data_analysis.ipy

import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import os

# Set the style for seaborn
sns.set(style='whitegrid')

# Define directories
data_dir = 'data/'
figures_dir = 'figures/'
os.makedirs(figures_dir, exist_ok=True)

# Load simulation data
results_file = os.path.join(data_dir, 'simulation_results.csv')

if not os.path.exists(results_file):
    raise FileNotFoundError(f"The results file does not exist at: {results_file}. "
                            "Please ensure the simulation script has run and generated the data.")

df = pd.read_csv(results_file)

# Display the first few rows
print("First few rows of the dataset:")
print(df.head())

# Statistical Analysis
print("Statistical Summary:")
print(df.describe())

# Plot Best Path Length Distribution
plt.figure(figsize=(10, 6))
sns.histplot(df['best_path_length'], bins=15, kde=True)
plt.title('Distribution of Best Path Lengths')
plt.xlabel('Best Path Length')
plt.ylabel('Frequency')
plt.savefig(os.path.join(figures_dir, 'path_length_distribution.png'))
plt.show()

# Plot Convergence Time Distribution
plt.figure(figsize=(10, 6))
sns.histplot(df['iterations'], bins=15, kde=True, color='orange')
plt.title('Distribution of Iterations to Convergence')
plt.xlabel('Iterations')
plt.ylabel('Frequency')
plt.savefig(os.path.join(figures_dir, 'iterations_distribution.png'))
plt.show()

# Plot Total Time Distribution
plt.figure(figsize=(10, 6))
sns.histplot(df['total_time'], bins=15, kde=True, color='green')
plt.title('Distribution of Total Simulation Time')
plt.xlabel('Total Time (seconds)')
plt.ylabel('Frequency')
plt.savefig(os.path.join(figures_dir, 'total_time_distribution.png'))
plt.show()

# Box Plot for Best Path Lengths
plt.figure(figsize=(8, 6))
sns.boxplot(y='best_path_length', data=df)
plt.title('Box Plot of Best Path Lengths')
plt.ylabel('Best Path Length')
plt.savefig(os.path.join(figures_dir, 'best_path_length_boxplot.png'))
plt.show()

# Scatter Plot of Best Path Length vs. Iterations
plt.figure(figsize=(10, 6))
sns.scatterplot(x='iterations', y='best_path_length', data=df)
plt.title('Best Path Length vs. Iterations')
plt.xlabel('Iterations')
plt.ylabel('Best Path Length')
plt.savefig(os.path.join(figures_dir, 'best_path_vs_iterations.png'))
plt.show()

# Correlation Analysis
correlation = df.corr()
print("Correlation Matrix:")
print(correlation)

# Heatmap of Correlation Matrix
plt.figure(figsize=(8, 6))
sns.heatmap(correlation, annot=True, cmap='coolwarm')
plt.title('Correlation Matrix Heatmap')
plt.savefig(os.path.join(figures_dir, 'correlation_heatmap.png'))
plt.show()