Can sub-columns be created in a pandas data frame?

Question

Data frame

I am working with a data frame in Jupyter Notebooks and I am having some difficulty with it. The data frame consists of locations and these are represented by

Answer 1

To add a top to column to a pd.DataFrame run:

def add_top_column(df, top_col, inplace=False):
    if not inplace:
        df = df.copy()
    
    df.columns = pd.MultiIndex.from_product([[top_col], df.columns])
    return df


orig_df = pd.DataFrame([[1, 2], [3, 4]], columns=['a', 'b'])
new_df = add_top_column(orig_df, "new column")

In order to combine 3 DataFrames each with its own new top column:

new_df2 = add_top_column(orig_df, "new column2")
new_df3 = add_top_column(orig_df, "new column3")
print(pd.concat([new_df, new_df2, new_df3], axis=1))

"""
# And this is the expected output:
  new column    new column2    new column3   
           a  b           a  b           a  b
0          1  2           1  2           1  2
1          3  4           3  4           3  4
"""

Note that if the DataFrames' index do not match, you might need to reset the index.

Answer 2

I think need here MultiIndex created by MultiIndex.from_product:

mux = pd.MultiIndex.from_product([['Start','Intermediary','End'], ['lat','lng']])
df = pd.DataFrame(data, columns=mux)

EDIT:

Setup:

temp=u"""                          start                                   intermediary                           end
('54.957055',' -7.740156')        ('54.956915136264', ' -7.753690062122')     ('54.957055','-7.740156')
('54.8913208', '-7.5740475')    ('54.864402885577', '-7.653445692445'),('54','0')   ('54.8913208','-7.5740475')
('55.2375819', '-7.2357427')     ('55.253936739337', '-7.259624609577'), ('54','2'),('54','1')   ('55.2375819','-7.2357427')
('54.5298806', '-8.1350247')    ('54.504374314741', '-8.188334960168')      ('54.5298806','-8.1350247')
('54.2810187',  ' -7.896937')   ('54.303836850038', '-8.180136033695'), ('54','3')       ('54.2810187','-7.896937')

"""
#after testing replace 'pd.compat.StringIO(temp)' to 'filename.csv'
df = pd.read_csv(pd.compat.StringIO(temp), sep="\s{3,}")

---

print (df)
                           start  \
0     ('54.957055',' -7.740156')   
1   ('54.8913208', '-7.5740475')   
2   ('55.2375819', '-7.2357427')   
3   ('54.5298806', '-8.1350247')   
4  ('54.2810187',  ' -7.896937')   

                                        intermediary  \
0            ('54.956915136264', ' -7.753690062122')   
1  ('54.864402885577', '-7.653445692445'),('54','0')   
2  ('55.253936739337', '-7.259624609577'), ('54',...   
3             ('54.504374314741', '-8.188334960168')   
4  ('54.303836850038', '-8.180136033695'), ('54',...   

                           end  
0    ('54.957055','-7.740156')  
1  ('54.8913208','-7.5740475')  
2  ('55.2375819','-7.2357427')  
3  ('54.5298806','-8.1350247')  
4   ('54.2810187','-7.896937') 

---

import ast

#convert string values to tuples
df = df.applymap(lambda x: ast.literal_eval(x))
#convert onpy pairs values to nested lists
df['intermediary'] = df['intermediary'].apply(lambda x: list(x) if isinstance(x[1], tuple) else [x])

#DataFrame by first Start column
df1 = pd.DataFrame(df['start'].values.tolist(), columns=['lat','lng'])

#DataFrame by intermediary column with reshape for 2 columns df
df2 = (pd.concat([pd.DataFrame(x, columns=['lat','lng']) for x in df['intermediary']], keys=df.index)
       .reset_index(level=1, drop=True)
       .add_prefix('intermediary_'))
print (df2)

#join all DataFrames together
df3 = df1.add_prefix('start_').join(df2).join(df1.add_prefix('end_'))

#create MultiIndex by split
df3.columns = df3.columns.str.split('_', expand=True)

---

print (df3)

        start                 intermediary                           end  \
          lat         lng              lat               lng         lat   
0   54.957055   -7.740156  54.956915136264   -7.753690062122   54.957055   
1  54.8913208  -7.5740475  54.864402885577   -7.653445692445  54.8913208   
1  54.8913208  -7.5740475               54                 0  54.8913208   
2  55.2375819  -7.2357427  55.253936739337   -7.259624609577  55.2375819   
2  55.2375819  -7.2357427               54                 2  55.2375819   
2  55.2375819  -7.2357427               54                 1  55.2375819   
3  54.5298806  -8.1350247  54.504374314741   -8.188334960168  54.5298806   
4  54.2810187   -7.896937  54.303836850038   -8.180136033695  54.2810187   
4  54.2810187   -7.896937               54                 3  54.2810187   


          lng  
0   -7.740156  
1  -7.5740475  
1  -7.5740475  
2  -7.2357427  
2  -7.2357427  
2  -7.2357427  
3  -8.1350247  
4   -7.896937  
4   -7.896937  

Answer 3

You can read an Excel file with 2 headers (2 levels of columns).

   df = pd.read_excel(
        sourceFilePath,
        index_col = [0],
        header = [0, 1]
    )

You can reshape your df like this in order to keep just 1 header (its easier to work with only 1 header):

df = df.stack([0,1], dropna=False).to_frame('Valeur').reset_index()