##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

chip <- read.csv("/home/shmick/Downloads/chip_dataset.csv")
#chip <- na.omit(chip)
##BONUS: convert from EPOCH: as.Date(as.POSIXct(1100171890,origin = "1970-01-01"))
#View(chip)
##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$Type == 'CPU',]
CPU <- subset(CPU, select= c(Product,Type,Release.Date,Process.Size..nm.,TDP..W.,Die.Size..mm.2.,Transistors..million.,Freq..MHz.))
GPU <- chip[chip$Type == 'GPU',]
GPU <- subset(GPU, select= c(Product,Type,Release.Date,Process.Size..nm.,TDP..W.,Die.Size..mm.2.,Transistors..million.,Freq..MHz.))
#Calculate a crude 'performance factor' - the number of transistors multiplied by their frequency.
CPU["Performance Factor"] <- CPU$Transistors..million.*CPU$Freq..MHz.
GPU["Performance Factor"] <- GPU$Transistors..million.*GPU$Freq..MHz.
View(CPU)
View(GPU)
#Range of total transistor advancement
max(CPU$Transistors..million.,na.rm=TRUE) - min(CPU$Transistors..million.,na.rm=TRUE)
max(GPU$Transistors..million.,na.rm=TRUE) - min(GPU$Transistors..million.,na.rm=TRUE)
#Omit chips with missing data
CPU <- na.omit(CPU)
GPU <- na.omit(GPU)
##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 categorcial variables - month (?), is documentation