5_GC_repeats_histograms

from glob import glob
import jenkspy
import matplotlib.pyplot as plt
import matplotlib as mpl
import multiprocessing
from natsort import natsorted
import numpy as np
import os
import pandas as pd
import snoop
import copy
from matplotlib import colors
from matplotlib.ticker import PercentFormatter
import pickle
from math import ceil
from collections import OrderedDict
from PIL import Image
from glob import glob
import ckmeans

where_i_am = '/my_path/to/data/' # replace with your path

n_bins=100
all_data={}
all_breaks={}

work_items={'Group_name': [['organism name',
   '/path/to/output/files_per_windows_1000.csv']]}

work_items = {'Group_name':[['organism name1',f'{where_i_am}Group_name/path/to/output/files_per_windows_1000.csv'],
                          ['organism name2',f'{where_i_am}Group_name/Spath/to/output/files_per_windows_1000.csv']]}

import matplotlib.pyplot as plt
import numpy as np

from matplotlib import colors
from matplotlib.ticker import PercentFormatter
n_bins = 150

path_to_histogram = f'{where_i_am}/histograms_of_all/'
try:
    os.mkdir(f'{where_i_am}histograms_of_all/')
except OSError as error:
    pass

for k,v in work_items.items():
    for organism in v:     
        try:
            df_my_csv = pd.read_csv(f'{organism[1]}')            
            df_my_csv['GC proc'] = pd.to_numeric(df_my_csv['GC proc'])
            try:
                df_my_csv['gc proc'] = pd.to_numeric(df_my_csv['gc proc'])
            except ValueError:
                df_my_csv['gc proc'] = 0.0
            # Generate two normal distributions           
            
            # Create histogram for data1
            plt.hist(df_my_csv['GC proc']*100, bins=n_bins, density=False, color='blue', edgecolor='DarkBlue', alpha=0.3, label='GC%',range=[20,60])

            # Create histogram for data2
            plt.hist(df_my_csv['gc proc']*100,  bins=n_bins, density=False, color='red', edgecolor='DarkRed', alpha=0.3, label='gc%',range=[20,60])
            
            # Set labels and title
            plt.xlabel('gc%')
            plt.ylabel('Number of Occurrences')
            plt.legend()
            plt.grid(True)
            plt.title(f'{k} {organism[0]}', fontsize=18)
            plt.savefig(f'{where_i_am}histograms_of_all/{organism[0]}_hist.svg', format="svg")
            plt.show()
            
        except FileNotFoundError:
            print('not found',organism[1])
            pass