酶活性检测机器学习源代码（欠拟合、过拟合）

import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from sklearn.preprocessing import PolynomialFeatures

data_train = pd.read_csv('T-R-train.csv')  # 数据预先分离
data_test = pd.read_csv('T-R-test.csv')
# print(data_train)

x_train = data_train.loc[:, 'T']
y_train = data_train.loc[:, 'rate']
x_test = data_test.loc[:, 'T']
y_test = data_test.loc[:, 'rate']

x_train = np.array(x_train).reshape(-1,1)

# fig1 = plt.figure()
# plt.scatter(x_train, y_train)
# plt.title('raw data')
# plt.xlabel('temperature')
# plt.ylabel('rate')
# plt.show()

x_train = np.array(x_train).reshape(-1, 1)
x_test = np.array(x_test).reshape(-1, 1)

# 线性回归模型
lr1 = LinearRegression()
lr1.fit(x_train, y_train)
y_train_predict = lr1.predict(x_train)
y_test_predict = lr1.predict(x_test)
r2_train = r2_score(y_train, y_train_predict)
r2_test = r2_score(y_test, y_test_predict)

# print('r2_train:', r2_train, '\nr2_test:', r2_test)   
# # r2_train: 0.016665703886981964 
# # r2_test: -0.758336343735132

x_range = np.linspace(40, 90, 300).reshape(-1, 1)
# y_range_predict = lr1.predict(x_range)
# fig2 = plt.figure()
# plt.plot(x_range, y_range_predict)
# plt.title('prediction data')
# plt.scatter(x_train, y_train)
# plt.xlabel('temprature')
# plt.ylabel('rate')
# plt.show()

# 多项式模型2
poly2 = PolynomialFeatures(degree=2)
x_2_train = poly2.fit_transform(x_train)
x_2_test = poly2.transform(x_test)
# print(x_2_train)

lr2 = LinearRegression()
lr2.fit(x_2_train, y_train)
y_2_train_predict = lr2.predict(x_2_train)
y_2_test_predict = lr2.predict(x_2_test)
r2_2_train = r2_score(y_train, y_2_train_predict)
r2_2_test = r2_score(y_test, y_2_test_predict)
# print('training r2_2:', r2_2_train)
# print('test r2_2:', r2_2_test)
# # training r2_2: 0.9700515400689432
# # test r2_2: 0.996395455646867

x_2_range = np.linspace(40, 90, 300).reshape(-1, 1)
x_2_range = poly2.transform(x_2_range)
y_2_range_predict = lr2.predict(x_2_range)

# fig3 = plt.figure()
# plt.plot(x_range, y_2_range_predict)
# plt.title('polynomial prediction result(2)')
# plt.scatter(x_train, y_train)
# plt.xlabel('temprature')
# plt.ylabel('rate')
# plt.show()

# 多项式模型5
poly5 = PolynomialFeatures(degree=5)
x_5_train = poly5.fit_transform(x_train)
x_5_test = poly5.transform(x_test)
# print(x_2_train)

lr5 = LinearRegression()
lr5.fit(x_5_train, y_train)
y_5_train_predict = lr5.predict(x_5_train)
y_5_test_predict = lr5.predict(x_5_test)
r2_5_train = r2_score(y_train, y_5_train_predict)
r2_5_test = r2_score(y_test, y_5_test_predict)
# print('training r2_5:', r2_5_train)
# print('test r2_5:', r2_5_test)
# # training r2_5: 0.9978527267154614
# # test r2_5: 0.5437832506091483

x_5_range = np.linspace(40, 90, 300).reshape(-1, 1)
x_5_range = poly5.transform(x_5_range)
y_5_range_predict = lr5.predict(x_5_range)

fig4 = plt.figure()
plt.plot(x_range, y_5_range_predict)
plt.title('polynomial prediction result(5)')
plt.scatter(x_train, y_train)
plt.scatter(x_test, y_test)
plt.xlabel('temprature')
plt.ylabel('rate')
plt.show()

效果图：

参考：

35 实战（一）_哔哩哔哩_bilibili 

数据集：

链接: T-R-test.
提取码：g2ym

链接: T-R-train.
提取码：re7s

总结：欠拟合-训练集，测试集效果都不理想

过拟合：训练集准确，但测试集VERY GOOD

过拟合与欠拟合都不能满足需求，应根据情况选择合适的模型进行预测