Reformat code

.pre-commit-config.yaml

@@ -0,0 +1,17 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v3.2.0
+  hooks:
+  -   id: trailing-whitespace
+  -   id: end-of-file-fixer
+  -   id: check-yaml
+  -   id: check-added-large-files
+- repo: https://github.com/astral-sh/ruff-pre-commit
+  # Ruff version.
+  rev: 'v0.5.5'
+  hooks:
+    - id: ruff
+      args: [--fix, --exit-non-zero-on-fix]
+    - id: ruff-format

.ruff.toml

@@ -0,0 +1,19 @@
+# Same as Black.
+line-length = 88
+indent-width = 4
+
+# Assume Python 3.11
+target-version = "py311"
+
+[format]
+# Like Black, use double quotes for strings.
+quote-style = "double"
+
+# Like Black, indent with spaces, rather than tabs.
+indent-style = "space"
+
+# Like Black, respect magic trailing commas.
+skip-magic-trailing-comma = false
+
+# Like Black, automatically detect the appropriate line ending.
+line-ending = "auto"

LICENSE.md

@@ -23,4 +23,3 @@ HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY,
 WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
 FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR
 OTHER DEALINGS IN THE SOFTWARE.
-

compile_db.py

@@ -1,5 +1,4 @@
 import argparse
-import ast
 import hyperscan
 import json
 import pickle
@@ -22,7 +21,7 @@
             flags=(hyperscan.HS_FLAG_SINGLEMATCH | hyperscan.HS_FLAG_UTF8,),
         )
         regexes.add(line)
-    except hyperscan.error as e:
+    except hyperscan.error:
         pass
 
 # Build input for the final Hyperscan database

explain.py

@@ -1,6 +1,5 @@
 import argparse
 import io
-import json
 import random
 
 import matplotlib.pyplot as plt
@@ -42,9 +41,9 @@ def update_sample(samples, N, sample):
 )
 
 # See https://github.com/slundberg/shap/issues/1406
-shap.explainers._deep.deep_tf.op_handlers[
-    "AddV2"
-] = shap.explainers._deep.deep_tf.passthrough
+shap.explainers._deep.deep_tf.op_handlers["AddV2"] = (
+    shap.explainers._deep.deep_tf.passthrough
+)
 
 # Load the trained model
 model = tf.keras.models.model_from_json(open("nn_model_sherlock.json").read())
@@ -66,7 +65,7 @@ def update_sample(samples, N, sample):
 # Use SHAP to create a summary plot
 e = shap.DeepExplainer(model, matrix)
 shap_values = e.shap_values(sample)
-feature_names = [l.strip() for l in open("pattern_ids.txt")]
+feature_names = [line.strip() for line in open("pattern_ids.txt")]
 shap.summary_plot(
     shap_values, sample, class_names=class_names, feature_names=feature_names
 )

preprocess.py

@@ -1,8 +1,6 @@
 import argparse
 import ast
-import itertools
 import math
-import json
 import numpy as np
 import os
 import pickle
@@ -12,10 +10,6 @@
 from pyarrow.parquet import ParquetFile
 from tqdm import tqdm
 import hyperscan
-import joblib
-import numpy as np
-import scipy
-import scipy.sparse
 
 
 BATCH_SIZE = 1000

test.py

@@ -47,9 +47,9 @@
 
         y_pred = model.predict(matrix)
         y_pred = np.argmax(y_pred, axis=1)
-        labels_pred[
-            batch * BATCH_SIZE : batch * BATCH_SIZE + len(matrix)
-        ] = le.inverse_transform(y_pred)
+        labels_pred[batch * BATCH_SIZE : batch * BATCH_SIZE + len(matrix)] = (
+            le.inverse_transform(y_pred)
+        )
         batch += 1
         pbar.update(len(matrix))