Phantom Index when NaN in MultiIndex · Issue #5286 · pandas-dev/pandas (original) (raw)

csv_str = """u1,u2,u3,d1,d2,d3,d4
Good Things,C,,1,1,1,1
Good Things,R,,1,1,1,1
Bad Things,C,,1,1,1,1
Bad Things,T,,1,1,1,1
Okay Things,N,B,1,1,1,1
Okay Things,N,D,1,1,1,1
Okay Things,B,,1,1,1,1
Okay Things,D,,1,1,1,1"""
d_nan = pd.read_csv(StringIO.StringIO(csv_str), na_filter=False,index_col=[0,1,2])
d_no_nan = pd.read_csv(StringIO.StringIO(csv_str), na_filter=False,index_col=[0,1,2],na_values=[], keep_default_na=False)

In [63]: d_nan
Out[63]: 
                    d1  d2  d3  d4
u1          u2 u3                 
Good Things C  NaN   1   1   1   1
            R  NaN   1   1   1   1
Bad Things  C  NaN   1   1   1   1
            T  NaN   1   1   1   1
Okay Things N  B     1   1   1   1
               D     1   1   1   1
            B  NaN   1   1   1   1
            D  NaN   1   1   1   1

In [64]: d_nan.loc["Good Things"]
Out[64]: 
        d1  d2  d3  d4
u2 u3                 
C  NaN   1   1   1   1
R  NaN   1   1   1   1

In [65]: d_nan.loc["Good Things"].loc['C']
Out[65]: 
    d1  d2  d3  d4
u3                
D    1   1   1   1

In [67]: d_no_nan
Out[67]: 
                   d1  d2  d3  d4
u1          u2 u3                
Good Things C       1   1   1   1
            R       1   1   1   1
Bad Things  C       1   1   1   1
            T       1   1   1   1
Okay Things N  B    1   1   1   1
               D    1   1   1   1
            B       1   1   1   1
            D       1   1   1   1

In [68]: d_no_nan.loc["Good Things"].loc['C']
Out[68]: 
    d1  d2  d3  d4
u3                
     1   1   1   1