R Markdown

This is an R Markdown document. Markdown is a simple formatting syntax for authoring HTML, PDF, and MS Word documents. For more details on using R Markdown see http://rmarkdown.rstudio.com.

When you click the Knit button a document will be generated that includes both content as well as the output of any embedded R code chunks within the document. You can embed an R code chunk like this:

#ANALİZDE KULLANILACAK PAKETLERİN YÜKLENMESİ VE KÜTÜPHANEYE ALMAK

library(ggplot2)
library(readr)
library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ stringr   1.5.2
## ✔ forcats   1.0.1     ✔ tibble    3.3.0
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.1.0     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors
library(dplyr)

Including Plots

You can also embed plots, for example:

## Rows: 395 Columns: 33
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ";"
## chr (17): school, sex, address, famsize, Pstatus, Mjob, Fjob, reason, guardi...
## dbl (16): age, Medu, Fedu, traveltime, studytime, failures, famrel, freetime...
## 
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.
#VERİ SETİNİ İNCELEMEK için glimpse FONKSİYONU KULLANILMIŞTIR
glimpse(df)
## Rows: 395
## Columns: 33
## $ school     <chr> "GP", "GP", "GP", "GP", "GP", "GP", "GP", "GP", "GP", "GP",…
## $ sex        <chr> "F", "F", "F", "F", "F", "M", "M", "F", "M", "M", "F", "F",…
## $ age        <dbl> 18, 17, 15, 15, 16, 16, 16, 17, 15, 15, 15, 15, 15, 15, 15,…
## $ address    <chr> "U", "U", "U", "U", "U", "U", "U", "U", "U", "U", "U", "U",…
## $ famsize    <chr> "GT3", "GT3", "LE3", "GT3", "GT3", "LE3", "LE3", "GT3", "LE…
## $ Pstatus    <chr> "A", "T", "T", "T", "T", "T", "T", "A", "A", "T", "T", "T",…
## $ Medu       <dbl> 4, 1, 1, 4, 3, 4, 2, 4, 3, 3, 4, 2, 4, 4, 2, 4, 4, 3, 3, 4,…
## $ Fedu       <dbl> 4, 1, 1, 2, 3, 3, 2, 4, 2, 4, 4, 1, 4, 3, 2, 4, 4, 3, 2, 3,…
## $ Mjob       <chr> "at_home", "at_home", "at_home", "health", "other", "servic…
## $ Fjob       <chr> "teacher", "other", "other", "services", "other", "other", …
## $ reason     <chr> "course", "course", "other", "home", "home", "reputation", …
## $ guardian   <chr> "mother", "father", "mother", "mother", "father", "mother",…
## $ traveltime <dbl> 2, 1, 1, 1, 1, 1, 1, 2, 1, 1, 1, 3, 1, 2, 1, 1, 1, 3, 1, 1,…
## $ studytime  <dbl> 2, 2, 2, 3, 2, 2, 2, 2, 2, 2, 2, 3, 1, 2, 3, 1, 3, 2, 1, 1,…
## $ failures   <dbl> 0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 0,…
## $ schoolsup  <chr> "yes", "no", "yes", "no", "no", "no", "no", "yes", "no", "n…
## $ famsup     <chr> "no", "yes", "no", "yes", "yes", "yes", "no", "yes", "yes",…
## $ paid       <chr> "no", "no", "yes", "yes", "yes", "yes", "no", "no", "yes", …
## $ activities <chr> "no", "no", "no", "yes", "no", "yes", "no", "no", "no", "ye…
## $ nursery    <chr> "yes", "no", "yes", "yes", "yes", "yes", "yes", "yes", "yes…
## $ higher     <chr> "yes", "yes", "yes", "yes", "yes", "yes", "yes", "yes", "ye…
## $ internet   <chr> "no", "yes", "yes", "yes", "no", "yes", "yes", "no", "yes",…
## $ romantic   <chr> "no", "no", "no", "yes", "no", "no", "no", "no", "no", "no"…
## $ famrel     <dbl> 4, 5, 4, 3, 4, 5, 4, 4, 4, 5, 3, 5, 4, 5, 4, 4, 3, 5, 5, 3,…
## $ freetime   <dbl> 3, 3, 3, 2, 3, 4, 4, 1, 2, 5, 3, 2, 3, 4, 5, 4, 2, 3, 5, 1,…
## $ goout      <dbl> 4, 3, 2, 2, 2, 2, 4, 4, 2, 1, 3, 2, 3, 3, 2, 4, 3, 2, 5, 3,…
## $ Dalc       <dbl> 1, 1, 2, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2, 1,…
## $ Walc       <dbl> 1, 1, 3, 1, 2, 2, 1, 1, 1, 1, 2, 1, 3, 2, 1, 2, 2, 1, 4, 3,…
## $ health     <dbl> 3, 3, 3, 5, 5, 5, 3, 1, 1, 5, 2, 4, 5, 3, 3, 2, 2, 4, 5, 5,…
## $ absences   <dbl> 6, 4, 10, 2, 4, 10, 0, 6, 0, 0, 0, 4, 2, 2, 0, 4, 6, 4, 16,…
## $ G1         <dbl> 5, 5, 7, 15, 6, 15, 12, 6, 16, 14, 10, 10, 14, 10, 14, 14, …
## $ G2         <dbl> 6, 5, 8, 14, 10, 15, 12, 5, 18, 15, 8, 12, 14, 10, 16, 14, …
## $ G3         <dbl> 6, 6, 10, 15, 10, 15, 11, 6, 19, 15, 9, 12, 14, 11, 16, 14,…

#ALIŞTIRMA 1 VERİ DÜZENLEME

# TÜM VERİ SETİNİN İÇERİSİNDEN ÖĞRENCİLERİN OKUL, YAŞ, ÇALIŞMA SÜRESİ, 3 FARKLI NOT DEĞERİ, DERSE KATILIM VE CİNSİYET DEĞİŞKENLERİ SEÇİLMİŞTİR.
df_sel <- df %>% select(school, age, studytime, G1, G2, G3, absences, sex)
# VERİ SETİNDE BULUNAN ÖĞRENCİLERDEN ERKEK VE YAŞI 19'DAN BÜYÜK ÖĞRENCİLER FİLTRELENMİŞ VE YAŞLARI BÜYÜKTEN KÜÇÜĞE DOĞRU SIRALANMIŞTIR
df_fil <- df %>% filter(sex == "M", age >= 19) %>%
                 arrange(desc(age))
# MUTATE İLE ÖĞRENCİ NOTLARININ AĞIRLIKLI NOT ORTALMASINA İLİŞKİN average_g DEĞİŞKENİ OLUŞTURULMUŞ VE IF ELSE İLE average_g <=10 PASS VEYA FAİL OLARAK ATANMIŞTIR.
df_mut <- df_sel %>% mutate( 
  average_g = round( ((((G1 + G2) / 2) + G3)/2),2),
  pass = if_else(average_g >=10, "pass", "fail")
  )
# ÖĞRENCİLER  OKUL VE CİNSİYETE GÖRE GRUPLANMIŞ, NOT, DERSTE BULUNMA VE  DERSTEN GEÇME ORANLARININ ORTALAMASI HESAPLANMIŞTIR
summary_by_school_sex <- df_mut %>%
  group_by(school, sex) %>%
  summarise(
    mean_avg = round(mean(average_g, na.rm = TRUE), 2),
    median_absences = median(absences, na.rm = TRUE),
    pass_rate_pct = round(mean(pass == "pass", na.rm = TRUE) * 100, 1)) %>%
  arrange(desc(mean_avg))
## `summarise()` has grouped output by 'school'. You can override using the
## `.groups` argument.

#ALIŞTIRMA 2 VERİ GÖRSELLEŞTİRME

#Öğrencilerin Agırlıklandırılmıs Not Ortalamalarına Gore Histogram Grafiginde Dagılımı
ggplot(df_mut , aes(x = average_g)) +
  geom_histogram(bins = 20, fill = "#4E79A7", color = "white", alpha = 0.8) +
  geom_vline(aes(xintercept = mean(average_g, na.rm = TRUE)),
             color = "red", linetype = "dashed", linewidth = 2) +
  labs(
    title = "Ogrencilerin Not Ortalamalarının Dağılımı",
    x = "Agirliklandirilmis Not Ortalamasi",
    y = "Ogrenci Sayısı"
  ) +
  theme_minimal(base_size = 15)

#Ogrencilerin not dağılımı normal dagılıma yakın bir dagılım göstermektedir. Ogrenci puanları grafigin orta noktalarına yıgılmıs ve uc noktalara dogru azalmıstır.
#Ogrencilerin Ders Calısma Suresi ile Ortalama Notları Arassındaki İliskinin Dağılım Grafiği ile İncelenmesi
ggplot(df_mut, aes(x = studytime, y = average_g)) +
  geom_point(aes(color = sex), size = 2, alpha = 0.7) +
  scale_color_manual(values = c("F" = "red", "M" = "green"),
                     name = "Cinsiyet", labels = c("Kız", "Erkek")) +
 
  labs(
    title = "Ders Calısma Suresi ile Ortalama Not Arasındaki İliski",
    x = "Ders Calısma Suresi (1=az, 4=cok)",
    y = "Ortalama Not"
  ) +
  theme_minimal(base_size = 13)

# Az (1 saat)  calısma suresinde erkek ogrencilerin daha yuksek notlar aldıgı, kız ogrencilerin ise daha dusuk notlara sahip oldugu gorulmektedir. Erkek ogrencilerin cogu az (1 saat) calısma süresine yıgılmısken kız ogrencilerin ise 2 saat ve 3 saat calısma sürelerine yıgıldıgını gormekteyız.

Note that the echo = FALSE parameter was added to the code chunk to prevent printing of the R code that generated the plot.