Encoding Categorical Variables for Machine Learning

Encoding Categorical Variables

Machine learning models require numeric input, so we must convert categorical variables.

One‑Hot Encoding (low cardinality)

df_onehot = pd.get_dummies(df, columns=['city', 'gender'], drop_first=True)

Label Encoding with scikit‑learn

from sklearn.preprocessing import LabelEncoder
le = LabelEncoder()
df['dept_code'] = le.fit_transform(df['department'])

Frequency Encoding

freq = df['category'].value_counts() / len(df)
df['category_freq'] = df['category'].map(freq)

Target Encoding (mean encoding) – risk of leakage

target_means = df.groupby('city')['target'].mean()
df['city_target_enc'] = df['city'].map(target_means)

Choosing the right encoder

Cardinality	Recommended Encoder
< 10	One‑Hot
10‑100	Frequency / Target
> 100	Hashing or Embedding