Spread within variables

In [2]:

    

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
%pylab inline
pd.__version__ # need 0.14.0 for multiindex slicing


    

    




Populating the interactive namespace from numpy and matplotlib






    
Out[2]:





'0.14.1'

In [3]:

    

o = pd.read_table("overall_statistics_ksmall.txt").set_index(["K","M","STATISTIC"])["VALUE"].unstack().loc[(10,200),:]
v = pd.read_table("variable_statistics_ksmall.txt").set_index(["K","M","STATISTIC","VARIABLE"])["VALUE"].unstack().unstack().loc[(10,200),:].unstack()


    

In [4]:

    

statistics_of_interest = ["rms_error","max_error","precisionbits","srr","correlation"]


    

In [5]:

    

# load variable information for joining levels to variables
v_info = pd.read_table("variable_information.txt").set_index(["VARIABLE","INFO"]).unstack().loc[:,"VALUE"]
v_info["levels"] = v_info["levels"].astype("int")
v_info.columns.name = ""


    

In [8]:

    

v.sort("rms_error")[["rms_error","max_error","precisionbits","srr"]].join(v_info["name"]).tail(5)


    

    
Out[8]:






  

    

      

      
rms_error
      
max_error
      
precisionbits
      
srr
      
name
    
    

      
VARIABLE
      

      

      

      

      

    
  
  

    

      
FREQS
      
 0.002167
      
 0.051397
      
 3.28217
      
 6.26081
      
          Fractional occurance of snow
    
    

      
FREQZM
      
 0.002256
      
 0.022684
      
 4.46221
      
 6.60402
      
 Fractional occurance of ZM convection
    
    

      
PSL
      
 0.002299
      
 0.024323
      
 4.36156
      
 6.29992
      
                    Sea level pressure
    
    

      
CLDMED
      
 0.002491
      
 0.030366
      
 4.04140
      
 6.07505
      
 Vertically-integrated mid-level cloud
    
    

      
SSTSFMBL
      
 0.002599
      
 0.062668
      
 2.99611
      
 6.28976
      
          Mobilization flux at surface
    
  

In [ ]:

    

v.sort("rms_error")[statistics_of_interest].join(v_info).tail(10)


    

In [ ]:

    

v.sort("max_error")[statistics_of_interest].join(v_info).head(10)


    

In [ ]:

    

v.sort("max_error")[statistics_of_interest].join(v_info).tail(10)


    

In [ ]:

    

v["error_ratio"] = v.max_error / v.rms_error
er = v.loc(axis=1)[("error_ratio",)].sort("error_ratio")
(er.mean(), er.median(),er.head(5),er.tail(5))


    

In [ ]:

    

v.loc[["U","FSDSC","Z3","CCN3"],["max_error","rms_error"]].T