Python Pandas - Highlighting maximum value in column

Question

I have a dataframe produced by this code:

hmdf = pd.DataFrame(hm01)
new_hm02 = hmdf[[\'FinancialYear\',\'Month\']]
new_hm01 = hmdf[[\'FinancialYear\',\'Month         


        

Answer 1

Variation highlighting max value column-wise (axis=1) using two colors. One color highlights duplicate max values. The other color highlights only the last column containing the max value.

def highlight_last_max(data, colormax='antiquewhite', colormaxlast='lightgreen'):
    colormax_attr = f'background-color: {colormax}'
    colormaxlast_attr = f'background-color: {colormaxlast}'
    max_value = data.max()
    is_max = [colormax_attr if v == max_value else '' for v in data]
    is_max[len(data) - list(reversed(data)).index(max_value) -  1] = colormaxlast_attr
    return is_max

df.style.apply(highlight_last_max,axis=1)

Answer 2

If you are using Python 3 this should easily do the trick

dfPercent.style.highlight_max(color = 'yellow', axis = 0)

Answer 3

There is problem you need convert values to floats for correct max, because get max value of strings - 9 is more as 1:

def highlight_max(data, color='yellow'):
    '''
    highlight the maximum in a Series or DataFrame
    '''
    attr = 'background-color: {}'.format(color)
    #remove % and cast to float
    data = data.replace('%','', regex=True).astype(float)
    if data.ndim == 1:  # Series from .apply(axis=0) or axis=1
        is_max = data == data.max()
        return [attr if v else '' for v in is_max]
    else:  # from .apply(axis=None)
        is_max = data == data.max().max()
        return pd.DataFrame(np.where(is_max, attr, ''),
                            index=data.index, columns=data.columns)

Sample:

dfPercent = pd.DataFrame({'2014/2015':['10.3%','9.7%','9.2%'],
                   '2015/2016':['4.8%','100.8%','9.7%']})
print (dfPercent)
  2014/2015 2015/2016
0     10.3%      4.8%
1      9.7%    100.8%
2      9.2%      9.7%

Command:

dfPercent.style.apply(highlight_max)