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

Question 1, kind of

Browse Source
This commit is contained in:
Matan Horovitz
2023-02-26 18:25:07 +02:00
parent 6bd14b5476
commit 2d44b377fb
1 changed files with 21 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

31
R_Final_Tasks_Statistics.R
View File

@@ -3,27 +3,38 @@
#+We have chosen a dataset of CPU and GPU performance trends since 2000 - 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/michaelbryantds/cpu-and-gpu-product-data #+https://www.kaggle.com/datasets/michaelbryantds/cpu-and-gpu-product-data
raw_perf_data <- read.csv("/home/shmick/Downloads/chip_dataset.csv") 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")) ##BONUS: convert from EPOCH: as.Date(as.POSIXct(1100171890,origin = "1970-01-01"))
View(raw_perf_data) #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 perfomance 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.))
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.))
CPU_Transistor_Count <- order(CPU$Transistors..million.) #Calculate a crude 'performance factor' - the number of transistors multiplied by their frequency.
GPU_Transistor_Count <- order(GPU$Transistors..million.) 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 ##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])} #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 ##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.
#Calculate total number of columns in our dataset #Calculate total number of columns in our dataset
n <- ncol(kernel_commits) #n <- ncol(kernel_commits)
View(n) #View(n)
##QUESTION 3: pick two categorial variables - month (?), is documentation ##QUESTION 3: pick two categorcial variables - month (?), is documentation