Second attempt

R_Final_Tasks_Statistics.R

@@ -1,32 +1,23 @@
 ##Final R assignment in Intro to Statistics course, fall semster.
 #+Written by Matan Horovitz (207130253) and Guy Amzaleg ()
-#+We have chosen a dataset of the first 600,000 commits to the  Linux Kernel Git repository - as published on Kaggle:
+#+We have chosen a dataset of CPU and GPU performance trends since 2000 - as published on Kaggle:
-#+https://www.kaggle.com/datasets/philschmidt/linux-kernel-git-revision-history
+#+https://www.kaggle.com/datasets/michaelbryantds/cpu-and-gpu-product-data
-#+This dataset examines commits made to the Linux kernel project over the last 12 years.
+
-raw_kernel_commits <- read.csv("/home/shmick/linux_kernel_git_revlog.csv")
+raw_perf_data <- read.csv("/home/shmick/Downloads/chip_dataset.csv")
 ##BONUS: convert from EPOCH: as.Date(as.POSIXct(1100171890,origin = "1970-01-01"))
-View(raw_kernel_commits)
+View(raw_perf_data)
-##For question 1, we have chosen to examine whether the amount of changes (additions and deletions) vary over time.
+##For question 1, we have chosen to examine which type of chip has examined the greater improvement over the years - GPU chips or CPU chips.
-##A larger amount of changes per commit is correlated with a decrease in the quality of the code - as more changes
+#+As chip perfomance is most directly correlated with the number of transistors, we have measured the pace of development based on pace of 
-#+are harder to track and audit, while a smaller amount of changes per commit implies stricter coding standards
+#+increasing transistor count.
-#+over time.
+CPU <- chip[chip$Type == 'CPU',]
-##To examine the correlation, we made a subset of the dataset, discarding data which is irrelevant to our question,
+GPU <- chip[chip$Type == 'GPU',]
-#+and summed all changes from the same commits into an aggregate - as we are not concerned about the files changed,
-#+only the total amount of changes on each individual commit.
 
-kernel_commits <- subset(raw_kernel_commits, select= c(author_timestamp,n_additions,n_deletions))
+CPU_Transistor_Count <- order(CPU$Transistors..million.)
-#  Make a subset  ^ of the dataset which includes  ^ the EPOCH time,^ additions ^ and deletions. 
+GPU_Transistor_Count <- order(GPU$Transistors..million.)
-#Rename the resulting dataset into friendlier column names
+##Iterate over date entries
-colnames(kernel_commits) <- c("EPOCH","Additions","Deletions")
+for (i in 1:length(CPU$Release.Date)){print(i)}
-#Sum additions and deletion into a new column, named "Total changes"
+##Get date
-kernel_commits["Total changes"] <- kernel_commits["Additions"]+kernel_commits["Deletions"]
+for (i in 1:length(CPU$Release.Date)){print(CPU$Release.Date[i])}
-View(kernel_commits) #< examine the resulting dataset
-#Unite all commits with same EPOCH to get changes PER COMMIT
-kernel_commits_sum <- aggregate(. ~ EPOCH,data=kernel_commits,FUN=sum)
-                          
-View(kernel_commits_sum)
-#Measure the correlation between EPOCH time (from oldest to newest) and the total number of changes per commit.
-cor(kernel_commits_sum["EPOCH"],kernel_commits_sum["Total changes"])
 
 ##QUESTION 2: measure number of columns in our dataset and calculate a permutation and combination of 
 #+that number, minus two, and 3.