def read_metadata(*args, **kwargs): meta, stats, parts, index = ArrowEngine.read_metadata(*args, **kwargs) # If `strings_to_categorical==True`, convert objects to int32 strings_to_cats = kwargs.get("strings_to_categorical", False) new_meta = cudf.DataFrame(index=meta.index) for col in meta.columns: if meta[col].dtype == "O": new_meta[col] = as_column( meta[col], dtype="int32" if strings_to_cats else "object") else: new_meta[col] = as_column(meta[col]) return (new_meta, stats, parts, index)
def read_metadata(*args, **kwargs): meta, stats, parts = ArrowEngine.read_metadata(*args, **kwargs) # If `strings_to_categorical==True`, convert objects to int32 strings_to_cats = kwargs.get("strings_to_categorical", False) dtypes = {} for col in meta.columns: if meta[col].dtype == "O": dtypes[col] = "int32" if strings_to_cats else "object" meta = cudf.DataFrame.from_pandas(meta) for col, dtype in dtypes.items(): meta[col] = meta[col].astype(dtype) return (meta, stats, parts)