library(readxl)
housing.df <- read.csv("BostonHousing.csv")
View(housing.df)
dim(housing.df)
## [1] 506 15
summary(housing.df)
## CRIM ZN INDUS CHAS
## Min. : 0.00632 Min. : 0.00 Min. : 0.46 Min. :0.00000
## 1st Qu.: 0.08205 1st Qu.: 0.00 1st Qu.: 5.19 1st Qu.:0.00000
## Median : 0.25651 Median : 0.00 Median : 9.69 Median :0.00000
## Mean : 3.61352 Mean : 11.36 Mean :11.14 Mean :0.06917
## 3rd Qu.: 3.67708 3rd Qu.: 12.50 3rd Qu.:18.10 3rd Qu.:0.00000
## Max. :88.97620 Max. :100.00 Max. :27.74 Max. :1.00000
## NOX RM AGE DIS
## Min. :0.3850 Min. :3.561 Min. : 2.90 Min. : 1.130
## 1st Qu.:0.4490 1st Qu.:5.886 1st Qu.: 45.02 1st Qu.: 2.100
## Median :0.5380 Median :6.208 Median : 77.50 Median : 3.207
## Mean :0.5547 Mean :6.285 Mean : 68.57 Mean : 3.795
## 3rd Qu.:0.6240 3rd Qu.:6.623 3rd Qu.: 94.08 3rd Qu.: 5.188
## Max. :0.8710 Max. :8.780 Max. :100.00 Max. :12.127
## RAD TAX PTRATIO B
## Min. : 1.000 Min. :187.0 Min. :12.60 Min. : 0.32
## 1st Qu.: 4.000 1st Qu.:279.0 1st Qu.:17.40 1st Qu.:375.38
## Median : 5.000 Median :330.0 Median :19.05 Median :391.44
## Mean : 9.549 Mean :408.2 Mean :18.46 Mean :356.67
## 3rd Qu.:24.000 3rd Qu.:666.0 3rd Qu.:20.20 3rd Qu.:396.23
## Max. :24.000 Max. :711.0 Max. :22.00 Max. :396.90
## LSTAT MEDV CAT..MEDV
## Min. : 1.73 Min. : 5.00 Min. :0.000
## 1st Qu.: 6.95 1st Qu.:17.02 1st Qu.:0.000
## Median :11.36 Median :21.20 Median :0.000
## Mean :12.65 Mean :22.53 Mean :0.166
## 3rd Qu.:16.95 3rd Qu.:25.00 3rd Qu.:0.000
## Max. :37.97 Max. :50.00 Max. :1.000
library(psych)
## Warning: package 'psych' was built under R version 4.0.5
describe(housing.df)
## vars n mean sd median trimmed mad min max range
## CRIM 1 506 3.61 8.60 0.26 1.68 0.33 0.01 88.98 88.97
## ZN 2 506 11.36 23.32 0.00 5.08 0.00 0.00 100.00 100.00
## INDUS 3 506 11.14 6.86 9.69 10.93 9.37 0.46 27.74 27.28
## CHAS 4 506 0.07 0.25 0.00 0.00 0.00 0.00 1.00 1.00
## NOX 5 506 0.55 0.12 0.54 0.55 0.13 0.38 0.87 0.49
## RM 6 506 6.28 0.70 6.21 6.25 0.51 3.56 8.78 5.22
## AGE 7 506 68.57 28.15 77.50 71.20 28.98 2.90 100.00 97.10
## DIS 8 506 3.80 2.11 3.21 3.54 1.91 1.13 12.13 11.00
## RAD 9 506 9.55 8.71 5.00 8.73 2.97 1.00 24.00 23.00
## TAX 10 506 408.24 168.54 330.00 400.04 108.23 187.00 711.00 524.00
## PTRATIO 11 506 18.46 2.16 19.05 18.66 1.70 12.60 22.00 9.40
## B 12 506 356.67 91.29 391.44 383.17 8.09 0.32 396.90 396.58
## LSTAT 13 506 12.65 7.14 11.36 11.90 7.11 1.73 37.97 36.24
## MEDV 14 506 22.53 9.20 21.20 21.56 5.93 5.00 50.00 45.00
## CAT..MEDV 15 506 0.17 0.37 0.00 0.08 0.00 0.00 1.00 1.00
## skew kurtosis se
## CRIM 5.19 36.60 0.38
## ZN 2.21 3.95 1.04
## INDUS 0.29 -1.24 0.30
## CHAS 3.39 9.48 0.01
## NOX 0.72 -0.09 0.01
## RM 0.40 1.84 0.03
## AGE -0.60 -0.98 1.25
## DIS 1.01 0.46 0.09
## RAD 1.00 -0.88 0.39
## TAX 0.67 -1.15 7.49
## PTRATIO -0.80 -0.30 0.10
## B -2.87 7.10 4.06
## LSTAT 0.90 0.46 0.32
## MEDV 1.10 1.45 0.41
## CAT..MEDV 1.79 1.21 0.02
ftable(CHAS ~ RAD, data=housing.df)
## CHAS 0 1
## RAD
## 1 19 1
## 2 24 0
## 3 36 2
## 4 102 8
## 5 104 11
## 6 26 0
## 7 17 0
## 8 19 5
## 24 124 8
plot(housing.df)
plot(housing.df[,c(3,5,6,11,13,14)],pch=3)
cor(housing.df,housing.df$MV)
## CRIM ZN INDUS CHAS NOX
## CRIM 1.00000000 -0.20046922 0.40658341 -0.055891582 0.42097171
## ZN -0.20046922 1.00000000 -0.53382819 -0.042696719 -0.51660371
## INDUS 0.40658341 -0.53382819 1.00000000 0.062938027 0.76365145
## CHAS -0.05589158 -0.04269672 0.06293803 1.000000000 0.09120281
## NOX 0.42097171 -0.51660371 0.76365145 0.091202807 1.00000000
## RM -0.21924670 0.31199059 -0.39167585 0.091251225 -0.30218819
## AGE 0.35273425 -0.56953734 0.64477851 0.086517774 0.73147010
## DIS -0.37967009 0.66440822 -0.70802699 -0.099175780 -0.76923011
## RAD 0.62550515 -0.31194783 0.59512927 -0.007368241 0.61144056
## TAX 0.58276431 -0.31456332 0.72076018 -0.035586518 0.66802320
## PTRATIO 0.28994558 -0.39167855 0.38324756 -0.121515174 0.18893268
## B -0.38506394 0.17552032 -0.35697654 0.048788485 -0.38005064
## LSTAT 0.45562148 -0.41299457 0.60379972 -0.053929298 0.59087892
## MEDV -0.38830461 0.36044534 -0.48372516 0.175260177 -0.42732077
## CAT..MEDV -0.15198696 0.36529623 -0.36627559 0.108631150 -0.23250184
## RM AGE DIS RAD TAX
## CRIM -0.21924670 0.35273425 -0.37967009 0.625505145 0.58276431
## ZN 0.31199059 -0.56953734 0.66440822 -0.311947826 -0.31456332
## INDUS -0.39167585 0.64477851 -0.70802699 0.595129275 0.72076018
## CHAS 0.09125123 0.08651777 -0.09917578 -0.007368241 -0.03558652
## NOX -0.30218819 0.73147010 -0.76923011 0.611440563 0.66802320
## RM 1.00000000 -0.24026493 0.20524621 -0.209846668 -0.29204783
## AGE -0.24026493 1.00000000 -0.74788054 0.456022452 0.50645559
## DIS 0.20524621 -0.74788054 1.00000000 -0.494587930 -0.53443158
## RAD -0.20984667 0.45602245 -0.49458793 1.000000000 0.91022819
## TAX -0.29204783 0.50645559 -0.53443158 0.910228189 1.00000000
## PTRATIO -0.35550149 0.26151501 -0.23247054 0.464741179 0.46085304
## B 0.12806864 -0.27353398 0.29151167 -0.444412816 -0.44180801
## LSTAT -0.61380827 0.60233853 -0.49699583 0.488676335 0.54399341
## MEDV 0.69535995 -0.37695457 0.24992873 -0.381626231 -0.46853593
## CAT..MEDV 0.64126541 -0.19119589 0.11888651 -0.197924023 -0.27368672
## PTRATIO B LSTAT MEDV CAT..MEDV
## CRIM 0.2899456 -0.38506394 0.4556215 -0.3883046 -0.1519870
## ZN -0.3916785 0.17552032 -0.4129946 0.3604453 0.3652962
## INDUS 0.3832476 -0.35697654 0.6037997 -0.4837252 -0.3662756
## CHAS -0.1215152 0.04878848 -0.0539293 0.1752602 0.1086312
## NOX 0.1889327 -0.38005064 0.5908789 -0.4273208 -0.2325018
## RM -0.3555015 0.12806864 -0.6138083 0.6953599 0.6412654
## AGE 0.2615150 -0.27353398 0.6023385 -0.3769546 -0.1911959
## DIS -0.2324705 0.29151167 -0.4969958 0.2499287 0.1188865
## RAD 0.4647412 -0.44441282 0.4886763 -0.3816262 -0.1979240
## TAX 0.4608530 -0.44180801 0.5439934 -0.4685359 -0.2736867
## PTRATIO 1.0000000 -0.17738330 0.3740443 -0.5077867 -0.4434247
## B -0.1773833 1.00000000 -0.3660869 0.3334608 0.1551370
## LSTAT 0.3740443 -0.36608690 1.0000000 -0.7376627 -0.4699108
## MEDV -0.5077867 0.33346082 -0.7376627 1.0000000 0.7897888
## CAT..MEDV -0.4434247 0.15513696 -0.4699108 0.7897888 1.0000000