##Final R assignment in Intro to Statistics course, fall semster.
#+Written by Matan Horovitz (207130253) and Guy Amzaleg ()
#+We have chosen a dataset of CPU and GPU performance trends since 2000 - as published on Kaggle:
#+https://www.kaggle.com/datasets/michaelbryantds/cpu-and-gpu-product-data

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_perf_data)
##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.
#+As chip perfomance is most directly correlated with the number of transistors, we have measured the pace of development based on pace of 
#+increasing transistor count.
CPU <- chip[chip$Type == 'CPU',]
GPU <- chip[chip$Type == 'GPU',]

CPU_Transistor_Count <- order(CPU$Transistors..million.)
GPU_Transistor_Count <- order(GPU$Transistors..million.)
##Iterate over date entries
for (i in 1:length(CPU$Release.Date)){print(i)}
##Get date
for (i in 1:length(CPU$Release.Date)){print(CPU$Release.Date[i])}

##QUESTION 2: measure number of columns in our dataset and calculate a permutation and combination of 
#+that number, minus two, and 3.

#Calculate total number of columns in our dataset
n <- ncol(kernel_commits)
View(n)

##QUESTION 3: pick two categorial variables - month (?), is documentation