Python 3.6.0 (v3.6.0:41df79263a11, Dec 23 2016, 08:06:12) [MSC v.1900 64 bit (AMD64)] on win32
Type "copyright", "credits" or "license()" for more information.
>>> a = 'hello world'
>>> b = a
>>> id(a)
1866435412720
>>> id(b)
1866435412720
>>> c = [1,2,3]
>>> d = c
>>> d
[1, 2, 3]
>>> d.append(9999)
>>> d
[1, 2, 3, 9999]
>>> c
[1, 2, 3, 9999]
>>> a = 'hello world'
>>> b = 'hello world'
>>> id(a)
1866435478768
>>> id(b)
1866435895856
>>> a is b
False
>>> cache = { }
>>> cache[a] = a
>>> cache
{'hello world': 'hello world'}
>>> b
'hello world'
>>> id(a)
1866435478768
>>> id(b)
1866435895856
>>> b = cache[b]
>>> b
'hello world'
>>> id(b)
1866435478768
>>> id(a)
1866435478768
>>> id(b)
1866435478768
>>> d = { }
>>> d.setdefault('x', 'x')
'x'
>>> d
{'x': 'x'}
>>> 
====== RESTART: C:\Users\dave\Desktop\DataDeepDive\buscode.py ======
Pause: look at memory
Total: 185
24154
Most popular routes in 2016
79 8268367
66 7088030
77 6671135
4 6424587
8 6375504
9 6329587
53 5895532
82 5775101
3 5698439
22 5620134
Greatest increase 2001-2016
J14 3296029
15 2301408
X9 2075111
146 1516226
147 1315199
115 1114940
12 1001598
26 920307
134 722110
18 684923
>>> a = 73
>>> b = 73
>>> a is b
True
>>> id(a)
1392749920
>>> id(b)
1392749920
>>> c = 'hello'
>>> d = 'hello'
>>> id(c)
2171018046184
>>> id(d)
2171018046184
>>> import sys
>>> sys.intern('hello world')
'hello world'
>>> c = sys.intern('hello world')
>>> d = sys.intern('hello world')
>>> id(c)
2171091190320
>>> id(d)
2171091190320
>>> # How dictionaries work
>>> d = { 'route': '22', 'date': '01/01/2001', 'daytype': 'U', 'rides': 12345 }
>>> entries = [ None ] * 8
>>> entries
[None, None, None, None, None, None, None, None]
>>> 'route'.__hash__()
-7418148954346439983
>>> 'route'.__hash__() % len(entries)
1
>>> entries[1] = ('route', '22')
>>> entries
[None, ('route', '22'), None, None, None, None, None, None]
>>> 'date'.__hash__() % len(entries)
2
>>> entries[2] = ('date', '01/01/2001')
>>> 'daytype'.__hash__() % len(entries)
2
>>> entries[2]
('date', '01/01/2001')
>>> entries
[None, ('route', '22'), ('date', '01/01/2001'), None, None, None, None, None]
>>> 'daytype'.__hash__()
-7336238433013629286
>>> _ >> 5
-229257451031675916
>>> _ % len(entries)
4
>>> entries[4] = ('daytype', 'U')
>>> 'rides'.__hash__() % len(entries)
5
>>> entries[5] = ('rides', 12345)
>>> entries
[None, ('route', '22'), ('date', '01/01/2001'), None, ('daytype', 'U'), ('rides', 12345), None, None]
>>> d
{'route': '22', 'date': '01/01/2001', 'daytype': 'U', 'rides': 12345}
>>> import sys
>>> sys.getsizeof(d)
240
>>> d['spam'] = 42
>>> d
{'route': '22', 'date': '01/01/2001', 'daytype': 'U', 'rides': 12345, 'spam': 42}
>>> sys.getsizeof(d)
240
>>> d['blah'] = 40
>>> d
{'route': '22', 'date': '01/01/2001', 'daytype': 'U', 'rides': 12345, 'spam': 42, 'blah': 40}
>>> sys.getsizeof(d)
368
>>> 
====== RESTART: C:\Users\dave\Desktop\DataDeepDive\buscode.py ======
Pause: look at memory
====== RESTART: C:\Users\dave\Desktop\DataDeepDive\buscode.py ======
Pause: look at memory
Traceback (most recent call last):
  File "C:\Users\dave\Desktop\DataDeepDive\buscode.py", line 80, in <module>
    routes.add(row.route)
AttributeError: 'dict' object has no attribute 'route'
>>> 
>>> d = { }
>>> import sys
>>> sys.getsizeof(d)
240
>>> for i in range(1000000):
	d[i] = None

	
>>> len(d)
1000000
>>> sys.getsizeof(d)
41943144
>>> for i in range(1000000):
	del d[i]

	
>>> len(d)
0
>>> d
{}
>>> sys.getsizeof(d)
41943144
>>> d['a'] = 23
>>> d['b']
Traceback (most recent call last):
  File "<pyshell#89>", line 1, in <module>
    d['b']
KeyError: 'b'
>>> d['b'] = 42
>>> sys.getsizeof(d)
41943144
>>> d
{'a': 23, 'b': 42}
>>> sys.getsizeof(d)
41943144
>>> d.clear()
>>> sys.getsizeof(d)
72
>>> d['a'] = 23
>>> sys.getsizeof(d)
240
>>> del d
>>> len(rows)
736461
>>> rows[0]
{'route': '3', 'date': '01/01/2001', 'daytype': 'U', 'rides': 7354, 'spam': None, 'blah': None}
>>> busy = [ row for row in rows if row['route'] == '22' and row['rides'] > 25000 ]
>>> len(busy)
63
>>> busy[0]
{'route': '22', 'date': '03/06/2008', 'daytype': 'W', 'rides': 25419, 'spam': None, 'blah': None}
>>> busy[1]
{'route': '22', 'date': '03/13/2008', 'daytype': 'W', 'rides': 25238, 'spam': None, 'blah': None}
>>> sum([row['rides'] for row in rows if row['route'] == '22'])
111886681
>>> 
====== RESTART: C:\Users\dave\Desktop\DataDeepDive\buscode.py ======
Pause: look at memory
Total: 185
24154
Most popular routes in 2016
79 8268367
66 7088030
77 6671135
4 6424587
8 6375504
9 6329587
53 5895532
82 5775101
3 5698439
22 5620134
Greatest increase 2001-2016
J14 3296029
15 2301408
X9 2075111
146 1516226
147 1315199
115 1114940
12 1001598
26 920307
134 722110
18 684923
>>> # Find out what day route 22 had highest ridership
>>> rt22 = [ row for row in rows if row.route == '22' ]
>>> len(rt22)
5995
>>> max(rt22, key=lambda row: row.rides)
<__main__.Row object at 0x000002AFE70FA510>
>>> r = _
>>> r.date
'06/11/2008'
>>> r.rides
26896
>>> max([(row.rides, row.date) for row in rt22])
(26896, '06/11/2008')
>>> from functools import reduce
>>> data = [1,4,5,19,20]
>>> def f(x, y):
	return x + y

>>> reduce(f, data)
49
>>> def f(x, y):
	print(x,  y)
	return x + y

>>> reduce(f, data)
1 4
5 5
10 19
29 20
49
>>> reduce(lambda x, y: x+y, data)
49
>>> def f(x, y):
	return (x, y)   # Tuple

>>> reduce(f, data)
((((1, 4), 5), 19), 20)
>>> (1, (4, (5, (19, 20))))
(1, (4, (5, (19, 20))))
>>> 
====== RESTART: C:\Users\dave\Desktop\DataDeepDive\buscode.py ======
Pause: look at memory
====== RESTART: C:\Users\dave\Desktop\DataDeepDive\buscode.py ======
Pause: look at memory
Traceback (most recent call last):
  File "C:\Users\dave\Desktop\DataDeepDive\buscode.py", line 104, in <module>
    # Set comprehension
NameError: name 'rows' is not defined
>>> len(columns)
4
>>> columns[0][0:10]
['3', '4', '6', '8', '9', '10', '11', '12', '18', '20']
>>> columns[1][0:10]
['01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001', '01/01/2001']
>>> columns[2][0:10]
['U', 'U', 'U', 'U', 'U', 'U', 'U', 'U', 'U', 'U']
>>> columns[3][0:10]
[7354, 9288, 6048, 6309, 11207, 385, 610, 3678, 375, 7096]
>>> rows = zip(*columns)
>>> rows
<zip object at 0x0000025DE4354308>
>>> next(rows)
('3', '01/01/2001', 'U', 7354)
>>> next(rows)
('4', '01/01/2001', 'U', 9288)
>>> import numpy
a 
>>> 
>>> a = numpy.array([1,2,3,4,5,6,7])
>>> a
array([1, 2, 3, 4, 5, 6, 7])
>>> a + 10
array([11, 12, 13, 14, 15, 16, 17])
>>> a * 0.5
array([ 0.5,  1. ,  1.5,  2. ,  2.5,  3. ,  3.5])
>>> numpy.sqrt(a)
array([ 1.        ,  1.41421356,  1.73205081,  2.        ,  2.23606798,
        2.44948974,  2.64575131])
>>> b = numpy.arange(0, 10, 0.000001)
>>> len(b)
10000000
>>> b
array([  0.00000000e+00,   1.00000000e-06,   2.00000000e-06, ...,
         9.99999700e+00,   9.99999800e+00,   9.99999900e+00])
>>> c = b * 1000
>>> c
array([  0.00000000e+00,   1.00000000e-03,   2.00000000e-03, ...,
         9.99999700e+03,   9.99999800e+03,   9.99999900e+03])
>>> d = b + 42
>>> d
array([ 42.      ,  42.000001,  42.000002, ...,  51.999997,  51.999998,
        51.999999])
>>> a
array([1, 2, 3, 4, 5, 6, 7])
>>> # Figure out where a < 4
>>> for x in a:
	if x < 4:
		# No
		pass

	
>>> a < 4
array([ True,  True,  True, False, False, False, False], dtype=bool)
>>> a[a < 4 ]
array([1, 2, 3])
>>> numpy.where(a < 4, a, 4)  # Clipping
array([1, 2, 3, 4, 4, 4, 4])
>>> a + 10
array([11, 12, 13, 14, 15, 16, 17])
>>> a
array([1, 2, 3, 4, 5, 6, 7])
>>> b = a[1:5]
>>> b
array([2, 3, 4, 5])
>>> a
array([1, 2, 3, 4, 5, 6, 7])
>>> b
array([2, 3, 4, 5])
>>> b[1] = 999
>>> b
array([  2, 999,   4,   5])
>>> a
array([  1,   2, 999,   4,   5,   6,   7])
>>> d = [1,2,3,4,5,6,7]
>>> e = d[1:5]
>>> e
[2, 3, 4, 5]
>>> e[1] = 999
>>> e
[2, 999, 4, 5]
>>> d
[1, 2, 3, 4, 5, 6, 7]
>>> a
array([  1,   2, 999,   4,   5,   6,   7])
>>> a += 10
>>> a
array([  11,   12, 1009,   14,   15,   16,   17])
>>> b
array([  12, 1009,   14,   15])
>>> b *= 1000
>>> b
array([  12000, 1009000,   14000,   15000])
>>> a
array([     11,   12000, 1009000,   14000,   15000,      16,      17])
>>> len(columns)
4
>>> data = {
	'routes': numpy.array(columns[0]),
	'dates': numpy.array(columns[1]),
	'daytypes': numpy.array(columns[2]),
	'rides': numpy.array(columns[3])
	}
>>> data
{'routes': array(['3', '4', '6', ..., 'X98', 'X98', 'X98'], 
      dtype='<U4'), 'dates': array(['01/01/2001', '01/01/2001', '01/01/2001', ..., '05/26/2017',
       '05/30/2017', '05/31/2017'], 
      dtype='<U10'), 'daytypes': array(['U', 'U', 'U', ..., 'W', 'W', 'W'], 
      dtype='<U1'), 'rides': array([7354, 9288, 6048, ...,    3,   20,   24])}
>>> data['route']
Traceback (most recent call last):
  File "<pyshell#192>", line 1, in <module>
    data['route']
KeyError: 'route'
>>> data['routes']
array(['3', '4', '6', ..., 'X98', 'X98', 'X98'], 
      dtype='<U4')
>>> rt22 = data['routes'] == '22'
>>> rt22
array([False, False, False, ..., False, False, False], dtype=bool)
>>> data['rides'][rt22]
array([ 7877, 19558, 19286, ..., 10654, 16190, 16350])
>>> sum(_)
111886681
>>> import pandas
>>> data = pandas.read_csv('ctabus.csv')
>>> data
       route        date daytype  rides
0          3  01/01/2001       U   7354
1          4  01/01/2001       U   9288
2          6  01/01/2001       U   6048
3          8  01/01/2001       U   6309
4          9  01/01/2001       U  11207
5         10  01/01/2001       U    385
6         11  01/01/2001       U    610
7         12  01/01/2001       U   3678
8         18  01/01/2001       U    375
9         20  01/01/2001       U   7096
10        21  01/01/2001       U   3454
11        22  01/01/2001       U   7877
12        27  01/01/2001       U   1903
13        28  01/01/2001       U   5462
14        29  01/01/2001       U   9303
15        30  01/01/2001       U    600
16        34  01/01/2001       U   3541
17        35  01/01/2001       U   1526
18        36  01/01/2001       U   7044
19        43  01/01/2001       U    311
20        44  01/01/2001       U   1463
21        47  01/01/2001       U   2676
22        49  01/01/2001       U  11829
23        50  01/01/2001       U   1832
24        51  01/01/2001       U   1752
25        52  01/01/2001       U   4061
26        53  01/01/2001       U   8058
27        54  01/01/2001       U   4675
28        55  01/01/2001       U   5805
29        56  01/01/2001       U   5461
...      ...         ...     ...    ...
736431    X9  05/19/2017       W   7673
736432    X9  05/22/2017       W   8626
736433    X9  05/23/2017       W   8696
736434    X9  05/24/2017       W   9170
736435    X9  05/25/2017       W   8632
736436    X9  05/26/2017       W   7990
736437    X9  05/30/2017       W   8591
736438    X9  05/31/2017       W   8998
736439   X98  05/01/2017       W     13
736440   X98  05/02/2017       W     13
736441   X98  05/03/2017       W     19
736442   X98  05/04/2017       W     18
736443   X98  05/05/2017       W     19
736444   X98  05/08/2017       W     25
736445   X98  05/09/2017       W     23
736446   X98  05/10/2017       W     20
736447   X98  05/11/2017       W     21
736448   X98  05/12/2017       W     19
736449   X98  05/15/2017       W     22
736450   X98  05/16/2017       W     24
736451   X98  05/17/2017       W     21
736452   X98  05/18/2017       W     24
736453   X98  05/19/2017       W     24
736454   X98  05/22/2017       W     24
736455   X98  05/23/2017       W     27
736456   X98  05/24/2017       W     28
736457   X98  05/25/2017       W     22
736458   X98  05/26/2017       W      3
736459   X98  05/30/2017       W     20
736460   X98  05/31/2017       W     24

[736461 rows x 4 columns]
>>> rt22 = data['route'] == '22'
>>> rt22
0         False
1         False
2         False
3         False
4         False
5         False
6         False
7         False
8         False
9         False
10        False
11         True
12        False
13        False
14        False
15        False
16        False
17        False
18        False
19        False
20        False
21        False
22        False
23        False
24        False
25        False
26        False
27        False
28        False
29        False
          ...  
736431    False
736432    False
736433    False
736434    False
736435    False
736436    False
736437    False
736438    False
736439    False
736440    False
736441    False
736442    False
736443    False
736444    False
736445    False
736446    False
736447    False
736448    False
736449    False
736450    False
736451    False
736452    False
736453    False
736454    False
736455    False
736456    False
736457    False
736458    False
736459    False
736460    False
Name: route, dtype: bool
>>> 
>>> data[rt22]['rides'].sum()
111886681
>>> 
====== RESTART: C:/Users/dave/Desktop/DataDeepDive/genbus.py ======
Traceback (most recent call last):
  File "C:/Users/dave/Desktop/DataDeepDive/genbus.py", line 29, in <module>
    rows = read_rides_as_instance('ctabus.csv')
NameError: name 'read_rides_as_instance' is not defined
>>> 
====== RESTART: C:/Users/dave/Desktop/DataDeepDive/genbus.py ======
>>> rows
<generator object read_rides_as_instances at 0x0000020058632830>
>>> next(rows)
<__main__.Row object at 0x0000020058658120>
>>> def find_route(rows, route):
	for row in rows:
		if row.route == route:
			yield row

			
>>> rt22 = find_route(rows, '22')
>>> rt22
<generator object find_route at 0x0000020058632938>
>>> next(rt22)
<__main__.Row object at 0x00000200586584C8>
>>> rt22.route
Traceback (most recent call last):
  File "<pyshell#215>", line 1, in <module>
    rt22.route
AttributeError: 'generator' object has no attribute 'route'
>>> next(rt22)
<__main__.Row object at 0x0000020058661BD0>
>>> r = _
>>> r.route
'22'
>>> r.date
'01/02/2001'
>>> def rides_and_date(rows):
	for row in rows:
		yield (row.date, row.rides)

		
>>> data = rides_and_date(rt22)
>>> data
<generator object rides_and_date at 0x00000200586328E0>
>>> next(data)
('01/03/2001', 19286)
>>> next(data)
('01/04/2001', 20265)
>>> max(data)
('12/31/2016', 11654)
>>> 
====== RESTART: C:/Users/dave/Desktop/DataDeepDive/genbus.py ======
(26896, '06/11/2008')
>>>