%load_ext watermark
%watermark -a 'Sebastian Raschka' -v -p pandas,numpy,scikit-learn -d

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

df.columns = ['color', 'size', 'prize', 'class label']
df

class_mapping = {label:idx for idx,label in enumerate(set(df['class label']))}

df['class label'] = df['class label'].map(class_mapping)
df

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

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

color_mapping = {
           'green': (0,0,1),
           'red': (0,1,0),
           'blue': (1,0,0)}

df['color'] = df['color'].map(color_mapping)
df

import numpy as np
y = df['class label'].values
X = df.iloc[:, :-1].values
X = np.apply_along_axis(func1d= lambda x: np.array(list(x[0]) + list(x[1:])), axis=1, arr=X)

print('Class labels:', y)
print('\nFeatures:\n', X)


inv_color_mapping = {v: k for k, v in color_mapping.items()}
inv_size_mapping = {v: k for k, v in size_mapping.items()}
inv_class_mapping = {v: k for k, v in class_mapping.items()}

df['color'] = df['color'].map(inv_color_mapping)
df['size'] = df['size'].map(inv_size_mapping)
df['class label'] = df['class label'].map(inv_class_mapping)
df

from sklearn.preprocessing import LabelEncoder

class_le = LabelEncoder()
df['class label'] = class_le.fit_transform(df['class label'])

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

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

class_le.inverse_transform(df['class label'])

df.transpose().to_dict().values()

from sklearn.feature_extraction import DictVectorizer
dvec = DictVectorizer(sparse=False)

X = dvec.fit_transform(df.transpose().to_dict().values())
X

pd.DataFrame(X, columns=dvec.get_feature_names())

color_le = LabelEncoder()
df['color'] = color_le.fit_transform(df['color'])

df

from sklearn.preprocessing import OneHotEncoder
ohe = OneHotEncoder(sparse=False)

X = ohe.fit_transform(df[['color']].values)
X

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

df.columns = ['color', 'size', 'prize', 'class label']

size_mapping = {
           'XL': 3,
           'L': 2,
           'M': 1}
df['size'] = df['size'].map(size_mapping)

class_mapping = {label:idx for idx,label in enumerate(set(df['class label']))}
df['class label'] = df['class label'].map(class_mapping)


df

pd.get_dummies(df)