Merge pull request #14 from jvachier/jv/ruff

Ruff.

.github/workflows/checks.yml

@@ -22,6 +22,9 @@ jobs:
     - name: Install dependencies
       run: |
         make install
-    - name: Black
+    # - name: Black
+    #   run: |
+    #     make black
+    - name: Ruff
       run: |
-        make black
+        make ruff

.gitignore

@@ -17,17 +17,22 @@
 *.bin
 *.h5
 *.keras
+*.pyc
+*.so
+*.pylintrc
+
 *data/
 *videos/
 *pickle_files/
-*.pyc
+*predictions/
+
 *__pycache__/
 __pycache__/
-*.so
-*.pylintrc
+*.ruff_cache/
+
 
 # Ignore specific file
-test.mp4
+*.mp4
 
 # Ignore all executable files
 *.o
@@ -38,5 +43,4 @@ test.mp4
 *.ipynb
 
 # Ignore all json file
-*.json
-
+*.json

Makefile

@@ -7,4 +7,8 @@ lint:
 
 black:
 	python -m black src/
-
+
+ruff:
+	ruff check src/
+	ruff check --fix src/
+	ruff format src/

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "kth machine learning"
-version = "1.2.2"
+version = "1.3.4"
 description = ""
 authors = ["Jeremy Vachier"]
 readme = "README.md"
@@ -19,10 +19,9 @@ statsmodels = "^0.14.1"
 pylint = "^3.0.3"
 scikit-optimize = "^0.9.0"
 black = "^24.1.1"
+ruff = "^0.2.1"
+pyarrow = "^15.0.0"
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
-
-[tool.pylint.main]
-load-plugins = "pylint_actions"

requirements.txt

@@ -7,4 +7,5 @@ datetime == 5.4
 statsmodels == 0.14.1
 pylint == 3.0.3
 scikit-optimize == 0.9.0
-black == 24.1.1
+black == 24.1.1
+ruff == 0.2.1

ruff.toml

@@ -0,0 +1,77 @@
+# Exclude a variety of commonly ignored directories.
+exclude = [
+    ".bzr",
+    ".direnv",
+    ".eggs",
+    ".git",
+    ".git-rewrite",
+    ".hg",
+    ".ipynb_checkpoints",
+    ".mypy_cache",
+    ".nox",
+    ".pants.d",
+    ".pyenv",
+    ".pytest_cache",
+    ".pytype",
+    ".ruff_cache",
+    ".svn",
+    ".tox",
+    ".venv",
+    ".vscode",
+    "__pypackages__",
+    "_build",
+    "buck-out",
+    "build",
+    "dist",
+    "node_modules",
+    "site-packages",
+    "venv",
+]
+# Same as Black.
+line-length = 88
+indent-width = 4
+
+[lint]
+# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
+# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
+# McCabe complexity (`C901`) by default.
+select = ["E4", "E7", "E9", "F"]
+ignore = []
+
+# Allow fix for all enabled rules (when `--fix`) is provided.
+fixable = ["ALL"]
+unfixable = []
+
+# Allow unused variables when underscore-prefixed.
+dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
+
+[lint.isort]
+case-sensitive = true
+from-first = false
+
+[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"
+
+# Enable auto-formatting of code examples in docstrings. Markdown,
+# reStructuredText code/literal blocks and doctests are all supported.
+#
+# This is currently disabled by default, but it is planned for this
+# to be opt-out in the future.
+docstring-code-format = false
+
+# Set the line length limit used when formatting code snippets in
+# docstrings.
+#
+# This only has an effect when the `docstring-code-format` setting is
+# enabled.
+docstring-code-line-length = "dynamic"

src/main.py

@@ -1,10 +1,9 @@
 import os.path
 from argparse import ArgumentParser
+
 from keras.models import load_model
 
-from src.modules import data_preparation
-from src.modules import models
-from src.modules import loading
+from src.modules import data_preparation, loading, models
 
 
 def main() -> None:
@@ -21,7 +20,7 @@ def main() -> None:
 
     print("Loading data\n")
 
-    load = loading.Loading_files()
+    load = loading.LoadingFiles()
 
     if os.path.isfile("./pickle_files/loading/telemetry") is False:
         (
@@ -40,13 +39,13 @@ def main() -> None:
             df_maintenance,
         ) = load.load_db_file()
 
-    data = data_preparation.Data_Preparation(
+    data = data_preparation.DataPreparation(
         df_telemetry,
         df_maintenance,
         df_errors,
         df_failures,
     )
-    load_data = data_preparation.Load_Save()
+    load_data = data_preparation.LoadSave()
 
     if os.path.isfile("./pickle_files/data_preparation/data_set") is False:
         data.date_to_time()
@@ -60,7 +59,7 @@ def main() -> None:
         print("Models prediction\n")
         model = models.Predictions(data_set_prepared)
 
-        save_model = models.Save_Load_models()
+        save_model = models.SaveLoadmodels()
 
         x_train, x_test, y_train, y_test = model.train_split()
         clf_rfc = model.model_rf(25, 10, "sqrt", 4)
@@ -102,10 +101,10 @@ def main() -> None:
         print("\n")
         print("Models Anomaly Detection\n")
 
-        anomaly_isolation = models.Anomaly_detection_isolationforest(
+        anomaly_isolation = models.AnomalyDetectionIsolationforest(
             df_telemetry, "pressure", 1
         )
-        anomaly_autoencoder = models.Anomaly_detection_autoencoder(
+        anomaly_autoencoder = models.AnomalyDetectionAutoencoder(
             df_telemetry, "pressure", 1, 5
         )
 

src/modules/data_preparation.py

@@ -1,10 +1,11 @@
-from dataclasses import dataclass
 import pickle
+from dataclasses import dataclass
+
 import pandas as pd
 
 
 @dataclass(slots=True)
-class Data_Preparation:
+class DataPreparation:
     """
     Class to prepare data to be ingested by the model
     Input:
@@ -84,7 +85,7 @@ def _merge1(self, features1: pd.DataFrame, feature2: pd.DataFrame) -> pd.DataFra
 
 
 @dataclass(slots=True)
-class Load_Save:
+class LoadSave:
     """
     Class to load and save the prepared data into a pickle format: data_set
     Two functions:

src/modules/loading.py

@@ -1,11 +1,12 @@
-from typing import Tuple
-from dataclasses import dataclass
 import pickle
+from dataclasses import dataclass
+from typing import Tuple
+
 import pandas as pd
 
 
 @dataclass(slots=True)
-class Loading_files:
+class LoadingFiles:
     """
     Class to load and save required data into a pickle format
     """

src/modules/models.py

@@ -1,33 +1,26 @@
+import os.path
+import pickle
 from dataclasses import dataclass
 from typing import Tuple
 
-import pickle
-import os.path
-
-import pandas as pd
-import numpy as np
 import matplotlib.pyplot as plt
-
-
+import numpy as np
+import pandas as pd
+import tensorflow as tf
+from keras.layers import Dense, Input
+from keras.models import Model
+from keras.optimizers.legacy import Adam
+from sklearn import metrics
+from sklearn.ensemble import IsolationForest, RandomForestClassifier
+from sklearn.linear_model import LogisticRegression
 from sklearn.metrics import (
-    precision_recall_fscore_support,
     RocCurveDisplay,
 )
-from sklearn.ensemble import IsolationForest, RandomForestClassifier
+from sklearn.model_selection import learning_curve, train_test_split
+from sklearn.pipeline import Pipeline, make_pipeline
 from sklearn.preprocessing import StandardScaler
-from sklearn.model_selection import train_test_split, learning_curve
-from sklearn.pipeline import make_pipeline, Pipeline
-from sklearn.linear_model import LogisticRegression
-
-from sklearn import metrics
-
 from skopt.searchcv import BayesSearchCV
 
-import tensorflow as tf
-from keras.layers import Input, Dense
-from keras.models import Model
-from keras.optimizers.legacy import Adam
-
 
 @dataclass(slots=True)
 class Predictions:
@@ -294,7 +287,7 @@ def visualization_accuracy(
 
 
 @dataclass(slots=True)
-class Save_Load_models:
+class SaveLoadmodels:
     def save_model_sklearn(
         self, name: str, model: object, prediction: np.array, prediction_proba: np.array
     ) -> None:
@@ -325,7 +318,7 @@ def load_model_sklearn(self, name: str) -> Tuple[object, np.array, np.array]:
 
 
 @dataclass(slots=True)
-class Anomaly_detection_isolationforest:
+class AnomalyDetectionIsolationforest:
     data: pd.DataFrame
     name: str
     machine_name: int
@@ -363,7 +356,7 @@ def visulaization_isolationforest(self) -> None:
 
 
 @dataclass(slots=True)
-class Anomaly_detection_autoencoder:
+class AnomalyDetectionAutoencoder:
     data: pd.DataFrame
     name: str
     machine_name: int