[skip ci] Code formatting

examples/features/images_cats_and_dogs.py

@@ -14,7 +14,10 @@
 # However, popular larger files shouldn't be a problem (LFW, CelebA).
 data_path = get_data_path() / "cat-and-dog"
 kaggle.api.dataset_download_files(
-    "tongpython/cat-and-dog", path=str(data_path), quiet=False, unzip=True,
+    "tongpython/cat-and-dog",
+    path=str(data_path),
+    quiet=False,
+    unzip=True,
 )
 
 # At the first run, we find that the dataset not only contains images, "_DS_Store" and "cat-and-dog.zip" are present too.

src/pandas_profiling/config.py

@@ -40,16 +40,28 @@ def set_file(self, file_name: Union[str, Path]) -> None:
             "vars": {"cat": {"redact": True}},
         },
         "dark_mode": {
-            "html": {"style": {"theme": "flatly", "primary_color": "#2c3e50",}}
+            "html": {
+                "style": {
+                    "theme": "flatly",
+                    "primary_color": "#2c3e50",
+                }
+            }
         },
         "orange_mode": {
-            "html": {"style": {"theme": "united", "primary_color": "#d34615",}}
+            "html": {
+                "style": {
+                    "theme": "united",
+                    "primary_color": "#d34615",
+                }
+            }
         },
         "explorative": {
             "vars": {
                 "cat": {"unicode": True},
                 "file": {"active": True},
-                "image": {"active": True,},
+                "image": {
+                    "active": True,
+                },
             },
             "n_obs_unique": 10,
             "n_extreme_obs": 10,

src/pandas_profiling/controller/console.py

@@ -84,7 +84,7 @@ def parse_args(args: Union[list, None] = None) -> argparse.Namespace:
 
 
 def main(args=None) -> None:
-    """ Run the `pandas_profiling` package.
+    """Run the `pandas_profiling` package.
 
     Args:
       args: Arguments for the programme (Default value=None).

src/pandas_profiling/model/correlations.py

@@ -112,16 +112,16 @@ def calculate_correlation(
     df: pd.DataFrame, variables: dict, correlation_name: str
 ) -> Union[pd.DataFrame, None]:
     """Calculate the correlation coefficients between variables for the correlation types selected in the config
-        (pearson, spearman, kendall, phi_k, cramers).
+    (pearson, spearman, kendall, phi_k, cramers).
 
-        Args:
-            variables: A dict with column names and variable types.
-            df: The DataFrame with variables.
-            correlation_name:
+    Args:
+        variables: A dict with column names and variable types.
+        df: The DataFrame with variables.
+        correlation_name:
 
-        Returns:
-            The correlation matrices for the given correlation measures. Return None if correlation is empty.
-        """
+    Returns:
+        The correlation matrices for the given correlation measures. Return None if correlation is empty.
+    """
 
     categorical_correlations = {"cramers": cramers_matrix}
     correlation = None

src/pandas_profiling/model/describe.py

@@ -54,7 +54,13 @@ def describe(title: str, df: pd.DataFrame, sample: Optional[dict] = None) -> dic
 
     correlation_names = [
         correlation_name
-        for correlation_name in ["pearson", "spearman", "kendall", "phi_k", "cramers",]
+        for correlation_name in [
+            "pearson",
+            "spearman",
+            "kendall",
+            "phi_k",
+            "cramers",
+        ]
         if config["correlations"][correlation_name]["calculate"].get(bool)
     ]
 

src/pandas_profiling/model/summary.py

@@ -178,9 +178,9 @@ def describe_numeric_1d(series: pd.Series, series_description: dict) -> dict:
         """
 
         def mad(arr):
-            """ Median Absolute Deviation: a "Robust" version of standard deviation.
-                Indices variability of the sample.
-                https://en.wikipedia.org/wiki/Median_absolute_deviation
+            """Median Absolute Deviation: a "Robust" version of standard deviation.
+            Indices variability of the sample.
+            https://en.wikipedia.org/wiki/Median_absolute_deviation
             """
             return np.median(np.abs(arr - np.median(arr)))
 

src/pandas_profiling/report/structure/report.py

@@ -174,7 +174,9 @@ def get_duplicates_items(duplicates: pd.DataFrame):
     if duplicates is not None and len(duplicates) > 0:
         items.append(
             Duplicate(
-                duplicate=duplicates, name="Most frequent", anchor_id="duplicates",
+                duplicate=duplicates,
+                name="Most frequent",
+                anchor_id="duplicates",
             )
         )
     return items
@@ -192,7 +194,11 @@ def get_definition_items(definitions: pd.DataFrame):
     items = []
     if definitions is not None and len(definitions) > 0:
         items.append(
-            Duplicate(duplicate=definitions, name="Columns", anchor_id="definitions",)
+            Duplicate(
+                duplicate=definitions,
+                name="Columns",
+                anchor_id="definitions",
+            )
         )
     return items
 

src/pandas_profiling/report/structure/variables/render_categorical.py

@@ -261,7 +261,10 @@ def render_categorical_unicode(summary, varid, redact):
     ]
 
     return Container(
-        citems, name="Unicode", sequence_type="tabs", anchor_id=f"{varid}unicode",
+        citems,
+        name="Unicode",
+        sequence_type="tabs",
+        anchor_id=f"{varid}unicode",
     )
 
 

src/pandas_profiling/report/structure/variables/render_file.py

@@ -51,7 +51,10 @@ def render_file(summary):
             )
 
     file_tab = Container(
-        file_tabs, name="File", sequence_type="tabs", anchor_id=f"{varid}file",
+        file_tabs,
+        name="File",
+        sequence_type="tabs",
+        anchor_id=f"{varid}file",
     )
 
     template_variables["bottom"].content["items"].append(file_tab)

src/pandas_profiling/report/structure/variables/render_image.py

@@ -177,7 +177,10 @@ def render_image(summary):
     image_items.append(image_shape)
 
     image_tab = Container(
-        image_items, name="Image", sequence_type="tabs", anchor_id=f"{varid}image",
+        image_items,
+        name="Image",
+        sequence_type="tabs",
+        anchor_id=f"{varid}image",
     )
 
     template_variables["bottom"].content["items"].append(image_tab)

src/pandas_profiling/report/structure/variables/render_path.py

@@ -114,7 +114,10 @@ def render_path(summary):
     ]
 
     path_tab = Container(
-        path_items, name="Path", sequence_type="tabs", anchor_id=f"{varid}path",
+        path_items,
+        name="Path",
+        sequence_type="tabs",
+        anchor_id=f"{varid}path",
     )
 
     template_variables["bottom"].content["items"].append(path_tab)

src/pandas_profiling/report/structure/variables/render_real.py

@@ -227,7 +227,9 @@ def render_real(summary):
     )
 
     template_variables["bottom"] = Container(
-        [statistics, hist, fq, evs], sequence_type="tabs", anchor_id=f"{varid}bottom",
+        [statistics, hist, fq, evs],
+        sequence_type="tabs",
+        anchor_id=f"{varid}bottom",
     )
 
     return template_variables

src/pandas_profiling/serialize_report.py

@@ -129,11 +129,11 @@ def dump(self, output_file: Union[Path, str]):
 
     def load(self, load_file: Union[Path, str], ignore_config: bool = False):
         """
-       Load ProfileReport from file
+        Load ProfileReport from file
 
-       Raises:
-            ValueError: if the DataFrame or Config do not match with the current ProfileReport
-       """
+        Raises:
+             ValueError: if the DataFrame or Config do not match with the current ProfileReport
+        """
         if not isinstance(load_file, Path):
             load_file = Path(str(load_file))
 

src/pandas_profiling/utils/common.py

@@ -10,7 +10,7 @@
 
 
 def update(d: dict, u: Mapping) -> dict:
-    """ Recursively update a dict.
+    """Recursively update a dict.
 
     Args:
         d: Dictionary to update.

src/pandas_profiling/visualisation/context.py

@@ -12,8 +12,7 @@
 
 @contextlib.contextmanager
 def manage_matplotlib_context():
-    """Return a context manager for temporarily changing matplotlib unit registries and rcParams.
-    """
+    """Return a context manager for temporarily changing matplotlib unit registries and rcParams."""
     originalRcParams = matplotlib.rcParams.copy()
 
     ## Credits for this style go to the ggplot and seaborn packages.

src/pandas_profiling/visualisation/plot.py

@@ -171,7 +171,9 @@ def correlation_matrix(data: pd.DataFrame, vmin: int = -1) -> str:
         legend_elements = [Patch(facecolor=cmap(np.nan), label="invalid\ncoefficient")]
 
         plt.legend(
-            handles=legend_elements, loc="upper right", handleheight=2.5,
+            handles=legend_elements,
+            loc="upper right",
+            handleheight=2.5,
         )
 
     axes_cor.set_xticks(np.arange(0, data.shape[0], float(data.shape[0]) / len(labels)))

tests/unit/test_dataset_schema.py

@@ -17,7 +17,11 @@ def test_dataset_schema():
     )
 
     # Length left out due to correlation with weight.
-    report = df.profile_report(title="Dataset schema", dataset=metadata, minimal=True,)
+    report = df.profile_report(
+        title="Dataset schema",
+        dataset=metadata,
+        minimal=True,
+    )
 
     html = report.to_html()
 
@@ -36,7 +40,9 @@ def test_dataset_schema_empty():
 
     # Length left out due to correlation with weight.
     report = df.profile_report(
-        title="Dataset schema empty", minimal=True, dataset=None,
+        title="Dataset schema empty",
+        minimal=True,
+        dataset=None,
     )
 
     html = report.to_html()

tests/unit/test_html_export.py

@@ -76,7 +76,8 @@ def test_html_export_cdn(test_output_dir):
     )
 
     profile = df.profile_report(
-        minimal=True, html={"inline": False, "use_local_assets": False},
+        minimal=True,
+        html={"inline": False, "use_local_assets": False},
     )
 
     report = test_output_dir / "cdn.html"
@@ -96,7 +97,8 @@ def test_html_export_theme(test_output_dir):
     )
 
     profile = df.profile_report(
-        minimal=True, html={"inline": False, "style": {"theme": "united"}},
+        minimal=True,
+        html={"inline": False, "style": {"theme": "united"}},
     )
 
     report = test_output_dir / "united.html"