numpy介绍

#Use %timeit来计算时间
%timeit L = [n ** 2 for n in range(1000)]

268 µs ± 8.03 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

#展示操作
%history -n 1-4

   1:
#Use %timeit来计算时间
%timeit L = [n ** 2 for n in range(1000)]
   2:
#展示操作
%history -n 1-4

#To run
%run myscript.py
#run myscript.py and output results in the current cell
#• To load/import
%load myscript.py
#load "import" myscript.py into the current cell
#• To write/save
%%writefile myfile.py.

#可以调用Shell语句
contents = !ls
print(contents)
message = "hello from Python"
!echo {message}

['$RECYCLE.BIN', '2020.夏学习', '2020秋学习', '2021 春学习', '2021冬学习', 'E5A92AD8-ADB5-4A77-A9FE-57B8F8D43B51.png', 'TOFEL', 'Thumbs.db', 'U201913821+朱旭鹏汇编语言实验报告.pdf', 'Windows', 'abab.html', 'abab.ipynb', 'desktop.ini', 'exp.', 'midi合集', 'myfile.py.', 'svn', '书', '第11-13章基础练习题(修订版).docx', '汇编', '结果.pdf', '杂七杂八', '题目设计.docx', '阿巴阿巴.md', '每日计划.xlsx', '汇编语言实验报告.docx', '汇编语言实验报告.pdf']
hello from Python

def func1(a, b):
    return a / b
def func2(x):
    a = x
    b = x - 1
    return func1(a, b)

%debug func2(1)
#运行会产生ipdb>
#输入语句可以产生效果

NOTE: Enter 'c' at the ipdb>  prompt to continue execution.
> <string>(1)<module>()

ipdb> up
> /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/bdb.py(587)run()
    585         sys.settrace(self.trace_dispatch)
    586         try:
--> 587             exec(cmd, globals, locals)
    588         except BdbQuit:
    589             pass

ipdb> print(a)
*** NameError: name 'a' is not defined
ipdb> exit

print("hello")

hello

%%writefile myfile.py.
print("hello")

Overwriting myfile.py.

#Python自带的List
L=[1,2,3,4,5]
print(L)

[1, 2, 3, 4, 5]

import numpy as np

#一些声明的方法
#二维声明
a = np.array([[1,  2],  [3,  4]])  
print (a)
# dtype 参数  
a = np.array([1,  2,  3], dtype = complex)  
print (a)

[[1 2]
 [3 4]]
[1.+0.j 2.+0.j 3.+0.j]

#定义数据结构并且声明数组
dt = np.dtype([('age',np.int8)]) 
a = np.array([(10,),(20,),(30,)], dtype = dt)
#限制输出的元素
print(a['age'])
student = np.dtype([('name','S20'), ('age', 'i1'), ('marks', 'f4')]) 
a = np.array([('abc', 21, 50),('xyz', 18, 75)], dtype = student) 
print(a)

[10 20 30]
[(b'abc', 21, 50.) (b'xyz', 18, 75.)]

#全部填充0
b=np.zeros(10, dtype=int)
print(b)
#全部填充1
b=np.ones((3, 5), dtype=float)
print(b)
#全部填充某个值
b=np.full((3, 5), 3.14)
print(b)
#每步跳2
b=np.arange(0, 20, 2)
print(b)
#一共走n步
b=np.linspace(0, 1, 5)
print(b)

[0 0 0 0 0 0 0 0 0 0]
[[1. 1. 1. 1. 1.]
 [1. 1. 1. 1. 1.]
 [1. 1. 1. 1. 1.]]
[[3.14 3.14 3.14 3.14 3.14]
 [3.14 3.14 3.14 3.14 3.14]
 [3.14 3.14 3.14 3.14 3.14]]
[ 0  2  4  6  8 10 12 14 16 18]
[0.   0.25 0.5  0.75 1.  ]

#ramdom函数:生成随机数
np.random.random((3, 3))

array([[0.61499486, 0.51899507, 0.79505671],
       [0.81141113, 0.4516106 , 0.65727601],
       [0.89103435, 0.93678756, 0.2953434 ]])

#取值
np.random.normal(0,1, (3, 3))

array([[ 0.36907848,  1.28557422,  0.28982773],
       [ 0.70328736,  0.68839499, -0.15777985],
       [ 0.82233816, -2.18052732, -0.27150497]])

#随机取整数值
np.random.seed(0)
x1 = np.random.randint(10, size=6) # One-dimensional array
x2 = np.random.randint(10, size=(3, 4)) # Two-dimensional array
x3 = np.random.randint(10, size=(3, 4, 5)) # Three-dimensional arra
print(x2)
#可以取n:m的值,n默认为0,m默认为最大值
x2_sub = x2[:2, :2]
x2_sub2 = x2[2: ,2:]
#可以像n维数组那样取值
x2_sub[0, 0] = 99
print(x2_sub)
print(x2_sub2)
a = np.array([[1,2,3],[3,4,5],[4,5,6]])  
print (a[...,1])   # 第2列元素
print (a[1,...])   # 第2行元素
print (a[...,1:])  # 第2列及剩下的所有元素

[[3 5 2 4]
 [7 6 8 8]
 [1 6 7 7]]
[[99  5]
 [ 7  6]]
[[7 7]]
[2 4 5]
[3 4 5]
[[2 3]
 [4 5]
 [5 6]]

#这个是引用的,类似于C的数组
print(x2)

[[99  5  2  4]
 [ 7  6  8  8]
 [ 1  6  7  7]]

#深拷贝
x2_copy = x2[:2, :2].copy()
x2_copy[0, 0] = 9999
print(x2_copy)
print(x2)

[[9999    5]
 [   7    6]]
[[99  5  2  4]
 [ 7  6  8  8]
 [ 1  6  7  7]]

#reshape可以改变维度
a = np.arange(24)  
print (a.ndim)             # a 现只有一个维度
# 现在调整其大小
b = a.reshape(2,4,3)  # b 现在拥有三个维度
print (b.ndim)
# 当然可以通过shape来改变(reshape是个方法,shape是个成员)
a = np.array([[1,2,3],[4,5,6]]) 
a.shape =  (3,2)  
print (a)

1
3
[[1 2]
 [3 4]
 [5 6]]

#可以通过已有数组来构建narray
x =  [1,2,3] 
a = np.asarray(x)  
print (a)
x =  [(1,2,3),(4,5)] 
a = np.asarray(x)  
print (a)

[1 2 3]
[(1, 2, 3) (4, 5)]

a = np.arange(10)
s = slice(2,7,2)   # 从索引 2 开始到索引 7 停止，间隔为2
print (a[s])
b = a[2:7:2]   # 从索引 2 开始到索引 7 停止，间隔为 2
print(b)

grid = np.arange(1, 10).reshape((3, 3))
print(grid)

[[1 2 3]
 [4 5 6]
 [7 8 9]]

#转置
x=np.array(range(1,10)).reshape((3,3))
print(x.T)
x=np.arange(10)
print(x.T)
#布尔索引
print  ('大于 5 的元素是：')
print (x[x >  5])

[[1 4 7]
 [2 5 8]
 [3 6 9]]
[0 1 2 3 4 5 6 7 8 9]
大于 5 的元素是：
[6 7 8 9]

x=np.arange(32).reshape((8,4))
print (x)
print (x[np.ix_([1,5,7,2],[0,3,1,2])])#选择行,选择列

[[ 0  1  2  3]
 [ 4  5  6  7]
 [ 8  9 10 11]
 [12 13 14 15]
 [16 17 18 19]
 [20 21 22 23]
 [24 25 26 27]
 [28 29 30 31]]
[[ 4  7  5  6]
 [20 23 21 22]
 [28 31 29 30]
 [ 8 11  9 10]]

#广播
a = np.array([[ 0, 0, 0],
           [10,10,10],
           [20,20,20],
           [30,30,30]])
b = np.array([1,2,3])
print(a + b)

[[ 1  2  3]
 [11 12 13]
 [21 22 23]
 [31 32 33]]

grid = np.array([[1, 2, 3],
[4, 5, 6]])
np.concatenate([grid, grid])
np.concatenate([grid, grid], axis= 1)

array([[1, 2, 3, 1, 2, 3],
       [4, 5, 6, 4, 5, 6]])

def compute_reciprocals(values):
    output = np.empty(len(values))
    for i in range(len(values)):
        output[i] = 1.0 / values[i]
    return output
values = np.random.randint(1, 10, size=5)
compute_reciprocals(values)

array([0.2       , 0.25      , 0.2       , 0.2       , 0.11111111])

big_array = np.random.randint(1, 100, size=1000000)
%timeit compute_reciprocals(big_array)
%timeit (1.0 / big_array)

1.97 s ± 37.6 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
2.95 ms ± 63.9 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

M = np.random.random((3, 4))
print(M)
M.sum()
a=M.min(axis=0)
print(a)
a=M.max(axis=1) 
print(a)

[[0.35944446 0.48089353 0.68866118 0.88047589]
 [0.91823547 0.21682214 0.56518887 0.86510256]
 [0.50896896 0.91672295 0.92115761 0.08311249]]
[0.35944446 0.21682214 0.56518887 0.08311249]
[0.88047589 0.91823547 0.92115761]

#传统的关于字典的操作
datatable = [{'temp':28, 'humidity':80},
            {'temp':26, 'humidity':75},
            {'temp':32, 'humidity':50},
            {'temp':30, 'humidity':65},
            {'temp':33, 'humidity':55}]
#遍历元素
for i in range(0, len(datatable)):
    for j in datatable[i]:
        print('Row {} Cell {}: {}'.format(i, j, datatable[i][j]))
columns = []
columns.append([])
columns.append([])

for i in range(0, len(datatable)):
    columns[0].append(datatable[i]['temp'])
    columns[1].append(datatable[i]['humidity'])
#遍历列
for i in range(0, len(columns)):
    print('Column {}: {}'.format(i, columns[i]))

Row 0 Cell temp: 28
Row 0 Cell humidity: 80
Row 1 Cell temp: 26
Row 1 Cell humidity: 75
Row 2 Cell temp: 32
Row 2 Cell humidity: 50
Row 3 Cell temp: 30
Row 3 Cell humidity: 65
Row 4 Cell temp: 33
Row 4 Cell humidity: 55
Column 0: [28, 26, 32, 30, 33]
Column 1: [80, 75, 50, 65, 55]

datatable2 = [{'temp':28, 'humidity':80},
            {'temp':26, 'humidity':75},
            {'temp':32, 'humidity':50},
            {'temp':30, 'humidity':65},
            {'temp':33, 'humidity':55}]
averages = []

for i in range(0, len(datatable1)):
    averages.append((datatable1[i]['temp'] + datatable2[i]['temp']) / 2)
for i in range(0, len(datatable1)):
    print('Average for Row {}: {}'.format(i, averages[i]))

Average for Row 0: 28.0
Average for Row 1: 26.0
Average for Row 2: 32.0
Average for Row 3: 30.0
Average for Row 4: 33.0

#声明一个Series
!pip install pandas
import numpy as np
import pandas as pd
#index默认为从0开始的
s = pd.Series([12, -4, 7, 9])
print(s)

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting pandas
  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/d6/66/35235bc1d1ebc34d807c100c4b54a13660695f18c2fb29d2192ebbb5a613/pandas-1.2.4-cp38-cp38-macosx_10_9_x86_64.whl (10.5 MB)
     |████████████████████████████████| 10.5 MB 1.3 MB/s eta 0:00:01
Requirement already satisfied: python-dateutil>=2.7.3 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from pandas) (2.8.1)
Collecting pytz>=2017.3
  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/70/94/784178ca5dd892a98f113cdd923372024dc04b8d40abe77ca76b5fb90ca6/pytz-2021.1-py2.py3-none-any.whl (510 kB)
     |████████████████████████████████| 510 kB 3.4 MB/s eta 0:00:01
Requirement already satisfied: numpy>=1.16.5 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from pandas) (1.18.2)
Requirement already satisfied: six>=1.5 in /Users/xupengzhu/Library/Python/3.8/lib/python/site-packages (from python-dateutil>=2.7.3->pandas) (1.14.0)
Installing collected packages: pytz, pandas
Successfully installed pandas-1.2.4 pytz-2021.1
WARNING: You are using pip version 21.0.1; however, version 21.1.1 is available.
You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.8/bin/python3 -m pip install --upgrade pip' command.
0    12
1    -4
2     7
3     9
dtype: int64

s = pd.Series([12, -4, 7, 9], index=['a', 'b', 'c', 'd'])
print(s)
# Selecting elements
print(s[2])#第二个
print(s['b'])
print(s[0:2])
print(s[['b','c']])
#赋值
s[1] = 0
print(s)
# 布尔索引
print(s[s>8])
# Operations and math functions
print(s/2)

a    12
b    -4
c     7
d     9
dtype: int64
7
-4
a    12
b    -4
dtype: int64
b   -4
c    7
dtype: int64
a    12
b     0
c     7
d     9
dtype: int64
a    12
d     9
dtype: int64
a    6.0
b    0.0
c    3.5
d    4.5
dtype: float64

serd = pd.Series([1,0,2,1,2,3], index=['white','white','blue','green','green','yellow'])
print(serd)

print(serd.unique())
print(serd.value_counts())
#在里面么?不再的话就是True
print(serd.isin([0,3]))
print(serd[serd.isin([0,3])])

white     1
white     0
blue      2
green     1
green     2
yellow    3
dtype: int64
[1 0 2 3]
1    2
2    2
0    1
3    1
dtype: int64
white     False
white      True
blue      False
green     False
green     False
yellow     True
dtype: bool
white     0
yellow    3
dtype: int64

#根据字典赋值
mydict1 = {'red':2000, 'blue': 1000, 'yellow':500, 'orange':1000}
myseries1 = pd.Series(mydict1)
print(myseries1)
mydict2 = {'red':400, 'yellow':1000, 'black':700}
myseries2 = pd.Series(mydict2)
print(myseries2)
#如果一个没有一个有.默认为NaN
myseries3 = myseries1 + myseries2
print(myseries3)

red       2000
blue      1000
yellow     500
orange    1000
dtype: int64
red        400
yellow    1000
black      700
dtype: int64
black        NaN
blue         NaN
orange       NaN
red       2400.0
yellow    1500.0
dtype: float64

#构建dataFrame
data = {'color': ['blue','green','yellow','red','white'],
        'object': ['ball','pen','pencil','paper','mug'],
        'price':[1.2,1.0,0.6,0.9,1.7]}

print(data)
frame = pd.DataFrame(data)
print(frame)
#有什么行
print(frame.columns)
#有什么列
print(frame.index)
#把值按照矩阵的形式输出
print(frame.values)
#只输出某一列
print(frame['price'])
print(frame.price)
#输出某一行
print(frame.iloc[0])
#某一行某一列元素
print(frame.iloc[0]['price'])
#可以改变元素的值
#另外一个方法寻找
for i in range(0, len(frame.index)):
    frame.loc[i,'price'] = 8.88

print(frame.price)

{'color': ['blue', 'green', 'yellow', 'red', 'white'], 'object': ['ball', 'pen', 'pencil', 'paper', 'mug'], 'price': [1.2, 1.0, 0.6, 0.9, 1.7]}
    color  object  price
0    blue    ball    1.2
1   green     pen    1.0
2  yellow  pencil    0.6
3     red   paper    0.9
4   white     mug    1.7
Index(['color', 'object', 'price'], dtype='object')
RangeIndex(start=0, stop=5, step=1)
[['blue' 'ball' 1.2]
 ['green' 'pen' 1.0]
 ['yellow' 'pencil' 0.6]
 ['red' 'paper' 0.9]
 ['white' 'mug' 1.7]]
0    1.2
1    1.0
2    0.6
3    0.9
4    1.7
Name: price, dtype: float64
0    1.2
1    1.0
2    0.6
3    0.9
4    1.7
Name: price, dtype: float64
color     blue
object    ball
price      1.2
Name: 0, dtype: object
1.2
0    8.88
1    8.88
2    8.88
3    8.88
4    8.88
Name: price, dtype: float64

#利用字典加上一个index数组构造dataFrame
data1 = {'ball': [0,4,8,12],
        'pen': [1,5,9,13],
        'pencil': [2,6,10,14],
        'paper':[3,7,11,15]}

frame1 = pd.DataFrame(data1, index=['red','blue','yellow','white'])

print(frame1)
data2 = {'mug': [0,3,6,9],
        'pen': [1,4,7,10],
        'ball': [2,5,8,11]}

frame2 = pd.DataFrame(data2, index=['blue','green','white','yellow'])

print(frame2)

        ball  pen  pencil  paper
red        0    1       2      3
blue       4    5       6      7
yellow     8    9      10     11
white     12   13      14     15
        mug  pen  ball
blue      0    1     2
green     3    4     5
white     6    7     8
yellow    9   10    11

frame3 = frame1.add(frame2)
print(frame3)
#有重复的就是NaN

        ball  mug  paper   pen  pencil
blue     6.0  NaN    NaN   6.0     NaN
green    NaN  NaN    NaN   NaN     NaN
red      NaN  NaN    NaN   NaN     NaN
white   20.0  NaN    NaN  20.0     NaN
yellow  19.0  NaN    NaN  19.0     NaN

print(frame1.sum())
print(frame1.mean())
print(frame1.describe())

ball      24
pen       28
pencil    32
paper     36
dtype: int64
ball      6.0
pen       7.0
pencil    8.0
paper     9.0
dtype: float64
            ball        pen     pencil      paper
count   4.000000   4.000000   4.000000   4.000000
mean    6.000000   7.000000   8.000000   9.000000
std     5.163978   5.163978   5.163978   5.163978
min     0.000000   1.000000   2.000000   3.000000
25%     3.000000   4.000000   5.000000   6.000000
50%     6.000000   7.000000   8.000000   9.000000
75%     9.000000  10.000000  11.000000  12.000000
max    12.000000  13.000000  14.000000  15.000000

#读入csv
csvframe1 = pd.read_csv('/Users/xupengzhu/Desktop/src/data/myCSV_01.csv')
print(csvframe1)

   white  red  blue  green animal
0      1    5     2      3    cat
1      2    7     8      5    dog
2      3    3     6      7  horse
3      2    2     8      3   duck
4      4    4     2      1  mouse

csvframe1 = pd.read_csv('/Users/xupengzhu/Desktop/src/data/myCSV_01.csv',index_col=4)
print(csvframe1)

        white  red  blue  green
animal                         
cat         1    5     2      3
dog         2    7     8      5
horse       3    3     6      7
duck        2    2     8      3
mouse       4    4     2      1

csvframe = pd.read_csv('/Users/xupengzhu/Desktop/src/data/myCSV_01.csv')
csvframe['total'] = csvframe['white'] + csvframe['red'] + csvframe['blue'] + csvframe['green']
csvframe['excess'] = False
#综合利用
for i in range(len(csvframe)):
    if csvframe.loc[i,'total'] > 15:
        csvframe.loc[i,'excess'] = True

print(csvframe)

   white  red  blue  green animal  total  excess
0      1    5     2      3    cat     11   False
1      2    7     8      5    dog     22    True
2      3    3     6      7  horse     19    True
3      2    2     8      3   duck     15   False
4      4    4     2      1  mouse     11   False

#删除元素
csvframe = csvframe.drop('total', axis=1)
csvframe = csvframe.drop(0, axis=0)

print(csvframe)

   white  red  blue  green animal  excess
1      2    7     8      5    dog    True
2      3    3     6      7  horse    True
3      2    2     8      3   duck   False
4      4    4     2      1  mouse   False

! pip install matplotlib
! pip install seaborn 
import matplotlib.pyplot as plt
import seaborn
seaborn.set()

Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Requirement already satisfied: matplotlib in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (3.4.2)
Requirement already satisfied: cycler>=0.10 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib) (0.10.0)
Requirement already satisfied: numpy>=1.16 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib) (1.18.2)
Requirement already satisfied: pyparsing>=2.2.1 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib) (2.4.7)
Requirement already satisfied: python-dateutil>=2.7 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib) (2.8.1)
Requirement already satisfied: pillow>=6.2.0 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib) (8.2.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib) (1.3.1)
Requirement already satisfied: six in /Users/xupengzhu/Library/Python/3.8/lib/python/site-packages (from cycler>=0.10->matplotlib) (1.14.0)
WARNING: You are using pip version 21.0.1; however, version 21.1.1 is available.
You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.8/bin/python3 -m pip install --upgrade pip' command.
Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple
Collecting seaborn
  Downloading https://pypi.tuna.tsinghua.edu.cn/packages/68/ad/6c2406ae175f59ec616714e408979b674fe27b9587f79d59a528ddfbcd5b/seaborn-0.11.1-py3-none-any.whl (285 kB)
     |████████████████████████████████| 285 kB 1.6 MB/s eta 0:00:01
Requirement already satisfied: matplotlib>=2.2 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from seaborn) (3.4.2)
Requirement already satisfied: scipy>=1.0 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from seaborn) (1.4.1)
Requirement already satisfied: pandas>=0.23 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from seaborn) (1.2.4)
Requirement already satisfied: numpy>=1.15 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from seaborn) (1.18.2)
Requirement already satisfied: kiwisolver>=1.0.1 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (1.3.1)
Requirement already satisfied: pyparsing>=2.2.1 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (2.4.7)
Requirement already satisfied: pillow>=6.2.0 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (8.2.0)
Requirement already satisfied: python-dateutil>=2.7 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (2.8.1)
Requirement already satisfied: cycler>=0.10 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from matplotlib>=2.2->seaborn) (0.10.0)
Requirement already satisfied: six in /Users/xupengzhu/Library/Python/3.8/lib/python/site-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.14.0)
Requirement already satisfied: pytz>=2017.3 in /Library/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages (from pandas>=0.23->seaborn) (2021.1)
Installing collected packages: seaborn
Successfully installed seaborn-0.11.1
WARNING: You are using pip version 21.0.1; however, version 21.1.1 is available.
You should consider upgrading via the '/Library/Frameworks/Python.framework/Versions/3.8/bin/python3 -m pip install --upgrade pip' command.

csvframe.plot()

<AxesSubplot:>