chore: fmt black

pyhdx/batch_processing.py

@@ -29,7 +29,9 @@ class DataFile(object):
     filepath_or_buffer: Union[Path, StringIO]
 
     def __post_init__(self):
-        warnings.warn("Will be removed in favour of the `hdxms-datasets` package ", DeprecationWarning)
+        warnings.warn(
+            "Will be removed in favour of the `hdxms-datasets` package ", DeprecationWarning
+        )
 
     @cached_property
     def data(self) -> pd.DataFrame:
@@ -62,8 +64,9 @@ def __init__(
         # filter_kwargs: Optional[dict[str, Any]] = None,
         # correction_kwargs: Optional[dict[str, Any]] = None,
     ) -> None:
-
-        warnings.warn("Will be removed in favour of the `hdxms-datasets` package ", DeprecationWarning)
+        warnings.warn(
+            "Will be removed in favour of the `hdxms-datasets` package ", DeprecationWarning
+        )
         self.hdx_spec = hdx_spec
         self.data_files: dict[str, DataFile] = {}
 

pyhdx/cli.py

@@ -11,6 +11,8 @@
 from pyhdx.datasets import DataVault
 
 app = typer.Typer()
+
+
 @app.command()
 def serve(
     scheduler_address: Optional[str] = typer.Option(None, help="Address for dask scheduler to use"),
@@ -61,6 +63,8 @@ def serve(
 
 
 datasets_app = typer.Typer(help="Manage HDX datasets")
+
+
 @datasets_app.command()
 def fetch(num: int = typer.Option(10, min=1, help="Maximum number of datasets to download")):
     """Update the datasets from the PyHDX repository"""
@@ -72,6 +76,7 @@ def fetch(num: int = typer.Option(10, min=1, help="Maximum number of datasets to
         for data_id in tqdm(todo):
             vault.fetch_dataset(data_id)
 
+
 @datasets_app.command()
 def clear():
     """Clear the local dataset cache"""
@@ -81,6 +86,7 @@ def clear():
 
 app.add_typer(datasets_app, name="datasets")
 
+
 @app.callback()
 def callback():
     pass

pyhdx/config.py

@@ -146,6 +146,7 @@ def context(self, settings: dict) -> Generator[PyHDXConfig, None, None]:
         finally:
             cfg.conf = original_config
 
+
 def valid_config() -> bool:
     """Checks if the current config file in the user home directory is a valid config
     file for the current pyhdx version.

pyhdx/datasets.py

@@ -1 +1 @@
-from hdxms_datasets import *
+from hdxms_datasets import *

pyhdx/fileIO.py

@@ -80,7 +80,9 @@ def read_header(file_obj: Union[TextIO, BinaryIO], comment: str = "#") -> List[s
     return header
 
 
-def parse_header(filepath_or_buffer: Union[Path[str], str, StringIO, BytesIO], comment: str = "#") -> dict:
+def parse_header(
+    filepath_or_buffer: Union[Path[str], str, StringIO, BytesIO], comment: str = "#"
+) -> dict:
     """
     Reads the header from a file and returns JSON metadata from header lines marked as comment.
 

pyhdx/plot.py

@@ -615,7 +615,6 @@ def linear_bars(
     sort=False,
     **figure_kwargs,
 ):
-
     # input data should always be 3 levels
     # grouping is done by the first level
     # second level gives each bar
@@ -1141,6 +1140,7 @@ def get(self, item, default=None):
         except KeyError:
             return default
 
+
 # should be a frozen dataclas
 CMAP_NORM_DEFAULTS = ColorTransforms()
 

pyhdx/process.py

@@ -255,7 +255,9 @@ def filter_peptides(
 
     """
 
-    warnings.warn("`filter_peptides` will be moved to the `hdxms-datasets` package", DeprecationWarning)
+    warnings.warn(
+        "`filter_peptides` will be moved to the `hdxms-datasets` package", DeprecationWarning
+    )
     if state:
         df = df[df["state"] == state]
 

pyhdx/support.py

@@ -848,6 +848,7 @@ def array_intersection(arrays: Iterable[np.ndarray], fields: Iterable[str]) -> l
 
     return selected
 
+
 # https://stackoverflow.com/questions/31174295/getattr-and-setattr-on-nested-subobjects-chained-properties
 def rsetattr(obj, attr, val):
     pre, _, post = attr.rpartition(".")

pyhdx/web/controllers.py

@@ -47,7 +47,8 @@
 from pyhdx.datasets import HDXDataSet, DataVault, DataFile
 from pyhdx.fitting_torch import TorchFitResultSet
 from pyhdx.models import (
-    PeptideUptakeModel, HDXMeasurement,
+    PeptideUptakeModel,
+    HDXMeasurement,
 )
 from pyhdx.plot import (
     dG_scatter_figure,
@@ -293,7 +294,9 @@ class PeptideFileInputControl(PyHDXControlPanel):
 
     batch_file = param.Parameter(doc="Batch file input:")
 
-    dataset_id = param.Selector(label="Dataset ID", doc="Dataset ID to load from hdxms-datasets database")
+    dataset_id = param.Selector(
+        label="Dataset ID", doc="Dataset ID to load from hdxms-datasets database"
+    )
 
     nd_control = param.Boolean(
         default=False, precedence=-1, doc="Whether to allow users to input a ND control"
@@ -410,7 +413,7 @@ def __init__(self, parent, **params):
             todo = list(missing_datasets)[:num]
             for data_id in tqdm(todo):
                 self.data_vault.fetch_dataset(data_id)
-        self.param['dataset_id'].objects = self.data_vault.datasets
+        self.param["dataset_id"].objects = self.data_vault.datasets
         if self.data_vault.datasets:
             self.dataset_id = self.data_vault.datasets[0]
 
@@ -512,19 +515,17 @@ def _update_mode(self):
                 "measurement_name",
                 "download_spec_button",
             },
-            "Batch": {
-                "input_files_label",
-                "input_files",
-                "batch_file",
-                "batch_file_label"
-            },
+            "Batch": {"input_files_label", "input_files", "batch_file", "batch_file_label"},
             "Database": {
                 "dataset_id",
-            }
+            },
         }
 
-        #widget_dict.pop(self.input_mode)
-        excluded = set.union(*(v for k, v in widget_dict.items() if k != self.input_mode)) - widget_dict[self.input_mode]
+        # widget_dict.pop(self.input_mode)
+        excluded = (
+            set.union(*(v for k, v in widget_dict.items() if k != self.input_mode))
+            - widget_dict[self.input_mode]
+        )
         #
         #
         # if self.input_mode == "Manual":
@@ -814,7 +815,9 @@ def _action_load_datasets(self) -> None:
         """Load all specified HDX measurements"""
         if self.input_mode == "Manual":
             data_src = self.data_file_history
-            dataset = HDXDataSet(data_id=uuid.uuid4().hex, data_files=data_src, hdx_spec=self.hdx_spec)
+            dataset = HDXDataSet(
+                data_id=uuid.uuid4().hex, data_files=data_src, hdx_spec=self.hdx_spec
+            )
         elif self.input_mode == "Batch":
             if self.hdxm_list:
                 self.parent.logger.info("Cannot add data in batch after manually inputting data")
@@ -831,7 +834,9 @@ def _action_load_datasets(self) -> None:
             self.state_spec = hdx_spec["states"]
             self.data_spec = hdx_spec["data_files"]
 
-            dataset = HDXDataSet(data_id=uuid.uuid4().hex, data_files=data_src, hdx_spec=self.hdx_spec)
+            dataset = HDXDataSet(
+                data_id=uuid.uuid4().hex, data_files=data_src, hdx_spec=self.hdx_spec
+            )
             self.param["hdxm_list"].objects = dataset.states
         elif self.input_mode == "Database":
             if self.dataset_id is None:
@@ -841,18 +846,18 @@ def _action_load_datasets(self) -> None:
             self.parent.logger.info(f"Loaded dataset {dataset.data_id} from hdxms database")
 
             try:
-                authors = ", ".join([author['name'] for author in dataset.metadata['authors']])
+                authors = ", ".join([author["name"] for author in dataset.metadata["authors"]])
                 self.parent.logger.info(f"Author(s): {authors}")
             except KeyError:
                 pass
 
-            publications = dataset.metadata.get('publications', [])
+            publications = dataset.metadata.get("publications", [])
             if publications:
                 for pub in publications:
-                    pub_str = pub['title']
-                    if 'DOI' in pub:
+                    pub_str = pub["title"]
+                    if "DOI" in pub:
                         pub_str += f' ([{pub["DOI"]}](https://doi.org/{pub["DOI"]}))'
-                    elif 'URL' in pub:
+                    elif "URL" in pub:
                         pub_str += f' ([URL]({pub["URL"]}))'
                     self.parent.logger.info("Publication: " + pub_str)
         else:

templates/02_load_from_yaml.py

@@ -17,7 +17,7 @@
 hdx_spec = yaml.safe_load(yaml_stream)
 input_dir = current_dir.parent / "tests" / "test_data" / "input"
 
-#%%
+# %%
 
 dataset = HDXDataSet.from_spec(
     hdx_spec,
@@ -26,9 +26,9 @@
 
 print(dataset.describe())
 
-#%%
+# %%
 # Load an HDX measurement by state name
-hdxm = HDXMeasurement.from_dataset(dataset, state='SecB_tetramer')
+hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_tetramer")
 print(hdxm)
 print(hdxm.timepoints)
 
@@ -39,6 +39,6 @@
 print(hdxm.timepoints)
 
 
-#%%
+# %%
 hdxm_set = HDXMeasurementSet.from_dataset(dataset)
 print(hdxm_set)

templates/03_initial_guesses.py

@@ -27,7 +27,9 @@
     hdxm = HDXMeasurement.from_dataset(dataset, state=name)
 
     # Save sequence info + intrinsic rates
-    dataframe_to_file(output_dir / f"{name}_intrinsic_rates.csv", hdxm.coverage.protein, fmt='pprint')
+    dataframe_to_file(
+        output_dir / f"{name}_intrinsic_rates.csv", hdxm.coverage.protein, fmt="pprint"
+    )
 
     fr = fit_rates_weighted_average(hdxm, client=client)
     dataframe_to_file(output_dir / f"{name}_rates_guess.csv", fr.output)

tests/test_fileIO.py

@@ -40,9 +40,7 @@ def hdxm() -> HDXMeasurement:
     peptides_corrected = correct_d_uptake(peptides_control)
 
     temperature, pH = 273.15 + 30, 8.0
-    hdxm = HDXMeasurement(
-        peptides_corrected, temperature=temperature, pH=pH, c_term=155
-    )
+    hdxm = HDXMeasurement(peptides_corrected, temperature=temperature, pH=pH, c_term=155)
 
     return hdxm
 
@@ -122,6 +120,7 @@ def test_read_write_tables(tmp_path):
     assert len(lines) == 38
     assert lines[0].strip() == pyhdx.VERSION_STRING
 
+
 def test_load_save_fitresult(tmp_path, fit_result: TorchFitResult, hdxm: HDXMeasurement):
     # todo missing read batch result test
 

tests/test_fitting.py

@@ -43,8 +43,8 @@ def dataset() -> HDXDataSet:
     hdx_spec = yaml.safe_load(yaml_pth.read_text())
 
     # add truncated tetramer state
-    hdx_spec['states']['SecB_tetramer_red'] = copy.deepcopy(hdx_spec['states']['SecB_tetramer'])
-    hdx_spec['states']['SecB_tetramer_red']['peptides']['experiment']['query'] = ["stop < 40"]
+    hdx_spec["states"]["SecB_tetramer_red"] = copy.deepcopy(hdx_spec["states"]["SecB_tetramer"])
+    hdx_spec["states"]["SecB_tetramer_red"]["peptides"]["experiment"]["query"] = ["stop < 40"]
 
     dataset = HDXDataSet.from_spec(hdx_spec, data_dir=input_dir)
 
@@ -53,24 +53,24 @@ def dataset() -> HDXDataSet:
 
 @pytest.fixture()
 def hdxm_apo(dataset: HDXDataSet) -> HDXMeasurement:
-    with cfg.context({'analysis.drop_first': 1}):
-        hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_tetramer", d_percentage=100.)
+    with cfg.context({"analysis.drop_first": 1}):
+        hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_tetramer", d_percentage=100.0)
 
     return hdxm
 
 
 @pytest.fixture()
 def hdxm_dimer(dataset: HDXDataSet) -> HDXMeasurement:
-    with cfg.context({'analysis.drop_first': 1}):
-        hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_dimer", d_percentage=100.)
+    with cfg.context({"analysis.drop_first": 1}):
+        hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_dimer", d_percentage=100.0)
 
     return hdxm
 
 
 @pytest.fixture()
 def hdxm_apo_red(dataset: HDXDataSet) -> HDXMeasurement:
-    with cfg.context({'analysis.drop_first': 1}):
-        hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_tetramer_red", d_percentage=100.)
+    with cfg.context({"analysis.drop_first": 1}):
+        hdxm = HDXMeasurement.from_dataset(dataset, state="SecB_tetramer_red", d_percentage=100.0)
 
     return hdxm
 
@@ -260,16 +260,28 @@ def test_batch_fit(hdxm_apo: HDXMeasurement, hdxm_dimer: HDXMeasurement, tmp_pat
     assert errors.shape == (hdx_set.Ns, hdx_set.Np, hdx_set.Nt)
 
     test = fr_global.get_peptide_mse().fillna(-1)
-    name_mapping = {'SecB his dimer apo': 'SecB_dimer', 'SecB WT apo': 'SecB_tetramer'}
-    ref = csv_to_dataframe(output_dir / "ecSecB_batch_peptide_mse.csv").fillna(-1).rename(columns=name_mapping)
+    name_mapping = {"SecB his dimer apo": "SecB_dimer", "SecB WT apo": "SecB_tetramer"}
+    ref = (
+        csv_to_dataframe(output_dir / "ecSecB_batch_peptide_mse.csv")
+        .fillna(-1)
+        .rename(columns=name_mapping)
+    )
     assert_frame_equal(test, ref, atol=1e-1, rtol=5e-1)
 
     test = fr_global.get_residue_mse().fillna(-1)
-    ref = csv_to_dataframe(output_dir / "ecSecB_batch_residue_mse.csv").fillna(-1).rename(columns=name_mapping)
+    ref = (
+        csv_to_dataframe(output_dir / "ecSecB_batch_residue_mse.csv")
+        .fillna(-1)
+        .rename(columns=name_mapping)
+    )
     assert_frame_equal(test, ref, atol=1e-1, rtol=5e-1)
 
     test = fr_global.losses.fillna(-1)
-    ref = csv_to_dataframe(output_dir / "ecSecB_batch_loss.csv").fillna(-1).rename(columns=name_mapping)
+    ref = (
+        csv_to_dataframe(output_dir / "ecSecB_batch_loss.csv")
+        .fillna(-1)
+        .rename(columns=name_mapping)
+    )
     assert_frame_equal(test, ref, atol=1e-3, rtol=1e-2)
 
     # test alignment fit
@@ -281,11 +293,11 @@ def test_batch_fit(hdxm_apo: HDXMeasurement, hdxm_dimer: HDXMeasurement, tmp_pat
     hdx_set.add_alignment(list(mock_alignment.values()))
 
     gibbs_guess = hdx_set[0].guess_deltaG(guess["rate"])  # Guesses from first measurement
-    aligned_result = fit_gibbs_global_batch_aligned(
-        hdx_set, gibbs_guess, r1=2, r2=5, epochs=1000
-    )
+    aligned_result = fit_gibbs_global_batch_aligned(hdx_set, gibbs_guess, r1=2, r2=5, epochs=1000)
     output = aligned_result.output
-    check_df = csv_to_dataframe(output_dir / "ecSecB_batch_aligned.csv").rename(columns=name_mapping)
+    check_df = csv_to_dataframe(output_dir / "ecSecB_batch_aligned.csv").rename(
+        columns=name_mapping
+    )
     states = ["SecB_tetramer", "SecB_dimer"]
 
     for state in states: