python csv into dictionary

Question

I am pretty new to python. I need to create a class that loads csv data into a dictionary.

I want to be able to control the keys and value So let say the following code, I can pull out worker1.name or worker1.age anytime i want.

class ageName(object):
'''class to represent a person'''
def __init__(self, name, age):
self.name = name
self.age = age

worker1 = ageName('jon', 40)
worker2 = ageName('lise', 22)

#Now if we print this you see that it`s stored in a dictionary
print worker1.__dict__
print worker2.__dict__
#
'''
{'age': 40, 'name': 'jon'}
#
{'age': 22, 'name': 'lise'}
#
'''
#

#when we call (key)worker1.name we are getting the (value)
print worker1.name
#
'''
#
jon
#
'''

But I am stuck at loading my csv data into keys and value.

[1] I want to create my own keys worker1 = ageName([name],[age],[id],[gender])

[2] each [name],[age],[id] and [gender] comes from specific a column in a csv data file

I really do not know how to work on this. I tried many methods but I failed. I need some helps to get started on this.

---- Edit This is my original code

import csv

# let us first make student an object

class Student():
    def __init__(self):
        self.fname = []
        self.lname = []
        self.ID = []
        self.sport = []
        # let us read this file
        for row in list(csv.reader(open("copy-john.csv", "rb")))[1:]:
            self.fname.append(row[0])
            self.lname.append(row[1])   
            self.ID.append(row[2])
            self.sport.append(row[3])
    def Tableformat(self):
        print "%-14s|%-10s|%-5s|%-11s" %('First Name','Last Name','ID','Favorite Sport')
        print "-" * 45
        for (i, fname) in enumerate(self.fname):
           print "%-14s|%-10s|%-5s|%3s" %(fname,self.lname[i],self.ID[i],self.sport[i])
    def Table(self):
        print self.lname

class Database(Student):
    def __init__(self):
        g = 0
        choice = ['Basketball','Football','Other','Baseball','Handball','Soccer','Volleyball','I do not like sport']
        data = student.sport
        k = len(student.fname)
        print k
        freq = {}
        for i in data:
            freq[i] = freq.get(i, 0) + 1
        for i in choice:
            if i not in freq:
                freq[i] = 0
            print i, freq[i]


student = Student()
database = Database()

This is my current code (incomplete)

import csv
class Student(object):
    '''class to represent a person'''
    def __init__(self, lname, fname, ID, sport):
        self.lname = lname
        self.fname = fname
        self.ID = ID
        self.sport = sport
reader = csv.reader(open('copy-john.csv'), delimiter=',', quotechar='"')
student = [Student(row[0], row[1], row[2], row[3]) for row in reader][1::]
print "%-14s|%-10s|%-5s|%-11s" %('First Name','Last Name','ID','Favorite Sport')
print "-" * 45
for i in range(len(student)):
    print "%-14s|%-10s|%-5s|%3s" %(student[i].lname,student[i].fname,student[i].ID,student[i].sport)

choice = ['Basketball','Football','Other','Baseball','Handball','Soccer','Volleyball','I do not like sport']
lst = []
h = 0
k = len(student)
# 23
for i in range(len(student)):
    lst.append(student[i].sport) # merge together

for a in set(lst):
    print a, lst.count(a)

for i in set(choice):
    if i not in set(lst):
        lst.append(i)
        lst.count(i) = 0
        print lst.count(i)

Answer 1

import csv

reader = csv.reader(open('workers.csv', newline=''), delimiter=',', quotechar='"')
workers = [ageName(row[0], row[1]) for row in reader]

workers now has a list of all the workers

>>> workers[0].name
'jon'

added edit after question was altered

Is there any reason you're using old style classes? I'm using new style here.

class Student:
    sports = []
    def __init__(self, row):
       self.lname, self.fname, self.ID, self.sport = row
       self.sports.append(self.sport)
    def get(self):
       return (self.lname, self.fname, self.ID, self.sport)

reader = csv.reader(open('copy-john.csv'), delimiter=',', quotechar='"')
print "%-14s|%-10s|%-5s|%-11s" % tuple(reader.next()) # read header line from csv
print "-" * 45
students = list(map(Student, reader)) # read all remaining lines
for student in students:
    print "%-14s|%-10s|%-5s|%3s" % student.get()

# Printing all sports that are specified by students
for s in set(Student.sports): # class attribute
    print s, Student.sports.count(s)

# Printing sports that are not picked 
allsports = ['Basketball','Football','Other','Baseball','Handball','Soccer','Volleyball','I do not like sport']
for s in set(allsports) - set(Student.sports):
    print s, 0

Hope this gives you some ideas of the power of python sequences. ;)

edit 2, shortened as much as possible... just to show off :P

Ladies and gentlemen, 7(.5) lines.

allsports = ['Basketball','Football','Other','Baseball','Handball',
             'Soccer','Volleyball','I do not like sport']
sports = []
reader = csv.reader(open('copy-john.csv'))
for row in reader:
    if reader.line_num: sports.append(s[3])
    print "%-14s|%-10s|%-5s|%-11s" % tuple(s)
for s in allsports: print s, sports.count(s)

Answer 2

I know this is a pretty old question, but it's impossible to read this, and not think of the amazing new(ish) Python library, pandas. Its main unit of analysis is a think called a DataFrame which is modelled after the way R handles data.

Let's say you have a (very silly) csv file called example.csv which looks like this:

day,fruit,sales
Monday,Banana,10
Monday,Orange,20
Tuesday,Banana,12
Tuesday,Orange,22

If you want to read in a csv in double-quick time, and do 'stuff' with it, you'd be hard pressed to beat the following code for either brevity or ease of use:

>>> import pandas as pd
>>> csv = pd.read_csv('example.csv')
>>> csv
       day   fruit  sales
0   Monday  Banana     10
1   Monday  Orange     20
2  Tuesday  Banana     12
3  Tuesday  Orange     22
>>> csv[csv.fruit=='Banana']
       day   fruit  sales
0   Monday  Banana     10
2  Tuesday  Banana     12
>>> csv[(csv.fruit=='Banana') & (csv.day=='Monday')]
      day   fruit  sales
0  Monday  Banana     10

In my opinion, this is really fantastic stuff. Never iterate over a csv.reader object again!