cols // 2).astype("i8")
+        arr3 = np.random.randn(n_rows, n_cols // 4).astype("f8")
         df2 = pd.concat(
             [pd.DataFrame(arr1), pd.DataFrame(arr2), pd.DataFrame(arr3)],
             axis=1,

asv_bench/benchmarks/frame_methods.py

@@ -263,7 +263,7 @@ class Repr:
     def setup(self):
         nrows = 10000
         data = np.random.randn(nrows, 10)
-        arrays = np.tile(np.random.randn(3, int(nrows / 100)), 100)
+        arrays = np.tile(np.random.randn(3, nrows // 100), 100)
         idx = MultiIndex.from_arrays(arrays)
         self.df3 = DataFrame(data, index=idx)
         self.df4 = DataFrame(data, index=np.random.randn(nrows))
@@ -648,9 +648,9 @@ class Describe:
     def setup(self):
         self.df = DataFrame(
             {
-                "a": np.random.randint(0, 100, int(1e6)),
-                "b": np.random.randint(0, 100, int(1e6)),
-                "c": np.random.randint(0, 100, int(1e6)),
+                "a": np.random.randint(0, 100, 10 ** 6),
+                "b": np.random.randint(0, 100, 10 ** 6),
+                "c": np.random.randint(0, 100, 10 ** 6),
             }
         )
 

asv_bench/benchmarks/inference.py

@@ -42,7 +42,7 @@ class ToNumericDowncast:
     ]
 
     N = 500000
-    N2 = int(N / 2)
+    N2 = N // 2
 
     data_dict = {
         "string-int": ["1"] * N2 + [2] * N2,

asv_bench/benchmarks/rolling.py

@@ -171,7 +171,7 @@ class PeakMemFixedWindowMinMax:
     params = ["min", "max"]
 
     def setup(self, operation):
-        N = int(1e6)
+        N = 10 ** 6
         arr = np.random.random(N)
         self.roll = pd.Series(arr).rolling(2)
 
@@ -233,7 +233,7 @@ class GroupbyLargeGroups:
 
     def setup(self):
         N = 100000
-        self.df = pd.DataFrame({"A": [1, 2] * int(N / 2), "B": np.random.randn(N)})
+        self.df = pd.DataFrame({"A": [1, 2] * (N // 2), "B": np.random.randn(N)})
 
     def time_rolling_multiindex_creation(self):
         self.df.groupby("A").rolling(3).mean()

asv_bench/benchmarks/series_methods.py

@@ -284,7 +284,7 @@ def time_dir_strings(self):
 class SeriesGetattr:
     # https://github.com/pandas-dev/pandas/issues/19764
     def setup(self):
-        self.s = Series(1, index=date_range("2012-01-01", freq="s", periods=int(1e6)))
+        self.s = Series(1, index=date_range("2012-01-01", freq="s", periods=10 ** 6))
 
     def time_series_datetimeindex_repr(self):
         getattr(self.s, "a", None)

asv_bench/benchmarks/timeseries.py

@@ -346,7 +346,7 @@ def time_iso8601_tz_spaceformat(self):
 class ToDatetimeNONISO8601:
     def setup(self):
         N = 10000
-        half = int(N / 2)
+        half = N // 2
         ts_string_1 = "March 1, 2018 12:00:00+0400"
         ts_string_2 = "March 1, 2018 12:00:00+0500"
         self.same_offset = [ts_string_1] * N
@@ -376,7 +376,7 @@ def setup(self):
         self.same_offset = ["10/11/2018 00:00:00.045-07:00"] * N
         self.diff_offset = [
             f"10/11/2018 00:00:00.045-0{offset}:00" for offset in range(10)
-        ] * int(N / 10)
+        ] * (N // 10)
 
     def time_exact(self):
         to_datetime(self.s2, format="%d%b%y")

pandas/_testing/__init__.py

@@ -901,7 +901,7 @@ def _create_missing_idx(nrows, ncols, density, random_state=None):
         random_state = np.random.RandomState(random_state)
 
     # below is cribbed from scipy.sparse
-    size = int(np.round((1 - density) * nrows * ncols))
+    size = round((1 - density) * nrows * ncols)
     # generate a few more to ensure unique values
     min_rows = 5
     fac = 1.02

pandas/core/arrays/datetimes.py

@@ -572,7 +572,7 @@ def __iter__(self):
             data = self.asi8
             length = len(self)
             chunksize = 10000
-            chunks = int(length / chunksize) + 1
+            chunks = (length // chunksize) + 1
             for i in range(chunks):
                 start_i = i * chunksize
                 end_i = min((i + 1) * chunksize, length)

pandas/core/arrays/timedeltas.py

@@ -338,7 +338,7 @@ def __iter__(self):
             data = self.asi8
             length = len(self)
             chunksize = 10000
-            chunks = int(length / chunksize) + 1
+            chunks = (length // chunksize) + 1
             for i in range(chunks):
                 start_i = i * chunksize
                 end_i = min((i + 1) * chunksize, length)

pandas/core/generic.py

@@ -5336,7 +5336,7 @@ def sample(
         elif n is not None and frac is None and n % 1 != 0:
             raise ValueError("Only integers accepted as `n` values")
         elif n is None and frac is not None:
-            n = int(round(frac * axis_length))
+            n = round(frac * axis_length)
         elif n is not None and frac is not None:
             raise ValueError("Please enter a value for `frac` OR `n`, not both")
 

pandas/core/tools/datetimes.py

@@ -122,7 +122,7 @@ def should_cache(
             return False
 
         if len(arg) <= 5000:
-            check_count = int(len(arg) * 0.1)
+            check_count = len(arg) // 10
         else:
             check_count = 500
     else:

pandas/io/formats/csvs.py

@@ -282,7 +282,7 @@ def _generate_multiindex_header_rows(self) -> Iterator[List[Label]]:
 
     def _save_body(self) -> None:
         nrows = len(self.data_index)
-        chunks = int(nrows / self.chunksize) + 1
+        chunks = (nrows // self.chunksize) + 1
         for i in range(chunks):
             start_i = i * self.chunksize
             end_i = min(start_i + self.chunksize, nrows)

pandas/io/formats/string.py

@@ -160,7 +160,7 @@ def _fit_strcols_to_terminal_width(self, strcols: List[List[str]]) -> str:
         counter = 0
         while adj_dif > 0 and n_cols > 1:
             counter += 1
-            mid = int(round(n_cols / 2.0))
+            mid = round(n_cols / 2)
             mid_ix = col_lens.index[mid]
             col_len = col_lens[mid_ix]
             # adjoin adds one

pandas/io/sql.py

@@ -905,7 +905,7 @@ def insert(self, chunksize: Optional[int] = None, method: Optional[str] = None):
         elif chunksize == 0:
             raise ValueError("chunksize argument should be non-zero")
 
-        chunks = int(nrows / chunksize) + 1
+        chunks = (nrows // chunksize) + 1
 
         with self.pd_sql.run_transaction() as conn:
             for i in range(chunks):

pandas/plotting/_matplotlib/converter.py

@@ -182,7 +182,7 @@ def __call__(self, x, pos=0) -> str:
         """
         fmt = "%H:%M:%S.%f"
         s = int(x)
-        msus = int(round((x - s) * 1e6))
+        msus = round((x - s) * 1e6)
         ms = msus // 1000
         us = msus % 1000
         m, s = divmod(s, 60)

pandas/plotting/_matplotlib/tools.py

@@ -61,12 +61,10 @@ def _get_layout(nplots: int, layout=None, layout_type: str = "box") -> Tuple[int
 
         nrows, ncols = layout
 
-        # Python 2 compat
-        ceil_ = lambda x: int(ceil(x))
         if nrows == -1 and ncols > 0:
-            layout = nrows, ncols = (ceil_(float(nplots) / ncols), ncols)
+            layout = nrows, ncols = (ceil(nplots / ncols), ncols)
         elif ncols == -1 and nrows > 0:
-            layout = nrows, ncols = (nrows, ceil_(float(nplots) / nrows))
+            layout = nrows, ncols = (nrows, ceil(nplots / nrows))
         elif ncols <= 0 and nrows <= 0:
             msg = "At least one dimension of layout must be positive"
             raise ValueError(msg)

pandas/tests/generic/test_generic.py

@@ -305,14 +305,14 @@ def test_truncate_out_of_bounds(self):
         # GH11382
 
         # small
-        shape = [int(2e3)] + ([1] * (self._ndim - 1))
+        shape = [2000] + ([1] * (self._ndim - 1))
         small = self._construct(shape, dtype="int8", value=1)
         self._compare(small.truncate(), small)
         self._compare(small.truncate(before=0, after=3e3), small)
         self._compare(small.truncate(before=-1, after=2e3), small)
 
         # big
-        shape = [int(2e6)] + ([1] * (self._ndim - 1))
+        shape = [2_000_000] + ([1] * (self._ndim - 1))
         big = self._construct(shape, dtype="int8", value=1)
         self._compare(big.truncate(), big)
         self._compare(big.truncate(before=0, after=3e6), big)

pandas/tests/io/pytables/test_store.py

@@ -3164,7 +3164,7 @@ def test_select_iterator_many_empty_frames(self, setup_path):
         # GH 8014
         # using iterator and where clause can return many empty
         # frames.
-        chunksize = int(1e4)
+        chunksize = 10_000
 
         # with iterator, range limited to the first chunk
         with ensure_clean_store(setup_path) as store:

pandas/tests/plotting/test_datetimelike.py

@@ -1075,7 +1075,7 @@ def test_time_musec(self):
         for t, l in zip(ticks, labels):
             m, s = divmod(int(t), 60)
 
-            us = int(round((t - int(t)) * 1e6))
+            us = round((t - int(t)) * 1e6)
 
             h, m = divmod(m, 60)
             rs = l.get_text()

pandas/tests/series/methods/test_fillna.py

@@ -231,7 +231,7 @@ def test_timedelta_fillna(self, frame_or_series):
         expected = frame_or_series(expected)
         tm.assert_equal(result, expected)
 
-        result = obj.fillna(np.timedelta64(int(1e9)))
+        result = obj.fillna(np.timedelta64(10 ** 9))
         expected = Series(
             [
                 timedelta(seconds=1),

pandas/tests/tools/test_to_timedelta.py

@@ -184,7 +184,7 @@ def test_to_timedelta_float(self):
         # https://github.com/pandas-dev/pandas/issues/25077
         arr = np.arange(0, 1, 1e-6)[-10:]
         result = pd.to_timedelta(arr, unit="s")
-        expected_asi8 = np.arange(999990000, int(1e9), 1000, dtype="int64")
+        expected_asi8 = np.arange(999990000, 10 ** 9, 1000, dtype="int64")
         tm.assert_numpy_array_equal(result.asi8, expected_asi8)
 
     def test_to_timedelta_coerce_strings_unit(self):