CSV Pie Chart

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np

# Replace 'Line Plot.csv' with the actual CSV file path
df = pd.read_csv('Line Plot.csv')

# Extract data from the DataFrame
values1 = df['Raw Reads']
values2 = df['Trimmed Reads']
values3 = df['Aligned Reads']
values4 = df['Deduplicated Reads']
values5 = df['Stitched Reads']

# Combine the data into a list of lists
data = [values1, values2, values3, values4, values5]

# Apply a log10 transformation to all data points
data_log10 = [np.log10(data_point) for data_point in data]

# Define custom colors for each violin
colors = ['skyblue', 'lightcoral', 'lightgreen', 'orange', 'lightseagreen']

# Set the figure size (optional)
plt.figure(figsize=(12, 6))

# Create a ViolinPlot object
vp = plt.violinplot(data_log10, showmedians=True, vert=False, widths=0.8)

# Customize the violin plot
for i, body in enumerate(vp['bodies']):
    body.set_facecolor(colors[i])
    body.set_edgecolor('black')
    body.set_alpha(0.7)

# Add labels to the medians
medians = [median.get_xdata().mean() for median in vp['cmedians']]
for i, median in enumerate(vp['cmedians']):
    median.set_label(f'Median {i + 1}')
    plt.text(median.get_xdata().mean(), i, f'{medians[i]:.2f}', horizontalalignment='center', verticalalignment='bottom')

# Add a legend
plt.legend()

# Set y-axis labels
plt.yticks(np.arange(1, 6), ['Raw Reads', 'Trimmed Reads', 'Aligned Reads', 'Deduplicated Reads', 'Stitched Reads'])
plt.ylabel('Read Types')

# Customize the plot
plt.title('Violin Plot of Reads (log10 scale)')
plt.xlabel('Reads (log10 scale)')

# Show the plot
plt.tight_layout()
plt.show()