Перед применением линейной регрессии у меня есть следующий этап предварительной обработки. Можно ли добавить термины взаимодействия «Numeric_Var1Categorical_Var1» и «Numeric_Var2Categorical_Var1» после разделения набора данных на обучающий и тестовый наборы?
Пример данных и пример Код (до решения)
import pandas as pd
import numpy as np
from sklearn.preprocessing import StandardScaler, OneHotEncoder
from sklearn.compose import ColumnTransformer
from sklearn.model_selection import train_test_split
# Sample dataset
data = {
'Numeric_Var1': [10, 20, 30, 40, 50],
'Numeric_Var2': [2.5, 3.0, 4.5, 5.5, 6.0],
'Categorical_Var1': ['A', 'B', 'A', 'B', 'B'],
'Categorical_Var2': ['X', 'Y', 'X', 'Y', 'X'],
'Dependent_Var': [100, 200, 250, 300, 400]
}
# Creating DataFrame
df = pd.DataFrame(data)
# Define independent and dependent variables
indep_vars = ['Numeric_Var1', 'Numeric_Var2', 'Categorical_Var1', 'Categorical_Var2']
dep_var = 'Dependent_Var'
# Extract the datasets
X = df[indep_vars]
y = df[dep_var]
# Standardizing non-binary numeric variables
numeric = ['Numeric_Var1', 'Numeric_Var2']
X_numerical = X[numeric]
sc_X = StandardScaler()
X_numerical_scaled = sc_X.fit_transform(X_numerical)
X_scaled = X.copy()
X_scaled[numeric] = X_numerical_scaled
sc_y = StandardScaler()
y_scaled = sc_y.fit_transform(y.values.reshape(-1, 1))
# Encoding categorical variables into dummies
categorical_indices = [2, 3] # assuming indices for categorical variables
ct = ColumnTransformer(
transformers=[('encoder', OneHotEncoder(), categorical_indices)],
remainder='passthrough'
)
X_scaled_dummified = ct.fit_transform(X_scaled)
X_scaled_array = X_scaled_dummified.toarray()
# Splitting the dataset into the Training set and Test set
X_train, X_test, y_train, y_test = \
train_test_split(X_scaled_array, y_scaled, test_size=1/3, random_state=0)
m_lr = LinearRegression()
m_lr.fit(X_train, y_train)
p_lr = m_lr.predict(X_test)
r_lr = r2_score(y_test, p_lr)
print(r_lr)
Подробнее здесь: https://stackoverflow.com/questions/784 ... -test-sets
