HW11
Pheobe Buffay
5/3/2022
#Loading necessary packages
library(tidyverse)
library(skimr)
library(rpart)
library(randomForest)
library(rattle)
library(neuralnet)
library(nnet)
library(caret)Task 1 (really easy)
Loading the datasets
#Import training and testing data:
train_raw <- read.csv2("train.csv", sep = ",",
stringsAsFactors = TRUE)
test_raw <- read.csv2("test.csv", sep = ",",
stringsAsFactors = TRUE)
dim(train_raw)## [1] 1460 81dim(test_raw)## [1] 1459 80#This is useful to look at data, from skimr package. Doesn't render in latex though.
skim(train_raw)| Name | train_raw |
| Number of rows | 1460 |
| Number of columns | 81 |
| _______________________ | |
| Column type frequency: | |
| factor | 43 |
| numeric | 38 |
| ________________________ | |
| Group variables | None |
Variable type: factor
| skim_variable | n_missing | complete_rate | ordered | n_unique | top_counts |
|---|---|---|---|---|---|
| MSZoning | 0 | 1.00 | FALSE | 5 | RL: 1151, RM: 218, FV: 65, RH: 16 |
| Street | 0 | 1.00 | FALSE | 2 | Pav: 1454, Grv: 6 |
| Alley | 1369 | 0.06 | FALSE | 2 | Grv: 50, Pav: 41 |
| LotShape | 0 | 1.00 | FALSE | 4 | Reg: 925, IR1: 484, IR2: 41, IR3: 10 |
| LandContour | 0 | 1.00 | FALSE | 4 | Lvl: 1311, Bnk: 63, HLS: 50, Low: 36 |
| Utilities | 0 | 1.00 | FALSE | 2 | All: 1459, NoS: 1 |
| LotConfig | 0 | 1.00 | FALSE | 5 | Ins: 1052, Cor: 263, Cul: 94, FR2: 47 |
| LandSlope | 0 | 1.00 | FALSE | 3 | Gtl: 1382, Mod: 65, Sev: 13 |
| Neighborhood | 0 | 1.00 | FALSE | 25 | NAm: 225, Col: 150, Old: 113, Edw: 100 |
| Condition1 | 0 | 1.00 | FALSE | 9 | Nor: 1260, Fee: 81, Art: 48, RRA: 26 |
| Condition2 | 0 | 1.00 | FALSE | 8 | Nor: 1445, Fee: 6, Art: 2, Pos: 2 |
| BldgType | 0 | 1.00 | FALSE | 5 | 1Fa: 1220, Twn: 114, Dup: 52, Twn: 43 |
| HouseStyle | 0 | 1.00 | FALSE | 8 | 1St: 726, 2St: 445, 1.5: 154, SLv: 65 |
| RoofStyle | 0 | 1.00 | FALSE | 6 | Gab: 1141, Hip: 286, Fla: 13, Gam: 11 |
| RoofMatl | 0 | 1.00 | FALSE | 8 | Com: 1434, Tar: 11, WdS: 6, WdS: 5 |
| Exterior1st | 0 | 1.00 | FALSE | 15 | Vin: 515, HdB: 222, Met: 220, Wd : 206 |
| Exterior2nd | 0 | 1.00 | FALSE | 16 | Vin: 504, Met: 214, HdB: 207, Wd : 197 |
| MasVnrType | 8 | 0.99 | FALSE | 4 | Non: 864, Brk: 445, Sto: 128, Brk: 15 |
| ExterQual | 0 | 1.00 | FALSE | 4 | TA: 906, Gd: 488, Ex: 52, Fa: 14 |
| ExterCond | 0 | 1.00 | FALSE | 5 | TA: 1282, Gd: 146, Fa: 28, Ex: 3 |
| Foundation | 0 | 1.00 | FALSE | 6 | PCo: 647, CBl: 634, Brk: 146, Sla: 24 |
| BsmtQual | 37 | 0.97 | FALSE | 4 | TA: 649, Gd: 618, Ex: 121, Fa: 35 |
| BsmtCond | 37 | 0.97 | FALSE | 4 | TA: 1311, Gd: 65, Fa: 45, Po: 2 |
| BsmtExposure | 38 | 0.97 | FALSE | 4 | No: 953, Av: 221, Gd: 134, Mn: 114 |
| BsmtFinType1 | 37 | 0.97 | FALSE | 6 | Unf: 430, GLQ: 418, ALQ: 220, BLQ: 148 |
| BsmtFinType2 | 38 | 0.97 | FALSE | 6 | Unf: 1256, Rec: 54, LwQ: 46, BLQ: 33 |
| Heating | 0 | 1.00 | FALSE | 6 | Gas: 1428, Gas: 18, Gra: 7, Wal: 4 |
| HeatingQC | 0 | 1.00 | FALSE | 5 | Ex: 741, TA: 428, Gd: 241, Fa: 49 |
| CentralAir | 0 | 1.00 | FALSE | 2 | Y: 1365, N: 95 |
| Electrical | 1 | 1.00 | FALSE | 5 | SBr: 1334, Fus: 94, Fus: 27, Fus: 3 |
| KitchenQual | 0 | 1.00 | FALSE | 4 | TA: 735, Gd: 586, Ex: 100, Fa: 39 |
| Functional | 0 | 1.00 | FALSE | 7 | Typ: 1360, Min: 34, Min: 31, Mod: 15 |
| FireplaceQu | 690 | 0.53 | FALSE | 5 | Gd: 380, TA: 313, Fa: 33, Ex: 24 |
| GarageType | 81 | 0.94 | FALSE | 6 | Att: 870, Det: 387, Bui: 88, Bas: 19 |
| GarageFinish | 81 | 0.94 | FALSE | 3 | Unf: 605, RFn: 422, Fin: 352 |
| GarageQual | 81 | 0.94 | FALSE | 5 | TA: 1311, Fa: 48, Gd: 14, Ex: 3 |
| GarageCond | 81 | 0.94 | FALSE | 5 | TA: 1326, Fa: 35, Gd: 9, Po: 7 |
| PavedDrive | 0 | 1.00 | FALSE | 3 | Y: 1340, N: 90, P: 30 |
| PoolQC | 1453 | 0.00 | FALSE | 3 | Gd: 3, Ex: 2, Fa: 2 |
| Fence | 1179 | 0.19 | FALSE | 4 | MnP: 157, GdP: 59, GdW: 54, MnW: 11 |
| MiscFeature | 1406 | 0.04 | FALSE | 4 | She: 49, Gar: 2, Oth: 2, Ten: 1 |
| SaleType | 0 | 1.00 | FALSE | 9 | WD: 1267, New: 122, COD: 43, Con: 9 |
| SaleCondition | 0 | 1.00 | FALSE | 6 | Nor: 1198, Par: 125, Abn: 101, Fam: 20 |
Variable type: numeric
| skim_variable | n_missing | complete_rate | mean | sd | p0 | p25 | p50 | p75 | p100 | hist |
|---|---|---|---|---|---|---|---|---|---|---|
| Id | 0 | 1.00 | 730.50 | 421.61 | 1 | 365.75 | 730.5 | 1095.25 | 1460 | ▇▇▇▇▇ |
| MSSubClass | 0 | 1.00 | 56.90 | 42.30 | 20 | 20.00 | 50.0 | 70.00 | 190 | ▇▅▂▁▁ |
| LotFrontage | 259 | 0.82 | 70.05 | 24.28 | 21 | 59.00 | 69.0 | 80.00 | 313 | ▇▃▁▁▁ |
| LotArea | 0 | 1.00 | 10516.83 | 9981.26 | 1300 | 7553.50 | 9478.5 | 11601.50 | 215245 | ▇▁▁▁▁ |
| OverallQual | 0 | 1.00 | 6.10 | 1.38 | 1 | 5.00 | 6.0 | 7.00 | 10 | ▁▂▇▅▁ |
| OverallCond | 0 | 1.00 | 5.58 | 1.11 | 1 | 5.00 | 5.0 | 6.00 | 9 | ▁▁▇▅▁ |
| YearBuilt | 0 | 1.00 | 1971.27 | 30.20 | 1872 | 1954.00 | 1973.0 | 2000.00 | 2010 | ▁▂▃▆▇ |
| YearRemodAdd | 0 | 1.00 | 1984.87 | 20.65 | 1950 | 1967.00 | 1994.0 | 2004.00 | 2010 | ▅▂▂▃▇ |
| MasVnrArea | 8 | 0.99 | 103.69 | 181.07 | 0 | 0.00 | 0.0 | 166.00 | 1600 | ▇▁▁▁▁ |
| BsmtFinSF1 | 0 | 1.00 | 443.64 | 456.10 | 0 | 0.00 | 383.5 | 712.25 | 5644 | ▇▁▁▁▁ |
| BsmtFinSF2 | 0 | 1.00 | 46.55 | 161.32 | 0 | 0.00 | 0.0 | 0.00 | 1474 | ▇▁▁▁▁ |
| BsmtUnfSF | 0 | 1.00 | 567.24 | 441.87 | 0 | 223.00 | 477.5 | 808.00 | 2336 | ▇▅▂▁▁ |
| TotalBsmtSF | 0 | 1.00 | 1057.43 | 438.71 | 0 | 795.75 | 991.5 | 1298.25 | 6110 | ▇▃▁▁▁ |
| X1stFlrSF | 0 | 1.00 | 1162.63 | 386.59 | 334 | 882.00 | 1087.0 | 1391.25 | 4692 | ▇▅▁▁▁ |
| X2ndFlrSF | 0 | 1.00 | 346.99 | 436.53 | 0 | 0.00 | 0.0 | 728.00 | 2065 | ▇▃▂▁▁ |
| LowQualFinSF | 0 | 1.00 | 5.84 | 48.62 | 0 | 0.00 | 0.0 | 0.00 | 572 | ▇▁▁▁▁ |
| GrLivArea | 0 | 1.00 | 1515.46 | 525.48 | 334 | 1129.50 | 1464.0 | 1776.75 | 5642 | ▇▇▁▁▁ |
| BsmtFullBath | 0 | 1.00 | 0.43 | 0.52 | 0 | 0.00 | 0.0 | 1.00 | 3 | ▇▆▁▁▁ |
| BsmtHalfBath | 0 | 1.00 | 0.06 | 0.24 | 0 | 0.00 | 0.0 | 0.00 | 2 | ▇▁▁▁▁ |
| FullBath | 0 | 1.00 | 1.57 | 0.55 | 0 | 1.00 | 2.0 | 2.00 | 3 | ▁▇▁▇▁ |
| HalfBath | 0 | 1.00 | 0.38 | 0.50 | 0 | 0.00 | 0.0 | 1.00 | 2 | ▇▁▅▁▁ |
| BedroomAbvGr | 0 | 1.00 | 2.87 | 0.82 | 0 | 2.00 | 3.0 | 3.00 | 8 | ▁▇▂▁▁ |
| KitchenAbvGr | 0 | 1.00 | 1.05 | 0.22 | 0 | 1.00 | 1.0 | 1.00 | 3 | ▁▇▁▁▁ |
| TotRmsAbvGrd | 0 | 1.00 | 6.52 | 1.63 | 2 | 5.00 | 6.0 | 7.00 | 14 | ▂▇▇▁▁ |
| Fireplaces | 0 | 1.00 | 0.61 | 0.64 | 0 | 0.00 | 1.0 | 1.00 | 3 | ▇▇▁▁▁ |
| GarageYrBlt | 81 | 0.94 | 1978.51 | 24.69 | 1900 | 1961.00 | 1980.0 | 2002.00 | 2010 | ▁▁▅▅▇ |
| GarageCars | 0 | 1.00 | 1.77 | 0.75 | 0 | 1.00 | 2.0 | 2.00 | 4 | ▁▃▇▂▁ |
| GarageArea | 0 | 1.00 | 472.98 | 213.80 | 0 | 334.50 | 480.0 | 576.00 | 1418 | ▂▇▃▁▁ |
| WoodDeckSF | 0 | 1.00 | 94.24 | 125.34 | 0 | 0.00 | 0.0 | 168.00 | 857 | ▇▂▁▁▁ |
| OpenPorchSF | 0 | 1.00 | 46.66 | 66.26 | 0 | 0.00 | 25.0 | 68.00 | 547 | ▇▁▁▁▁ |
| EnclosedPorch | 0 | 1.00 | 21.95 | 61.12 | 0 | 0.00 | 0.0 | 0.00 | 552 | ▇▁▁▁▁ |
| X3SsnPorch | 0 | 1.00 | 3.41 | 29.32 | 0 | 0.00 | 0.0 | 0.00 | 508 | ▇▁▁▁▁ |
| ScreenPorch | 0 | 1.00 | 15.06 | 55.76 | 0 | 0.00 | 0.0 | 0.00 | 480 | ▇▁▁▁▁ |
| PoolArea | 0 | 1.00 | 2.76 | 40.18 | 0 | 0.00 | 0.0 | 0.00 | 738 | ▇▁▁▁▁ |
| MiscVal | 0 | 1.00 | 43.49 | 496.12 | 0 | 0.00 | 0.0 | 0.00 | 15500 | ▇▁▁▁▁ |
| MoSold | 0 | 1.00 | 6.32 | 2.70 | 1 | 5.00 | 6.0 | 8.00 | 12 | ▃▆▇▃▃ |
| YrSold | 0 | 1.00 | 2007.82 | 1.33 | 2006 | 2007.00 | 2008.0 | 2009.00 | 2010 | ▇▇▇▇▅ |
| SalePrice | 0 | 1.00 | 180921.20 | 79442.50 | 34900 | 129975.00 | 163000.0 | 214000.00 | 755000 | ▇▅▁▁▁ |
Cleaning the dataset
# Functions to replace NAs with most frequent level or median
replace_na_most <- function(x){
fct_explicit_na(x, na_level = names(which.max(table(x))))
}
replace_na_med <- function(x){
x[is.na(x)] <- median(x,na.rm = TRUE)
x
}
cleanup_minimal <- function(data){
nomis <- data %>%
mutate_if(is.factor, replace_na_most) %>%
mutate_if(is.numeric, replace_na_med)
nomis
}
train_minclean <- cleanup_minimal(train_raw)
test_minclean <- cleanup_minimal(test_raw)Run the simplest tree algorithm and plot it
mod_rpart <- rpart(SalePrice~., data=train_minclean)
# Try this command to make a nice tree plot!
fancyRpartPlot(mod_rpart, caption = NULL)
Exporting the predictions in appropriate format
pred_rpart <- predict(mod_rpart, newdata = test_minclean)
submission_rpart <- tibble(Id=test_raw$Id, SalePrice=pred_rpart)
head(submission_rpart)## # A tibble: 6 x 2
## Id SalePrice
## <int> <dbl>
## 1 1461 118199.
## 2 1462 151246.
## 3 1463 185210.
## 4 1464 185210.
## 5 1465 249392.
## 6 1466 185210.# Obviously, your file path might be different here:
write_csv(submission_rpart, file="C:/Users/Asus/OneDrive - University of Georgia/PhD/Spring 2022/AAEC 8610/HW11/home-data-for-ml-course/submission_rpart.csv")
My submission of predictions using rpart in Kaggle
Task 2: Push further, as much as you like
# Training a random forest
mod_rf <- randomForest(SalePrice ~ ., data = train_minclean)
# These 2 lines below are just a stupid trick to fix a bug in R. Without it prediction gets an error
trainX <- select(train_minclean, -SalePrice)
test_minclean <- rbind(trainX[1, ] , test_minclean)
test_minclean <- test_minclean[-1,]
# Get my predictions:
pred_rf <-predict(mod_rf, newdata = test_minclean)
submission_rf_1 <- tibble(Id=test_raw$Id, SalePrice=pred_rf)
write_csv(submission_rf_1, file="C:/Users/Asus/OneDrive - University of Georgia/PhD/Spring 2022/AAEC 8610/HW11/home-data-for-ml-course/submission_rf_1.csv")
My submission of predictions using randomforest in Kaggle
# Merging, then normalizing and hot-encoding
merged <- rbind(select(train_minclean,-SalePrice),test_minclean)
preProcessor <- preProcess(merged[,-1]) # not processing the ID variable
normed <- predict(preProcessor, newdata = merged)
hotencoder <- dummyVars(" ~ .", data=normed)
encoded <- predict(hotencoder, newdata = normed)
# Spliting training and testing back out
train_encoded = encoded[1:dim(train_minclean)[1], ]
train_proc <- cbind(train_encoded,SalePrice=train_raw$SalePrice)
train_proc <- train_proc[,-1]
test_proc = encoded[(dim(train_minclean)[1]+1):dim(encoded)[1], ]
# Training a neural net
# (note: Dividing roughly by the approximate max value of SalePrice to make it [0,1].
mod_nn <- nnet(SalePrice/800000 ~ ., data = train_proc, size = 15, linout = TRUE, MaxNWts = 10000)## # weights: 4351
## initial value 232.164465
## iter 10 value 5.777563
## iter 20 value 3.309414
## iter 30 value 1.550244
## iter 40 value 1.002767
## iter 50 value 0.734708
## iter 60 value 0.598571
## iter 70 value 0.509123
## iter 80 value 0.432249
## iter 90 value 0.355826
## iter 100 value 0.287284
## final value 0.287284
## stopped after 100 iterations# Now predicting back:
pred_nnet <- (predict(mod_nn, newdata=test_proc))*800000
pp <- data.frame(pred_nnet)
submission_nnet <- tibble(Id=test_raw$Id, SalePrice=pp$pred_nnet)
write_csv(submission_nnet, file="C:/Users/Asus/OneDrive - University of Georgia/PhD/Spring 2022/AAEC 8610/HW11/home-data-for-ml-course/submission_nnet.csv")
My submission of predictions using nnet in Kaggle: