[MNT] Updating pre-commit hooks and corresponding changes (#7109)

Maintenance only changes. 1. pre-commit autoupdate 2. pre-commit run --all-files `ruff` detected a bunch of problems in different notebooks and solved most of them manually. Rest of them are done manually.
sktime · Sep 14, 2024 · 67acec5 · 67acec5
1 parent 73bc154
commit 67acec5
Show file tree

Hide file tree

Showing 14 changed files with 93 additions and 109 deletions.
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
@@ -16,7 +16,7 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.5.7
+    rev: v0.6.4
     hooks:
       - id: ruff-format
       - id: ruff

diff --git a/examples/01_forecasting.ipynb b/examples/01_forecasting.ipynb
@@ -5648,7 +5648,9 @@
     "fh_ins = -np.arange(len(y_train))  # in-sample forecasting horizon\n",
     "y_pred = forecaster.fit(y_train).predict(fh=fh_ins)\n",
     "\n",
-    "plot_series(y_train, y_pred, yt, labels=[\"y_train\", \"fitted linear trend\", \"residuals\"]);"
+    "plot_series(\n",
+    "    y_train, y_pred, yt, labels=[\"y_train\", \"fitted linear trend\", \"residuals\"]\n",
+    ");"
    ]
   },
   {

diff --git a/examples/01a_forecasting_sklearn.ipynb b/examples/01a_forecasting_sklearn.ipynb
@@ -191,8 +191,7 @@
     "\n",
     "\n",
     "def split_into_train_test(data, in_num, fh):\n",
-    "    \"\"\"\n",
-    "    Splits the series into train and test sets.\n",
+    "    \"\"\"Split the series into train and test sets.\n",
     "\n",
     "    Each step takes multiple points as inputs\n",
     "    :param data: an individual TS\n",

diff --git a/examples/01c_forecasting_hierarchical_global.ipynb b/examples/01c_forecasting_hierarchical_global.ipynb
@@ -4527,9 +4527,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sktime.utils._testing.hierarchical import _make_hierarchical\n",
     "from sklearn.model_selection import train_test_split\n",
     "\n",
+    "from sktime.utils._testing.hierarchical import _make_hierarchical\n",
+    "\n",
     "data = _make_hierarchical(\n",
     "    hierarchy_levels=(100, 1), max_timepoints=10, min_timepoints=10, n_columns=1\n",
     ")\n",
@@ -5278,9 +5279,10 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "from sktime.utils._testing.hierarchical import _make_hierarchical\n",
     "from sklearn.model_selection import train_test_split\n",
     "\n",
+    "from sktime.utils._testing.hierarchical import _make_hierarchical\n",
+    "\n",
     "data = _make_hierarchical(\n",
     "    hierarchy_levels=(100, 1), max_timepoints=10, min_timepoints=10, n_columns=2\n",
     ")\n",
@@ -5290,9 +5292,7 @@
     "X_train, X_test, y_train, y_test = train_test_split(\n",
     "    x, y, test_size=0.1, train_size=0.9, shuffle=False\n",
     ")\n",
-    "y_test = y_test.groupby(level=0).apply(\n",
-    "    lambda x: x.droplevel(0).iloc[:-3]\n",
-    ")"
+    "y_test = y_test.groupby(level=0).apply(lambda x: x.droplevel(0).iloc[:-3])"
    ]
   },
   {

diff --git a/examples/05_graphical_pipelines.ipynb b/examples/05_graphical_pipelines.ipynb
@@ -153,7 +153,6 @@
     }
    ],
    "source": [
-    "\n",
     "general_pipeline = Pipeline()\n",
     "differencer = Differencer()\n",
     "\n",
@@ -392,7 +391,7 @@
    ],
    "source": [
     "pipe = Pipeline()\n",
-    "pipe.set_config(warnings=\"off\")\n"
+    "pipe.set_config(warnings=\"off\")"
    ]
   },
   {

diff --git a/examples/06_distances_kernels_alignment.ipynb b/examples/06_distances_kernels_alignment.ipynb
@@ -946,6 +946,7 @@
    "source": [
     "# example 1: flat Gaussian RBF kernel between time series\n",
     "from sklearn.gaussian_process.kernels import RBF\n",
+    "\n",
     "from sktime.dists_kernels import FlatDist\n",
     "\n",
     "flat_gaussian_tskernel = FlatDist(RBF(length_scale=10))\n",
@@ -1329,7 +1330,11 @@
    "source": [
     "from sktime.utils.plotting import plot_series\n",
     "\n",
-    "plot_series(X1_al.reset_index(drop=True), X2_al.reset_index(drop=True), labels=[\"leaf_1\", \"leaf_2\"])"
+    "plot_series(\n",
+    "    X1_al.reset_index(drop=True),\n",
+    "    X2_al.reset_index(drop=True),\n",
+    "    labels=[\"leaf_1\", \"leaf_2\"],\n",
+    ")"
    ]
   },
   {
@@ -1363,7 +1368,8 @@
     }
    ],
    "source": [
-    "# the AlignerDTW class (based on dtw-python) doesn't just align, it also produces a distance\n",
+    "# the AlignerDTW class (based on dtw-python) doesn't just align\n",
+    "# it also produces a distance\n",
     "aligner.get_tags()"
    ]
   },

diff --git a/examples/forecasting/window_splitters.ipynb b/examples/forecasting/window_splitters.ipynb
diff --git a/examples/transformation/fracdiff/example_exercise.ipynb b/examples/transformation/fracdiff/example_exercise.ipynb
diff --git a/examples/transformation/fracdiff/example_howto.ipynb b/examples/transformation/fracdiff/example_howto.ipynb
diff --git a/examples/transformation/fracdiff/example_prado.ipynb b/examples/transformation/fracdiff/example_prado.ipynb
diff --git a/examples/transformation/interpolation.ipynb b/examples/transformation/interpolation.ipynb
@@ -123,15 +123,13 @@
     }
    ],
    "source": [
-    "# randomly cut the data series in-place\n",
-    "\n",
-    "\n",
     "def random_cut(df):\n",
+    "    \"\"\"Randomly cut the data series in-place.\"\"\"\n",
     "    for row_i in range(df.shape[0]):\n",
     "        for dim_i in range(df.shape[1]):\n",
     "            ts = df.iloc[row_i][f\"dim_{dim_i}\"]\n",
     "            df.iloc[row_i][f\"dim_{dim_i}\"] = pd.Series(\n",
-    "                ts.tolist()[: random.randint(len(ts) - 5, len(ts) - 3)]\n",
+    "                ts.tolist()[: random.randint(len(ts) - 5, len(ts) - 3)]  # noqa: S311\n",
     "            )  # here is a problem\n",
     "\n",
     "\n",

diff --git a/examples/transformation/minirocket.ipynb b/examples/transformation/minirocket.ipynb
@@ -51,9 +51,9 @@
     "from sklearn.pipeline import make_pipeline\n",
     "from sklearn.preprocessing import StandardScaler\n",
     "\n",
-    "from sktime.datasets import load_arrow_head  # univariate dataset\n",
-    "from sktime.datasets import load_basic_motions  # multivariate dataset\n",
     "from sktime.datasets import (\n",
+    "    load_arrow_head,  # univariate dataset\n",
+    "    load_basic_motions,  # multivariate dataset\n",
     "    load_japanese_vowels,  # multivariate dataset with unequal length\n",
     ")\n",
     "from sktime.transformations.panel.rocket import (\n",

diff --git a/examples/transformation/rocket.ipynb b/examples/transformation/rocket.ipynb
@@ -63,8 +63,10 @@
     "from sklearn.linear_model import RidgeClassifierCV\n",
     "from sklearn.pipeline import make_pipeline\n",
     "\n",
-    "from sktime.datasets import load_arrow_head  # univariate dataset\n",
-    "from sktime.datasets import load_basic_motions  # multivariate dataset\n",
+    "from sktime.datasets import (\n",
+    "    load_arrow_head,  # univariate dataset\n",
+    "    load_basic_motions,  # multivariate dataset\n",
+    ")\n",
     "from sktime.transformations.panel.rocket import Rocket"
    ]
   },

diff --git a/examples/transformation/signature_method.ipynb b/examples/transformation/signature_method.ipynb
@@ -221,9 +221,9 @@
     ")\n",
     "\n",
     "# The simply transform the stream data\n",
-    "print(\"Raw data shape is: {}\".format(train_x.shape))\n",
+    "print(f\"Raw data shape is: {train_x.shape}\")\n",
     "train_signature_x = signature_transform.fit_transform(train_x)\n",
-    "print(\"Signature shape is: {}\".format(train_signature_x.shape))"
+    "print(f\"Signature shape is: {train_signature_x.shape}\")"
    ]
   },
   {
@@ -261,7 +261,7 @@
     "# Evaluate\n",
     "test_signature_x = signature_transform.transform(test_x)\n",
     "test_pred = model.predict(test_signature_x)\n",
-    "print(\"Accuracy: {:.3f}%\".format(accuracy_score(test_y, test_pred)))"
+    "print(f\"Accuracy: {accuracy_score(test_y, test_pred):.3f}%\")"
    ]
   },
   {
@@ -341,11 +341,7 @@
     "test_preds = best_classifier.predict(test_x)\n",
     "train_score = accuracy_score(train_y, train_preds)\n",
     "test_score = accuracy_score(test_y, test_preds)\n",
-    "print(\n",
-    "    \"Train acc: {:.3f}%  |  Test acc: {:.3f}%\".format(\n",
-    "        train_score * 100, test_score * 100\n",
-    "    )\n",
-    ")"
+    "print(f\"Train acc: {train_score * 100:.3f}%  |  Test acc: {test_score * 100:.3f}%\")"
    ]
   },
   {