Linear regression (기본 선형회귀 모델)

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression

from sklearn.model_selection import train_test_split

from sklearn.metrics import r2_score, mean_squared_error

# Data load

df = pd.read_csv('./data/xxx.csv')

# Target data separation

y = df['y']

X = df.drop('y', axis = 1)

# Split train : test data set = 7:3 and set random seed

X_train, X_test, y_train, y_test = train_test_split(X,

                                                    y,

                                                    test_size = 0.3,

                                                    random_state = 42)

# Define model structure

lr = LinearRegression()

# Train model

lr.fit(X_train, y_train)

# Model prediction

lr_pred = lr.predict(X_test)

# Confirm coefficient

lr.coef_

# Error metric

print("r2 score:", r2_score(y_test, lr_pred))

print("RMSE:", np.sqrt(mean_squared_error(y_test, lr_pred)))

# Plot

plt.scatter(lr_pred, y_test)