第二次训练¶

本部分内容综合几本经典数据科学导论给出的训练内容，请依据顺序完成，并思考其中的逻辑关系。

数据类型与数据结构¶

基本数据类型¶

Integers 整型¶

In [13]:

a = 10
type(a)

a = 10 type(a)

Out[13]:

int

In [15]:

a.bit_length()

a.bit_length()

Out[15]:

4

In [17]:

a = 100000
a.bit_length()

a = 100000 a.bit_length()

Out[17]:

17

In [19]:

googol = 10 ** 100
googol

googol = 10 ** 100 googol

Out[19]:

10000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000000

In [21]:

googol.bit_length()

googol.bit_length()

Out[21]:

333

In [23]:

1 + 4

1 + 4

Out[23]:

5

In [25]:

1 / 4

1 / 4

Out[25]:

0.25

In [27]:

type(1 / 4)

type(1 / 4)

Out[27]:

float

Floats 浮点型¶

In [30]:

1.6 / 4

1.6 / 4

Out[30]:

0.4

In [32]:

type (1.6 / 4)

type (1.6 / 4)

Out[32]:

float

In [34]:

b = 0.35
type(b)

b = 0.35 type(b)

Out[34]:

float

In [36]:

b + 0.1

b + 0.1

Out[36]:

0.44999999999999996

In [38]:

c = 0.5
c.as_integer_ratio()

c = 0.5 c.as_integer_ratio()

Out[38]:

(1, 2)

In [40]:

b.as_integer_ratio()

b.as_integer_ratio()

Out[40]:

(3152519739159347, 9007199254740992)

In [42]:

import decimal
from decimal import Decimal

import decimal from decimal import Decimal

In [44]:

decimal.getcontext()

decimal.getcontext()

Out[44]:

Context(prec=28, rounding=ROUND_HALF_EVEN, Emin=-999999, Emax=999999, capitals=1, clamp=0, flags=[], traps=[InvalidOperation, DivisionByZero, Overflow])

In [46]:

d = Decimal(1) / Decimal (11)
d

d = Decimal(1) / Decimal (11) d

Out[46]:

Decimal('0.09090909090909090909090909091')

In [48]:

decimal.getcontext().prec = 4

decimal.getcontext().prec = 4

In [50]:

e = Decimal(1) / Decimal (11)
e

e = Decimal(1) / Decimal (11) e

Out[50]:

Decimal('0.09091')

In [52]:

decimal.getcontext().prec = 50

decimal.getcontext().prec = 50

In [54]:

f = Decimal(1) / Decimal (11)
f

f = Decimal(1) / Decimal (11) f

Out[54]:

Decimal('0.090909090909090909090909090909090909090909090909091')

In [56]:

g = d + e + f
g

g = d + e + f g

Out[56]:

Decimal('0.27272818181818181818181818181909090909090909090909')

Boolean 布尔型¶

In [59]:

import keyword

import keyword

In [61]:

keyword.kwlist

keyword.kwlist

Out[61]:

['False',
 'None',
 'True',
 'and',
 'as',
 'assert',
 'async',
 'await',
 'break',
 'class',
 'continue',
 'def',
 'del',
 'elif',
 'else',
 'except',
 'finally',
 'for',
 'from',
 'global',
 'if',
 'import',
 'in',
 'is',
 'lambda',
 'nonlocal',
 'not',
 'or',
 'pass',
 'raise',
 'return',
 'try',
 'while',
 'with',
 'yield']

In [63]:

4 > 3

4 > 3

Out[63]:

True

In [65]:

type(4 > 3)

type(4 > 3)

Out[65]:

bool

In [67]:

type(False)

type(False)

Out[67]:

bool

In [69]:

4 >= 3

4 >= 3

Out[69]:

True

In [71]:

4 < 3

4 < 3

Out[71]:

False

In [73]:

4 <= 3

4 <= 3

Out[73]:

False

In [75]:

4 == 3

4 == 3

Out[75]:

False

In [77]:

4 != 3

4 != 3

Out[77]:

True

In [79]:

True and True

True and True

Out[79]:

True

In [81]:

True and False

True and False

Out[81]:

False

In [83]:

False and False

False and False

Out[83]:

False

In [85]:

True or True

True or True

Out[85]:

True

In [87]:

True or False

True or False

Out[87]:

True

In [89]:

False or False

False or False

Out[89]:

False

In [91]:

not True

not True

Out[91]:

False

In [93]:

not False

not False

Out[93]:

True

In [95]:

(4 > 3) and (2 > 3)

(4 > 3) and (2 > 3)

Out[95]:

False

In [97]:

(4 == 3) or (2 != 3)

(4 == 3) or (2 != 3)

Out[97]:

True

In [99]:

not (4 != 4)

not (4 != 4)

Out[99]:

True

In [101]:

(not (4 != 4)) and (2 == 3)

(not (4 != 4)) and (2 == 3)

Out[101]:

False

In [103]:

if 4 > 3:  
    print('condition true')

if 4 > 3: print('condition true')

condition true

In [105]:

i = 0  
while i < 4:  
    print('condition true, i = ', i)  
    i += 1

i = 0 while i < 4: print('condition true, i = ', i) i += 1

condition true, i =  0
condition true, i =  1
condition true, i =  2
condition true, i =  3

In [107]:

int(True)

int(True)

Out[107]:

1

In [109]:

int(False)

int(False)

Out[109]:

0

In [111]:

float(True)

float(True)

Out[111]:

1.0

In [113]:

float(False)

float(False)

Out[113]:

0.0

In [115]:

bool(0)

bool(0)

Out[115]:

False

In [117]:

bool(0.0)

bool(0.0)

Out[117]:

False

In [119]:

bool(1)

bool(1)

Out[119]:

True

In [121]:

bool(10.5)

bool(10.5)

Out[121]:

True

In [123]:

bool(-2)

bool(-2)

Out[123]:

True

Strings 字符型¶

In [126]:

t = 'this is a string object'

t = 'this is a string object'

In [128]:

t.capitalize()

t.capitalize()

Out[128]:

'This is a string object'

In [130]:

t.split()

t.split()

Out[130]:

['this', 'is', 'a', 'string', 'object']

In [132]:

t.find('string')

t.find('string')

Out[132]:

10

In [134]:

t.find('Python')

t.find('Python')

Out[134]:

-1

In [136]:

t.replace(' ', '|')

t.replace(' ', '|')

Out[136]:

'this|is|a|string|object'

In [138]:

'http://www.python.org'.strip('htp:/')

'http://www.python.org'.strip('htp:/')

Out[138]:

'www.python.org'

In [140]:

a = "我是张三"
print(a)

a = "我是张三" print(a)

我是张三

In [142]:

张三 = 100
李四 = 300
print(张三 + 李四)

张三 = 100 李四 = 300 print(张三 + 李四)

400

循环: 打印与字符替代¶

In [145]:

print('Python for Finance')

print('Python for Finance')

Python for Finance

In [147]:

print(t)

print(t)

this is a string object

In [149]:

i = 0
while i < 4:
    print(i)  
    i += 1

i = 0 while i < 4: print(i) i += 1

0
1
2
3

In [151]:

i = 0
while i < 4:
    print(i, end='|')  
    i += 1

i = 0 while i < 4: print(i, end='|') i += 1

0|1|2|3|

In [153]:

'this is an integer %d' % 15

'this is an integer %d' % 15

Out[153]:

'this is an integer 15'

In [155]:

'this is an integer %4d' % 15

'this is an integer %4d' % 15

Out[155]:

'this is an integer   15'

In [157]:

'this is an integer %04d' % 15

'this is an integer %04d' % 15

Out[157]:

'this is an integer 0015'

In [159]:

'this is a float %f' % 15.3456

'this is a float %f' % 15.3456

Out[159]:

'this is a float 15.345600'

In [161]:

'this is a float %.2f' % 15.3456

'this is a float %.2f' % 15.3456

Out[161]:

'this is a float 15.35'

In [163]:

'this is a float %8f' % 15.3456

'this is a float %8f' % 15.3456

Out[163]:

'this is a float 15.345600'

In [165]:

'this is a float %8.2f' % 15.3456

'this is a float %8.2f' % 15.3456

Out[165]:

'this is a float    15.35'

In [167]:

'this is a float %08.2f' % 15.3456

'this is a float %08.2f' % 15.3456

Out[167]:

'this is a float 00015.35'

In [169]:

'this is a string %s' % 'Python'

'this is a string %s' % 'Python'

Out[169]:

'this is a string Python'

In [171]:

'this is a string %10s' % 'Python'

'this is a string %10s' % 'Python'

Out[171]:

'this is a string     Python'

In [173]:

'this is an integer {:d}'.format(15)

'this is an integer {:d}'.format(15)

Out[173]:

'this is an integer 15'

In [175]:

'this is an integer {:4d}'.format(15)

'this is an integer {:4d}'.format(15)

Out[175]:

'this is an integer   15'

In [177]:

'this is an integer {:04d}'.format(15)

'this is an integer {:04d}'.format(15)

Out[177]:

'this is an integer 0015'

In [179]:

'this is a float {:f}'.format(15.3456)

'this is a float {:f}'.format(15.3456)

Out[179]:

'this is a float 15.345600'

In [181]:

'this is a float {:.2f}'.format(15.3456)

'this is a float {:.2f}'.format(15.3456)

Out[181]:

'this is a float 15.35'

In [183]:

'this is a float {:8f}'.format(15.3456)

'this is a float {:8f}'.format(15.3456)

Out[183]:

'this is a float 15.345600'

In [185]:

'this is a float {:8.2f}'.format(15.3456)

'this is a float {:8.2f}'.format(15.3456)

Out[185]:

'this is a float    15.35'

In [187]:

'this is a float {:08.2f}'.format(15.3456)

'this is a float {:08.2f}'.format(15.3456)

Out[187]:

'this is a float 00015.35'

In [189]:

'this is a string {:s}'.format('Python')

'this is a string {:s}'.format('Python')

Out[189]:

'this is a string Python'

In [191]:

'this is a string {:10s}'.format('Python')

'this is a string {:10s}'.format('Python')

Out[191]:

'this is a string Python    '

In [193]:

i = 0
while i < 4:
    print('the number is %d' % i)
    i += 1

i = 0 while i < 4: print('the number is %d' % i) i += 1

the number is 0
the number is 1
the number is 2
the number is 3

In [195]:

i = 0
while i < 4:
    print('the number is {:d}'.format(i))
    i += 1

i = 0 while i < 4: print('the number is {:d}'.format(i)) i += 1

the number is 0
the number is 1
the number is 2
the number is 3

正则表达（选修）¶

In [198]:

import re

import re

In [200]:

series = """
'01/18/2014 13:00:00', 100, '1st';
'01/18/2014 13:30:00', 110, '2nd';
'01/18/2014 14:00:00', 120, '3rd'
"""

series = """ '01/18/2014 13:00:00', 100, '1st'; '01/18/2014 13:30:00', 110, '2nd'; '01/18/2014 14:00:00', 120, '3rd' """

In [202]:

dt = re.compile("'[0-9/:\s]+'")  # datetime

dt = re.compile("'[0-9/:\s]+'") # datetime

<>:1: SyntaxWarning: invalid escape sequence '\s'
<>:1: SyntaxWarning: invalid escape sequence '\s'
C:\Users\getwa\AppData\Local\Temp\ipykernel_20404\231164877.py:1: SyntaxWarning: invalid escape sequence '\s'
  dt = re.compile("'[0-9/:\s]+'")  # datetime

In [206]:

result = dt.findall(series)
result

result = dt.findall(series) result

Out[206]:

["'01/18/2014 13:00:00'", "'01/18/2014 13:30:00'", "'01/18/2014 14:00:00'"]

In [208]:

from datetime import datetime
pydt = datetime.strptime(result[0].replace("'", ""),
                         '%m/%d/%Y %H:%M:%S')
pydt

from datetime import datetime pydt = datetime.strptime(result[0].replace("'", ""), '%m/%d/%Y %H:%M:%S') pydt

Out[208]:

datetime.datetime(2014, 1, 18, 13, 0)

In [210]:

print(pydt)

print(pydt)

2014-01-18 13:00:00

In [212]:

print(type(pydt))

print(type(pydt))

<class 'datetime.datetime'>

基本数据结构¶

Tuples 元组¶

In [216]:

t = (1, 2.5, 'data')
type(t)

t = (1, 2.5, 'data') type(t)

Out[216]:

tuple

In [218]:

t = 1, 2.5, 'data'
type(t)

t = 1, 2.5, 'data' type(t)

Out[218]:

tuple

In [220]:

t[2]

t[2]

Out[220]:

'data'

In [222]:

type(t[2])

type(t[2])

Out[222]:

str

In [224]:

t.count('data')

t.count('data')

Out[224]:

1

In [226]:

t.index(1)

t.index(1)

Out[226]:

0

Lists 列表¶

In [229]:

l = [1, 2.5, 'data']
l[2]

l = [1, 2.5, 'data'] l[2]

Out[229]:

'data'

In [231]:

l = list(t)
l

l = list(t) l

Out[231]:

[1, 2.5, 'data']

In [233]:

type(l)

type(l)

Out[233]:

list

In [235]:

l.append([4, 3])  
l

l.append([4, 3]) l

Out[235]:

[1, 2.5, 'data', [4, 3]]

In [237]:

l.extend([1.0, 1.5, 2.0])  
l

l.extend([1.0, 1.5, 2.0]) l

Out[237]:

[1, 2.5, 'data', [4, 3], 1.0, 1.5, 2.0]

In [239]:

l.insert(1, 'insert')  
l

l.insert(1, 'insert') l

Out[239]:

[1, 'insert', 2.5, 'data', [4, 3], 1.0, 1.5, 2.0]

In [241]:

l.remove('data')  
l

l.remove('data') l

Out[241]:

[1, 'insert', 2.5, [4, 3], 1.0, 1.5, 2.0]

In [243]:

p = l.pop(3)  
print(l, p)

p = l.pop(3) print(l, p)

[1, 'insert', 2.5, 1.0, 1.5, 2.0] [4, 3]

In [245]:

l[2:5]

l[2:5]

Out[245]:

[2.5, 1.0, 1.5]

Control Structures 控制结构¶

In [248]:

for element in l[2:5]:
    print(element ** 2)

for element in l[2:5]: print(element ** 2)

6.25
1.0
2.25

In [250]:

r = range(0, 8, 1)  
r

r = range(0, 8, 1) r

Out[250]:

range(0, 8)

In [252]:

type(r)

type(r)

Out[252]:

range

In [254]:

for i in range(2, 5):
    print(l[i] ** 2)

for i in range(2, 5): print(l[i] ** 2)

6.25
1.0
2.25

In [256]:

for i in range(1, 10):
    if i % 2 == 0:  
        print("%d is even" % i)
    elif i % 3 == 0:
        print("%d is multiple of 3" % i)
    else:
        print("%d is odd" % i)

for i in range(1, 10): if i % 2 == 0: print("%d is even" % i) elif i % 3 == 0: print("%d is multiple of 3" % i) else: print("%d is odd" % i)

1 is odd
2 is even
3 is multiple of 3
4 is even
5 is odd
6 is even
7 is odd
8 is even
9 is multiple of 3

In [258]:

total = 0
while total < 100:
    total += 1
print(total)

total = 0 while total < 100: total += 1 print(total)

100

In [260]:

m = [i ** 2 for i in range(5)]
m

m = [i ** 2 for i in range(5)] m

Out[260]:

[0, 1, 4, 9, 16]

函数编写¶

In [263]:

def f(x):
    return x ** 2
f(2)

def f(x): return x ** 2 f(2)

Out[263]:

4

In [265]:

def even(x):
    return x % 2 == 0
even(3)

def even(x): return x % 2 == 0 even(3)

Out[265]:

False

In [267]:

list(map(even, range(10)))

list(map(even, range(10)))

Out[267]:

[True, False, True, False, True, False, True, False, True, False]

In [269]:

list(map(lambda x: x ** 2, range(10)))

list(map(lambda x: x ** 2, range(10)))

Out[269]:

[0, 1, 4, 9, 16, 25, 36, 49, 64, 81]

In [271]:

list(filter(even, range(15)))

list(filter(even, range(15)))

Out[271]:

[0, 2, 4, 6, 8, 10, 12, 14]

Dicts 字典型数据¶

In [274]:

d = {
     'Name' : 'Angela Merkel',
     'Country' : 'Germany',
     'Profession' : 'Chancelor',
     'Age' : 64
     }
type(d)

d = { 'Name' : 'Angela Merkel', 'Country' : 'Germany', 'Profession' : 'Chancelor', 'Age' : 64 } type(d)

Out[274]:

dict

In [276]:

print(d['Name'], d['Age'])

print(d['Name'], d['Age'])

Angela Merkel 64

In [278]:

d.keys()

d.keys()

Out[278]:

dict_keys(['Name', 'Country', 'Profession', 'Age'])

In [280]:

d.values()

d.values()

Out[280]:

dict_values(['Angela Merkel', 'Germany', 'Chancelor', 64])

In [282]:

d.items()

d.items()

Out[282]:

dict_items([('Name', 'Angela Merkel'), ('Country', 'Germany'), ('Profession', 'Chancelor'), ('Age', 64)])

In [284]:

birthday = True
if birthday:
    d['Age'] += 1
print(d['Age'])

birthday = True if birthday: d['Age'] += 1 print(d['Age'])

65

In [286]:

for item in d.items():
    print(item)

for item in d.items(): print(item)

('Name', 'Angela Merkel')
('Country', 'Germany')
('Profession', 'Chancelor')
('Age', 65)

In [288]:

for value in d.values():
    print(type(value))

for value in d.values(): print(type(value))

<class 'str'>
<class 'str'>
<class 'str'>
<class 'int'>

Sets 集合¶

In [291]:

s = set(['u', 'd', 'ud', 'du', 'd', 'du'])
s

s = set(['u', 'd', 'ud', 'du', 'd', 'du']) s

Out[291]:

{'d', 'du', 'u', 'ud'}

In [293]:

t = set(['d', 'dd', 'uu', 'u'])

t = set(['d', 'dd', 'uu', 'u'])

In [295]:

s.union(t)

s.union(t)

Out[295]:

{'d', 'dd', 'du', 'u', 'ud', 'uu'}

In [297]:

s.intersection(t)

s.intersection(t)

Out[297]:

{'d', 'u'}

In [299]:

s.difference(t)

s.difference(t)

Out[299]:

{'du', 'ud'}

In [301]:

t.difference(s)

t.difference(s)

Out[301]:

{'dd', 'uu'}

In [303]:

s.symmetric_difference(t)

s.symmetric_difference(t)

Out[303]:

{'dd', 'du', 'ud', 'uu'}

In [305]:

from random import randint
l = [randint(0, 10) for i in range(1000)]  
len(l)

from random import randint l = [randint(0, 10) for i in range(1000)] len(l)

Out[305]:

1000

In [307]:

l[:20]

l[:20]

Out[307]:

[1, 6, 4, 6, 3, 2, 8, 0, 0, 0, 2, 4, 7, 2, 9, 7, 3, 0, 8, 3]

In [309]:

s = set(l)
s

s = set(l) s

Out[309]:

{0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10}

本课程训练结束