Clustering Examples (RSWN)

Introduction: Replace Space With Newline problem

This document will make clustering plots for data from a range of settings and results.

Setup code

library('ggplot2')
library('cluster')
library('apcluster')

setwd("~/Documents/R/Clustering/lexicase-clusturing-analysis/R_notebooks")

source('../scripts/clustering.R')

Run These Once To Get Data Into CSVs

These transform the original data files into error files, and transform the error data into data frames we can use.

Lexicase

Lexicase, Run 1, a success

# transform_data_file_into_error_file("data/RSWN/lexicase/data1.csv")
# data_frame1 = make_frame_from_errors_file(
#   "data/RSWN/lexicase/errors_data1.csv", 1, 
#   "replace-space-with-newline", "lexicase", 20, elitize_generation_data)
# write.csv(data_frame1, "data/RSWN/lexicase/error_counts_and_div1.csv")

Lexicase, Run 6, a success

# transform_data_file_into_error_file("data/RSWN/lexicase/data6.csv")
# data_frame6 = make_frame_from_errors_file(
#   "data/RSWN/lexicase/errors_data6.csv", 6, 
#   "replace-space-with-newline", "lexicase", 20, elitize_generation_data)
# write.csv(data_frame6, "data/RSWN/lexicase/error_counts_and_div6.csv")

Lexicase, Run 2, a failure

# transform_data_file_into_error_file("../data/RSWN/lexicase/data2.csv")
# data_frame2 = make_frame_from_errors_file(
#   "../data/RSWN/lexicase/errors_data2.csv", 2, 
#   "replace-space-with-newline", "lexicase", 20, elitize_generation_data)
# write.csv(data_frame2, "../data/RSWN/lexicase/error_counts_and_div2.csv")

Lexicase, Run 3, a failure

# transform_data_file_into_error_file("../data/RSWN/lexicase/data3.csv")
# data_frame3 = make_frame_from_errors_file(
#   "../data/RSWN/lexicase/errors_data3.csv", 3, 
#   "replace-space-with-newline", "lexicase", 20, elitize_generation_data)
# write.csv(data_frame3, "../data/RSWN/lexicase/error_counts_and_div3.csv")

Tourney, size 7

Tourney, Run 50, a success

# transform_data_file_into_error_file("../data/RSWN/tourney/data50.csv")
# data_frame50 = make_frame_from_errors_file(
#   "../data/RSWN/tourney/errors_data50.csv", 50, 
#   "replace-space-with-newline", "tourney", 20, elitize_generation_data)
# write.csv(data_frame50, "../data/RSWN/tourney/error_counts_and_div50.csv")

Tourney, Run 52, a success

# transform_data_file_into_error_file("../data/RSWN/tourney/data52.csv")
# data_frame52 = make_frame_from_errors_file(
#   "../data/RSWN/tourney/errors_data52.csv", 52, 
#   "replace-space-with-newline", "tourney", 20, elitize_generation_data)
# write.csv(data_frame52, "../data/RSWN/tourney/error_counts_and_div52.csv")

Tourney, Run 57, a failure

# transform_data_file_into_error_file("../data/RSWN/tourney/data57.csv")
# data_frame57 = make_frame_from_errors_file(
#   "../data/RSWN/tourney/errors_data57.csv", 57, 
#   "replace-space-with-newline", "tourney", 20, elitize_generation_data)
# write.csv(data_frame57, "../data/RSWN/tourney/error_counts_and_div57.csv")

Tourney, Run 58, a failure

# transform_data_file_into_error_file("../data/RSWN/tourney/data58.csv")
# data_frame58 = make_frame_from_errors_file(
#   "../data/RSWN/tourney/errors_data58.csv", 58, 
#   "replace-space-with-newline", "tourney", 20, elitize_generation_data)
# write.csv(data_frame58, "../data/RSWN/tourney/error_counts_and_div58.csv")

Lexicase

Success

data_frame1 = read.csv("../data/RSWN/lexicase/error_counts_and_div1.csv")
data_frame6 = read.csv("../data/RSWN/lexicase/error_counts_and_div6.csv")

lexicase_success <- rbind(data_frame1, data_frame6)

Clusters

ggplot(lexicase_success, aes(x=generation)) + 
  geom_line(aes(y=cluster.count, color=interaction("Run", run.num))) + 
  labs(y="Number of Clusters", color="") +
  coord_cartesian(ylim=c(0,200))

Diversity

ggplot(lexicase_success, aes(x=generation)) + 
  geom_line(aes(y=error.diversity, color=interaction("Run", run.num))) + 
  labs(y="Error Diversity", color="") +
  coord_cartesian(ylim=c(0,1))

Failure

data_frame2 = read.csv("../data/RSWN/lexicase/error_counts_and_div2.csv")
data_frame3 = read.csv("../data/RSWN/lexicase/error_counts_and_div3.csv")

lexicase_failure <- rbind(data_frame2, data_frame3)

Clusters

ggplot(lexicase_failure, aes(x=generation)) + 
  geom_line(aes(y=cluster.count, color=interaction("Run", run.num))) + 
  labs(y="Number of Clusters", color="") +
  coord_cartesian(ylim=c(0,200))

Diversity

ggplot(lexicase_failure, aes(x=generation)) + 
  geom_line(aes(y=error.diversity, color=interaction("Run", run.num))) + 
  labs(y="Error Diversity", color="") +
  coord_cartesian(ylim=c(0,1))

Tournament (size 7)

Success

tourney_data_frame50 = read.csv("../data/RSWN/tourney/error_counts_and_div50.csv")
tourney_data_frame52 = read.csv("../data/RSWN/tourney/error_counts_and_div52.csv")

tourney_success <- rbind(tourney_data_frame50, tourney_data_frame52)

Clusters

ggplot(tourney_success, aes(x=generation)) + 
  geom_line(aes(y=cluster.count, color=interaction("Run", run.num))) + 
  labs(y="Number of Clusters", color="") +
  coord_cartesian(ylim=c(0,200))

Diversity

ggplot(tourney_success, aes(x=generation)) + 
  geom_line(aes(y=error.diversity, color=interaction("Run", run.num))) + 
  labs(y="Error Diversity", color="") +
  coord_cartesian(ylim=c(0,1))

Failure

tourney_data_frame57 = read.csv("../data/RSWN/tourney/error_counts_and_div57.csv")
tourney_data_frame58 = read.csv("../data/RSWN/tourney/error_counts_and_div58.csv")

tourney_failure <- rbind(tourney_data_frame57, tourney_data_frame58)

Clusters

ggplot(tourney_failure, aes(x=generation)) + 
  geom_line(aes(y=cluster.count, color=interaction("Run", run.num))) + 
  labs(y="Number of Clusters", color="") +
  coord_cartesian(ylim=c(0,200))

Diversity

ggplot(tourney_failure, aes(x=generation)) + 
  geom_line(aes(y=error.diversity, color=interaction("Run", run.num))) + 
  labs(y="Error Diversity", color="") +
  coord_cartesian(ylim=c(0,1))