将以下代码转换为R语言import pandas as pd import numpy as np import matplotlib.pyplot as plt from sklearn.metrics import mean_squar

library(tidyverse) library(caret) library(glmnet) #load data and clean data #jiazai shuju Data <- read_excel('D:\\4 UCI\\Machine Learning\\HW1\\Iowa_Housing_Data_Mod.xlsx') Data$`Age of House` <- Data$YrSold - Data$YearBuilt Data$`CentralAC Dummy` <- ifelse(Data$CentralAir == 'Y', 1, 0) Data <- Data %>% select(-c(Unnamed.28, Unnamed.29, CentralAir, YrSold, YearBuilt, Id)) %>% drop_na() # First 1800 data items are training set; the next 600 are the validation set: the final 508 are the etst set train <- Data[1:1800,] val <- Data[1801:2400,] test <- Data[2401:2908,] #Simple Linear regression #two methods #method 1 Y_simple_1 <- as.matrix(Data$SalePrice) X_simple_1 <- as.matrix(Data$GrLivArea) X_simple_1 <- X_simple_1 %>% t() %>% as.data.frame() Y_simple_1 <- Y_simple_1 %>% t() %>% as.data.frame() lr_simple_1 <- train(X_simple_1, Y_simple_1, method = "lm") #coefficient of variables lr_simple_1$finalModel$coefficients #intercept lr_simple_1$finalModel$coef[1] #R-squared R_2_s <- cor(Y_simple_1, lr_simple_1$finalModel$fitted.values)^2 #Adjusted R-squared R_2_s_adjusted <- 1-(1-R_2_s)*(2908-1)/(2908-1-1) #method 2 Y_simple_2 <- Data$SalePrice X_simple_2 <- Data$GrLivArea X_simple_2 <- cbind(1, X_simple_2) ols <- lm(Y_simple_2 ~ X_simple_2) lr_simple_2 <- summary(ols) #multiple Linear regression #two methods #method 1 Y_multiple_1 <- as.matrix(Data$SalePrice) X_multiple_1 <- as.matrix(Data %>% select(LotArea, OverallQual, OverallCond, `Age of House