import numpy as np
import pandas as pd
import matplotlib
from matplotlib import pyplot as plt
from sklearn.metrics import r2_score
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
font = {
"family": "Microsoft YaHei"
}
matplotlib.rc("font", **font)
data = pd.read_excel("data150（人工智能数值类）.xlsx", index_col="序号")
ss_cha = StandardScaler()
x = ss_cha.fit_transform(data.iloc[:, :-1])
ss_tar = StandardScaler()
y = ss_tar.fit_transform(pd.DataFrame(data.iloc[:, -1]))
x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2)
rf = RandomForestRegressor()
rf.fit(x_train, y_train)
y_pred = rf.predict(x_test)
plt.plot(ss_tar.inverse_transform(y_test))
plt.plot(ss_tar.inverse_transform(y_pred))
plt.xlabel("样本")
plt.ylabel("熔融指数")
plt.title("测试集拟合结果")
plt.legend(["真实值", "预测值"])
plt.savefig("result.png")
plt.show()
print(r2_score(y_test, y_pred))
