物流预测模型，使用决策树。

import pandas as pd
import numpy as np
#决策树分类器
from sklearn.tree import DecisionTreeClassifier
#特征提取 字典提取：
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split
from sklearn.ensemble import  AdaBoostClassifier
def Demo_predict():

    #设置目标特征 、特征值
    data=pd.read_csv('2005年.csv')
    x=data[["GDP","物流消费总额","固定资产投资","进口总额","出口总额"]]
    y=data[["社会物流总额"]]
    #数据集划分

    x_train,x_test,y_trian,y_test=train_test_split(x,y,random_state=42,test_size=0.3)

    x_test_old=x_test
    y_test_old=y_test
    print("x_test_old测试集：",x_test_old)
    print("y_test_old测试集：", y_test_old)

    #特征工程
    transfer=DictVectorizer()
    x_train=x_train.to_dict(orient="records")
    print(x_train)
    x_test=x_test.to_dict(orient="records")
    print(x_test)

    x_train=transfer.fit_transform(x_train)
    x_test=transfer.fit_transform(x_test)
    print("x_train:",x_train)
    print("x_test:",x_test)
    #机器学习，模型训练

    estimator=DecisionTreeClassifier()
    estimator.fit(x_train,y_trian.astype('int'))

    #模型评估；和预测；
    y_pre=estimator.predict(x_test)
    print("测试集真实值：", y_test_old)
    print("测试集预测值：",y_pre)


    res=estimator.score(x_test,y_test.astype('int'))
    print("准确率结果res:",res)

if __name__ == '__main__':
    Demo_predict()

 数据集：

2005年.csv

社会物流总额,GDP,物流消费总额,固定资产投资,进口总额,出口总额
53.23,12.13,2.52,9.82,1.8,2.0
53.44,13.13,2.67,9.86,1.95,2.13
53.55,14.33,2.84,9.88,2.36,2.61
54.73,15.76,3.02,10.1,3.31,3.51
57.79,17.35,3.25,10.67,4.5,4.75
58.72,19.31,3.5,10.84,5.29,6.1
59.6,21.77,3.84,11.0,6.34,7.76
61.92,24.86,4.23,11.43,7.97,9.75
67.44,27.24,4.61,12.45,9.36,11.46
65.82,29.75,4.58,12.15,7.86,9.62
68.19,32.9,4.73,12.58,10.32,12.64
72.69,36.03,4.99,13.42,12.42,15.2
73.49,38.8,5.12,13.56,13.41,16.41
73.71,41.79,5.25,13.6,14.45,17.69
74.08,44.84,5.35,13.67,15.33,18.76
72.74,47.93,5.43,13.43,14.88,18.21