From c697a66f9f258c3775d4f8eb545600362653cdd6 Mon Sep 17 00:00:00 2001
From: Srinivas Reddy Thatiparthy <thatiparthysreenivas@gmail.com>
Date: Tue, 12 Nov 2019 15:59:26 +0530
Subject: [PATCH 1/3] Update .format(...) strings to f-expressions

---
 asv_bench/benchmarks/categoricals.py | 10 +++++-----
 asv_bench/benchmarks/gil.py          |  4 ++--
 asv_bench/benchmarks/index_object.py |  2 +-
 asv_bench/benchmarks/io/csv.py       |  8 ++++----
 asv_bench/benchmarks/io/excel.py     |  2 +-
 asv_bench/benchmarks/io/hdf.py       |  2 +-
 asv_bench/benchmarks/io/json.py      |  4 ++--
 asv_bench/benchmarks/io/msgpack.py   |  2 +-
 asv_bench/benchmarks/io/pickle.py    |  2 +-
 asv_bench/benchmarks/io/sql.py       |  4 ++--
 asv_bench/benchmarks/io/stata.py     |  4 ++--
 asv_bench/benchmarks/timedelta.py    |  6 +++---
 12 files changed, 25 insertions(+), 25 deletions(-)

diff --git a/asv_bench/benchmarks/categoricals.py b/asv_bench/benchmarks/categoricals.py
index 4384ccb7fa8b3..e21d859d18c8c 100644
--- a/asv_bench/benchmarks/categoricals.py
+++ b/asv_bench/benchmarks/categoricals.py
@@ -84,7 +84,7 @@ class ValueCounts:
 
     def setup(self, dropna):
         n = 5 * 10 ** 5
-        arr = ["s{:04d}".format(i) for i in np.random.randint(0, n // 10, size=n)]
+        arr = [f"s{i:04d}" for i in np.random.randint(0, n // 10, size=n)]
         self.ts = pd.Series(arr).astype("category")
 
     def time_value_counts(self, dropna):
@@ -102,7 +102,7 @@ def time_rendering(self):
 class SetCategories:
     def setup(self):
         n = 5 * 10 ** 5
-        arr = ["s{:04d}".format(i) for i in np.random.randint(0, n // 10, size=n)]
+        arr = [f"s{i:04d}" for i in np.random.randint(0, n // 10, size=n)]
         self.ts = pd.Series(arr).astype("category")
 
     def time_set_categories(self):
@@ -112,7 +112,7 @@ def time_set_categories(self):
 class RemoveCategories:
     def setup(self):
         n = 5 * 10 ** 5
-        arr = ["s{:04d}".format(i) for i in np.random.randint(0, n // 10, size=n)]
+        arr = [f"s{i:04d}" for i in np.random.randint(0, n // 10, size=n)]
         self.ts = pd.Series(arr).astype("category")
 
     def time_remove_categories(self):
@@ -166,7 +166,7 @@ def setup(self, dtype):
         sample_size = 100
         arr = [i for i in np.random.randint(0, n // 10, size=n)]
         if dtype == "object":
-            arr = ["s{:04d}".format(i) for i in arr]
+            arr = [f"s{i:04d}" for i in arr]
         self.sample = np.random.choice(arr, sample_size)
         self.series = pd.Series(arr).astype("category")
 
@@ -225,7 +225,7 @@ def setup(self, index):
         elif index == "non_monotonic":
             self.data = pd.Categorical.from_codes([0, 1, 2] * N, categories=categories)
         else:
-            raise ValueError("Invalid index param: {}".format(index))
+            raise ValueError(f"Invalid index param: {index}")
 
         self.scalar = 10000
         self.list = list(range(10000))
diff --git a/asv_bench/benchmarks/gil.py b/asv_bench/benchmarks/gil.py
index 43c8594b8c8df..97b670ae640ac 100644
--- a/asv_bench/benchmarks/gil.py
+++ b/asv_bench/benchmarks/gil.py
@@ -252,11 +252,11 @@ def setup(self, dtype):
             "object": DataFrame(
                 "foo",
                 index=range(rows),
-                columns=["object%03d".format(i) for i in range(5)],
+                columns=[f"object%03d" for i in range(5)],
             ),
         }
 
-        self.fname = "__test_{}__.csv".format(dtype)
+        self.fname = f"__test_{dtype}__.csv"
         df = data[dtype]
         df.to_csv(self.fname)
 
diff --git a/asv_bench/benchmarks/index_object.py b/asv_bench/benchmarks/index_object.py
index a94960d494707..f1d5209ac65ef 100644
--- a/asv_bench/benchmarks/index_object.py
+++ b/asv_bench/benchmarks/index_object.py
@@ -146,7 +146,7 @@ class Indexing:
 
     def setup(self, dtype):
         N = 10 ** 6
-        self.idx = getattr(tm, "make{}Index".format(dtype))(N)
+        self.idx = getattr(tm, f"make{dtype}Index")(N)
         self.array_mask = (np.arange(N) % 3) == 0
         self.series_mask = Series(self.array_mask)
         self.sorted = self.idx.sort_values()
diff --git a/asv_bench/benchmarks/io/csv.py b/asv_bench/benchmarks/io/csv.py
index 9b8599b0a1b64..85c4bbdbefdf6 100644
--- a/asv_bench/benchmarks/io/csv.py
+++ b/asv_bench/benchmarks/io/csv.py
@@ -202,7 +202,7 @@ def setup(self, sep, thousands):
         data = np.random.randn(N, K) * np.random.randint(100, 10000, (N, K))
         df = DataFrame(data)
         if thousands is not None:
-            fmt = ":{}".format(thousands)
+            fmt = f":{thousands}"
             fmt = "{" + fmt + "}"
             df = df.applymap(lambda x: fmt.format(x))
         df.to_csv(self.fname, sep=sep)
@@ -231,7 +231,7 @@ def setup(self, sep, decimal, float_precision):
         floats = [
             "".join(random.choice(string.digits) for _ in range(28)) for _ in range(15)
         ]
-        rows = sep.join(["0{}".format(decimal) + "{}"] * 3) + "\n"
+        rows = sep.join([f"0{decimal}" + "{}"] * 3) + "\n"
         data = rows * 5
         data = data.format(*floats) * 200  # 1000 x 3 strings csv
         self.StringIO_input = StringIO(data)
@@ -310,7 +310,7 @@ class ReadCSVCachedParseDates(StringIORewind):
 
     def setup(self, do_cache):
         data = (
-            "\n".join("10/{}".format(year) for year in range(2000, 2100)) + "\n"
+            "\n".join(f"10/{year}" for year in range(2000, 2100)) + "\n"
         ) * 10
         self.StringIO_input = StringIO(data)
 
@@ -336,7 +336,7 @@ class ReadCSVMemoryGrowth(BaseIO):
     def setup(self):
         with open(self.fname, "w") as f:
             for i in range(self.num_rows):
-                f.write("{i}\n".format(i=i))
+                f.write(f"{i}\n")
 
     def mem_parser_chunks(self):
         # see gh-24805.
diff --git a/asv_bench/benchmarks/io/excel.py b/asv_bench/benchmarks/io/excel.py
index c97cf768e27d9..75d87140488e3 100644
--- a/asv_bench/benchmarks/io/excel.py
+++ b/asv_bench/benchmarks/io/excel.py
@@ -14,7 +14,7 @@ def _generate_dataframe():
     C = 5
     df = DataFrame(
         np.random.randn(N, C),
-        columns=["float{}".format(i) for i in range(C)],
+        columns=[f"float{i}" for i in range(C)],
         index=date_range("20000101", periods=N, freq="H"),
     )
     df["object"] = tm.makeStringIndex(N)
diff --git a/asv_bench/benchmarks/io/hdf.py b/asv_bench/benchmarks/io/hdf.py
index b78dc63d17130..88c1a3dc48ea4 100644
--- a/asv_bench/benchmarks/io/hdf.py
+++ b/asv_bench/benchmarks/io/hdf.py
@@ -115,7 +115,7 @@ def setup(self, format):
         C = 5
         self.df = DataFrame(
             np.random.randn(N, C),
-            columns=["float{}".format(i) for i in range(C)],
+            columns=[f"float{i}" for i in range(C)],
             index=date_range("20000101", periods=N, freq="H"),
         )
         self.df["object"] = tm.makeStringIndex(N)
diff --git a/asv_bench/benchmarks/io/json.py b/asv_bench/benchmarks/io/json.py
index 5c1d39776b91c..8f037e94e0095 100644
--- a/asv_bench/benchmarks/io/json.py
+++ b/asv_bench/benchmarks/io/json.py
@@ -20,7 +20,7 @@ def setup(self, orient, index):
         }
         df = DataFrame(
             np.random.randn(N, 5),
-            columns=["float_{}".format(i) for i in range(5)],
+            columns=[f"float_{i}" for i in range(5)],
             index=indexes[index],
         )
         df.to_json(self.fname, orient=orient)
@@ -43,7 +43,7 @@ def setup(self, index):
         }
         df = DataFrame(
             np.random.randn(N, 5),
-            columns=["float_{}".format(i) for i in range(5)],
+            columns=[f"float_{i}" for i in range(5)],
             index=indexes[index],
         )
         df.to_json(self.fname, orient="records", lines=True)
diff --git a/asv_bench/benchmarks/io/msgpack.py b/asv_bench/benchmarks/io/msgpack.py
index f5038602539ab..a5b8b81bed85b 100644
--- a/asv_bench/benchmarks/io/msgpack.py
+++ b/asv_bench/benchmarks/io/msgpack.py
@@ -15,7 +15,7 @@ def setup(self):
         C = 5
         self.df = DataFrame(
             np.random.randn(N, C),
-            columns=["float{}".format(i) for i in range(C)],
+            columns=[f"float{i}" for i in range(C)],
             index=date_range("20000101", periods=N, freq="H"),
         )
         self.df["object"] = tm.makeStringIndex(N)
diff --git a/asv_bench/benchmarks/io/pickle.py b/asv_bench/benchmarks/io/pickle.py
index 647e9d27dec9d..12620656dd2bf 100644
--- a/asv_bench/benchmarks/io/pickle.py
+++ b/asv_bench/benchmarks/io/pickle.py
@@ -13,7 +13,7 @@ def setup(self):
         C = 5
         self.df = DataFrame(
             np.random.randn(N, C),
-            columns=["float{}".format(i) for i in range(C)],
+            columns=[f"float{i}" for i in range(C)],
             index=date_range("20000101", periods=N, freq="H"),
         )
         self.df["object"] = tm.makeStringIndex(N)
diff --git a/asv_bench/benchmarks/io/sql.py b/asv_bench/benchmarks/io/sql.py
index fe84c869717e3..6cc7f56ae3d65 100644
--- a/asv_bench/benchmarks/io/sql.py
+++ b/asv_bench/benchmarks/io/sql.py
@@ -19,7 +19,7 @@ def setup(self, connection):
             "sqlite": sqlite3.connect(":memory:"),
         }
         self.table_name = "test_type"
-        self.query_all = "SELECT * FROM {}".format(self.table_name)
+        self.query_all = f"SELECT * FROM {self.table_name}"
         self.con = con[connection]
         self.df = DataFrame(
             {
@@ -58,7 +58,7 @@ def setup(self, connection, dtype):
             "sqlite": sqlite3.connect(":memory:"),
         }
         self.table_name = "test_type"
-        self.query_col = "SELECT {} FROM {}".format(dtype, self.table_name)
+        self.query_col = f"SELECT {dtype} FROM {self.table_name}"
         self.con = con[connection]
         self.df = DataFrame(
             {
diff --git a/asv_bench/benchmarks/io/stata.py b/asv_bench/benchmarks/io/stata.py
index 28829785d72e9..f3125f8598418 100644
--- a/asv_bench/benchmarks/io/stata.py
+++ b/asv_bench/benchmarks/io/stata.py
@@ -17,7 +17,7 @@ def setup(self, convert_dates):
         C = self.C = 5
         self.df = DataFrame(
             np.random.randn(N, C),
-            columns=["float{}".format(i) for i in range(C)],
+            columns=[f"float{i}" for i in range(C)],
             index=date_range("20000101", periods=N, freq="H"),
         )
         self.df["object"] = tm.makeStringIndex(self.N)
@@ -47,7 +47,7 @@ def setup(self, convert_dates):
         for i in range(10):
             missing_data = np.random.randn(self.N)
             missing_data[missing_data < 0] = np.nan
-            self.df["missing_{0}".format(i)] = missing_data
+            self.df[f"missing_{i}"] = missing_data
         self.df.to_stata(self.fname, self.convert_dates)
 
 
diff --git a/asv_bench/benchmarks/timedelta.py b/asv_bench/benchmarks/timedelta.py
index 828134b80aa3d..37418d752f833 100644
--- a/asv_bench/benchmarks/timedelta.py
+++ b/asv_bench/benchmarks/timedelta.py
@@ -14,8 +14,8 @@ def setup(self):
         self.str_days = []
         self.str_seconds = []
         for i in self.ints:
-            self.str_days.append("{0} days".format(i))
-            self.str_seconds.append("00:00:{0:02d}".format(i))
+            self.str_days.append(f"{i} days")
+            self.str_seconds.append(f"00:00:{i:02d}")
 
     def time_convert_int(self):
         to_timedelta(self.ints, unit="s")
@@ -34,7 +34,7 @@ class ToTimedeltaErrors:
 
     def setup(self, errors):
         ints = np.random.randint(0, 60, size=10000)
-        self.arr = ["{0} days".format(i) for i in ints]
+        self.arr = [f"{i} days" for i in ints]
         self.arr[-1] = "apple"
 
     def time_convert(self, errors):

From 4ca5c72093d0b36506a5c8afdc59bacfaf51d892 Mon Sep 17 00:00:00 2001
From: Srinivas Reddy Thatiparthy <thatiparthysreenivas@gmail.com>
Date: Thu, 14 Nov 2019 09:36:00 +0530
Subject: [PATCH 2/3] Run black formatting on changed files

---
 asv_bench/benchmarks/gil.py    | 4 +---
 asv_bench/benchmarks/io/csv.py | 4 +---
 pandas/core/algorithms.py      | 2 +-
 pandas/core/groupby/grouper.py | 6 +++++-
 pandas/io/common.py            | 4 ++--
 5 files changed, 10 insertions(+), 10 deletions(-)

diff --git a/asv_bench/benchmarks/gil.py b/asv_bench/benchmarks/gil.py
index 97b670ae640ac..4683619d145e1 100644
--- a/asv_bench/benchmarks/gil.py
+++ b/asv_bench/benchmarks/gil.py
@@ -250,9 +250,7 @@ def setup(self, dtype):
                 np.random.randn(rows, cols), index=date_range("1/1/2000", periods=rows)
             ),
             "object": DataFrame(
-                "foo",
-                index=range(rows),
-                columns=[f"object%03d" for i in range(5)],
+                "foo", index=range(rows), columns=[f"object%03d" for i in range(5)],
             ),
         }
 
diff --git a/asv_bench/benchmarks/io/csv.py b/asv_bench/benchmarks/io/csv.py
index 85c4bbdbefdf6..adb3dd95e3574 100644
--- a/asv_bench/benchmarks/io/csv.py
+++ b/asv_bench/benchmarks/io/csv.py
@@ -309,9 +309,7 @@ class ReadCSVCachedParseDates(StringIORewind):
     param_names = ["do_cache"]
 
     def setup(self, do_cache):
-        data = (
-            "\n".join(f"10/{year}" for year in range(2000, 2100)) + "\n"
-        ) * 10
+        data = ("\n".join(f"10/{year}" for year in range(2000, 2100)) + "\n") * 10
         self.StringIO_input = StringIO(data)
 
     def time_read_csv_cached(self, do_cache):
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index b49a9d7957d51..ea75d46048e63 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -1159,7 +1159,7 @@ def compute(self, method):
         n = min(n, narr)
 
         kth_val = algos.kth_smallest(arr.copy(), n - 1)
-        ns, = np.nonzero(arr <= kth_val)
+        (ns,) = np.nonzero(arr <= kth_val)
         inds = ns[arr[ns].argsort(kind="mergesort")]
 
         if self.keep != "all":
diff --git a/pandas/core/groupby/grouper.py b/pandas/core/groupby/grouper.py
index e6e3ee62459ca..0edc3e4a4ff3d 100644
--- a/pandas/core/groupby/grouper.py
+++ b/pandas/core/groupby/grouper.py
@@ -288,7 +288,11 @@ def __init__(
             if self.name is None:
                 self.name = index.names[level]
 
-            self.grouper, self._codes, self._group_index = index._get_grouper_for_level(  # noqa: E501
+            (
+                self.grouper,
+                self._codes,
+                self._group_index,
+            ) = index._get_grouper_for_level(  # noqa: E501
                 self.grouper, level
             )
 
diff --git a/pandas/io/common.py b/pandas/io/common.py
index 0bef14e4999c7..e08fd37e65ad9 100644
--- a/pandas/io/common.py
+++ b/pandas/io/common.py
@@ -109,7 +109,7 @@ def _is_url(url) -> bool:
 
 
 def _expand_user(
-    filepath_or_buffer: FilePathOrBuffer[AnyStr]
+    filepath_or_buffer: FilePathOrBuffer[AnyStr],
 ) -> FilePathOrBuffer[AnyStr]:
     """Return the argument with an initial component of ~ or ~user
        replaced by that user's home directory.
@@ -139,7 +139,7 @@ def _validate_header_arg(header) -> None:
 
 
 def _stringify_path(
-    filepath_or_buffer: FilePathOrBuffer[AnyStr]
+    filepath_or_buffer: FilePathOrBuffer[AnyStr],
 ) -> FilePathOrBuffer[AnyStr]:
     """Attempt to convert a path-like object to a string.
 

From 27cdc551eb665c66fcc8d78d5b0a996c2ef068a7 Mon Sep 17 00:00:00 2001
From: Srinivas Reddy Thatiparthy <thatiparthysreenivas@gmail.com>
Date: Thu, 14 Nov 2019 23:39:19 +0530
Subject: [PATCH 3/3] Remove unnecessary variable

---
 asv_bench/benchmarks/gil.py | 2 +-
 pandas/core/algorithms.py   | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

diff --git a/asv_bench/benchmarks/gil.py b/asv_bench/benchmarks/gil.py
index 4683619d145e1..860c6cc6192bb 100644
--- a/asv_bench/benchmarks/gil.py
+++ b/asv_bench/benchmarks/gil.py
@@ -250,7 +250,7 @@ def setup(self, dtype):
                 np.random.randn(rows, cols), index=date_range("1/1/2000", periods=rows)
             ),
             "object": DataFrame(
-                "foo", index=range(rows), columns=[f"object%03d" for i in range(5)],
+                "foo", index=range(rows), columns=["object%03d" for _ in range(5)]
             ),
         }
 
diff --git a/pandas/core/algorithms.py b/pandas/core/algorithms.py
index ea75d46048e63..b49a9d7957d51 100644
--- a/pandas/core/algorithms.py
+++ b/pandas/core/algorithms.py
@@ -1159,7 +1159,7 @@ def compute(self, method):
         n = min(n, narr)
 
         kth_val = algos.kth_smallest(arr.copy(), n - 1)
-        (ns,) = np.nonzero(arr <= kth_val)
+        ns, = np.nonzero(arr <= kth_val)
         inds = ns[arr[ns].argsort(kind="mergesort")]
 
         if self.keep != "all":