Exercise 2.5 - Solution

Here is a version of readrides.py with changes for parts (c) and (d).
# readrides.py

import csv

def read_rides_as_tuples(filename):
    '''
    Read the bus ride data as a list of tuples
    '''
    records = []
    with open(filename) as f:
        rows = csv.reader(f)
        headings = next(rows)     # Skip headers
        for row in rows:
            route = row[0]
            date = row[1]
            daytype = row[2]
            rides = int(row[3])
            record = (route, date, daytype, rides)
            records.append(record)
    return records

def read_rides_as_dicts(filename):
    '''
    Read the bus ride data as a list of dicts
    '''
    records = RideData()          # <---- CHANGED
    with open(filename) as f:
        rows = csv.reader(f)
        headings = next(rows)     # Skip headers
        for row in rows:
            route = row[0]
            date = row[1]
            daytype = row[2]
            rides = int(row[3])
            record = {
                'route': route, 
                'date': date, 
                'daytype': daytype, 
                'rides' : rides
                }
            records.append(record)
    return records

class Row:
    __slots__ = ('route', 'date', 'daytype', 'rides')
    def __init__(self, route, date, daytype, rides):
        self.route = route
        self.date = date
        self.daytype = daytype
        self.rides = rides

def read_rides_as_instances(filename):
    '''
    Read the bus ride data as a list of instances
    '''
    records = []
    with open(filename) as f:
        rows = csv.reader(f)
        headings = next(rows)     # Skip headers
        for row in rows:
            route = row[0]
            date = row[1]
            daytype = row[2]
            rides = int(row[3])
            record = Row(route, date, daytype, rides)
            records.append(record)
    return records

# Read as columns
def read_rides_as_columns(filename):
    '''
    Read the bus ride data into 4 lists, representing columns
    '''
    routes = []
    dates = []
    daytypes = []
    numrides = []
    with open(filename) as f:
        rows = csv.reader(f)
        headings = next(rows)     # Skip headers
        for row in rows:
            routes.append(row[0])
            dates.append(row[1])
            daytypes.append(row[2])
            numrides.append(int(row[3]))
    return dict(routes=routes, dates=dates, daytypes=daytypes, numrides=numrides)

# The great "fake"

import collections
class RideData(collections.Sequence):
    def __init__(self):
        # Each value is a list with all of the values (a column)
        self.routes = []
        self.dates = []
        self.daytypes = []
        self.numrides = []
        
    def __len__(self):
        # All lists assumed to have the same length
        return len(self.routes)

    def append(self, d):
        self.routes.append(d['route'])
        self.dates.append(d['date'])
        self.daytypes.append(d['daytype'])
        self.numrides.append(d['rides'])
        
    def __getitem__(self, index):
        return { 'route': self.routes[index],
                 'date': self.dates[index],
                 'daytype': self.daytypes[index],
                 'rides': self.numrides[index] }

if __name__ == '__main__':
    import tracemalloc
    tracemalloc.start()
    read_rides = read_rides_as_dicts # Change to as_dicts, as_instances, etc.
    rides = read_rides("Data/ctabus.csv")

    print('Memory Use: Current %d, Peak %d' % tracemalloc.get_traced_memory())
Back
3.5 KiB Raw Blame History

Exercise 2.5 - Solution

3.5 KiB

Raw Blame History
