

In [1]:

    
import os
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline

Set up output



In [2]:

    
mclab = os.getenv('MCLAB')
odir = os.path.join(mclab, 'cegs_ase_paper/pipeline_output/qsim_bayesian/')

Import data



In [3]:

    
fname = '/home/jfear/mclab/cegs_ase_paper/pipeline_output/qsim_bayesian/output/ase_dataset_for_bayesian_w_qsim_summary.csv'
dat = pd.read_csv(fname)
dat.head(3)









    Out[3]:






  
    
      
      line
      mating_status
      fusion_id
      qsim_mean_theta
      qsim_q025
      qsim_q975
      Bayesianpvalue_qsim
      flag_AI_qsim
    
  
  
    
      0
      r324
      V
      S24441_SI
      0.430
      0.297
      0.566
      0.336
      0
    
    
      1
      r324
      M
      S24447_SI
      0.923
      0.876
      0.956
      0.000
      1
    
    
      2
      r324
      V
      S24447_SI
      0.916
      0.868
      0.952
      0.000
      1

Generate Plots for Mated and Virgin



In [4]:

    
# Split dataset by sex
mated = dat[dat['mating_status'] == 'M'][['line','qsim_mean_theta']]
virgin = dat[dat['mating_status'] == 'V'][['line','qsim_mean_theta']]
virgin.head(1)









    Out[4]:






  
    
      
      line
      qsim_mean_theta
    
  
  
    
      0
      r324
      0.43

Plot Mated



In [5]:

    
# Get group levels
mLines = np.array([x for x in set(mated['line'])])
mLines.sort()

# Create a mask to split into multiple figures of 6x4 plots
grp = np.concatenate([np.ones(16), np.ones(16)*2, np.ones(16)*3, np.ones(16)*4, np.ones(4)*5])

# Iterate over multi figure groups and plot
for g in range(1,6):
    curr = mLines[grp == g]
    
    # Figure out the number of subplots I need
    num = int(np.sqrt(curr.shape[0]))
    
    # Plot figure
    fig, axes = plt.subplots(num, num, figsize=(8, 8))
    fig.suptitle(u'Distribution of QSIM Thetas\nMated', fontsize=12)
    axs = np.ravel(axes)
    for i, line in enumerate(curr):
        p = mated[mated['line'] == line]
        p.plot(kind='kde', ax=axs[i], fontsize=8, title=line, legend=False, color = 'r')
        #axs[i].set_xlabel('Line <------> Tester', fontsize=12)
        axs[i].axvline(0.5, lw=1, c='k')
        axs[i].get_yaxis().set_visible(False)
    
    fig.text(0.5, 0.04, 'Line <------------> Tester', ha='center', fontsize=20)
    plt.savefig(os.path.join(odir, 'mated_dist_qsim_theta_g{0}.png'.format(str(g))), bbox_inches='tight')
    plt.close(fig)

Plot Virgin



In [6]:

    
# Get group levels
vLines = np.array([x for x in set(virgin['line'])])
vLines.sort()
                   
# Create a mask to split into multiple figures of 6x4 plots
grp = np.concatenate([np.ones(16), np.ones(16)*2, np.ones(16)*3, np.ones(16)*4, np.ones(4)*5])

# Iterate over multi figure groups and plot
for g in range(1,6):
    curr = vLines[grp == g]
    
    # Figure out the number of subplots I need
    num = int(np.sqrt(curr.shape[0]))
    
    # Plot figure
    fig, axes = plt.subplots(num, num, figsize=(8,8))
    fig.suptitle(u'Distribution of QSIM Thetas\nVirgin', fontsize=12)

    axs = np.ravel(axes)
    for i, line in enumerate(curr):
        p = virgin[virgin['line'] == line]
        p.plot(kind='kde', ax=axs[i], fontsize=8, title=line, legend=False, color = 'r')
        #axs[i].set_xlabel('Line <--- AB ---> Tester', fontsize=12)
        axs[i].axvline(0.5, lw=1, c='k')
        axs[i].get_yaxis().set_visible(False)
        
    fig.text(0.5, 0.04, 'Line <------------> Tester', ha='center', fontsize=20)
    plt.savefig(os.path.join(odir, 'virgin_dist_qsim_theta_g{0}.png'.format(str(g))), bbox_inches='tight')
    plt.close(fig)



In [ ]:

	line	mating_status	fusion_id	qsim_mean_theta	qsim_q025	qsim_q975	Bayesianpvalue_qsim	flag_AI_qsim
0	r324	V	S24441_SI	0.430	0.297	0.566	0.336	0
1	r324	M	S24447_SI	0.923	0.876	0.956	0.000	1
2	r324	V	S24447_SI	0.916	0.868	0.952	0.000	1