basit frekans hesaplamaları

Gerekli kütüphaneleri yükleme

library(dplyr)
## 
## Attaching package: 'dplyr'
## The following objects are masked from 'package:stats':
## 
##     filter, lag
## The following objects are masked from 'package:base':
## 
##     intersect, setdiff, setequal, union
library(openintro)
## Loading required package: airports
## Loading required package: cherryblossom
## Loading required package: usdata
data(ucb_admit) #veri seti

cinsiyete göre frekans dağılımı

ucb_admit %>% count(gender)
##   gender    n
## 1 female 1835
## 2   male 2691

Bolumlere gore frekans dagılımı

ucb_admit %>% count(dept)
##   dept   n
## 1    A 933
## 2    B 585
## 3    C 918
## 4    D 792
## 5    E 584
## 6    F 714

Kabul sonucları

ucb_admit %>% count(admit)
##      admit    n
## 1 admitted 1755
## 2 rejected 2771

cinsiyet ve kabul çapraz dağılımı

ucb_admit %>% count(gender, admit)
##   gender    admit    n
## 1 female admitted  557
## 2 female rejected 1278
## 3   male admitted 1198
## 4   male rejected 1493

cinsiyet ve kabul çapraz dağılımına oran ekleyelim

ucb_admit %>% 
  count(gender, admit) %>% 
  group_by(gender) %>% 
  mutate(prop_admit = n/sum(n))
## # A tibble: 4 × 4
## # Groups:   gender [2]
##   gender admit        n prop_admit
##   <chr>  <chr>    <int>      <dbl>
## 1 female admitted   557      0.304
## 2 female rejected  1278      0.696
## 3 male   admitted  1198      0.445
## 4 male   rejected  1493      0.555

kabul oranlarını grafikte verelim frekans olarak

library(ggplot2)
ggplot(ucb_admit, aes(x = gender, fill = admit)) +
  geom_bar() 

ggplot(ucb_admit, aes(x = gender, fill = admit)) +
  geom_bar(position = "fill")

bölümlere göre dağılım

ucb_admit %>% count(dept, gender, admit)
##    dept gender    admit   n
## 1     A female admitted  89
## 2     A female rejected  19
## 3     A   male admitted 512
## 4     A   male rejected 313
## 5     B female admitted  17
## 6     B female rejected   8
## 7     B   male admitted 353
## 8     B   male rejected 207
## 9     C female admitted 202
## 10    C female rejected 391
## 11    C   male admitted 120
## 12    C   male rejected 205
## 13    D female admitted 131
## 14    D female rejected 244
## 15    D   male admitted 138
## 16    D   male rejected 279
## 17    E female admitted  94
## 18    E female rejected 299
## 19    E   male admitted  53
## 20    E   male rejected 138
## 21    F female admitted  24
## 22    F female rejected 317
## 23    F   male admitted  22
## 24    F   male rejected 351

uzun tabloları genis tabloya donusturme

library(tidyr)

ucb_admit %>% count(dept, gender, admit) %>% pivot_wider(names_from =  dept, values_from = n)
## # A tibble: 4 × 8
##   gender admit        A     B     C     D     E     F
##   <chr>  <chr>    <int> <int> <int> <int> <int> <int>
## 1 female admitted    89    17   202   131    94    24
## 2 female rejected    19     8   391   244   299   317
## 3 male   admitted   512   353   120   138    53    22
## 4 male   rejected   313   207   205   279   138   351

grafik

ggplot(ucb_admit, aes(y=gender, fill = admit)) +
  geom_bar(position =  "fill") +
  facet_wrap(.~dept) +
  scale_x_continuous(labels= scales:: label_percent()) +
  theme(legend.position = "bottom") + #left right top  
  labs(x= "yuzde")

grafigi tablo yapma

ucb_admit %>%  
  count(dept, gender, admit) %>%
  group_by(dept, gender) %>% mutate(toplam = sum(n), oran = round(n/toplam, 3)) %>% 
  filter(admit == "admitted") %>% 
  rename(bolum=dept, cinsiyet=gender, kabul=admit)
## # A tibble: 12 × 6
## # Groups:   bolum, cinsiyet [12]
##    bolum cinsiyet kabul        n toplam  oran
##    <chr> <chr>    <chr>    <int>  <int> <dbl>
##  1 A     female   admitted    89    108 0.824
##  2 A     male     admitted   512    825 0.621
##  3 B     female   admitted    17     25 0.68 
##  4 B     male     admitted   353    560 0.63 
##  5 C     female   admitted   202    593 0.341
##  6 C     male     admitted   120    325 0.369
##  7 D     female   admitted   131    375 0.349
##  8 D     male     admitted   138    417 0.331
##  9 E     female   admitted    94    393 0.239
## 10 E     male     admitted    53    191 0.277
## 11 F     female   admitted    24    341 0.07 
## 12 F     male     admitted    22    373 0.059

adlandırma yapma

ucb_admit_2 <- ucb_admit %>% 
mutate( cinsiyet = case_when( 
            gender == "female" ~ "kadin",
             gender == "male" ~ "erkek"),
         kabul_durum = case_when(
           admit == "admitted" ~ "kabul",
          .default = "ret"
         )) %>% 
  select( -admit, -gender) %>% 
  rename(bolum = dept) %>% 
  count ( bolum , cinsiyet , kabul_durum) %>% 
  group_by(bolum, cinsiyet) %>% 
  mutate( toplam = sum(n), oran = round(n/toplam,3)) %>% 
  filter(kabul_durum == "kabul")