Implement check and handling for timezone-aware datetime objects, converting them to timezone-naive for the .astype() numpy conversion function to work properly and not throw a TypeError if the dataframe has any timezone-aware datetime objects.

The issue is attempted conversion via numpy's .astype() function via df[col[0]] = df[col[0]].astype(data_type) with "datetime64[ns]" as the data type on datetime objects with a timezone.

Numpy will throw the below error if there are any timezone-aware datetime objects in the dataframe:

TypeError: Cannot use .astype to convert from timezone-aware dtype to timezone-naive dtype. Use obj.tz_localize(None) or obj.tz_convert('UTC').tz_localize(None) instead.

The proposed fix allows the dataframe to have timezone-aware datetime objects and still use skimpy to visualize the data analysis.

This can be tested with dummy data such as below:

import pandas as pd
from datetime import datetime
import pytz

# Sample data
data = {
    "timezone_aware": [pd.Timestamp(datetime.now(), tz=pytz.UTC)],
    "timezone_naive": [pd.Timestamp(datetime.now())],
    "integer_col": [1],
}

df = pd.DataFrame(data)

skim(df)