In [23]:

    

import seaborn as sns
import pandas as pd
#plotting inside ipython
import matplotlib.pyplot as plt
import matplotlib
matplotlib.style.use('ggplot')
%matplotlib nbagg
import matplotlib.pyplot as plt
plt.gcf().subplots_adjust(bottom=0.15)


sns.set(style="ticks")
df = pd.read_csv('data3.csv')#, index_col='structure')


    

In [2]:

    

print df.head()


    

    




                           structure  ss+seq  ss+seq+conservation   \
0       lariat-capping ribozyme (#5)     NaN                   NaN   
1  adenosylcobalamin riboswitch (#6)     NaN                 19.83   
2                             sam #8     NaN                   NaN   
3          c-di-AMP riboswitch (#12)     NaN                   NaN   
4             ZMP riboswitch * (#13)    8.24                  7.11   

   ss+seq+homologs  ss+seq+homologs+conservation  
0              NaN                           NaN  
1              NaN                         14.92  
2              NaN                           NaN  
3              NaN                           NaN  
4              NaN                          5.55  

In [3]:

    

dfm = pd.melt(df,id_vars=['structure'])#, value_vars=['B', 'C'])


    

In [4]:

    

dfm.columns=['structure', 'mode', 'rmsd']
dfm


    

    
Out[4]:






  

    

      

      
structure
      
mode
      
rmsd
    
  
  

    

      
0
      
lariat-capping ribozyme (#5)
      
ss+seq
      
NaN
    
    

      
1
      
adenosylcobalamin riboswitch (#6)
      
ss+seq
      
NaN
    
    

      
2
      
sam #8
      
ss+seq
      
NaN
    
    

      
3
      
c-di-AMP riboswitch (#12)
      
ss+seq
      
NaN
    
    

      
4
      
ZMP riboswitch * (#13)
      
ss+seq
      
8.24
    
    

      
5
      
lariat-capping ribozyme (#5)
      
ss+seq+conservation
      
NaN
    
    

      
6
      
adenosylcobalamin riboswitch (#6)
      
ss+seq+conservation
      
19.83
    
    

      
7
      
sam #8
      
ss+seq+conservation
      
NaN
    
    

      
8
      
c-di-AMP riboswitch (#12)
      
ss+seq+conservation
      
NaN
    
    

      
9
      
ZMP riboswitch * (#13)
      
ss+seq+conservation
      
7.11
    
    

      
10
      
lariat-capping ribozyme (#5)
      
ss+seq+homologs
      
NaN
    
    

      
11
      
adenosylcobalamin riboswitch (#6)
      
ss+seq+homologs
      
NaN
    
    

      
12
      
sam #8
      
ss+seq+homologs
      
NaN
    
    

      
13
      
c-di-AMP riboswitch (#12)
      
ss+seq+homologs
      
NaN
    
    

      
14
      
ZMP riboswitch * (#13)
      
ss+seq+homologs
      
NaN
    
    

      
15
      
lariat-capping ribozyme (#5)
      
ss+seq+homologs+conservation
      
NaN
    
    

      
16
      
adenosylcobalamin riboswitch (#6)
      
ss+seq+homologs+conservation
      
14.92
    
    

      
17
      
sam #8
      
ss+seq+homologs+conservation
      
NaN
    
    

      
18
      
c-di-AMP riboswitch (#12)
      
ss+seq+homologs+conservation
      
NaN
    
    

      
19
      
ZMP riboswitch * (#13)
      
ss+seq+homologs+conservation
      
5.55
    
  

In [70]:

    

plt.rcParams['figure.figsize']=(20,10)
p = sns.factorplot(x="structure", y="rmsd", hue="mode", main="evoClustRNA", data=dfm, size=6, legend=False)
p.set_xticklabels(rotation=40)
p.axes[0][0].margins(x=1, y=1)
ax = p.axes[0][0]
ax.set_title('EvoClustRNA')
plt.tight_layout()
plt.figsize=(20, 6)
plt.legend(loc='upper left')
p.axes[0][0].set_ylim([0, 30])
#plt.legend(["f1"], loc="upper left")
#fig = p.get_figure()
#fig.set_size_inches(10, 10)
#fig.savefig("progress.png", orientation='portrait', dpi=500)


    

    















    












    
Out[70]:





(0, 30)

In [ ]: