One-Hot Encoding vs Label Encoding

บทความโดย ผศ.ดร.ณัฐโชติ พรหมฤทธิ์
ภาควิชาคอมพิวเตอร์
คณะวิทยาศาสตร์
มหาวิทยาลัยศิลปากร

import pandas as pd

data_string = {'Category': ['A', 'B', 'A', 'C', 'B', 'C', 'A'],
               'Color': ['Red', 'Blue', 'Green', 'Red', 'Blue', 'Green', 'Red'],
               'Value': [10, 25, 15, 30, 20, 35, 12],
               'Label': ['Yes', 'No', 'Yes', 'No', 'Yes', 'No', 'Yes']}

df_string = pd.DataFrame(data_string)

df_string

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline

X_string = df_string[['Category', 'Color', 'Value']]
y_string = df_string['Label']

label_encoder = LabelEncoder()
y_encoded = label_encoder.fit_transform(y_string)

categorical_features = ['Category', 'Color']

preprocessor = ColumnTransformer(
    transformers=[
        ('cat', OneHotEncoder(), categorical_features)],
    remainder='passthrough')

X_processed = preprocessor.fit_transform(X_string)

X_processed

y_encoded

from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import accuracy_score, classification_report, confusion_matrix

X_train, X_test, y_train, y_test = train_test_split(X_processed, y_encoded, test_size=0.3, random_state=42)

model = RandomForestClassifier(random_state=42)
model.fit(X_train, y_train)

y_pred = model.predict(X_test)

y_pred

feature_names_out = preprocessor.get_feature_names_out()

X_processed_df = pd.DataFrame(X_processed, columns=feature_names_out)

X_processed_df