房价预测

https://www.kaggle.com/competitions/house-prices-advanced-regression-techniques/data

随便做了下去除nan和字符列只用了回归树。

import matplotlib.pyplot as plt

import numpy as np

import pandas as pd

import torch

import torch.fft as fft

from sklearn import tree

df = pd.read_csv('train.csv')

df=df.drop(['Id'],axis=1)

df=df.dropna(axis=1,how='any')

w=df._get_numeric_data()

df=w.to_numpy()

feature=df[:,:-1]

label=df[:,-1]

from sklearn.model_selection import cross_val_score

label=np.reshape(label,(-1,1))

if np.NaN in label:

    print('yes')

if np.NaN in feature:

    print('yes')

for i in range(30):

    clf=tree_model = tree.DecisionTreeRegressor(max_depth=i+1 )

    scores = cross_val_score(clf,feature,label,cv=10)

    print(i,scores.mean())