import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingRegressor
import random
from sklearn.metrics import r2_score

df = pd.read_excel('data.xlsx')  # header=0表示第一行是表头，就自动去除了
df.head()


X = df.drop(columns='成绩')
y = df['成绩']
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=123)
model = GradientBoostingRegressor(random_state=123)
model.fit(X_train,y_train)
y_pred = model.predict(X_test)
y_pred[:20]

a = pd.DataFrame()
a['预测值'] = list(y_pred)
a['实际值'] = list(y_test)
a.head()   #汇总预测值和实际值

model.score(X_test,y_test)     #输出一：查看模型的预测效果,评估模型的拟合程度

a = pd.DataFrame()
a['特征'] = X.columns
a['特征重要性'] = model.feature_importances_
a.sort_values(by='特征重要性',ascending=False)#输出二：各个特征变量的特征重要性

model.predict([[2023,6,0,1]])  #输出三：预测2023年某一省份，某一批次，文科或者理科分数线
#以2023年安徽省理科一本为例