Categorical data

Nominal and ordinal features

Ordinal features: categorical values that can be sorted, i.e. t-shirt size
Nominal features: don’t imply any order, i.e. t-shirt color

import pandas as pd

df = pd.DataFrame([['green', 'M', 10.1, 'class2'],
                   ['red', 'L', 13.5, 'class1'],
                   ['blue', 'XL', 15.3, 'class2']])

df.columns = ['color', 'size', 'price', 'classlabel']
df

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}

Mapping ordinal features

size_mapping = {'XL': 3,
                'L': 2,
                'M': 1}

df['size'] = df['size'].map(size_mapping)
df

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}


# Inverse mapping
inv_size_mapping = {v: k for k, v in size_mapping.items()}
df['size'].map(inv_size_mapping)

0     M
1     L
2    XL
Name: size, dtype: object

One-hot encoding nominal features

Note you cannot use the LabelEncoder since it will introduce an order that did not exist orginally. Use One-Hot encoding

# option1: Pandas
pd.get_dummies(df[['price', 'color', 'size']], drop_first=True)

.dataframe tbody tr th {
    vertical-align: top;
}

.dataframe thead th {
    text-align: right;
}


# option2: scikit-learn
from sklearn.preprocessing import OneHotEncoder

X = df[['color', 'size', 'price']].values
color_ohe = OneHotEncoder()
color_ohe.fit_transform(X[:, 0].reshape(-1, 1)).toarray()

array([[0., 1., 0.],
       [0., 0., 1.],
       [1., 0., 0.]])

Encoding class labels

from sklearn.preprocessing import LabelEncoder
# Label encoding with sklearn's LabelEncoder
class_le = LabelEncoder()
y = class_le.fit_transform(df['classlabel'].values)
y

# reverse mapping
class_le.inverse_transform(y)

array(['class2', 'class1', 'class2'], dtype=object)