fast_data_analysis.R

# Plot the data

# Imports
library(reshape2)
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/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)

data_path <- '/home/reynaldo/Documents/School/Spring2017/HPC/project/parallel_mcmc/parallel/complete_analysisSmallFast.csv'
fast_perf_data <- read.csv(file=data_path, header=TRUE, sep=",")
fast_melted_data <- melt(fast_perf_data, id=c("trial", "block", "thread"))
fast_five_hundred_trials <- fast_melted_data[which(fast_melted_data$trial == 500), ]
fast_five_hundred_trials$thread = as.factor(fast_five_hundred_trials$thread)



# Generate Plots

# Create Scatter plot (Blocks vs Threads)
base_plot <- ggplot(fast_five_hundred_trials, aes(x=block, y=time, color=variable))
base_plot <- base_plot  +  geom_point(aes(x=block, y=thread, size=value, color=variable)) 
base_plot <- base_plot + scale_size(range = c(0, 10))
base_plot <- base_plot + xlab("Blocks") + ylab("Time (seconds)") + labs(colour = "Implementation", size="Time")
base_plot <- base_plot + ggtitle("Faster Blocks vs Time") + theme(plot.title = element_text(hjust = 0.5))
base_plot

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

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


# Merge two datasets
our_fast_time_melted = fast_melted_data[(which(fast_melted_data$variable == "our_fast_time")), ]
all_melted_data <- rbind(melted_data, our_fast_time_melted)
all_five_hundred_trials <- all_melted_data[which(all_melted_data$trial == 500), ]


# Best Number of threads vs The other implementations for Blocks vs Time
one_threads_500_trials <- all_five_hundred_trials[which(all_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)") + 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


# Trials vs Time vs Implementation
one_thread_one_block <- all_melted_data[which(all_melted_data$thread == 1 & all_melted_data$block == 1), ]

line_base <- ggplot(one_thread_one_block, aes(x=trial, y=value, group=variable, shape=variable, color=variable)) +
  geom_line() +
  geom_point()
line_base <- line_base +  xlab("Trials") + ylab("Time (seconds)") + labs(colour = "Implementations", shape="Implementations")
line_base <- line_base + ggtitle("Small Data Trials vs Time 1 Block 1 Thread") + theme(plot.title = element_text(hjust = 0.5))
line_base