shmick/R
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Digging into question 3

Browse Source
This commit is contained in:
Matan Horovitz
2023-03-06 15:15:02 +02:00
parent 2d44b377fb
commit d2cc765ed1
1 changed files with 35 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
R_Final_Tasks_Statistics.R
View File

@@ -8,27 +8,39 @@ chip <- read.csv("/home/shmick/Downloads/chip_dataset.csv")
##BONUS: convert from EPOCH: as.Date(as.POSIXct(1100171890,origin = "1970-01-01")) ##BONUS: convert from EPOCH: as.Date(as.POSIXct(1100171890,origin = "1970-01-01"))
#View(chip) #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. ##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 #+As chip performance is most directly correlated with the number of transistors, we have measured the pace of development based on pace of
#+increasing transistor count. #+increasing transistor count.
CPU <- chip[chip$Type == 'CPU',] CPU <- chip[chip$Type == 'CPU',]
CPU <- subset(CPU, select= c(Product,Type,Release.Date,Process.Size..nm.,TDP..W.,Die.Size..mm.2.,Transistors..million.,Freq..MHz.)) 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$Type == 'GPU',] GPU <- chip[chip$Type == 'GPU',]
GPU <- subset(GPU, select= c(Product,Type,Release.Date,Process.Size..nm.,TDP..W.,Die.Size..mm.2.,Transistors..million.,Freq..MHz.)) 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. #Calculate a crude 'performance factor' - the number of transistors multiplied by their frequency.
CPU["Performance Factor"] <- CPU$Transistors..million.*CPU$Freq..MHz. #CPU["Performance Factor"])
GPU["Performance Factor"] <- GPU$Transistors..million.*GPU$Freq..MHz.
View(CPU)
View(GPU)
#Range of total transistor advancement #Range of total transistor advancement
max(CPU$Transistors..million.,na.rm=TRUE) - min(CPU$Transistors..million.,na.rm=TRUE) 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) max(GPU$Transistors..million.,na.rm=TRUE) - min(GPU$Transistors..million.,na.rm=TRUE)
#Omit chips with missing data #Omit chips with missing data
CPU <- na.omit(CPU) #CPU <- na.omit(CPU)
GPU <- na.omit(GPU) #GPU <- na.omit(GPU)
##Iterate over date entries ##Iterate over date entries
#for (i in 1:length(CPU$Release.Date)){print(i)} #for (i in 1:length(CPU$Release.Date)){print(i)}
##Get date ##Get date
#for (i in 1:length(CPU$Release.Date)){print(CPU$Release.Date[i])} ##Install the 'lubridate' package to deal with conversion to EPOCH time
#install.packages('lubridate')
#library(lubridate)
#dates <- strptime(CPU$Release.Date,format="%Y-%m-%d")
#as.integer(as.POSIXct(CPU$Release.Date))
#posix_format_date <- c()
#or (date in 1:length(CPU$Release.Date)){
# cat("Date is", date)
# human_format_date <- CPU$Release.Date[date]
# print(human_format_date)
# posix_format_date[date] <- strptime(human_format_date,format="%Y-%m-%d")
#}
#for (i in CPU$Release.Date){
# print(i)
#}
##QUESTION 2: measure number of columns in our dataset and calculate a permutation and combination of ##QUESTION 2: measure number of columns in our dataset and calculate a permutation and combination of
#+that number, minus two, and 3. #+that number, minus two, and 3.
@@ -37,4 +49,18 @@ GPU <- na.omit(GPU)
#n <- ncol(kernel_commits) #n <- ncol(kernel_commits)
#View(n) #View(n)
##QUESTION 3: pick two categorcial variables - month (?), is documentation ##QUESTION 3: pick two categorcial variables (Chip type, foundry) and see whether they're dependent
#+1. Probablity of chip type
#+2. Probability of foundry
#+3. Multiplty
#Sample 1 variable from 'Type' column
chip_type_sample <- sample(chip$Type,1)
#Count how many times it appears in it's column
p_chip_type_sample <- (length(which(chip$Type==chip_type_sample)))/length(chip$Type)
chip_foundry_sample <- sample (chip$Foundry,1)
p_chip_foundry_sample <- (length(which(chip$Foundry==chip_foundry_sample)))/length(chip$Foundry)
chip_type_sample_matrix <- chip[chip$Type == chip_type_sample,]
p_chip_type_foundry_sample <- (length(which(chip_type_sample_matrix$Foundry==chip_foundry_sample)))/length(chip_type_sample_matrix$Foundry)
#p_victim_bastard <- p_neo_bastard * nrow(CPU )
p_chip_type_foundry_sample * p_chip_type_sample