fix(eda): scipy version issue

Author: jinglinpeng

.github/workflows/ci.yml

@@ -46,7 +46,7 @@ jobs:
           poetry run pyright --version
 
       - name: Check if the code is formatted
-        run: poetry run black --check --quiet dataprep
+        run: poetry run black --check dataprep
 
       - name: Type check the project
         run: poetry run pyright dataprep || true

dataprep/clean/clean_country.py

@@ -271,7 +271,7 @@ def _format_country(
     return result, 2 if val != result else 3
 
 
-@lru_cache(maxsize=2 ** 20)
+@lru_cache(maxsize=2**20)
 def _check_country(country: str, input_formats: Tuple[str, ...], strict: bool, clean: bool) -> Any:
     """
     Finds the index of the given country in the DATA dataframe.
@@ -322,7 +322,7 @@ def _check_country(country: str, input_formats: Tuple[str, ...], strict: bool, c
     return (None, "unknown") if clean else False
 
 
-@lru_cache(maxsize=2 ** 20)
+@lru_cache(maxsize=2**20)
 def _check_fuzzy_dist(country: str, fuzzy_dist: int) -> Any:
     """
     A match is found if a country has an edit distance <= fuzzy_dist

dataprep/eda/diff/render.py

@@ -574,7 +574,7 @@ def format_num_stats(data: Dict[str, List[Any]]) -> Dict[str, Dict[str, List[Any
     descriptive = {
         "Mean": data["mean"],
         "Standard Deviation": data["std"],
-        "Variance": [std ** 2 for std in data["std"]],
+        "Variance": [std**2 for std in data["std"]],
         "Sum": [mean * npres for mean, npres in zip(data["mean"], data["npres"])],
         "Skewness": [float(skew) for skew in data["skew"]],
         "Kurtosis": [float(kurt) for kurt in data["kurt"]],