In [1]:

    

import sys


    

In [2]:

    

import re


    

In [3]:

    

import glob
import pandas as pd


    

In [4]:

    

sys.path.append('./support_files/')


    

In [5]:

    

import aggregate_mummer_results as amr
import name_extractions


    

In [6]:

    

import plotting


    

In [7]:

    

import matplotlib.pyplot as plt
import matplotlib as mpl

% matplotlib inline


    

In [8]:

    

import seaborn as sns
sns.set_style('ticks')


    

In [9]:

    

summary_df = pd.read_csv("./percent_identities.tsv", sep='\t')


    

In [10]:

    

name_extractions.summary_stat_type('estimated % identity (2)')


    

    
Out[10]:





'estimated % identity'

In [11]:

    

summary_df.head()


    

    
Out[11]:






  

    

      

      
Unnamed: 0
      
% identity (1)
      
% identity (2)
      
estimated % identity (1)
      
estimated % identity (2)
      
frac of query aligned (1)
      
frac of query aligned (2)
      
mummer file
      
number alignments aggregated (1)
      
number alignments aggregated (2)
      
query alignment length total (1)
      
query alignment length total (2)
      
query bp
      
query contigs
      
query id
      
query name
      
ref bp
      
ref contigs
      
ref id
      
ref name
    
  
  

    

      
0
      
0
      
89.512390
      
89.512390
      
1.101441
      
1.101441
      
0.012305
      
0.012305
      
elviz-contigs-1056229.Burkholderiales-1/elviz-...
      
94
      
94
      
33702
      
33702
      
2738909
      
4662
      
Ga0066473
      
elviz-contigs-1056229.Burkholderiales-1
      
2022224
      
1990
      
Ga0066401
      
elviz-contigs-1056013.Comamonadaceae-1
    
    

      
1
      
0
      
90.094688
      
90.087233
      
9.281476
      
10.257853
      
0.103019
      
0.113866
      
elviz-contigs-1056229.Burkholderiales-1/elviz-...
      
799
      
918
      
282160
      
311868
      
2738909
      
4662
      
Ga0066473
      
elviz-contigs-1056229.Burkholderiales-1
      
4860710
      
5582
      
Ga0066479
      
elviz-contigs-1056247.Burkholderiales-1
    
    

      
2
      
0
      
91.209037
      
91.226886
      
3.687345
      
3.793253
      
0.040427
      
0.041580
      
elviz-contigs-1056229.Burkholderiales-1/elviz-...
      
280
      
293
      
110727
      
113885
      
2738909
      
4662
      
Ga0066473
      
elviz-contigs-1056229.Burkholderiales-1
      
2881263
      
2858
      
Ga0066437
      
elviz-contigs-1056121.Comamonadaceae-2
    
    

      
3
      
0
      
100.000000
      
100.000000
      
0.005769
      
0.005769
      
0.000058
      
0.000058
      
elviz-contigs-1056229.Burkholderiales-1/elviz-...
      
1
      
1
      
158
      
158
      
2738909
      
4662
      
Ga0066473
      
elviz-contigs-1056229.Burkholderiales-1
      
2904105
      
102
      
Ga0066438
      
elviz-contigs-1056124.Methylophilus-1
    
    

      
4
      
0
      
93.064607
      
92.872315
      
5.462180
      
5.595582
      
0.058692
      
0.060250
      
elviz-contigs-1056229.Burkholderiales-1/elviz-...
      
270
      
282
      
160753
      
165020
      
2738909
      
4662
      
Ga0066473
      
elviz-contigs-1056229.Burkholderiales-1
      
3012106
      
445
      
Ga0081644
      
Acidovorax-69
    
  

In [14]:

    

column_pairs = [
    ('% identity (1)', '% identity (2)'),
    ('% of query aligned (1)', '% of query aligned (2)'),
    ('estimated % identity (1)', 'estimated % identity (2)')
               ]


    

In [15]:

    

plotting.plot_old_versus_new_ani(summary_df, column_pairs)


    

    




0
('% identity (1)', '% identity (2)')
Axes(0.125,0.125;0.227941x0.775)
1
('% of query aligned (1)', '% of query aligned (2)')
Axes(0.398529,0.125;0.227941x0.775)
2
('estimated % identity (1)', 'estimated % identity (2)')
Axes(0.672059,0.125;0.227941x0.775)






    

In [ ]: