南大《探索数据的奥秘》课件示例代码笔记01

In [2]: import math
my_list1=['haha',True, math.pi,56,7,8]
print(my_list1[0])
print(my_list1[1])
print(my_list1[2])
print('\n')
print(my_list1[-1])
haha
True
3.141592653589793
8
In [3]: # 列表元素切取
print('\n')
first_three=my_list1[:3]
print(first_three)
last_three=my_list1[-3:]
print(last_three)
without_first_last=my_list1[1:-1]
print(without_first_last)
y=my_list1[1:3]
print(y)
['haha', True, 3.141592653589793]
[56, 7, 8]
[True, 3.141592653589793, 56, 7]
[True, 3.141592653589793]
In [4]: my_list1[0]=0
print(my_list1)
[0, True, 3.141592653589793, 56, 7, 8]
In [8]: my_list1=['haha',True, math.pi,56,7,8]
print(my_list1)
my_list1.append('hehe')
print(my_list1)
my_list1.insert(3,'你好！ ')
print(my_list1)
['haha', True, 3.141592653589793, 56, 7, 8]
['haha', True, 3.141592653589793, 56, 7, 8, 'hehe']
['haha', True, 3.141592653589793, ' 你好！ ', 56, 7, 8, 'hehe']
In [10]: # 元组
my_tuple_x=(1,2,3)
my_tuple_y=4,5
print(my_tuple_x,my_tuple_y)
try:
my_tuple_x[1]='haha'
except TypeError:
print('不允许修改元组！ ')
print(my_tuple_x)
(1, 2, 3) (4, 5)
不允许修改元组！
(1, 2, 3)
In [51]: #dict
z={'haha':80,'wuwu':20}
my_score=z['haha']
print(my_score)
print('xixi' in z)
80
False
In [52]: z['haha']=90
z['hehe']=10
print(z)
print(z.keys())
print(z.values())
print(z.items())
{'haha': 90, 'wuwu': 20, 'hehe': 10}
dict_keys(['haha', 'wuwu', 'hehe'])
dict_values([90, 20, 10])
dict_items([('haha', 90), ('wuwu', 20), ('hehe', 10)])
In [1]: my_dict={1:20,2:30,4:50}
print(my_dict)
{1: 20, 2: 30, 4: 50}
In [20]: #set
my_set={'123','456',89,True}
print(my_set)
{89, '456', '123', True}
In [12]: #ndarray
import numpy as np
x=[1,2,3,4,5,6]
print(type(x))
print(x+x)
<class 'list'>
[1, 2, 3, 4, 5, 6, 1, 2, 3, 4, 5, 6]
In [13]: my_ndarray1=np.array(x)
type(my_ndarray1)
Out[13]: numpy.ndarray
In [15]: my_ndarray2=np.array([0,1,0,1,0,1])
my_sum=my_ndarray1+my_ndarray2
my_sum
Out[15]: array([1, 3, 3, 5, 5, 7])
In [16]: a=my_sum.reshape((2,3))
print(a)
print('\n')
print(a[0,2])
[[1 3 3]
[5 5 7]]
In [20]: #dataframe
import pandas as pd
import numpy as np
my_dataframe=pd.DataFrame(np.random.randn(4,5),
index=['a','b','c','d'],
columns=['A','B','C','D','E'])
my_dataframe
Out[20]: A B C D E
a 1.385596 -0.646824 -0.247810 2.318796 -0.211721
b 0.452257 0.671649 0.615052 0.240041 0.470151
c 0.341342 1.604788 -0.885914 -0.796825 -0.619792
d 1.800393 1.076134 1.029607 -0.047988 2.193134
In [21]: type(my_dataframe)
Out[21]: pandas.core.frame.DataFrame
In [22]: my_dataframe[['B','C']] # 指定列访问 1，有列标题，返回值仍是 dataframe
Out[22]: B C
a -0.646824 -0.247810
b 0.671649 0.615052
c 1.604788 -0.885914
d 1.076134 1.029607
In [23]: my_dataframe[['B']] # 指定列访问 2，有列标题，返回值仍是 dataframe
Out[23]: B
a -0.646824
b 0.671649
c 1.604788
d 1.076134
In [24]: my_dataframe['B'] # 指定列访问 3，无列标题，返回值是序列 series
Out[24]: a -0.646824
b 0.671649
c 1.604788
d 1.076134
Name: B, dtype: float64
In [25]: my_dataframe.iloc[1] # 指定行访问 1，指定行号
Out[25]: A 0.452257
B 0.671649
5C 0.615052
D 0.240041
E 0.470151
Name: b, dtype: float64
In [27]: my_dataframe.loc['b'] # 指定行访问 2，指定行索引
Out[27]: A 0.452257
B 0.671649
C 0.615052
D 0.240041
E 0.470151
Name: b, dtype: float64