찰떡개발자 코딩

import numpy as np
import pandas as pd

df = pd.read_csv('https://bit.ly/perch_csv')

perch_numpy = np.array(df)

perch_weight = np.array([5.9, 32.0, 40.0, 51.5, 70.0, 100.0, 78.0, 80.0, 85.0, 85.0, 110.0,
       115.0, 125.0, 130.0, 120.0, 120.0, 130.0, 135.0, 110.0, 130.0,
       150.0, 145.0, 150.0, 170.0, 225.0, 145.0, 188.0, 180.0, 197.0,
       218.0, 300.0, 260.0, 265.0, 250.0, 250.0, 300.0, 320.0, 514.0,
       556.0, 840.0, 685.0, 700.0, 700.0, 690.0, 900.0, 650.0, 820.0,
       850.0, 900.0, 1015.0, 820.0, 1100.0, 1000.0, 1100.0, 1000.0,
       1000.0])

from sklearn.model_selection import train_test_split
train_input, test_input, train_target, test_target = train_test_split(perch_numpy,perch_weight,random_state=42)

#다중회기 변환기 사용 => 다중 특성사용으로 정확도 상승
from sklearn.preprocessing import PolynomialFeatures
poly = PolynomialFeatures(include_bias=False)
poly.fit(train_input)
train_poly = poly.transform(train_input)
test_poly = poly.transform(test_input)

#선형회귀 모델 사용
from sklearn.linear_model import LinearRegression
lr = LinearRegression()
lr.fit(train_poly,train_target)
print(lr.score(train_poly,train_target))
print(lr.score(test_poly,test_target))

poly = PolynomialFeatures(degree=5, include_bias=False)
poly.fit(train_input)
train_poly = poly.transform(train_input)
test_poly = poly.transform(test_input)

lr.fit(train_poly,train_target)
print(lr.score(train_poly,train_target))
print(lr.score(test_poly,test_target))

#규제
from sklearn.preprocessing import StandardScaler
ss = StandardScaler()
ss.fit(train_poly)
train_scaled = ss.transform(train_poly)
test_scaled = ss.transform(test_poly)

#릿지 회귀모델 훈련
from sklearn.linear_model import Ridge
ridge = Ridge()
ridge.fit(train_scaled,train_target)
print(ridge.score(train_scaled,train_target))
print(ridge.score(test_scaled,test_target))

#Ridge alpha값 (규제의수)확인
train_score = []
test_score = []
alpha_list = [0.001,0.01,0.1,1,10,100]
for alpha in alpha_list:
  ridge = Ridge(alpha=alpha)
  ridge.fit(train_scaled,train_target)
  train_score.append(ridge.score(train_scaled,train_target))
  test_score.append(ridge.score(test_scaled,test_target))

import matplotlib.pyplot as plt
plt.plot(np.log10(alpha_list),train_score)
plt.plot(np.log10(alpha_list),test_score)
plt.show()

#최종 훈련
ridge = Ridge(0.1)
ridge.fit(train_scaled,train_target)
print(ridge.score(train_scaled,train_target))
print(ridge.score(test_scaled,test_target))