pre-commit changes

.github/workflows/requirements_precommit.txt

@@ -1,8 +1,8 @@
-pycln==2.4.0
-isort==5.12.0
-yapf==0.40.1
+docformatter==1.7.5
 flake8==7.0.0
-pylint==3.1.0
 interrogate==1.7.0
-docformatter==1.7.5
-pre-commit
+isort==5.12.0
+pre-commit
+pycln==2.4.0
+pylint==3.1.0
+yapf==0.40.1

docs/source/getting_started.rst

@@ -17,5 +17,3 @@ These series of notebook-based tutorials are designed to introduce the reader to
    getting_started/01_processing_03_processing_workflow.ipynb
    getting_started/02_analysis_01_dendrograms_waveforms.ipynb
    getting_started/02_analysis_02_timewindow_cluster_comparison.ipynb
-
-

pre-commit-hooks/.pre-commit-config.yaml

@@ -22,12 +22,12 @@ repos:
     -   id: pycln
         args: [--all]
 -   repo: https://github.com/pycqa/isort
-    rev: 5.12.0
+    rev: 5.13.2
     hooks:
     -   id: isort
         args: [-l 120]
 -   repo: https://github.com/google/yapf
-    rev: v0.40.1
+    rev: v0.40.2
     hooks:
     -   id: yapf
         args: [-vv, -r, "--style={based_on_style: pep8, column_limit: 120}", -i]
@@ -42,12 +42,12 @@ repos:
     -   id: python-bandit-vulnerability-check
         args: [-ll, --skip, "B321,B402,B301", --recursive, .]
 -   repo: https://github.com/Lucas-C/pre-commit-hooks-safety
-    rev: v1.3.1
+    rev: v1.3.3
     hooks:
     -   id: python-safety-dependencies-check
         files: requirements.txt
 -   repo: https://github.com/pylint-dev/pylint
-    rev: v3.1.0
+    rev: v3.2.2
     hooks:
     -   id: pylint
         name: pylint
@@ -62,7 +62,7 @@ repos:
              "--load-plugins=pylint.extensions.docparams", # Load an extension
            ]
 -   repo: https://github.com/MarcoGorelli/madforhooks # sorts environment.yml
-    rev: 0.3.0
+    rev: 0.4.1
     hooks:
     -   id: conda-env-sorter
 -   repo: https://github.com/pryorda/dockerfilelint-precommit-hooks

readme.MD

@@ -33,7 +33,7 @@ To help you get started with ScatCluster, we have created a set of notebooks loc
 
 The Processing section includes three notebooks that prepare your data for interpretation:
 
-- **01_processing_01_choose_network.ipynb**: This notebook offers an interactive means to determine the best network architecture for your dataset. 
+- **01_processing_01_choose_network.ipynb**: This notebook offers an interactive means to determine the best network architecture for your dataset.
 
 - **01_processing_02_set_config.ipynb**: In this notebook, you will set the parameters for your experiment and specify the location where results will be stored. This step is crucial for ensuring that your data processing and analysis are properly configured.
 

scatcluster/analysis/crosstab.py

@@ -103,7 +103,7 @@ def _build_crosstab_data(self,
         else:
             raise ValueError(
                 f"Provided Normalization is not valid. This can be 'None' or [{normalization_options}]. Kindly see "
-                f"https://pandas.pydata.org/docs/reference/api/pandas.crosstab.html for more info.")
+                f'https://pandas.pydata.org/docs/reference/api/pandas.crosstab.html for more info.')
         ct_data = ct_data.sort_index(ascending=False)
         return ct_data, factor_difference, fowlkes_mallows_score(df_preds.predictions_1, df_preds.predictions_2)
 

scatcluster/analysis/waveforms.py

@@ -31,7 +31,7 @@ def plot_waveforms_per_cluster(self, clusters: List[int] = None, waveforms_n_sam
         stream = self.load_data(starttime=UTCDateTime(self.data_sample_starttime),
                                 endtime=UTCDateTime(self.data_sample_endtime),
                                 channel=self.data_channel)
-        channel_list = sorted(list(set([trace.stats.channel for trace in stream])))
+        channel_list = sorted(trace.stats.channel for trace in stream)
 
         if clusters is not None:
             classes = clusters

scatcluster/helper.py

@@ -52,7 +52,7 @@ def tqdm_importer():
     """
     A function that imports the tqdm module based on the current environment.
     """
-    if is_notebook:
+    if is_notebook():
         pass
     else:
         pass

scatcluster/processing/ica.py

@@ -13,7 +13,6 @@
 from scipy.signal import medfilt
 from sklearn.decomposition import FastICA
 from sklearn.metrics import explained_variance_score, mean_squared_error
-from sklearn.preprocessing import RobustScaler
 
 from scatcluster.helper import demad, list_of_strings
 
@@ -86,7 +85,8 @@ def process_ICA_single(self,
         # check if reduction exists already
         if os.path.exists(ica_model_path) and self.ica_overwrite_previous_models is False:
             print('  Using pre-calculated model')
-            model = pickle.load(open(ica_model_path, 'rb'))
+            with open(ica_model_path, 'rb') as f:
+                model = pickle.load(f)
         else:
             # else fit
             kwargs['max_iter'] = 1000 if kwargs.get('max_iter') is None else kwargs.get('max_iter')
@@ -180,14 +180,13 @@ def preload_ICA(self, num_ICA: int) -> None:
         if not os.path.exists(f'{self.data_savepath}ICA/{self.data_network}_{self.data_station}_{self.data_location}_'
                               f'{self.network_name}_dimension_{num_ICA}.pickle'):
             raise ValueError(
-                f"The supplied number of ICAs {num_ICA} has not been computed. Choose another number for the ICAs or "
+                f'The supplied number of ICAs {num_ICA} has not been computed. Choose another number for the ICAs or '
                 f"calcate using 'process_ICA_single'")
 
-        self.ica = pickle.load(
-            open(
-                f'{self.data_savepath}ICA/{self.data_network}_{self.data_station}_{self.data_location}_'
-                f'{self.network_name}_dimension_{num_ICA}.pickle', 'rb'))
-
+        ica_file = f'{self.data_savepath}ICA/{self.data_network}_{self.data_station}_{self.data_location}_' + \
+                    f'{self.network_name}_dimension_{num_ICA}.pickle'
+        with open(ica_file, 'rb') as f:
+            self.ica = pickle.load(f)
         ica_results = np.load(f'{self.data_savepath}data/{self.data_network}_{self.data_station}_{self.data_location}_'
                               f'{self.network_name}_features_{num_ICA}.npz')
         self.ica_features = ica_results['features']