Python

Yayu Wang included in Programming_languages

2022-04-03 1293 words 3 minutes

String & Bytes

bytes to string

1
return b"abc123".decode("utf-8")

abc123

string to bytes

1
return "abc123".encode("utf-8")

b'abc123'

Virtual Env

create

1
python -m venv NAME

activate

1
source NAME/bin/activate

deactivate

1
deactivate

Arguments

argparse

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
  import argparse

  # Create the parser object
  parser = argparse.ArgumentParser(description="Process something")

  # Add an argument to the parser
  parser.add_argument(
      "-i",
      "--integers",
      metavar="N",
      required=True,
      type=int,
      help="an integer to be processed",
  )

  # Parse the arguments
  args = parser.parse_args()

  # Access the parsed arguments
  print(args.integers)

File

file exists

1
2
3
4
5
6
7
import os

filename = "example.txt"
if os.path.exists(filename):
    print("File exists")
else:
    print("File does not exist")

parent dir

1
2
3
import os

parent_dir = os.path.dirname(file_path)

list directory

1
2
3
4
import os

path = os.getcwd()
dir_list = os.listdir(path)

rename

1
2
3
import os

os.rename(old_name, new_name)

path join

1
2
3
4
5
6
7
import os

path1 = "/path/to/directory"
path2 = "subdirectory"
filename = "file.txt"
joined_path = os.path.join(path1, path2, filename)
print(joined_path)

directory create

1
2
3
4
5
6
7
8
9
import os

directory = "/path/to/directory"

if not os.path.exists(directory):
    os.makedirs(directory)
    print("Directory created:", directory)
else:
    print("Directory already exists:", directory)

threads

thread pool

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
22
import concurrent.futures

def execute_command(command):
    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
    stdout, stderr = process.communicate()
    return stdout, stderr

commands = [
    ['ls', '-l'],
    ['echo', 'Hello, world!'],
    ['pwd']
]

with concurrent.futures.ThreadPoolExecutor(max_workers=3) as executor:
    # Submit tasks to the thread pool
    future_results = [executor.submit(execute_command, command) for command in commands]

    # Get the results as they become available
    for future in concurrent.futures.as_completed(future_results):
        stdout, stderr = future.result()
        print("Standard Output:")
        print(stdout)

Random

choice

1
2
3
import random

random.choice([1, 2, 3, 4, 5])

uuid

1
2
3
import uuid

uuid.uuid4()

Data process

unique

1
2
3
import numpy as np

return np.unique([1, 1, 3, 2, 3])

Json

load from file

1
2
3
4
with open('data.json', 'r') as f:
    data = json.load(f)

print(data)

dump to file

1
2
with open('data.json', 'w') as f:
    json.dump(data, f)

dump class to file

1
2
3
4
5
6
7
8
9
class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age

person = Person("John Smith", 35)

with open('person.json', 'w') as f:
    json.dump(person.__dict__, f)

load class from file

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
class Person:
    def __init__(self, name, age):
        self.name = name
        self.age = age

with open('person.json', 'r') as f:
    data = json.load(f)
    person = Person(data['name'], data['age'])

print(person.name)
print(person.age)

Time

1
2
3
4
5
6
7
from time import gmtime, localtime, strftime

def print_gmtime():
    strftime("%a, %d %b %Y %H:%M:%S +0000", gmtime())

def print_localtime():
    return strftime("%a, %d %b %Y %H:%M:%S +0000", localtime())

None

duration

1
2
3
4
5
import time
start_time = time.perf_counter()
end_time = time.perf_counter()
elapsed_time = end_time - start_time
print(elapsed_time * 1000, "ms")

0.00015999830793589354

date

1
2
3
4
import datetime
x = datetime.datetime.now()
print(x)
return str(x)

2024-04-25 20:05:59.259296

socket

server

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
# Echo server program
import socket
from time import gmtime, strftime

HOST = '127.0.0.1'                 # Symbolic name meaning all available interfaces
PORT = 50007              # Arbitrary non-privileged port
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
    s.bind((HOST, PORT))
    s.listen(1)
    conn, addr = s.accept()
    with conn:
        print('Connected by', addr)
        while True:
            data = conn.recv(1024)
            print(strftime("%a, %d %b %Y %H:%M:%S +0000", gmtime()) + "receive: " + str(data))
            if not data: break
            conn.sendall(data)

client

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
# Echo client program
import socket
import time

HOST = '127.0.0.1'    # The remote host
PORT = 50007              # The same port as used by the server
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
    s.connect((HOST, PORT))
    while True:
        s.sendall(b'Hello, world')
        data = s.recv(1024)
        print('Received', repr(data))
        time.sleep(1)

class

super

理论上 super() 可以直接 call 嗷, 返回父类
- 调用父类函数时候, self指向的是子类
多继承的时候, 直接 super().func() 会从 mro 中, 从第二个找拥有 func() 的类
- 如果使用 super(clazz, self).func() 则会从 clazz.mro 中的第二个类开始找

enum

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
from enum import Enum

class Color(Enum):
    RED = 1
    GREEN = 2
    BLUE = 3

print(Color.RED)         # Output: Color.RED
print(Color.GREEN)       # Output: Color.GREEN
print(Color.BLUE)        # Output: Color.BLUE

print(Color.RED.value)   # Output: 1
print(Color.GREEN.value) # Output: 2
print(Color.BLUE.value)  # Output: 3

plot

networkx → graphviz

networkx to graphviz

1
2
3
4
5
6
7
8
9
import graphviz
import networkx as nx

G = nx.DiGraph()
# G.add_node(u)
# G.add_edge(u, v, label=label)
A = nx.nx_agraph.to_agraph(G)
A.layout("dot")
A.draw('graph.pdf')

colormesh (heatmap)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20
21
import matplotlib.pyplot as plt
import numpy as np

# generate 2 2d grids for the x & y bounds
y, x = np.meshgrid(np.linspace(-3, 3, 100), np.linspace(-3, 3, 100))

z = (1 - x / 2. + x ** 5 + y ** 3) * np.exp(-x ** 2 - y ** 2)
# x and y are bounds, so z should be the value *inside* those bounds.
# Therefore, remove the last value from the z array.
z = z[:-1, :-1]
z_min, z_max = -np.abs(z).max(), np.abs(z).max()

fig, ax = plt.subplots()

c = ax.pcolormesh(x, y, z, cmap='RdBu', vmin=z_min, vmax=z_max)
ax.set_title('pcolormesh')
# set the limits of the plot to the limits of the data
ax.axis([x.min(), x.max(), y.min(), y.max()])
fig.colorbar(c, ax=ax)

plt.show()

standard deviation / std / error bar

1
2
3
import matplotlib.pyplot as plt

plt.errorbar(x, y_mean, y_std, linestyle='None', marker='^')

dot

example

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
digraph {
  rankdir=LR;
  node [shape=ellipse];
  edge [color=red];

  A [label="Start"];
  B [label="Read input"];
  C [label="Process input"];
  D [label="Write output"];
  E [label="Stop"];

  A -> B;
  B -> C;
  C -> D [label="Yes"];
  D -> E;
  C -> E [label="No"];

  {rank=same; B C}
}

cli

1
dot -Tpng -Kdot -odot.png example.dot

pandas

from list

1
2
3
4
5
6
import pandas as pd

df = pd.DataFrame(
    [["wyy", "Pad Gra Paow", 80, "good", "2023-06-05 Mon"]],
    columns=["reviewer", "dish", "score", "comment", "date"],
)

to json

1
2
3
4
5
6
7
8
import pandas as pd

df = pd.DataFrame(
    [["wyy", "Pad Gra Paow", 80, "good", "2023-06-05 Mon"]],
    columns=["reviewer", "dish", "score", "comment", "date"],
)

return df.to_json(orient='split', force_ascii=False) # use unicode

groupby

1
df = df[["restaurant", "score"]].groupby('restaurant').mean()

count

1
review_df[["reviewer"]].groupby("reviewer").size().sort_values(ascending=False)

unique

1
pd.unique(review_df["restaurant"])

reverse

1
df = df.iloc[::-1]

to markdown

1
2
3
4
5
6
7
import pandas as pd

df = pd.DataFrame(
    [["wyy", "Pad Gra Paow", 80, "good", "2023-06-05 Mon"]],
    columns=["reviewer", "dish", "score", "comment", "date"],
)
return df.to_markdown()

concat

1
2
3
import pandas as pd

pd.concat([data1, data2])

horizontal

1
2
3
import pandas as pd

pd.concat([data1, data2], axis=1)

reset index

1
2
3
import pandas as pd

pd.concat([...]).reset_index(drop=True)

for loop/iterate

1
2
3
4
5
6
7
import pandas as pd

df = pd.DataFrame({'c1': [10, 11, 12], 'c2': [100, 110, 120]})
df = df.reset_index()  # make sure indexes pair with number of rows

for index, row in df.iterrows():
    print(index, row)

convert to numeric

1
df['score'] = pd.to_numeric(df['score'])

drop

1
df.drop(index='cow', columns='small')

numpy

percent

1
2
import numpy as np
np.percentile(arr, 99.9)

std

1
2
import numpy as np
np.std(array)

type

return void

1
2
def func() -> None:
    return

regex

1
2
3
import re

re.sub('[a-z]+@', 'ABC@', s, 2)

Contents

Python

String & Bytes

bytes to string

string to bytes

Virtual Env

create

activate

deactivate

Arguments

argparse

File

file exists

parent dir

list directory

rename

path join

directory create

threads

thread pool

Random

choice

uuid

Data process

unique

Json

load from file

dump to file

dump class to file

load class from file

Time

duration

date

socket

server

client

class

super

enum

plot

networkx to graphviz

colormesh (heatmap)

standard deviation / std / error bar

dot

cli

pandas

from list

to json

groupby

count

unique

reverse

to markdown

concat

horizontal

reset index

for loop/iterate

convert to numeric

drop

numpy

percent

std

type

return void

regex