Skip to content

Commit

Permalink
Browse files Browse the repository at this point in the history
Created a more file of small_data analysis called complete_analysis (…
…which isn't complete yet, I need analysis3.csv). Added code to generate plot for blocks vs time vs algorithm for 1 thread.
  • Loading branch information
rjm11010 committed May 3, 2017
1 parent 8cf890b commit ae4f00b
Show file tree
Hide file tree
Showing 2 changed files with 197 additions and 6 deletions.
19 changes: 13 additions & 6 deletions data_analysis.R
Expand Up @@ -7,10 +7,12 @@ library(ggplot2)
# Load the data
# Change path to file
# data_path <- '../parallel/analysis.csv' # You can use this instead
data_path <- '/home/reynaldo/Documents/School/Spring2017/HPC/project/parallel_mcmc/parallel/analysis.csv'
data_path <- '/home/reynaldo/Documents/School/Spring2017/HPC/project/parallel_mcmc/parallel/complete_analysis.csv'
perf_data <- read.csv(file=data_path, header=TRUE, sep=",")
melted_data <- melt(perf_data, id=c("trial", "block", "thread"))
five_hundred_trials <- melted_data[which(melted_data$trial == 500), ]
five_hundred_trials$thread = as.factor(five_hundred_trials$thread)


# Generate Plots

Expand All @@ -23,7 +25,6 @@ base_plot <- base_plot + ggtitle("Blocks vs Time") + theme(plot.title = element_
base_plot

# Find which combination of blocks and threads works best
five_hundred_trials$thread = as.factor(five_hundred_trials$thread)
ours_five_hundred_trials <- five_hundred_trials[which(five_hundred_trials$variable == "our_time"), ]
ours_five_hundred_trials <- ours_five_hundred_trials[which(!is.na(ours_five_hundred_trials$thread)), ]

Expand All @@ -34,10 +35,16 @@ line_base <- line_base + xlab("Blocks") + ylab("Time (seconds)") + labs(colour
line_base <- line_base + ggtitle("Blocks vs Time vs Threads") + theme(plot.title = element_text(hjust = 0.5))
line_base

# Line Plot
line_base <- ggplot(five_hundred_trials, aes(x=block, y=value, group=variable, shape=variable, color=variable)) +

# Best Number of threads vs The other implementations for Blocks vs Time
one_threads_500_trials <- five_hundred_trials[which(five_hundred_trials$thread == 1), ]

line_base <- ggplot(one_threads_500_trials, aes(x=block, y=value, group=variable, shape=variable, color=variable)) +
geom_line() +
geom_point()
line_base <- line_base + xlab("Blocks") + ylab("Time (seconds)")
line_base <- line_base + ggtitle("Blocks vs Time") + theme(plot.title = element_text(hjust = 0.5))
line_base <- line_base + xlab("Blocks") + ylab("Time (seconds)") + labs(colour = "Implementations", shape="Implementations")
line_base <- line_base + ggtitle("Blocks vs Time vs Implementation") + theme(plot.title = element_text(hjust = 0.5))
line_base



184 changes: 184 additions & 0 deletions parallel/complete_analysis.csv
@@ -0,0 +1,184 @@
trial,block,thread,seq_time,our_time,their_time
1000,10,1,2.48,7.14,5.51
1000,10,1,2.53,6.67,5.51
1000,10,16,2.50,139.07,5.48
1000,10,16,2.54,178.51,5.44
1000,10,2,2.51,8.21,5.53
1000,10,2,2.52,8.76,5.73
1000,10,32,2.51,538.93,5.67
1000,10,4,2.52,13.49,5.76
1000,10,4,2.56,16.78,5.43
1000,10,8,2.48,38.57,5.68
1000,10,8,2.50,49.38,5.51
1000,1,1,2.52,15.32,3.50
1000,1,1,2.56,17.62,5.64
1000,1,16,2.50,27.86,5.47
1000,1,16,2.52,4.98,3.51
1000,1,2,2.49,9.16,3.48
1000,1,2,2.50,11.39,5.43
1000,1,32,2.48,52.96,5.74
1000,1,32,2.54,8.68,3.48
1000,1,4,2.53,8.39,5.42
1000,1,4,2.56,6.09,3.47
1000,1,8,2.53,7.11,5.84
1000,1,8,2.54,4.80,3.48
1000,2,1,2.50,11.11,5.80
1000,2,1,2.53,9.06,3.53
1000,2,16,2.49,8.60,3.49
1000,2,16,2.53,12.81,5.52
1000,2,2,2.52,6.00,3.49
1000,2,2,2.53,8.29,5.54
1000,2,32,2.51,33.89,5.45
1000,2,32,2.54,24.51,3.52
1000,2,4,2.49,7.04,5.56
1000,2,4,2.52,4.74,3.48
1000,2,8,2.48,27.41,5.68
1000,2,8,2.48,4.85,3.46
1000,3,1,2.50,6.92,3.48
1000,3,1,2.51,9.33,5.67
1000,3,16,2.50,15.13,3.48
1000,3,16,2.50,21.80,5.75
1000,3,2,2.48,5.03,3.43
1000,3,2,2.49,7.32,5.64
1000,3,32,2.51,51.25,3.50
1000,3,32,2.55,68.31,5.77
1000,3,4,2.48,4.48,3.49
1000,3,4,2.51,20.97,5.62
1000,3,8,2.51,6.26,3.49
1000,3,8,2.54,9.66,5.54
1000,4,1,2.51,8.08,5.41
1000,4,1,2.56,5.88,3.52
1000,4,16,2.51,33.86,5.76
1000,4,16,2.52,26.73,5.79
1000,4,2,2.48,7.51,5.56
1000,4,2,2.49,4.64,3.43
1000,4,32,2.49,116.94,5.75
1000,4,32,2.53,90.77,5.67
1000,4,4,2.49,9.10,5.70
1000,4,4,2.53,7.95,5.80
1000,4,8,2.52,10.62,5.57
1000,4,8,2.55,12.74,5.42
1000,5,1,2.48,7.32,5.71
1000,5,1,2.48,7.45,5.60
1000,5,16,2.55,49.56,5.50
1000,5,16,2.58,38.65,5.47
1000,5,2,2.48,6.85,5.81
1000,5,2,2.51,7.19,5.40
1000,5,32,2.52,139.01,5.45
1000,5,32,2.60,178.62,5.43
1000,5,4,2.50,32.43,5.55
1000,5,4,2.52,7.65,5.66
1000,5,8,2.51,17.09,5.76
1000,5,8,2.54,13.71,5.54
1000,6,1,2.49,7.02,5.72
1000,6,1,2.50,7.37,5.83
1000,6,16,2.48,53.47,5.64
1000,6,16,2.51,68.46,5.76
1000,6,2,2.53,6.64,5.64
1000,6,2,2.55,7.03,5.40
1000,6,32,2.50,253.79,5.50
1000,6,32,2.51,197.33,5.52
1000,6,4,2.48,8.74,5.50
1000,6,4,2.50,9.83,5.65
1000,6,8,2.48,17.27,5.44
1000,6,8,2.54,23.41,5.85
1000,7,1,2.49,6.93,5.51
1000,7,1,2.50,7.14,5.43
1000,7,16,2.51,70.84,5.40
1000,7,16,2.51,90.67,5.52
1000,7,2,2.48,6.81,5.54
1000,7,2,2.48,7.59,5.54
1000,7,32,2.51,342.33,5.46
1000,7,32,2.54,266.71,5.59
1000,7,4,2.50,9.88,5.60
1000,7,4,2.52,11.09,5.50
1000,7,8,2.49,27.16,5.48
1000,7,8,2.50,21.47,5.72
1000,8,1,2.49,6.63,5.56
1000,8,1,2.52,6.93,5.61
1000,8,16,2.51,116.35,5.51
1000,8,16,2.52,90.62,5.77
1000,8,2,2.52,7.20,5.69
1000,8,2,2.53,26.16,5.58
1000,8,32,2.49,444.95,5.70
1000,8,32,2.54,346.69,5.90
1000,8,4,2.48,12.75,5.58
1000,8,4,2.56,12.69,5.52
1000,8,8,2.50,33.50,5.39
1000,8,8,2.51,26.50,5.41
1000,9,1,2.53,7.05,5.69
1000,9,1,2.57,6.84,5.53
1000,9,16,2.52,145.90,5.79
1000,9,16,2.53,113.43,6.01
1000,9,2,2.52,8.06,5.59
1000,9,2,2.53,7.56,5.47
1000,9,32,2.52,437.83,5.73
1000,9,32,2.52,560.67,5.59
1000,9,4,2.51,12.51,5.68
1000,9,4,2.52,14.89,5.59
1000,9,8,2.51,41.42,6.13
1000,9,8,2.52,32.33,5.51
1500,1,1,3.77,24.00,6.07
1500,1,2,3.76,14.91,5.99
1500,1,4,3.76,10.19,6.00
1500,1,8,3.78,8.27,5.87
500,10,1,1.25,5.79,4.94
500,10,16,1.27,91.35,5.14
500,10,2,1.25,6.78,5.38
500,10,32,1.25,347.22,4.99
500,10,4,1.25,10.76,5.09
500,10,8,1.28,27.12,5.07
500,1,1,1.32,11.04,5.19
500,1,16,1.23,11.17,5.09
500,1,2,1.25,7.83,5.12
500,1,32,1.23,19.00,5.06
500,1,4,1.23,6.29,5.26
500,1,8,1.23,5.71,4.91
500,2,1,1.24,7.77,4.93
500,2,16,1.26,8.75,5.10
500,2,2,1.23,6.46,5.08
500,2,32,1.24,19.14,5.01
500,2,4,1.31,5.81,5.20
500,2,8,1.31,11.47,5.36
500,3,1,1.26,6.83,5.16
500,3,16,1.24,13.03,5.14
500,3,2,1.25,5.91,5.15
500,3,32,1.26,36.76,5.08
500,3,4,1.28,9.60,5.05
500,3,8,1.30,7.16,5.15
500,4,1,1.28,6.42,5.03
500,4,16,1.24,19.18,5.13
500,4,2,1.25,7.63,5.07
500,4,32,1.29,60.84,5.30
500,4,4,1.27,6.24,5.02
500,4,8,1.25,8.76,5.15
500,5,1,1.27,6.14,5.01
500,5,16,1.24,26.93,4.97
500,5,2,1.28,5.66,5.10
500,5,32,1.27,91.70,5.16
500,5,4,1.29,7.33,5.05
500,5,8,1.23,10.78,5.47
500,6,1,1.24,5.86,5.38
500,6,16,1.25,36.46,5.02
500,6,2,1.24,5.90,5.24
500,6,32,1.25,129.10,5.10
500,6,4,1.25,7.49,4.99
500,6,8,1.23,13.03,5.03
500,7,1,1.27,5.94,5.04
500,7,16,1.30,48.24,4.95
500,7,2,1.25,6.21,5.07
500,7,32,1.26,173.50,5.05
500,7,4,1.23,7.91,5.04
500,7,8,1.24,15.93,5.00
500,8,1,1.24,5.87,5.11
500,8,16,1.26,60.60,4.93
500,8,2,1.26,6.27,5.56
500,8,32,1.23,224.66,5.02
500,8,4,1.25,8.68,5.42
500,8,8,1.24,19.21,5.11
500,9,1,1.28,6.08,5.30
500,9,16,1.25,75.13,5.04
500,9,2,1.25,6.55,5.15
500,9,32,1.26,282.70,4.96
500,9,4,1.31,9.61,5.14
500,9,8,1.30,23.06,4.95

0 comments on commit ae4f00b

Please sign in to comment.