#this is where we write code
ls()
## character(0)
rm("x")
## Warning in rm("x"): object 'x' not found
rm(list=ls())
ls()
## character(0)
data(iris)
head(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
tail(iris)
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginica
names(iris)
## [1] "Sepal.Length" "Sepal.Width" "Petal.Length" "Petal.Width"
## [5] "Species"
iris$Sepal.Length2=32*iris$Sepal.Length
attach(iris)
mean(Sepal.Length2)
## [1] 186.9867
for (i in 1:125) {print(i)}
## [1] 1
## [1] 2
## [1] 3
## [1] 4
## [1] 5
## [1] 6
## [1] 7
## [1] 8
## [1] 9
## [1] 10
## [1] 11
## [1] 12
## [1] 13
## [1] 14
## [1] 15
## [1] 16
## [1] 17
## [1] 18
## [1] 19
## [1] 20
## [1] 21
## [1] 22
## [1] 23
## [1] 24
## [1] 25
## [1] 26
## [1] 27
## [1] 28
## [1] 29
## [1] 30
## [1] 31
## [1] 32
## [1] 33
## [1] 34
## [1] 35
## [1] 36
## [1] 37
## [1] 38
## [1] 39
## [1] 40
## [1] 41
## [1] 42
## [1] 43
## [1] 44
## [1] 45
## [1] 46
## [1] 47
## [1] 48
## [1] 49
## [1] 50
## [1] 51
## [1] 52
## [1] 53
## [1] 54
## [1] 55
## [1] 56
## [1] 57
## [1] 58
## [1] 59
## [1] 60
## [1] 61
## [1] 62
## [1] 63
## [1] 64
## [1] 65
## [1] 66
## [1] 67
## [1] 68
## [1] 69
## [1] 70
## [1] 71
## [1] 72
## [1] 73
## [1] 74
## [1] 75
## [1] 76
## [1] 77
## [1] 78
## [1] 79
## [1] 80
## [1] 81
## [1] 82
## [1] 83
## [1] 84
## [1] 85
## [1] 86
## [1] 87
## [1] 88
## [1] 89
## [1] 90
## [1] 91
## [1] 92
## [1] 93
## [1] 94
## [1] 95
## [1] 96
## [1] 97
## [1] 98
## [1] 99
## [1] 100
## [1] 101
## [1] 102
## [1] 103
## [1] 104
## [1] 105
## [1] 106
## [1] 107
## [1] 108
## [1] 109
## [1] 110
## [1] 111
## [1] 112
## [1] 113
## [1] 114
## [1] 115
## [1] 116
## [1] 117
## [1] 118
## [1] 119
## [1] 120
## [1] 121
## [1] 122
## [1] 123
## [1] 124
## [1] 125
for (i in 1:5) {
y=rnorm(i,10,5)
print(y)
}
## [1] 11.71084
## [1] 14.441111 5.545809
## [1] 6.763619 15.847062 12.994043
## [1] 12.466964 9.621464 4.663421 12.291968
## [1] 11.760415 -1.408712 12.997844 14.859923 17.269609
sd(Sepal.Length2)
## [1] 26.49812
sd(Sepal.Length)
## [1] 0.8280661
yourname=function(x){
y=x^3+log(32*x)-21*x+12
}
print(yourname(10))
## [1] 807.7683
yourname=function(x){
y=x^3+12
}
print(yourname(10))
## [1] 1012
for (i in 1:25) {print(yourname(i))}
## [1] 13
## [1] 20
## [1] 39
## [1] 76
## [1] 137
## [1] 228
## [1] 355
## [1] 524
## [1] 741
## [1] 1012
## [1] 1343
## [1] 1740
## [1] 2209
## [1] 2756
## [1] 3387
## [1] 4108
## [1] 4925
## [1] 5844
## [1] 6871
## [1] 8012
## [1] 9273
## [1] 10660
## [1] 12179
## [1] 13836
## [1] 15637
dim(iris)
## [1] 150 6
str(iris)
## 'data.frame': 150 obs. of 6 variables:
## $ Sepal.Length : num 5.1 4.9 4.7 4.6 5 5.4 4.6 5 4.4 4.9 ...
## $ Sepal.Width : num 3.5 3 3.2 3.1 3.6 3.9 3.4 3.4 2.9 3.1 ...
## $ Petal.Length : num 1.4 1.4 1.3 1.5 1.4 1.7 1.4 1.5 1.4 1.5 ...
## $ Petal.Width : num 0.2 0.2 0.2 0.2 0.2 0.4 0.3 0.2 0.2 0.1 ...
## $ Species : Factor w/ 3 levels "setosa","versicolor",..: 1 1 1 1 1 1 1 1 1 1 ...
## $ Sepal.Length2: num 163 157 150 147 160 ...
getwd()
## [1] "C:/Users/Dell/Documents/R"
setwd("C:/Users/Dell/Desktop")
dir()
## [1] "16508797_10155115909410362_414170078812994931_n.jpg"
## [2] "AJAY.xps"
## [3] "BigDiamonds.csv"
## [4] "BLOOD REPORT.pdf"
## [5] "CAM- Ajay Ohri.pdf"
## [6] "clustersas.html"
## [7] "desktop.ini"
## [8] "Dropbox.lnk"
## [9] "DVD.csv"
## [10] "GermanCredit.csv"
## [11] "Git Shell.lnk"
## [12] "GitHub.appref-ms"
## [13] "GoToMeeting.lnk"
## [14] "groceries.csv"
## [15] "IMS proschool"
## [16] "logistic regression - script for ppt.R"
## [17] "Program 1-results.rtf"
## [18] "Rdatasets"
## [19] "Results_ Modeling and Forecasting.html"
## [20] "Results_ Program 5.sas.html"
## [21] "Results_ Time Series Exploration.ctk.html"
## [22] "sas-university-edition-107140.pdf"
## [23] "test"
dir(pattern = ".csv")
## [1] "BigDiamonds.csv" "DVD.csv" "GermanCredit.csv"
## [4] "groceries.csv"
BigDiamonds2=read.csv("BigDiamonds.csv",header=T)
head(BigDiamonds2)
## X carat cut color clarity table depth cert measurements price
## 1 1 0.25 V.Good K I1 59 63.7 GIA 3.96 x 3.95 x 2.52 NA
## 2 2 0.23 Good G I1 61 58.1 GIA 4.00 x 4.05 x 2.30 NA
## 3 3 0.34 Good J I2 58 58.7 GIA 4.56 x 4.53 x 2.67 NA
## 4 4 0.21 V.Good D I1 60 60.6 GIA 3.80 x 3.82 x 2.31 NA
## 5 5 0.31 V.Good K I1 59 62.2 EGL 4.35 x 4.26 x 2.68 NA
## 6 6 0.20 Good G SI2 60 64.4 GIA 3.74 x 3.67 x 2.38 NA
## x y z
## 1 3.96 3.95 2.52
## 2 4.00 4.05 2.30
## 3 4.56 4.53 2.67
## 4 3.80 3.82 2.31
## 5 4.35 4.26 2.68
## 6 3.74 3.67 2.38
str(BigDiamonds2)
## 'data.frame': 598024 obs. of 13 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ carat : num 0.25 0.23 0.34 0.21 0.31 0.2 0.2 0.22 0.23 0.2 ...
## $ cut : Factor w/ 3 levels "Good","Ideal",..: 3 1 1 3 3 1 1 3 3 1 ...
## $ color : Factor w/ 9 levels "D","E","F","G",..: 8 4 7 1 8 4 4 1 8 3 ...
## $ clarity : Factor w/ 9 levels "I1","I2","IF",..: 1 1 2 1 1 5 5 1 5 4 ...
## $ table : num 59 61 58 60 59 60 63 61 57.5 65 ...
## $ depth : num 63.7 58.1 58.7 60.6 62.2 64.4 62.6 59.2 63.6 54.9 ...
## $ cert : Factor w/ 9 levels "AGS","EGL","EGL Intl.",..: 6 6 6 6 2 6 6 6 8 6 ...
## $ measurements: Factor w/ 241453 levels ""," 3.99 x 3.95 x 2.44",..: 19960 21917 48457 15701 37341 14661 14400 19642 17115 16177 ...
## $ price : int NA NA NA NA NA NA NA NA NA NA ...
## $ x : num 3.96 4 4.56 3.8 4.35 3.74 3.72 3.95 3.87 3.83 ...
## $ y : num 3.95 4.05 4.53 3.82 4.26 3.67 3.65 3.97 3.9 4 ...
## $ z : num 2.52 2.3 2.67 2.31 2.68 2.38 2.31 2.34 2.47 2.14 ...
head(BigDiamonds2)
## X carat cut color clarity table depth cert measurements price
## 1 1 0.25 V.Good K I1 59 63.7 GIA 3.96 x 3.95 x 2.52 NA
## 2 2 0.23 Good G I1 61 58.1 GIA 4.00 x 4.05 x 2.30 NA
## 3 3 0.34 Good J I2 58 58.7 GIA 4.56 x 4.53 x 2.67 NA
## 4 4 0.21 V.Good D I1 60 60.6 GIA 3.80 x 3.82 x 2.31 NA
## 5 5 0.31 V.Good K I1 59 62.2 EGL 4.35 x 4.26 x 2.68 NA
## 6 6 0.20 Good G SI2 60 64.4 GIA 3.74 x 3.67 x 2.38 NA
## x y z
## 1 3.96 3.95 2.52
## 2 4.00 4.05 2.30
## 3 4.56 4.53 2.67
## 4 3.80 3.82 2.31
## 5 4.35 4.26 2.68
## 6 3.74 3.67 2.38
str(BigDiamonds2)
## 'data.frame': 598024 obs. of 13 variables:
## $ X : int 1 2 3 4 5 6 7 8 9 10 ...
## $ carat : num 0.25 0.23 0.34 0.21 0.31 0.2 0.2 0.22 0.23 0.2 ...
## $ cut : Factor w/ 3 levels "Good","Ideal",..: 3 1 1 3 3 1 1 3 3 1 ...
## $ color : Factor w/ 9 levels "D","E","F","G",..: 8 4 7 1 8 4 4 1 8 3 ...
## $ clarity : Factor w/ 9 levels "I1","I2","IF",..: 1 1 2 1 1 5 5 1 5 4 ...
## $ table : num 59 61 58 60 59 60 63 61 57.5 65 ...
## $ depth : num 63.7 58.1 58.7 60.6 62.2 64.4 62.6 59.2 63.6 54.9 ...
## $ cert : Factor w/ 9 levels "AGS","EGL","EGL Intl.",..: 6 6 6 6 2 6 6 6 8 6 ...
## $ measurements: Factor w/ 241453 levels ""," 3.99 x 3.95 x 2.44",..: 19960 21917 48457 15701 37341 14661 14400 19642 17115 16177 ...
## $ price : int NA NA NA NA NA NA NA NA NA NA ...
## $ x : num 3.96 4 4.56 3.8 4.35 3.74 3.72 3.95 3.87 3.83 ...
## $ y : num 3.95 4.05 4.53 3.82 4.26 3.67 3.65 3.97 3.9 4 ...
## $ z : num 2.52 2.3 2.67 2.31 2.68 2.38 2.31 2.34 2.47 2.14 ...
#install.packages("XML")
library(XML)
url="http://stats.espncricinfo.com/ci/engine/stats/index.html?class=1;team=6;template=results;type=batting"
#Note I can also break the url string and use paste command to modify this url with parameters
tables=readHTMLTable(url)
ajay=tables$"Overall figures"
ajay
## Player Span Mat Inns NO Runs HS Ave 100 50 0
## 1 SR Tendulkar 1989-2013 200 329 33 15921 248* 53.78 51 68 14
## 2 R Dravid 1996-2012 163 284 32 13265 270 52.63 36 63 7
## 3 SM Gavaskar 1971-1987 125 214 16 10122 236* 51.12 34 45 12
## 4 VVS Laxman 1996-2012 134 225 34 8781 281 45.97 17 56 14
## 5 V Sehwag 2001-2013 103 178 6 8503 319 49.43 23 31 16
## 6 SC Ganguly 1996-2008 113 188 17 7212 239 42.17 16 35 13
## 7 DB Vengsarkar 1976-1992 116 185 22 6868 166 42.13 17 35 15
## 8 M Azharuddin 1984-2000 99 147 9 6215 199 45.03 22 21 5
## 9 GR Viswanath 1969-1983 91 155 10 6080 222 41.93 14 35 10
## 10 N Kapil Dev 1978-1994 131 184 15 5248 163 31.05 8 27 16
## 11 MS Dhoni 2005-2014 90 144 16 4876 224 38.09 6 33 10
## 12 M Amarnath 1969-1988 69 113 10 4378 138 42.50 11 24 12
## 13 V Kohli 2011-2017 54 91 7 4320 235 51.42 16 14 4
## 14 G Gambhir 2004-2016 58 104 5 4154 206 41.95 9 22 7
## 15 RJ Shastri 1981-1992 80 121 14 3830 206 35.79 11 12 9
## 16 PR Umrigar 1948-1962 59 94 8 3631 223 42.22 12 14 5
## 17 CA Pujara 2010-2017 44 73 6 3339 206* 49.83 10 12 2
## 18 M Vijay 2008-2017 48 81 1 3288 167 41.10 9 14 5
## 19 VL Manjrekar 1951-1965 55 92 10 3208 189* 39.12 7 15 11
## 20 NS Sidhu 1983-1999 51 78 2 3202 201 42.13 9 15 9
## 21 CG Borde 1958-1969 55 97 11 3061 177* 35.59 5 18 13
## 22 MAK Pataudi 1961-1975 46 83 3 2793 203* 34.91 6 16 7
## 23 SMH Kirmani 1976-1986 88 124 22 2759 102 27.04 2 12 7
## 24 FM Engineer 1961-1975 46 87 3 2611 121 31.08 2 16 7
## 25 A Kumble 1990-2008 132 173 32 2506 110* 17.77 1 5 17
## 26 P Roy 1951-1960 43 79 4 2442 173 32.56 5 9 14
## 27 AM Rahane 2013-2017 33 56 8 2317 188 48.27 8 9 4
## 28 Harbhajan Singh 1998-2015 103 145 23 2224 115 18.22 2 9 19
## 29 VS Hazare 1946-1953 30 52 6 2192 164* 47.65 7 9 4
## 30 AL Wadekar 1966-1974 37 71 3 2113 143 31.07 1 14 7
## 31 MH Mankad 1946-1959 44 72 5 2109 231 31.47 5 6 7
## 32 CPS Chauhan 1969-1981 40 68 2 2084 97 31.57 0 16 6
## 33 K Srikkanth 1981-1992 43 72 3 2062 123 29.88 2 12 7
## 34 ML Jaisimha 1959-1971 39 71 4 2056 129 30.68 3 12 9
## 35 SV Manjrekar 1987-1996 37 61 6 2043 218 37.14 4 9 3
## 36 DN Sardesai 1961-1972 30 55 4 2001 212 39.23 5 9 4
## 37 AD Gaekwad 1974-1985 40 70 4 1985 201 30.07 2 10 4
## 38 W Jaffer 2000-2008 31 58 1 1944 212 34.10 5 11 6
## 39 Yuvraj Singh 2003-2012 40 62 6 1900 169 33.92 3 11 7
## 40 R Ashwin 2011-2017 45 62 10 1816 124 34.92 4 10 3
## 41 NJ Contractor 1955-1962 31 52 1 1611 108 31.58 1 11 2
## 42 Yashpal Sharma 1979-1983 37 59 11 1606 140 33.45 2 9 4
## 43 M Prabhakar 1984-1995 39 58 9 1600 120 32.65 1 9 3
## 44 SM Patil 1980-1984 29 47 4 1588 174 36.93 4 7 4
## 45 S Dhawan 2013-2016 23 39 1 1464 187 38.52 4 3 4
## 46 NR Mongia 1994-2001 44 68 8 1442 152 24.03 1 6 6
## 47 RG Nadkarni 1955-1968 41 67 12 1414 122* 25.70 1 7 6
## 48 S Ramesh 1999-2001 19 37 1 1367 143 37.97 2 8 3
## 49 SS Das 2000-2002 23 40 2 1326 110 34.89 2 9 3
## 50 KS More 1986-1993 49 64 14 1285 73 25.70 0 7 7
str(ajay)
## 'data.frame': 50 obs. of 12 variables:
## $ Player: Factor w/ 50 levels "A Kumble","AD Gaekwad",..: 40 31 37 47 44 36 8 17 12 24 ...
## $ Span : Factor w/ 46 levels "1946-1953","1946-1959",..: 29 33 16 33 38 32 19 26 14 20 ...
## $ Mat : Factor w/ 36 levels "103","113","116",..: 10 8 4 7 1 2 3 36 35 5 ...
## $ Inns : Factor w/ 44 levels "104","113","121",..: 17 16 14 15 10 13 12 7 8 11 ...
## $ NO : Factor w/ 21 levels "1","10","11",..: 14 13 7 15 18 8 10 21 2 6 ...
## $ Runs : Factor w/ 50 levels "10122","1285",..: 10 4 1 50 49 48 47 46 45 44 ...
## $ HS : Factor w/ 46 levels "102","108","110",..: 41 42 39 43 44 40 18 27 34 16 ...
## $ Ave : Factor w/ 48 levels "17.77","18.22",..: 48 47 45 40 43 36 35 39 33 9 ...
## $ 100 : Factor w/ 21 levels "0","1","10","11",..: 17 14 13 8 11 7 8 10 6 20 ...
## $ 50 : Factor w/ 24 levels "10","11","12",..: 21 20 16 18 13 15 15 8 15 11 ...
## $ 0 : Factor w/ 16 levels "10","11","12",..: 5 15 3 5 7 4 6 13 1 7 ...
## $ : Factor w/ 1 level "": 1 1 1 1 1 1 1 1 1 1 ...
ajay$Runs=as.numeric(paste(ajay$Runs))
summary(ajay$Runs)
## Min. 1st Qu. Median Mean 3rd Qu. Max.
## 1285 1954 2474 3723 4278 15920
tables
## $`NULL`
## View overall figures\n[change view]
## 1 Primary team India
## 2 Ordered by runs scored (descending)
##
## $`NULL`
## NULL
##
## $`Overall figures`
## Player Span Mat Inns NO Runs HS Ave 100 50 0
## 1 SR Tendulkar 1989-2013 200 329 33 15921 248* 53.78 51 68 14
## 2 R Dravid 1996-2012 163 284 32 13265 270 52.63 36 63 7
## 3 SM Gavaskar 1971-1987 125 214 16 10122 236* 51.12 34 45 12
## 4 VVS Laxman 1996-2012 134 225 34 8781 281 45.97 17 56 14
## 5 V Sehwag 2001-2013 103 178 6 8503 319 49.43 23 31 16
## 6 SC Ganguly 1996-2008 113 188 17 7212 239 42.17 16 35 13
## 7 DB Vengsarkar 1976-1992 116 185 22 6868 166 42.13 17 35 15
## 8 M Azharuddin 1984-2000 99 147 9 6215 199 45.03 22 21 5
## 9 GR Viswanath 1969-1983 91 155 10 6080 222 41.93 14 35 10
## 10 N Kapil Dev 1978-1994 131 184 15 5248 163 31.05 8 27 16
## 11 MS Dhoni 2005-2014 90 144 16 4876 224 38.09 6 33 10
## 12 M Amarnath 1969-1988 69 113 10 4378 138 42.50 11 24 12
## 13 V Kohli 2011-2017 54 91 7 4320 235 51.42 16 14 4
## 14 G Gambhir 2004-2016 58 104 5 4154 206 41.95 9 22 7
## 15 RJ Shastri 1981-1992 80 121 14 3830 206 35.79 11 12 9
## 16 PR Umrigar 1948-1962 59 94 8 3631 223 42.22 12 14 5
## 17 CA Pujara 2010-2017 44 73 6 3339 206* 49.83 10 12 2
## 18 M Vijay 2008-2017 48 81 1 3288 167 41.10 9 14 5
## 19 VL Manjrekar 1951-1965 55 92 10 3208 189* 39.12 7 15 11
## 20 NS Sidhu 1983-1999 51 78 2 3202 201 42.13 9 15 9
## 21 CG Borde 1958-1969 55 97 11 3061 177* 35.59 5 18 13
## 22 MAK Pataudi 1961-1975 46 83 3 2793 203* 34.91 6 16 7
## 23 SMH Kirmani 1976-1986 88 124 22 2759 102 27.04 2 12 7
## 24 FM Engineer 1961-1975 46 87 3 2611 121 31.08 2 16 7
## 25 A Kumble 1990-2008 132 173 32 2506 110* 17.77 1 5 17
## 26 P Roy 1951-1960 43 79 4 2442 173 32.56 5 9 14
## 27 AM Rahane 2013-2017 33 56 8 2317 188 48.27 8 9 4
## 28 Harbhajan Singh 1998-2015 103 145 23 2224 115 18.22 2 9 19
## 29 VS Hazare 1946-1953 30 52 6 2192 164* 47.65 7 9 4
## 30 AL Wadekar 1966-1974 37 71 3 2113 143 31.07 1 14 7
## 31 MH Mankad 1946-1959 44 72 5 2109 231 31.47 5 6 7
## 32 CPS Chauhan 1969-1981 40 68 2 2084 97 31.57 0 16 6
## 33 K Srikkanth 1981-1992 43 72 3 2062 123 29.88 2 12 7
## 34 ML Jaisimha 1959-1971 39 71 4 2056 129 30.68 3 12 9
## 35 SV Manjrekar 1987-1996 37 61 6 2043 218 37.14 4 9 3
## 36 DN Sardesai 1961-1972 30 55 4 2001 212 39.23 5 9 4
## 37 AD Gaekwad 1974-1985 40 70 4 1985 201 30.07 2 10 4
## 38 W Jaffer 2000-2008 31 58 1 1944 212 34.10 5 11 6
## 39 Yuvraj Singh 2003-2012 40 62 6 1900 169 33.92 3 11 7
## 40 R Ashwin 2011-2017 45 62 10 1816 124 34.92 4 10 3
## 41 NJ Contractor 1955-1962 31 52 1 1611 108 31.58 1 11 2
## 42 Yashpal Sharma 1979-1983 37 59 11 1606 140 33.45 2 9 4
## 43 M Prabhakar 1984-1995 39 58 9 1600 120 32.65 1 9 3
## 44 SM Patil 1980-1984 29 47 4 1588 174 36.93 4 7 4
## 45 S Dhawan 2013-2016 23 39 1 1464 187 38.52 4 3 4
## 46 NR Mongia 1994-2001 44 68 8 1442 152 24.03 1 6 6
## 47 RG Nadkarni 1955-1968 41 67 12 1414 122* 25.70 1 7 6
## 48 S Ramesh 1999-2001 19 37 1 1367 143 37.97 2 8 3
## 49 SS Das 2000-2002 23 40 2 1326 110 34.89 2 9 3
## 50 KS More 1986-1993 49 64 14 1285 73 25.70 0 7 7
##
## $`NULL`
## V1 V2 V3
## 1 Go to page
##
## $`NULL`
## NULL
##
## $`NULL`
## Statsguru includes the following current or recent Test matches:
## 1 India v Bangladesh at Hyderabad (Deccan), Only Test, Feb 9-13, 2017\n[Test # 2249 - Live]\n » India 356/3 (90.0 ov, V Kohli 111*, AM Rahane 45*, Shakib Al Hasan 0/45) - Stumps
## 2 New Zealand v Bangladesh at Christchurch, 2nd Test, Jan 20-23, 2017\n[Test # 2248]
## 3 New Zealand v Bangladesh at Wellington, 1st Test, Jan 12-16, 2017\n[Test # 2246]
##
## $`NULL`
## V1 V2
## 1
## 2
## 3 <NA>
##
## $`NULL`
## NULL
summary(BigDiamonds2)
## X carat cut color
## Min. : 1 Min. :0.200 Good : 59680 G :96204
## 1st Qu.:149507 1st Qu.:0.500 Ideal :369448 F :93573
## Median :299013 Median :0.900 V.Good:168896 E :93483
## Mean :299013 Mean :1.071 H :86619
## 3rd Qu.:448518 3rd Qu.:1.500 D :73630
## Max. :598024 Max. :9.250 I :70282
## (Other):84233
## clarity table depth cert
## SI1 :116631 Min. : 0.00 Min. : 0.00 GIA :463555
## VS2 :111082 1st Qu.:56.00 1st Qu.:61.00 IGI : 43667
## SI2 :104300 Median :58.00 Median :62.10 EGL : 33814
## VS1 : 97730 Mean :57.63 Mean :61.06 EGL USA : 16079
## VVS2 : 65500 3rd Qu.:59.00 3rd Qu.:62.70 EGL Intl. : 11447
## VVS1 : 54798 Max. :75.90 Max. :81.30 EGL ISRAEL: 11301
## (Other): 47983 (Other) : 18161
## measurements price x
## 0.00 x 0.00 x 0.00: 425 Min. : 300 Min. : 0.150
## 0.00 x 0.00 x 0.00 : 222 1st Qu.: 1220 1st Qu.: 4.740
## 4.3 x 4.27 x 2.67 : 97 Median : 3503 Median : 5.780
## 4.31 x 4.29 x 2.68 : 87 Mean : 8753 Mean : 5.991
## 4.29 x 4.26 x 2.67 : 86 3rd Qu.:11174 3rd Qu.: 6.970
## 4.3 x 4.28 x 2.67 : 84 Max. :99990 Max. :13.890
## (Other) :597023 NA's :713 NA's :1815
## y z
## Min. : 1.000 Min. : 0.040
## 1st Qu.: 4.970 1st Qu.: 3.120
## Median : 6.050 Median : 3.860
## Mean : 6.199 Mean : 4.033
## 3rd Qu.: 7.230 3rd Qu.: 4.610
## Max. :13.890 Max. :13.180
## NA's :1852 NA's :2544
ajay2=c(23,45,78,NA,NA,89,NA)
is.na(ajay2)
## [1] FALSE FALSE FALSE TRUE TRUE FALSE TRUE
table(is.na(BigDiamonds2$price))
##
## FALSE TRUE
## 597311 713
mean(BigDiamonds2$price,na.rm = T)
## [1] 8753.018
diamondsforever=na.omit(BigDiamonds2)
summary(diamondsforever)
## X carat cut color
## Min. : 494 Min. :0.200 Good : 59149 G :95363
## 1st Qu.:149638 1st Qu.:0.500 Ideal :367026 E :92859
## Median :299312 Median :0.900 V.Good:167609 F :92772
## Mean :299221 Mean :1.073 H :85951
## 3rd Qu.:448775 3rd Qu.:1.500 D :73201
## Max. :598024 Max. :9.250 I :69879
## (Other):83759
## clarity table depth cert
## SI1 :115898 Min. : 0.00 Min. : 0.00 GIA :460036
## VS2 :110402 1st Qu.:56.00 1st Qu.:61.00 IGI : 43339
## SI2 :103671 Median :58.00 Median :62.00 EGL : 33722
## VS1 : 97113 Mean :57.66 Mean :61.09 EGL USA : 16019
## VVS2 : 65002 3rd Qu.:59.00 3rd Qu.:62.70 EGL Intl. : 11439
## VVS1 : 54284 Max. :75.90 Max. :81.30 EGL ISRAEL: 11285
## (Other): 47414 (Other) : 17944
## measurements price x
## 4.3 x 4.27 x 2.67 : 97 Min. : 300 Min. : 0.150
## 4.31 x 4.29 x 2.68: 87 1st Qu.: 1218 1st Qu.: 4.740
## 4.29 x 4.26 x 2.67: 86 Median : 3503 Median : 5.780
## 4.3 x 4.28 x 2.67 : 84 Mean : 8756 Mean : 5.992
## 4.3 x 4.28 x 2.68 : 83 3rd Qu.:11186 3rd Qu.: 6.970
## 4.29 x 4.26 x 2.66: 80 Max. :99990 Max. :13.890
## (Other) :593267
## y z
## Min. : 1.000 Min. : 0.040
## 1st Qu.: 4.970 1st Qu.: 3.120
## Median : 6.050 Median : 3.860
## Mean : 6.201 Mean : 4.036
## 3rd Qu.: 7.230 3rd Qu.: 4.610
## Max. :13.890 Max. :13.180
##
nrow(BigDiamonds2)-nrow(diamondsforever)
## [1] 4240
#iris
par(mfrow=c(2,4))
plot(iris$Sepal.Length)
plot(iris$Sepal.Length,type='l')
hist(iris$Sepal.Length)
boxplot(iris$Sepal.Length)
barplot(iris$Sepal.Length)
pie(table(iris$Species))
boxplot(iris$Sepal.Length~iris$Species)
money=c("50000","$50000","50,000","$50,000",50000)
money=gsub(",","",money)
money=gsub("\\$","",money)
money=as.numeric(money)
money
## [1] 50000 50000 50000 50000 50000
mean(money)
## [1] 50000
#install.packages("lubridate")
library(lubridate)
##
## Attaching package: 'lubridate'
## The following object is masked from 'package:base':
##
## date
dates=c("26jun98","1/09/2005","1January2016")
dates2=dmy(dates)
dates2
## [1] "1998-06-26" "2005-09-01" "2016-01-01"
ages=difftime(Sys.Date(),dates2)
ages
## Time differences in days
## [1] 6804 4180 406
dates3=c("7jun77")
dates4=dmy(dates3)
ages=difftime(Sys.Date(),dates4)
ages
## Time difference of 14493 days
names=c("John","rambo")
substr(names,1,2)
## [1] "Jo" "ra"
nchar(names)
## [1] 4 5
paste(ages)
## [1] "14493"
iris[1,]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species Sepal.Length2
## 1 5.1 3.5 1.4 0.2 setosa 163.2
iris[,1]
## [1] 5.1 4.9 4.7 4.6 5.0 5.4 4.6 5.0 4.4 4.9 5.4 4.8 4.8 4.3 5.8 5.7 5.4
## [18] 5.1 5.7 5.1 5.4 5.1 4.6 5.1 4.8 5.0 5.0 5.2 5.2 4.7 4.8 5.4 5.2 5.5
## [35] 4.9 5.0 5.5 4.9 4.4 5.1 5.0 4.5 4.4 5.0 5.1 4.8 5.1 4.6 5.3 5.0 7.0
## [52] 6.4 6.9 5.5 6.5 5.7 6.3 4.9 6.6 5.2 5.0 5.9 6.0 6.1 5.6 6.7 5.6 5.8
## [69] 6.2 5.6 5.9 6.1 6.3 6.1 6.4 6.6 6.8 6.7 6.0 5.7 5.5 5.5 5.8 6.0 5.4
## [86] 6.0 6.7 6.3 5.6 5.5 5.5 6.1 5.8 5.0 5.6 5.7 5.7 6.2 5.1 5.7 6.3 5.8
## [103] 7.1 6.3 6.5 7.6 4.9 7.3 6.7 7.2 6.5 6.4 6.8 5.7 5.8 6.4 6.5 7.7 7.7
## [120] 6.0 6.9 5.6 7.7 6.3 6.7 7.2 6.2 6.1 6.4 7.2 7.4 7.9 6.4 6.3 6.1 7.7
## [137] 6.3 6.4 6.0 6.9 6.7 6.9 5.8 6.8 6.7 6.7 6.3 6.5 6.2 5.9
iris[3,]
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species Sepal.Length2
## 3 4.7 3.2 1.3 0.2 setosa 150.4
iris2=subset(iris,iris$Sepal.Length>5 | Species=="setosa")
iris2
## Sepal.Length Sepal.Width Petal.Length Petal.Width Species
## 1 5.1 3.5 1.4 0.2 setosa
## 2 4.9 3.0 1.4 0.2 setosa
## 3 4.7 3.2 1.3 0.2 setosa
## 4 4.6 3.1 1.5 0.2 setosa
## 5 5.0 3.6 1.4 0.2 setosa
## 6 5.4 3.9 1.7 0.4 setosa
## 7 4.6 3.4 1.4 0.3 setosa
## 8 5.0 3.4 1.5 0.2 setosa
## 9 4.4 2.9 1.4 0.2 setosa
## 10 4.9 3.1 1.5 0.1 setosa
## 11 5.4 3.7 1.5 0.2 setosa
## 12 4.8 3.4 1.6 0.2 setosa
## 13 4.8 3.0 1.4 0.1 setosa
## 14 4.3 3.0 1.1 0.1 setosa
## 15 5.8 4.0 1.2 0.2 setosa
## 16 5.7 4.4 1.5 0.4 setosa
## 17 5.4 3.9 1.3 0.4 setosa
## 18 5.1 3.5 1.4 0.3 setosa
## 19 5.7 3.8 1.7 0.3 setosa
## 20 5.1 3.8 1.5 0.3 setosa
## 21 5.4 3.4 1.7 0.2 setosa
## 22 5.1 3.7 1.5 0.4 setosa
## 23 4.6 3.6 1.0 0.2 setosa
## 24 5.1 3.3 1.7 0.5 setosa
## 25 4.8 3.4 1.9 0.2 setosa
## 26 5.0 3.0 1.6 0.2 setosa
## 27 5.0 3.4 1.6 0.4 setosa
## 28 5.2 3.5 1.5 0.2 setosa
## 29 5.2 3.4 1.4 0.2 setosa
## 30 4.7 3.2 1.6 0.2 setosa
## 31 4.8 3.1 1.6 0.2 setosa
## 32 5.4 3.4 1.5 0.4 setosa
## 33 5.2 4.1 1.5 0.1 setosa
## 34 5.5 4.2 1.4 0.2 setosa
## 35 4.9 3.1 1.5 0.2 setosa
## 36 5.0 3.2 1.2 0.2 setosa
## 37 5.5 3.5 1.3 0.2 setosa
## 38 4.9 3.6 1.4 0.1 setosa
## 39 4.4 3.0 1.3 0.2 setosa
## 40 5.1 3.4 1.5 0.2 setosa
## 41 5.0 3.5 1.3 0.3 setosa
## 42 4.5 2.3 1.3 0.3 setosa
## 43 4.4 3.2 1.3 0.2 setosa
## 44 5.0 3.5 1.6 0.6 setosa
## 45 5.1 3.8 1.9 0.4 setosa
## 46 4.8 3.0 1.4 0.3 setosa
## 47 5.1 3.8 1.6 0.2 setosa
## 48 4.6 3.2 1.4 0.2 setosa
## 49 5.3 3.7 1.5 0.2 setosa
## 50 5.0 3.3 1.4 0.2 setosa
## 51 7.0 3.2 4.7 1.4 versicolor
## 52 6.4 3.2 4.5 1.5 versicolor
## 53 6.9 3.1 4.9 1.5 versicolor
## 54 5.5 2.3 4.0 1.3 versicolor
## 55 6.5 2.8 4.6 1.5 versicolor
## 56 5.7 2.8 4.5 1.3 versicolor
## 57 6.3 3.3 4.7 1.6 versicolor
## 59 6.6 2.9 4.6 1.3 versicolor
## 60 5.2 2.7 3.9 1.4 versicolor
## 62 5.9 3.0 4.2 1.5 versicolor
## 63 6.0 2.2 4.0 1.0 versicolor
## 64 6.1 2.9 4.7 1.4 versicolor
## 65 5.6 2.9 3.6 1.3 versicolor
## 66 6.7 3.1 4.4 1.4 versicolor
## 67 5.6 3.0 4.5 1.5 versicolor
## 68 5.8 2.7 4.1 1.0 versicolor
## 69 6.2 2.2 4.5 1.5 versicolor
## 70 5.6 2.5 3.9 1.1 versicolor
## 71 5.9 3.2 4.8 1.8 versicolor
## 72 6.1 2.8 4.0 1.3 versicolor
## 73 6.3 2.5 4.9 1.5 versicolor
## 74 6.1 2.8 4.7 1.2 versicolor
## 75 6.4 2.9 4.3 1.3 versicolor
## 76 6.6 3.0 4.4 1.4 versicolor
## 77 6.8 2.8 4.8 1.4 versicolor
## 78 6.7 3.0 5.0 1.7 versicolor
## 79 6.0 2.9 4.5 1.5 versicolor
## 80 5.7 2.6 3.5 1.0 versicolor
## 81 5.5 2.4 3.8 1.1 versicolor
## 82 5.5 2.4 3.7 1.0 versicolor
## 83 5.8 2.7 3.9 1.2 versicolor
## 84 6.0 2.7 5.1 1.6 versicolor
## 85 5.4 3.0 4.5 1.5 versicolor
## 86 6.0 3.4 4.5 1.6 versicolor
## 87 6.7 3.1 4.7 1.5 versicolor
## 88 6.3 2.3 4.4 1.3 versicolor
## 89 5.6 3.0 4.1 1.3 versicolor
## 90 5.5 2.5 4.0 1.3 versicolor
## 91 5.5 2.6 4.4 1.2 versicolor
## 92 6.1 3.0 4.6 1.4 versicolor
## 93 5.8 2.6 4.0 1.2 versicolor
## 95 5.6 2.7 4.2 1.3 versicolor
## 96 5.7 3.0 4.2 1.2 versicolor
## 97 5.7 2.9 4.2 1.3 versicolor
## 98 6.2 2.9 4.3 1.3 versicolor
## 99 5.1 2.5 3.0 1.1 versicolor
## 100 5.7 2.8 4.1 1.3 versicolor
## 101 6.3 3.3 6.0 2.5 virginica
## 102 5.8 2.7 5.1 1.9 virginica
## 103 7.1 3.0 5.9 2.1 virginica
## 104 6.3 2.9 5.6 1.8 virginica
## 105 6.5 3.0 5.8 2.2 virginica
## 106 7.6 3.0 6.6 2.1 virginica
## 108 7.3 2.9 6.3 1.8 virginica
## 109 6.7 2.5 5.8 1.8 virginica
## 110 7.2 3.6 6.1 2.5 virginica
## 111 6.5 3.2 5.1 2.0 virginica
## 112 6.4 2.7 5.3 1.9 virginica
## 113 6.8 3.0 5.5 2.1 virginica
## 114 5.7 2.5 5.0 2.0 virginica
## 115 5.8 2.8 5.1 2.4 virginica
## 116 6.4 3.2 5.3 2.3 virginica
## 117 6.5 3.0 5.5 1.8 virginica
## 118 7.7 3.8 6.7 2.2 virginica
## 119 7.7 2.6 6.9 2.3 virginica
## 120 6.0 2.2 5.0 1.5 virginica
## 121 6.9 3.2 5.7 2.3 virginica
## 122 5.6 2.8 4.9 2.0 virginica
## 123 7.7 2.8 6.7 2.0 virginica
## 124 6.3 2.7 4.9 1.8 virginica
## 125 6.7 3.3 5.7 2.1 virginica
## 126 7.2 3.2 6.0 1.8 virginica
## 127 6.2 2.8 4.8 1.8 virginica
## 128 6.1 3.0 4.9 1.8 virginica
## 129 6.4 2.8 5.6 2.1 virginica
## 130 7.2 3.0 5.8 1.6 virginica
## 131 7.4 2.8 6.1 1.9 virginica
## 132 7.9 3.8 6.4 2.0 virginica
## 133 6.4 2.8 5.6 2.2 virginica
## 134 6.3 2.8 5.1 1.5 virginica
## 135 6.1 2.6 5.6 1.4 virginica
## 136 7.7 3.0 6.1 2.3 virginica
## 137 6.3 3.4 5.6 2.4 virginica
## 138 6.4 3.1 5.5 1.8 virginica
## 139 6.0 3.0 4.8 1.8 virginica
## 140 6.9 3.1 5.4 2.1 virginica
## 141 6.7 3.1 5.6 2.4 virginica
## 142 6.9 3.1 5.1 2.3 virginica
## 143 5.8 2.7 5.1 1.9 virginica
## 144 6.8 3.2 5.9 2.3 virginica
## 145 6.7 3.3 5.7 2.5 virginica
## 146 6.7 3.0 5.2 2.3 virginica
## 147 6.3 2.5 5.0 1.9 virginica
## 148 6.5 3.0 5.2 2.0 virginica
## 149 6.2 3.4 5.4 2.3 virginica
## 150 5.9 3.0 5.1 1.8 virginica
## Sepal.Length2
## 1 163.2
## 2 156.8
## 3 150.4
## 4 147.2
## 5 160.0
## 6 172.8
## 7 147.2
## 8 160.0
## 9 140.8
## 10 156.8
## 11 172.8
## 12 153.6
## 13 153.6
## 14 137.6
## 15 185.6
## 16 182.4
## 17 172.8
## 18 163.2
## 19 182.4
## 20 163.2
## 21 172.8
## 22 163.2
## 23 147.2
## 24 163.2
## 25 153.6
## 26 160.0
## 27 160.0
## 28 166.4
## 29 166.4
## 30 150.4
## 31 153.6
## 32 172.8
## 33 166.4
## 34 176.0
## 35 156.8
## 36 160.0
## 37 176.0
## 38 156.8
## 39 140.8
## 40 163.2
## 41 160.0
## 42 144.0
## 43 140.8
## 44 160.0
## 45 163.2
## 46 153.6
## 47 163.2
## 48 147.2
## 49 169.6
## 50 160.0
## 51 224.0
## 52 204.8
## 53 220.8
## 54 176.0
## 55 208.0
## 56 182.4
## 57 201.6
## 59 211.2
## 60 166.4
## 62 188.8
## 63 192.0
## 64 195.2
## 65 179.2
## 66 214.4
## 67 179.2
## 68 185.6
## 69 198.4
## 70 179.2
## 71 188.8
## 72 195.2
## 73 201.6
## 74 195.2
## 75 204.8
## 76 211.2
## 77 217.6
## 78 214.4
## 79 192.0
## 80 182.4
## 81 176.0
## 82 176.0
## 83 185.6
## 84 192.0
## 85 172.8
## 86 192.0
## 87 214.4
## 88 201.6
## 89 179.2
## 90 176.0
## 91 176.0
## 92 195.2
## 93 185.6
## 95 179.2
## 96 182.4
## 97 182.4
## 98 198.4
## 99 163.2
## 100 182.4
## 101 201.6
## 102 185.6
## 103 227.2
## 104 201.6
## 105 208.0
## 106 243.2
## 108 233.6
## 109 214.4
## 110 230.4
## 111 208.0
## 112 204.8
## 113 217.6
## 114 182.4
## 115 185.6
## 116 204.8
## 117 208.0
## 118 246.4
## 119 246.4
## 120 192.0
## 121 220.8
## 122 179.2
## 123 246.4
## 124 201.6
## 125 214.4
## 126 230.4
## 127 198.4
## 128 195.2
## 129 204.8
## 130 230.4
## 131 236.8
## 132 252.8
## 133 204.8
## 134 201.6
## 135 195.2
## 136 246.4
## 137 201.6
## 138 204.8
## 139 192.0
## 140 220.8
## 141 214.4
## 142 220.8
## 143 185.6
## 144 217.6
## 145 214.4
## 146 214.4
## 147 201.6
## 148 208.0
## 149 198.4
## 150 188.8
