Linear Regression

라이브러리 불러오기

• 코드

import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder, PolynomialFeatures
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

데이터 불러오기

• 코드

DF = sns.load_dataset('mpg')

DF.info()

데이터 전처리

• 코드

# null 데이터 처리
DF.drop(index=DF[DF['horsepower'].isnull()].index, inplace=True)
# origin 범주형 처리
encoder = LabelEncoder()
DF['orgin_state'] = encoder.fit_transform(DF[['origin']])
print('origin:', DF['orgin_state'].unique())
# object 컬럼 삭제
DF.drop(columns=['name', 'origin'], axis=1, inplace=True)
print("**" * 20)

DF.info()

데이터시각화1 (pairpot)

• 전체 컬럼

sns.pairplot(DF)
plt.show()

• 컬럼 범위 설정

sns.pairplot(DF, vars=['mpg', 'displacement', 'weight'])
plt.show()

• 특정 컬럼

sns.pairplot(DF, y_vars=['mpg'])
plt.show()

데이터시각화2 (heatmap)

• 전체 컬럼

sns.heatmap(DF.corr())
plt.show()

• 특정 컬럼

sns.heatmap(DF.corr()[['mpg']])
plt.show()

상관계수 출력

• 전체 컬럼

DF.corr()

• 특정 컬럼

DF.corr()[['mpg']]

• 특정 컬럼 (정렬)

DF.corr()[['mpg']].sort_values(by='mpg', key=abs, ascending=False)

단순회귀 (Simple Regression)

• 예시

X = DF[['weight']]
y = DF['mpg']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=2045)
RA = LinearRegression()
RA.fit(X_train, y_train)

print('weight:', RA.coef_)
print('bias:', RA.intercept_)
print('R Score:', RA.score(X_test, y_test))
y_hat_test = RA.predict(X_test)
mse = mean_squared_error(y_test, y_hat_test)
print('MSE: %.2f / %.2f' % (mse, np.sqrt(mse)))

plt.figure(figsize=(9, 6))
ax1 = sns.kdeplot(y_test, label='y_test')
ax2 = sns.kdeplot(y_hat_test, label='y_hat_simple', ax=ax1)
ax3 = sns.kdeplot(y_train, label='y_train', ax=ax1)
plt.legend()
plt.show()

다항회귀 (Polynomial Regression)

• 예시

X = DF[['weight']]
y = DF['mpg']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=6691)

poly = PolynomialFeatures(degree=2, include_bias=False)
X_train_poly = poly.fit_transform(X_train)
X_test_poly = poly.fit_transform(X_test)

RA = LinearRegression()
RA.fit(X_train_poly, y_train)

print('weight:', RA.coef_)
print('bias:', RA.intercept_)
print('R Score:', RA.score(X_test_poly, y_test))
y_hat_test = RA.predict(X_test_poly)
mse = mean_squared_error(y_test, y_hat_test)
print('MSE: %.2f / %.2f' % (mse, np.sqrt(mse)))

plt.figure(figsize=(9, 6))
ax1 = sns.kdeplot(y_test, label='y_test')
ax2 = sns.kdeplot(y_hat_test, label='y_hat_simple', ax=ax1)
ax3 = sns.kdeplot(y_train, label='y_train', ax=ax1)
plt.legend()
plt.show()

다중회귀 (Multiple Regression)

• 예시

X = DF[['weight', 'displacement', 'horsepower']]
y = DF['mpg']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=2045)
RA = LinearRegression()
RA.fit(X_train, y_train)

plt.figure(figsize=(9, 6))
ax1 = sns.kdeplot(y_test, label='y_test')
ax2 = sns.kdeplot(y_hat_test, label='y_hat_simple', ax=ax1)
ax3 = sns.kdeplot(y_train, label='y_train', ax=ax1)
plt.legend()
plt.show()