Curs 5

Incarcati tabelul pseudo_facebook.tsv

str(pf)

'data.frame':   99003 obs. of  15 variables:
 $ userid               : int  2094382 1192601 2083884 1203168 1733186 1524765 1136133 1680361 1365174 1712567 ...
 $ age                  : int  14 14 14 14 14 14 13 13 13 13 ...
 $ dob_day              : int  19 2 16 25 4 1 14 4 1 2 ...
 $ dob_year             : int  1999 1999 1999 1999 1999 1999 2000 2000 2000 2000 ...
 $ dob_month            : int  11 11 11 12 12 12 1 1 1 2 ...
 $ gender               : Factor w/ 2 levels "female","male": 2 1 2 1 2 2 2 1 2 2 ...
 $ tenure               : int  266 6 13 93 82 15 12 0 81 171 ...
 $ friend_count         : int  0 0 0 0 0 0 0 0 0 0 ...
 $ friendships_initiated: int  0 0 0 0 0 0 0 0 0 0 ...
 $ likes                : int  0 0 0 0 0 0 0 0 0 0 ...
 $ likes_received       : int  0 0 0 0 0 0 0 0 0 0 ...
 $ mobile_likes         : int  0 0 0 0 0 0 0 0 0 0 ...
 $ mobile_likes_received: int  0 0 0 0 0 0 0 0 0 0 ...
 $ www_likes            : int  0 0 0 0 0 0 0 0 0 0 ...
 $ www_likes_received   : int  0 0 0 0 0 0 0 0 0 0 ...

corelatia

cor.test(pf$age, pf$friend_count)

    Pearson's product-moment correlation

data:  pf$age and pf$friend_count
t = -8.6268, df = 99001, p-value < 2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.03363072 -0.02118189
sample estimates:
        cor 
-0.02740737 

?cor.test

qplot(pf$age, pf$friend_count)

r=cor.test(pf$tenure, pf$friend_count)

r

    Pearson's product-moment correlation

data:  pf$tenure and pf$friend_count
t = 53.049, df = 98999, p-value < 2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.1601927 0.1723067
sample estimates:
     cor 
0.166256 

r$estimate

     cor 
0.166256 

r$p.value

[1] 0

data(iris)

str(iris)

'data.frame':   150 obs. of  5 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 ...

pairs(iris)

pairs(iris[1:4])

library(ggplot2)

ggplot(aes(x=Sepal.Length, y=Petal.Length), data=iris)+
  geom_point(aes(color=Species))

install.packages('GGally')

library(GGally)

package <U+393C><U+3E31>GGally<U+393C><U+3E32> was built under R version 3.5.3
Attaching package: <U+393C><U+3E31>GGally<U+393C><U+3E32>

The following object is masked from <U+393C><U+3E31>package:dplyr<U+393C><U+3E32>:

    nasa

ggpairs(iris)

cor.test(iris[,1], iris[,3])

    Pearson's product-moment correlation

data:  iris[, 1] and iris[, 3]
t = 21.646, df = 148, p-value < 2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.8270363 0.9055080
sample estimates:
      cor 
0.8717538 

ggpairs(iris[1:4])

ggpairs(data=iris,  mapping=aes(color=Species, cols=4))

with(iris, cor.test(Sepal.Length, Sepal.Width))

    Pearson's product-moment correlation

data:  Sepal.Length and Sepal.Width
t = -1.4403, df = 148, p-value = 0.1519
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.27269325  0.04351158
sample estimates:
       cor 
-0.1175698 

cor.test(iris$Sepal.Length, iris$Sepal.Width)

    Pearson's product-moment correlation

data:  iris$Sepal.Length and iris$Sepal.Width
t = -1.4403, df = 148, p-value = 0.1519
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.27269325  0.04351158
sample estimates:
       cor 
-0.1175698 

with(subset(iris, iris$Species=='versicolor'), cor.test(Sepal.Length, Sepal.Width))

    Pearson's product-moment correlation

data:  Sepal.Length and Sepal.Width
t = 4.2839, df = 48, p-value = 8.772e-05
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.2900175 0.7015599
sample estimates:
      cor 
0.5259107 

with(pf, cor.test(likes_received, www_likes_received))

    Pearson's product-moment correlation

data:  likes_received and www_likes_received
t = 937.1, df = 99001, p-value < 2.2e-16
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 0.9473553 0.9486176
sample estimates:
      cor 
0.9479902 

ggplot(aes(x=likes_received, y=www_likes_received), data=pf)+
  geom_point()+
  coord_cartesian(xlim=c(0,quantile(pf$likes_received,0.99)), ylim=c(0,quantile(pf$www_likes_received,0.99)))

instalat pachet: alr3

library(alr3)

package <U+393C><U+3E31>alr3<U+393C><U+3E32> was built under R version 3.5.3Loading required package: car
package <U+393C><U+3E31>car<U+393C><U+3E32> was built under R version 3.5.3Loading required package: carData

Attaching package: <U+393C><U+3E31>car<U+393C><U+3E32>

The following object is masked from <U+393C><U+3E31>package:dplyr<U+393C><U+3E32>:

    recode

data("Mitchell")

str(Mitchell)

'data.frame':   204 obs. of  2 variables:
 $ Month: int  0 1 2 3 4 5 6 7 8 9 ...
 $ Temp : num  -5.18 -1.65 2.49 10.4 14.99 ...

?Mitchell

ggplot(data=Mitchell, aes(x=Month, y=Temp))+
  geom_point()

with(Mitchell, cor.test(Month, Temp))

    Pearson's product-moment correlation

data:  Month and Temp
t = 0.81816, df = 202, p-value = 0.4142
alternative hypothesis: true correlation is not equal to 0
95 percent confidence interval:
 -0.08053637  0.19331562
sample estimates:
       cor 
0.05747063 

Mitchell$Luna=Mitchell$Month%%12

table(Mitchell$Luna)

 0  1  2  3  4  5  6  7  8  9 10 11 
17 17 17 17 17 17 17 17 17 17 17 17 

ggplot(data=Mitchell, aes(x=Month, y=Temp))+
  geom_point()+
  facet_wrap(~Luna)

Mitchell$Luna <- factor(Mitchell$Luna, labels=c('ian','feb',
                'mar','apr','mai','iun','iul','aug','sep',
                'oct','nov','dec'))

ggplot(data=Mitchell, aes(x=Month, y=Temp))+
  geom_point(aes(color=Luna))

library(dplyr)

pf_varsta_sex <- group_by(pf, age, gender)

Factor `gender` contains implicit NA, consider using `forcats::fct_explicit_na`

pf_varsta_sex_statistici <- summarise(pf_varsta_sex,
                                      mediaFC=mean(friend_count),
                                      medianaFC=median(friend_count),
                                      n=n())

head(pf_varsta_sex_statistici)

ggplot(aes(x=age, y=medianaFC), data=subset(pf_varsta_sex_statistici, !is.na(gender)))+
  geom_line(aes(color=gender))

library(reshape2)

package <U+393C><U+3E31>reshape2<U+393C><U+3E32> was built under R version 3.5.3

head(pf_varsta_sex_statistici)

pf_Nou <- dcast(pf_varsta_sex_statistici, age~gender, value.var = 'medianaFC')

head(pf_Nou)

ggplot(data=pf_Nou, aes(x=age))+
  geom_line(aes(y=male, color=I('green')))+
  geom_line(aes(y=female, color=I('blue')))

ggplot(data=pf_Nou, aes(x=age, y=female/male))+
  geom_line()+
  geom_hline(yintercept = 1, linetype=4, color=I('red'))

pf$an <- 2019-ceiling(pf$tenure/365)

?ceiling

table(pf$an)

 2010  2011  2012  2013  2014  2015  2016  2017  2018  2019 
    9    15   581  1507  4557  5448  9860 33366 43588    70 

qplot(pf$an)

pf$an_intervale <- cut(pf$an, breaks=c(2010, 2013, 2015, 2017, 2019))

table(pf$an_intervale)

(2010,2013] (2013,2015] (2015,2017] (2017,2019] 
       2103       10005       43226       43658 

head(pf)

str(pf)

'data.frame':   99003 obs. of  17 variables:
 $ userid               : int  2094382 1192601 2083884 1203168 1733186 1524765 1136133 1680361 1365174 1712567 ...
 $ age                  : int  14 14 14 14 14 14 13 13 13 13 ...
 $ dob_day              : int  19 2 16 25 4 1 14 4 1 2 ...
 $ dob_year             : int  1999 1999 1999 1999 1999 1999 2000 2000 2000 2000 ...
 $ dob_month            : int  11 11 11 12 12 12 1 1 1 2 ...
 $ gender               : Factor w/ 2 levels "female","male": 2 1 2 1 2 2 2 1 2 2 ...
 $ tenure               : int  266 6 13 93 82 15 12 0 81 171 ...
 $ friend_count         : int  0 0 0 0 0 0 0 0 0 0 ...
 $ friendships_initiated: int  0 0 0 0 0 0 0 0 0 0 ...
 $ likes                : int  0 0 0 0 0 0 0 0 0 0 ...
 $ likes_received       : int  0 0 0 0 0 0 0 0 0 0 ...
 $ mobile_likes         : int  0 0 0 0 0 0 0 0 0 0 ...
 $ mobile_likes_received: int  0 0 0 0 0 0 0 0 0 0 ...
 $ www_likes            : int  0 0 0 0 0 0 0 0 0 0 ...
 $ www_likes_received   : int  0 0 0 0 0 0 0 0 0 0 ...
 $ an                   : num  2018 2018 2018 2018 2018 ...
 $ an_intervale         : Factor w/ 4 levels "(2010,2013]",..: 4 4 4 4 4 4 4 4 4 4 ...

ggplot(data=pf, aes(x=age, y=friend_count))+
  geom_line(stat='summary', fun.y=median, aes(color=an_intervale, linetype=an_intervale))

Incarcati tabelul diamonds in RStudio (fie il descarcati de pe site-ul cursului si il imprortati in R, fie il incarcati folosind data(diamonds), acesta fiind disponibil in pachetul ggplot2)

data("diamonds")

Cate observatii are tabelul?

str(diamonds)

Classes ‘tbl_df’, ‘tbl’ and 'data.frame':   53940 obs. of  10 variables:
 $ carat  : num  0.23 0.21 0.23 0.29 0.31 0.24 0.24 0.26 0.22 0.23 ...
 $ cut    : Ord.factor w/ 5 levels "Fair"<"Good"<..: 5 4 2 4 2 3 3 3 1 3 ...
 $ color  : Ord.factor w/ 7 levels "D"<"E"<"F"<"G"<..: 2 2 2 6 7 7 6 5 2 5 ...
 $ clarity: Ord.factor w/ 8 levels "I1"<"SI2"<"SI1"<..: 2 3 5 4 2 6 7 3 4 5 ...
 $ depth  : num  61.5 59.8 56.9 62.4 63.3 62.8 62.3 61.9 65.1 59.4 ...
 $ table  : num  55 61 65 58 58 57 57 55 61 61 ...
 $ price  : int  326 326 327 334 335 336 336 337 337 338 ...
 $ x      : num  3.95 3.89 4.05 4.2 4.34 3.94 3.95 4.07 3.87 4 ...
 $ y      : num  3.98 3.84 4.07 4.23 4.35 3.96 3.98 4.11 3.78 4.05 ...
 $ z      : num  2.43 2.31 2.31 2.63 2.75 2.48 2.47 2.53 2.49 2.39 ...

?diamonds

Cate variabile de tip factor sunt in tabel? Cate din ele sunt factor ordonat?

Construiti o histograma cu preturile diamantelor.

qplot(diamonds$price)

Calculati media si mediana preturilor.

mean(diamonds$price)

[1] 3932.8

median(diamonds$price)

[1] 2401

summary(diamonds$price)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    326     950    2401    3933    5324   18823 

Cate diamante au pretul mai mic de 500$?

cate=diamonds$price<500
table(cate)

cate
FALSE  TRUE 
52211  1729 

Dar mai mic de 250?

table(diamonds$price<250)

FALSE 
53940 

Dar mai mare sau egal cu 15000?

table(diamonds$price>=15000)

FALSE  TRUE 
52284  1656 

Personalizati histograma de la punctul 4 in 2 moduri (la alegere)

qplot(diamonds$price, main='titlu', color=I('coral'), fill=I('coral'))

Impartiti histograma de mai sus in functie de variabila cut.

qplot(data=diamonds, x=price, main='titlu', color=I('coral'), fill=I('coral'))+
  facet_wrap(~cut)

table(diamonds$cut)

     Fair      Good Very Good   Premium     Ideal 
     1610      4906     12082     13791     21551 

Care tip de diamant (cut) are:

cel mai mare pret?

cel mai mic pret?

cea mai mica valoare mediana?

by(diamonds$price, diamonds$cut, summary)

diamonds$cut: Fair
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    337    2050    3282    4359    5206   18574 
--------------------------------------------------- 
diamonds$cut: Good
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    327    1145    3050    3929    5028   18788 
--------------------------------------------------- 
diamonds$cut: Very Good
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    336     912    2648    3982    5373   18818 
--------------------------------------------------- 
diamonds$cut: Premium
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    326    1046    3185    4584    6296   18823 
--------------------------------------------------- 
diamonds$cut: Ideal
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    326     878    1810    3458    4678   18806 

with(diamonds, by(price, cut, summary))

cut: Fair
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    337    2050    3282    4359    5206   18574 
--------------------------------------------------- 
cut: Good
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    327    1145    3050    3929    5028   18788 
--------------------------------------------------- 
cut: Very Good
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    336     912    2648    3982    5373   18818 
--------------------------------------------------- 
cut: Premium
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    326    1046    3185    4584    6296   18823 
--------------------------------------------------- 
cut: Ideal
   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
    326     878    1810    3458    4678   18806 

x=by(diamonds$price, diamonds$cut, max)

max(x)

[1] 18823

Construiti boxplots pentru pret in functie de cut/clarity/color.