python CSV , find max and print the information

Question

My aim is to find the max of the individual column and print out the information. But there is problem when I print some of the information. For example CSIT135, nothing was printed out. CSIT121 only prints out one result. My data looks like:

first_name,last_name,student_id,CSIT110,CSIT121,CSIT135,CSIT142
Peter,Tan,S1012342D,89,67,54,78
John,Lim,S1014322H,87,78,86,67
Ada,Ang,S1023456I,54,78,65,54

def test():
 import csv          
 with open("data.csv") as a:     
     rows = csv.DictReader(a)      
     t2_list=[]
     for row in rows: 
         t2 = row['CSIT121']
         t2_list.append(t2)
         CSIT121=max(t2_list)           
     if row['CSIT121']==CSIT121:
         print("{0:<8}| {1:>10} | {2:<8}".format("CSIT121", "John","Lim"))
         print("{0:<8}| {1:>10} | {2:<8}".format("CSIT121", row['first_name'],row['last_name']))


 with open("data.csv") as a:     
     rows = csv.DictReader(a)      
     t3_list=[]
     for row in rows: 
         t3 = row['CSIT135']
         t3_list.append(t3)
         CSIT135=max(t3_list)  
         if row['CSIT135']==CSIT135:
             print("{0:<8}| {1:>10} | {2:<8}".format("CSIT135", row['first_name'],row['last_name'])) 

Code sample and run result pic

Answer 1

You haven't specified the format of the output, so instead of printing the result I written function returning dict with each key representing each column and each value containing dict representing row with max value in that column.

I don't like the file rewinding part, but it seems to be necessary, because the csv.DictReader during iteration is using the file handle it has received in the constructor and doesn't rewind it after the iteration. This might be why you only see one result with your code.

import csv

def get_maxes():
    with open("data.csv", "r") as data_file:
        data = csv.DictReader(data_file)

        # don't process first 3 colums
        columns_to_process = data.fieldnames[3:]
        column_max = {}
        for column in columns_to_process:
            data_file.seek(0) # rewind the file after iteration in line above
            data_file.readline() # skip the first line with header

            column_max[column] = max(data, key=lambda x: x[column])

    return column_max

if __name__ == '__main__':
    print(get_maxes())

Output:

{'CSIT110': {'CSIT110': '89',
             'CSIT121': '67',
             'CSIT135': '54',
             'CSIT142': '78',
             'first_name': 'Peter',
             'last_name': 'Tan',
             'student_id': 'S1012342D'},
 'CSIT121': {'CSIT110': '87',
             'CSIT121': '78',
             'CSIT135': '86',
             'CSIT142': '67',
             'first_name': 'John',
             'last_name': 'Lim',
             'student_id': 'S1014322H'},
 'CSIT135': {'CSIT110': '87',
             'CSIT121': '78',
             'CSIT135': '86',
             'CSIT142': '67',
             'first_name': 'John',
             'last_name': 'Lim',
             'student_id': 'S1014322H'},
 'CSIT142': {'CSIT110': '89',
             'CSIT121': '67',
             'CSIT135': '54',
             'CSIT142': '78',
             'first_name': 'Peter',
             'last_name': 'Tan',
             'student_id': 'S1012342D'}}

EDIT:

If you consume all the rows at once from the DictReader you don't need to rewind the file:

import csv

def get_maxes():
    with open("data.csv", 'r') as data_file:
        data = csv.DictReader(data_file)
        columns_to_process = data.fieldnames[3:] # don't process first 3 colums
        data = [row for row in data] # read all the data from DictReader and store it in the list

        column_max = {}
        for column in columns_to_process:
            column_max[column] = max(data, key=lambda x: x[column])

        return column_max

if __name__ == '__main__':
    import pprint
    pprint.pprint(get_maxes())