How to select rows from pandas dataframe by looking a feature' data types when a feature contains more than one type of value

Question

I have a dataframe with 3 features: id, name and point. I need to select rows that type of 'point' value is string.

id	name	point
0	x	5
1	y	6
2	z	ten
3	t	nine
4	q	two

How can I split the dataframe just looking by type of one feature' value?

I tried to modify select_dtypes method but I lost. Also I tried to divide dataset with using

df[df[point].dtype == str] or df[df[point].dtype is str]

but didn't work.

Answer 1

Technically, the answer would be:

out = df[df['point'].apply(lambda x: isinstance(x, str))]

But this would also select rows containing a string representation of a number ('5').

If you want to select "strings" as opposed to "numbers" whether those are real numbers or string representations, you could use:

m = pd.to_numeric(df['point'], errors='coerce')
out = df[df['point'].notna() & m]

The question is now, what if you have '1A' or 'AB123' as value?