guanjihuan/py.guanjihuan.com
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

0.1.127

Browse Source
This commit is contained in:
guanjihuan
2024-11-27 00:44:58 +08:00
parent 5b9a2d7267
commit 4982967bd6
8 changed files with 1022 additions and 1024 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
PyPI/setup.cfg
View File

@@ -1,7 +1,7 @@
[metadata] [metadata]
# replace with your username: # replace with your username:
name = guan name = guan
version = 0.1.126 version = 0.1.127
author = guanjihuan author = guanjihuan
author_email = guanjihuan@163.com author_email = guanjihuan@163.com
description = An open source python package description = An open source python package

2
PyPI/src/guan.egg-info/PKG-INFO
View File

@@ -1,6 +1,6 @@
Metadata-Version: 2.1 Metadata-Version: 2.1
Name: guan Name: guan
Version: 0.1.126 Version: 0.1.127
Summary: An open source python package Summary: An open source python package
Home-page: https://py.guanjihuan.com Home-page: https://py.guanjihuan.com
Author: guanjihuan Author: guanjihuan

1
PyPI/src/guan.egg-info/SOURCES.txt
View File

@@ -15,7 +15,6 @@ src/guan/deprecated.py
src/guan/figure_plotting.py src/guan/figure_plotting.py
src/guan/file_reading_and_writing.py src/guan/file_reading_and_writing.py
src/guan/machine_learning.py src/guan/machine_learning.py
src/guan/others.py
src/guan/quantum_transport.py src/guan/quantum_transport.py
src/guan/topological_invariant.py src/guan/topological_invariant.py
src/guan.egg-info/PKG-INFO src/guan.egg-info/PKG-INFO

1
PyPI/src/guan/__init__.py
View File

@@ -12,7 +12,6 @@ from .machine_learning import *
from .file_reading_and_writing import * from .file_reading_and_writing import *
from .figure_plotting import * from .figure_plotting import *
from .data_processing import * from .data_processing import *
from .others import *
from .decorators import * from .decorators import *
from .deprecated import * from .deprecated import *
statistics_of_guan_package() statistics_of_guan_package()

923
PyPI/src/guan/data_processing.py
View File

@@ -40,6 +40,40 @@ def chat(prompt='你好', model=1, stream=0, top_p=0.8, temperature=0.85):
print('\n--- End Stream Message ---\n') print('\n--- End Stream Message ---\n')
return response return response
# 将XYZ数据转成矩阵数据（说明：x_array/y_array的输入和输出不一样。要求z_array数据中y对应的数据为小循环，x对应的数据为大循环）
def convert_xyz_data_into_matrix_data(x_array, y_array, z_array):
import numpy as np
x_array_input = np.array(x_array)
y_array_input = np.array(y_array)
x_array = np.array(list(set(x_array_input)))
y_array = np.array(list(set(y_array_input)))
z_array = np.array(z_array)
len_x = len(x_array)
len_y = len(y_array)
matrix = np.zeros((len_x, len_y))
for ix in range(len_x):
for iy in range(len_y):
matrix[ix, iy] = z_array[ix*len_y+iy]
return x_array, y_array, matrix
# 将矩阵数据转成XYZ数据（说明：x_array/y_array的输入和输出不一样。生成的z_array数据中y对应的数据为小循环，x对应的数据为大循环）
def convert_matrix_data_into_xyz_data(x_array, y_array, matrix):
import numpy as np
x_array_input = np.array(x_array)
y_array_input = np.array(y_array)
matrix = np.array(matrix)
len_x = len(x_array_input)
len_y = len(y_array_input)
x_array = np.zeros((len_x*len_y))
y_array = np.zeros((len_x*len_y))
z_array = np.zeros((len_x*len_y))
for ix in range(len_x):
for iy in range(len_y):
x_array[ix*len_y+iy] = x_array_input[ix]
y_array[ix*len_y+iy] = y_array_input[iy]
z_array[ix*len_y+iy] = matrix[ix, iy]
return x_array, y_array, z_array
# 从列表中删除某个匹配的元素 # 从列表中删除某个匹配的元素
def remove_item_in_one_array(array, item): def remove_item_in_one_array(array, item):
new_array = [x for x in array if x != item] new_array = [x for x in array if x != item]
@@ -178,62 +212,6 @@ def run_programs_sequentially(program_files=['./a.py', './b.py'], execute='pytho
end = time.time() end = time.time()
print('Total running time = '+str((end-start)/60)+' min') print('Total running time = '+str((end-start)/60)+' min')
# 将XYZ数据转成矩阵数据（说明：x_array/y_array的输入和输出不一样。要求z_array数据中y对应的数据为小循环，x对应的数据为大循环）
def convert_xyz_data_into_matrix_data(x_array, y_array, z_array):
import numpy as np
x_array_input = np.array(x_array)
y_array_input = np.array(y_array)
x_array = np.array(list(set(x_array_input)))
y_array = np.array(list(set(y_array_input)))
z_array = np.array(z_array)
len_x = len(x_array)
len_y = len(y_array)
matrix = np.zeros((len_x, len_y))
for ix in range(len_x):
for iy in range(len_y):
matrix[ix, iy] = z_array[ix*len_y+iy]
return x_array, y_array, matrix
# 将矩阵数据转成XYZ数据（说明：x_array/y_array的输入和输出不一样。生成的z_array数据中y对应的数据为小循环，x对应的数据为大循环）
def convert_matrix_data_into_xyz_data(x_array, y_array, matrix):
import numpy as np
x_array_input = np.array(x_array)
y_array_input = np.array(y_array)
matrix = np.array(matrix)
len_x = len(x_array_input)
len_y = len(y_array_input)
x_array = np.zeros((len_x*len_y))
y_array = np.zeros((len_x*len_y))
z_array = np.zeros((len_x*len_y))
for ix in range(len_x):
for iy in range(len_y):
x_array[ix*len_y+iy] = x_array_input[ix]
y_array[ix*len_y+iy] = y_array_input[iy]
z_array[ix*len_y+iy] = matrix[ix, iy]
return x_array, y_array, z_array
# 通过定义计算R^2（基于实际值和预测值，数值有可能小于0）
def calculate_R2_with_definition(y_true_array, y_pred_array):
import numpy as np
y_mean = np.mean(y_true_array)
SS_tot = np.sum((y_true_array - y_mean) ** 2)
SS_res = np.sum((y_true_array - y_pred_array) ** 2)
R2 = 1 - (SS_res / SS_tot)
return R2
# 通过sklearn计算R^2，和上面定义的计算结果一致
def calculate_R2_with_sklearn(y_true_array, y_pred_array):
from sklearn.metrics import r2_score
R2 = r2_score(y_true_array, y_pred_array)
return R2
# 通过scipy计算线性回归后的R^2（基于线性回归模型，范围在0和1之间）
def calculate_R2_after_linear_regression_with_scipy(y_true_array, y_pred_array):
from scipy import stats
slope, intercept, r_value, p_value, std_err = stats.linregress(y_true_array, y_pred_array)
R2 = r_value**2
return R2
# 判断一个数是否接近于整数 # 判断一个数是否接近于整数
def close_to_integer(value, abs_tol=1e-3): def close_to_integer(value, abs_tol=1e-3):
import math import math
@@ -356,6 +334,98 @@ def hex_to_rgb(hex):
length = len(hex) length = len(hex)
return tuple(int(hex[i:i+length//3], 16) for i in range(0, length, length//3)) return tuple(int(hex[i:i+length//3], 16) for i in range(0, length, length//3))
# 拼接两个PDF文件
def combine_two_pdf_files(input_file_1='a.pdf', input_file_2='b.pdf', output_file='combined_file.pdf'):
import PyPDF2
output_pdf = PyPDF2.PdfWriter()
with open(input_file_1, 'rb') as file1:
pdf1 = PyPDF2.PdfReader(file1)
for page in range(len(pdf1.pages)):
output_pdf.add_page(pdf1.pages[page])
with open(input_file_2, 'rb') as file2:
pdf2 = PyPDF2.PdfReader(file2)
for page in range(len(pdf2.pages)):
output_pdf.add_page(pdf2.pages[page])
with open(output_file, 'wb') as combined_file:
output_pdf.write(combined_file)
# 将PDF文件转成文本
def pdf_to_text(pdf_path):
from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
import logging
logging.Logger.propagate = False
logging.getLogger().setLevel(logging.ERROR)
praser = PDFParser(open(pdf_path, 'rb'))
doc = PDFDocument()
praser.set_document(doc)
doc.set_parser(praser)
doc.initialize()
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
else:
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
content = ''
for page in doc.get_pages():
interpreter.process_page(page)
layout = device.get_result()
for x in layout:
if isinstance(x, LTTextBox):
content = content + x.get_text().strip()
return content
# 获取PDF文件页数
def get_pdf_page_number(pdf_path):
import PyPDF2
pdf_file = open(pdf_path, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)
num_pages = len(pdf_reader.pages)
return num_pages
# 获取PDF文件指定页面的内容
def pdf_to_txt_for_a_specific_page(pdf_path, page_num=1):
import PyPDF2
pdf_file = open(pdf_path, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)
num_pages = len(pdf_reader.pages)
for page_num0 in range(num_pages):
if page_num0 == page_num-1:
page = pdf_reader.pages[page_num0]
page_text = page.extract_text()
pdf_file.close()
return page_text
# 获取PDF文献中的链接。例如: link_starting_form='https://doi.org'
def get_links_from_pdf(pdf_path, link_starting_form=''):
import PyPDF2
import re
reader = PyPDF2.PdfReader(pdf_path)
pages = len(reader.pages)
i0 = 0
links = []
for page in range(pages):
pageSliced = reader.pages[page]
pageObject = pageSliced.get_object()
if '/Annots' in pageObject.keys():
ann = pageObject['/Annots']
old = ''
for a in ann:
u = a.get_object()
if '/A' in u.keys():
if '/URI' in u['/A']:
if re.search(re.compile('^'+link_starting_form), u['/A']['/URI']):
if u['/A']['/URI'] != old:
links.append(u['/A']['/URI'])
i0 += 1
old = u['/A']['/URI']
return links
# 使用MD5进行散列加密 # 使用MD5进行散列加密
def encryption_MD5(password, salt=''): def encryption_MD5(password, salt=''):
import hashlib import hashlib
@@ -713,130 +783,635 @@ def count_number_of_import_statements(filename, file_format='.py', num=1000):
import_statement_counter = Counter(import_array).most_common(num) import_statement_counter = Counter(import_array).most_common(num)
return import_statement_counter return import_statement_counter
# 查找文件名相同的文件 # 获取软件包的本机版本
def find_repeated_file_with_same_filename(directory='./', ignored_directory_with_words=[], ignored_file_with_words=[], num=1000): def get_current_version(package_name='guan'):
import os import importlib.metadata
from collections import Counter try:
file_list = [] current_version = importlib.metadata.version(package_name)
for root, dirs, files in os.walk(directory): return current_version
for i0 in range(len(files)): except:
file_list.append(files[i0]) return None
for word in ignored_directory_with_words:
if word in root:
file_list.remove(files[i0])
for word in ignored_file_with_words:
if word in files[i0]:
try:
file_list.remove(files[i0])
except:
pass
count_file = Counter(file_list).most_common(num)
repeated_file = []
for item in count_file:
if item[1]>1:
repeated_file.append(item)
return repeated_file
# 统计各个子文件夹中的文件数量 # 获取Python软件包的最新版本
def count_file_in_sub_directory(directory='./', sort=0, reverse=1, print_show=1, smaller_than_num=None): def get_latest_version(package_name='guan', timeout=5):
import requests
url = f"https://pypi.org/pypi/{package_name}/json"
try:
response = requests.get(url, timeout=timeout)
except:
return None
if response.status_code == 200:
data = response.json()
latest_version = data["info"]["version"]
return latest_version
else:
return None
# 获取包含某个字符的进程PID值
def get_PID_array(name):
import subprocess
command = "ps -ef | grep "+name
result = subprocess.run(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
if result.returncode == 0:
ps_ef = result.stdout
import re
ps_ef_1 = re.split(r'\n', ps_ef)
id_running_array = []
for ps_ef_item in ps_ef_1:
if ps_ef_item != '':
ps_ef_2 = re.split(r'\s+', ps_ef_item)
id_running_array.append(ps_ef_2[1])
return id_running_array
# 每日git commit次数的统计
def statistics_of_git_commits(print_show=0, str_or_datetime='str'):
import subprocess
import collections
since_date = '100 year ago'
result = subprocess.run(
['git', 'log', f'--since={since_date}', '--pretty=format:%ad', '--date=short'],
stdout=subprocess.PIPE,
text=True)
commits = result.stdout.strip().split('\n')
counter = collections.Counter(commits)
daily_commit_counts = dict(sorted(counter.items()))
date_array = []
commit_count_array = []
for date, count in daily_commit_counts.items():
if print_show == 1:
print(f"{date}: {count} commits")
if str_or_datetime=='datetime':
import datetime
date_array.append(datetime.datetime.strptime(date, "%Y-%m-%d"))
elif str_or_datetime=='str':
date_array.append(date)
commit_count_array.append(count)
return date_array, commit_count_array
# 将文件目录结构写入Markdown文件
def write_file_list_in_markdown(directory='./', filename='a', reverse_positive_or_negative=1, starting_from_h1=None, banned_file_format=[], hide_file_format=None, divided_line=None, show_second_number=None, show_third_number=None):
import os import os
import numpy as np f = open(filename+'.md', 'w', encoding="utf-8")
dirs_list = [] filenames1 = os.listdir(directory)
for root, dirs, files in os.walk(directory): u0 = 0
if dirs != []: for filename1 in filenames1[::reverse_positive_or_negative]:
for i0 in range(len(dirs)): filename1_with_path = os.path.join(directory,filename1)
dirs_list.append(root+'/'+dirs[i0]) if os.path.isfile(filename1_with_path):
count_file_array = [] if os.path.splitext(filename1)[1] not in banned_file_format:
for sub_dir in dirs_list: if hide_file_format == None:
file_list = [] f.write('+ '+str(filename1)+'\n\n')
for root, dirs, files in os.walk(sub_dir):
for i0 in range(len(files)):
file_list.append(files[i0])
count_file = len(file_list)
count_file_array.append(count_file)
if sort == 0:
if print_show == 1:
if smaller_than_num == None:
print(sub_dir)
print(count_file)
print()
else: else:
if count_file<smaller_than_num: f.write('+ '+str(os.path.splitext(filename1)[0])+'\n\n')
print(sub_dir)
print(count_file)
print()
if sort == 0:
sub_directory = dirs_list
num_in_sub_directory = count_file_array
if sort == 1:
sub_directory = []
num_in_sub_directory = []
if reverse == 1:
index_array = np.argsort(count_file_array)[::-1]
else: else:
index_array = np.argsort(count_file_array) u0 += 1
for i0 in index_array: if divided_line != None and u0 != 1:
sub_directory.append(dirs_list[i0]) f.write('--------\n\n')
num_in_sub_directory.append(count_file_array[i0]) if starting_from_h1 == None:
if print_show == 1: f.write('#')
if smaller_than_num == None: f.write('# '+str(filename1)+'\n\n')
print(dirs_list[i0])
print(count_file_array[i0]) filenames2 = os.listdir(filename1_with_path)
print() i0 = 0
for filename2 in filenames2[::reverse_positive_or_negative]:
filename2_with_path = os.path.join(directory, filename1, filename2)
if os.path.isfile(filename2_with_path):
if os.path.splitext(filename2)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename2)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename2)[0])+'\n\n')
else: else:
if count_file_array[i0]<smaller_than_num: i0 += 1
print(dirs_list[i0]) if starting_from_h1 == None:
print(count_file_array[i0]) f.write('#')
print() if show_second_number != None:
return sub_directory, num_in_sub_directory f.write('## '+str(i0)+'. '+str(filename2)+'\n\n')
else:
f.write('## '+str(filename2)+'\n\n')
# 在多个子文件夹中产生必要的文件，例如 readme.md j0 = 0
def creat_necessary_file(directory, filename='readme', file_format='.md', content='', overwrite=None, ignored_directory_with_words=[]): filenames3 = os.listdir(filename2_with_path)
import os for filename3 in filenames3[::reverse_positive_or_negative]:
directory_with_file = [] filename3_with_path = os.path.join(directory, filename1, filename2, filename3)
ignored_directory = [] if os.path.isfile(filename3_with_path):
for root, dirs, files in os.walk(directory): if os.path.splitext(filename3)[1] not in banned_file_format:
for i0 in range(len(files)): if hide_file_format == None:
if root not in directory_with_file: f.write('+ '+str(filename3)+'\n\n')
directory_with_file.append(root) else:
if files[i0] == filename+file_format: f.write('+ '+str(os.path.splitext(filename3)[0])+'\n\n')
if root not in ignored_directory: else:
ignored_directory.append(root) j0 += 1
if overwrite == None: if starting_from_h1 == None:
for root in ignored_directory: f.write('#')
directory_with_file.remove(root) if show_third_number != None:
ignored_directory_more =[] f.write('### ('+str(j0)+') '+str(filename3)+'\n\n')
for root in directory_with_file: else:
for word in ignored_directory_with_words: f.write('### '+str(filename3)+'\n\n')
if word in root:
if root not in ignored_directory_more:
ignored_directory_more.append(root)
for root in ignored_directory_more:
directory_with_file.remove(root)
for root in directory_with_file:
os.chdir(root)
f = open(filename+file_format, 'w', encoding="utf-8")
f.write(content)
f.close()
# 删除特定文件名的文件（谨慎使用） filenames4 = os.listdir(filename3_with_path)
def delete_file_with_specific_name(directory, filename='readme', file_format='.md'): for filename4 in filenames4[::reverse_positive_or_negative]:
import os filename4_with_path = os.path.join(directory, filename1, filename2, filename3, filename4)
for root, dirs, files in os.walk(directory): if os.path.isfile(filename4_with_path):
for i0 in range(len(files)): if os.path.splitext(filename4)[1] not in banned_file_format:
if files[i0] == filename+file_format: if hide_file_format == None:
os.remove(root+'/'+files[i0]) f.write('+ '+str(filename4)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename4)[0])+'\n\n')
else:
if starting_from_h1 == None:
f.write('#')
f.write('#### '+str(filename4)+'\n\n')
# 将所有文件移到根目录（谨慎使用） filenames5 = os.listdir(filename4_with_path)
def move_all_files_to_root_directory(directory): for filename5 in filenames5[::reverse_positive_or_negative]:
import os filename5_with_path = os.path.join(directory, filename1, filename2, filename3, filename4, filename5)
import shutil if os.path.isfile(filename5_with_path):
for root, dirs, files in os.walk(directory): if os.path.splitext(filename5)[1] not in banned_file_format:
for i0 in range(len(files)): if hide_file_format == None:
shutil.move(root+'/'+files[i0], directory+'/'+files[i0]) f.write('+ '+str(filename5)+'\n\n')
for i0 in range(100): else:
for root, dirs, files in os.walk(directory): f.write('+ '+str(os.path.splitext(filename5)[0])+'\n\n')
try: else:
os.rmdir(root) if starting_from_h1 == None:
except: f.write('#')
f.write('##### '+str(filename5)+'\n\n')
filenames6 = os.listdir(filename5_with_path)
for filename6 in filenames6[::reverse_positive_or_negative]:
filename6_with_path = os.path.join(directory, filename1, filename2, filename3, filename4, filename5, filename6)
if os.path.isfile(filename6_with_path):
if os.path.splitext(filename6)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename6)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename6)[0])+'\n\n')
else:
if starting_from_h1 == None:
f.write('#')
f.write('###### '+str(filename6)+'\n\n')
f.close()
# 从网页的标签中获取内容
def get_html_from_tags(link, tags=['title', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'li', 'a']):
from bs4 import BeautifulSoup
import urllib.request
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
html = urllib.request.urlopen(link).read().decode('utf-8')
soup = BeautifulSoup(html, features="lxml")
all_tags = soup.find_all(tags)
content = ''
for tag in all_tags:
text = tag.get_text().replace('\n', '')
if content == '':
content = text
else:
content = content + '\n\n' + text
return content
# 从HTML中获取所有的链接
def get_links_from_html(html_link, links_with_text=0):
from bs4 import BeautifulSoup
import urllib.request
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
html = urllib.request.urlopen(html_link).read().decode('utf-8')
soup = BeautifulSoup(html, features="lxml")
a_tags = soup.find_all('a')
if links_with_text == 0:
link_array = [tag.get('href') for tag in a_tags if tag.get('href')]
return link_array
else:
link_array_with_text = [(tag.get('href'), tag.text) for tag in a_tags if tag.get('href')]
return link_array_with_text
# 检查链接的有效性
def check_link(url, timeout=3, allow_redirects=True):
import requests
try:
response = requests.head(url, timeout=timeout, allow_redirects=allow_redirects)
if response.status_code == 200:
return True
else:
return False
except requests.exceptions.RequestException:
return False
# 检查链接数组中链接的有效性
def check_link_array(link_array, timeout=3, allow_redirects=True, try_again=0, print_show=1):
import guan
failed_link_array0 = []
for link in link_array:
if link=='#' or guan.check_link(link, timeout=timeout, allow_redirects=allow_redirects):
pass
else:
failed_link_array0.append(link)
if print_show:
print(link)
failed_link_array = []
if try_again:
if print_show:
print('\nTry again:\n')
for link in failed_link_array0:
if link=='#' or guan.check_link(link, timeout=timeout, allow_redirects=allow_redirects):
pass pass
else:
failed_link_array.append(link)
if print_show:
print(link)
else:
failed_link_array = failed_link_array0
return failed_link_array
# 生成二维码
def creat_qrcode(data="https://www.guanjihuan.com", filename='a', file_format='.png'):
import qrcode
img = qrcode.make(data)
img.save(filename+file_format)
# 通过Sci-Hub网站下载文献
def download_with_scihub(address=None, num=1):
from bs4 import BeautifulSoup
import re
import requests
import os
if num==1 and address!=None:
address_array = [address]
else:
address_array = []
for i in range(num):
address = input('\nInput：')
address_array.append(address)
for address in address_array:
r = requests.post('https://sci-hub.st/', data={'request': address})
print('\nResponse：', r)
print('Address：', r.url)
soup = BeautifulSoup(r.text, features='lxml')
pdf_URL = soup.embed['src']
# pdf_URL = soup.iframe['src'] # This is a code line of history version which fails to get pdf URL.
if re.search(re.compile('^https:'), pdf_URL):
pass
else:
pdf_URL = 'https:'+pdf_URL
print('PDF address：', pdf_URL)
name = re.search(re.compile('fdp.*?/'),pdf_URL[::-1]).group()[::-1][1::]
print('PDF name：', name)
print('Directory：', os.getcwd())
print('\nDownloading...')
r = requests.get(pdf_URL, stream=True)
with open(name, 'wb') as f:
for chunk in r.iter_content(chunk_size=32):
f.write(chunk)
print('Completed!\n')
if num != 1:
print('All completed!\n')
# 将字符串转成音频
def str_to_audio(str='hello world', filename='str', rate=125, voice=1, read=1, save=0, compress=0, bitrate='16k', print_text=0):
import pyttsx3
import guan
if print_text==1:
print(str)
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[voice].id)
engine.setProperty("rate", rate)
if save==1:
engine.save_to_file(str, filename+'.wav')
engine.runAndWait()
print('Wav file saved!')
if compress==1:
import os
os.rename(filename+'.wav', 'temp.wav')
guan.compress_wav_to_mp3('temp.wav', output_filename=filename+'.mp3', bitrate=bitrate)
os.remove('temp.wav')
if read==1:
engine.say(str)
engine.runAndWait()
# 将txt文件转成音频
def txt_to_audio(txt_path, rate=125, voice=1, read=1, save=0, compress=0, bitrate='16k', print_text=0):
import pyttsx3
import guan
f = open(txt_path, 'r', encoding ='utf-8')
text = f.read()
if print_text==1:
print(text)
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[voice].id)
engine.setProperty("rate", rate)
if save==1:
import re
filename = re.split('[/,\\\]', txt_path)[-1][:-4]
engine.save_to_file(text, filename+'.wav')
engine.runAndWait()
print('Wav file saved!')
if compress==1:
import os
os.rename(filename+'.wav', 'temp.wav')
guan.compress_wav_to_mp3('temp.wav', output_filename=filename+'.mp3', bitrate=bitrate)
os.remove('temp.wav')
if read==1:
engine.say(text)
engine.runAndWait()
# 将PDF文件转成音频
def pdf_to_audio(pdf_path, rate=125, voice=1, read=1, save=0, compress=0, bitrate='16k', print_text=0):
import pyttsx3
import guan
text = guan.pdf_to_text(pdf_path)
text = text.replace('\n', ' ')
if print_text==1:
print(text)
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[voice].id)
engine.setProperty("rate", rate)
if save==1:
import re
filename = re.split('[/,\\\]', pdf_path)[-1][:-4]
engine.save_to_file(text, filename+'.wav')
engine.runAndWait()
print('Wav file saved!')
if compress==1:
import os
os.rename(filename+'.wav', 'temp.wav')
guan.compress_wav_to_mp3('temp.wav', output_filename=filename+'.mp3', bitrate=bitrate)
os.remove('temp.wav')
if read==1:
engine.say(text)
engine.runAndWait()
# 将wav音频文件压缩成MP3音频文件
def compress_wav_to_mp3(wav_path, output_filename='a.mp3', bitrate='16k'):
# Note: Beside the installation of pydub, you may also need download FFmpeg on http://www.ffmpeg.org/download.html and add the bin path to the environment variable.
from pydub import AudioSegment
sound = AudioSegment.from_mp3(wav_path)
sound.export(output_filename,format="mp3",bitrate=bitrate)
# 将WordPress导出的XML格式文件转换成多个MarkDown格式的文件
def convert_wordpress_xml_to_markdown(xml_file='./a.xml', convert_content=1, replace_more=[]):
import xml.etree.ElementTree as ET
import re
tree = ET.parse(xml_file)
root = tree.getroot()
for item in root.findall('.//item'):
title = item.find('title').text
content = item.find('.//content:encoded', namespaces={'content': 'http://purl.org/rss/1.0/modules/content/'}).text
if convert_content == 1:
content = re.sub(r'<!--.*?-->', '', content)
content = content.replace('<p>', '')
content = content.replace('</p>', '')
content = content.replace('<ol>', '')
content = content.replace('</ol>', '')
content = content.replace('<ul>', '')
content = content.replace('</ul>', '')
content = content.replace('<strong>', '')
content = content.replace('</strong>', '')
content = content.replace('</li>', '')
content = content.replace('<li>', '+ ')
content = content.replace('</h3>', '')
content = re.sub(r'<h2.*?>', '## ', content)
content = re.sub(r'<h3.*?>', '### ', content)
content = re.sub(r'<h4.*?>', '#### ', content)
for replace_item in replace_more:
content = content.replace(replace_item, '')
for _ in range(100):
content = content.replace('\n\n\n', '\n\n')
else:
pass
markdown_content = f"# {title}\n{content}"
markdown_file_path = f"{title}.md"
cleaned_filename = re.sub(r'[/:*?"<>|\'\\]', ' ', markdown_file_path)
with open(cleaned_filename, 'w', encoding='utf-8') as md_file:
md_file.write(markdown_content)
# 凯利公式
def kelly_formula(p, b, a=1):
f=(p/a)-((1-p)/b)
return f
# 获取所有股票
def all_stocks():
import numpy as np
import akshare as ak
stocks = ak.stock_zh_a_spot_em()
title = np.array(stocks.columns)
stock_data = stocks.values
return title, stock_data
# 获取所有股票的代码
def all_stock_symbols():
import guan
title, stock_data = guan.all_stocks()
stock_symbols = stock_data[:, 1]
return stock_symbols
# 股票代码的分类
def stock_symbols_classification():
import guan
import re
stock_symbols = guan.all_stock_symbols()
# 上交所主板
stock_symbols_60 = []
for stock_symbol in stock_symbols:
find_600 = re.findall(r'^600', stock_symbol)
find_601 = re.findall(r'^601', stock_symbol)
find_603 = re.findall(r'^603', stock_symbol)
find_605 = re.findall(r'^605', stock_symbol)
if find_600 != [] or find_601 != [] or find_603 != [] or find_605 != []:
stock_symbols_60.append(stock_symbol)
# 深交所主板
stock_symbols_00 = []
for stock_symbol in stock_symbols:
find_000 = re.findall(r'^000', stock_symbol)
find_001 = re.findall(r'^001', stock_symbol)
find_002 = re.findall(r'^002', stock_symbol)
find_003 = re.findall(r'^003', stock_symbol)
if find_000 != [] or find_001 != [] or find_002 != [] or find_003 != []:
stock_symbols_00.append(stock_symbol)
# 创业板
stock_symbols_30 = []
for stock_symbol in stock_symbols:
find_300 = re.findall(r'^300', stock_symbol)
find_301 = re.findall(r'^301', stock_symbol)
if find_300 != [] or find_301 != []:
stock_symbols_30.append(stock_symbol)
# 科创板
stock_symbols_68 = []
for stock_symbol in stock_symbols:
find_688 = re.findall(r'^688', stock_symbol)
find_689 = re.findall(r'^689', stock_symbol)
if find_688 != [] or find_689 != []:
stock_symbols_68.append(stock_symbol)
# 新三板
stock_symbols_8_4 = []
for stock_symbol in stock_symbols:
find_82 = re.findall(r'^82', stock_symbol)
find_83 = re.findall(r'^83', stock_symbol)
find_87 = re.findall(r'^87', stock_symbol)
find_88 = re.findall(r'^88', stock_symbol)
find_430 = re.findall(r'^430', stock_symbol)
find_420 = re.findall(r'^420', stock_symbol)
find_400 = re.findall(r'^400', stock_symbol)
if find_82 != [] or find_83 != [] or find_87 != [] or find_88 != [] or find_430 != [] or find_420 != [] or find_400 != []:
stock_symbols_8_4.append(stock_symbol)
# 检查遗漏的股票代码
stock_symbols_others = []
for stock_symbol in stock_symbols:
if stock_symbol not in stock_symbols_60 and stock_symbol not in stock_symbols_00 and stock_symbol not in stock_symbols_30 and stock_symbol not in stock_symbols_68 and stock_symbol not in stock_symbols_8_4:
stock_symbols_others.others.append(stock_symbol)
return stock_symbols_60, stock_symbols_00, stock_symbols_30, stock_symbols_68, stock_symbols_8_4, stock_symbols_others
# 股票代码各个分类的数量
def statistics_of_stock_symbols_classification():
import guan
stock_symbols_60, stock_symbols_00, stock_symbols_30, stock_symbols_68, stock_symbols_8_4, stock_symbols_others = guan.stock_symbols_classification()
num_stocks_60 = len(stock_symbols_60)
num_stocks_00 = len(stock_symbols_00)
num_stocks_30 = len(stock_symbols_30)
num_stocks_68 = len(stock_symbols_68)
num_stocks_8_4 = len(stock_symbols_8_4)
num_stocks_others= len(stock_symbols_others)
return num_stocks_60, num_stocks_00, num_stocks_30, num_stocks_68, num_stocks_8_4, num_stocks_others
# 从股票代码获取股票名称
def find_stock_name_from_symbol(symbol='000002'):
import guan
title, stock_data = guan.all_stocks()
for stock in stock_data:
if symbol in stock:
stock_name = stock[2]
return stock_name
# 市值排序
def sorted_market_capitalization(num=10):
import numpy as np
import guan
title, stock_data = guan.all_stocks()
new_stock_data = []
for stock in stock_data:
if np.isnan(float(stock[9])):
continue
else:
new_stock_data.append(stock)
new_stock_data = np.array(new_stock_data)
list_index = np.argsort(new_stock_data[:, 17])
list_index = list_index[::-1]
if num == None:
num = len(list_index)
sorted_array = []
for i0 in range(num):
stock_symbol = new_stock_data[list_index[i0], 1]
stock_name = new_stock_data[list_index[i0], 2]
market_capitalization = new_stock_data[list_index[i0], 17]/1e8
sorted_array.append([i0+1, stock_symbol, stock_name, market_capitalization])
return sorted_array
# 美股市值排序
def sorted_market_capitalization_us(num=10):
import akshare as ak
import numpy as np
stocks = ak.stock_us_spot_em()
stock_data = stocks.values
new_stock_data = []
for stock in stock_data:
if np.isnan(float(stock[9])):
continue
else:
new_stock_data.append(stock)
new_stock_data = np.array(new_stock_data)
list_index = np.argsort(new_stock_data[:, 9])
list_index = list_index[::-1]
if num == None:
num = len(list_index)
sorted_array = []
for i0 in range(num):
stock_symbol = new_stock_data[list_index[i0], 15]
stock_name = new_stock_data[list_index[i0], 1]
market_capitalization = new_stock_data[list_index[i0], 9]/1e8
sorted_array.append([i0+1, stock_symbol, stock_name, market_capitalization])
return sorted_array
# 获取单个股票的历史数据
def history_data_of_one_stock(symbol='000002', period='daily', start_date="19000101", end_date='21000101'):
# period = 'daily'
# period = 'weekly'
# period = 'monthly'
import numpy as np
import akshare as ak
stock = ak.stock_zh_a_hist(symbol=symbol, period=period, start_date=start_date, end_date=end_date)
title = np.array(stock.columns)
stock_data = stock.values[::-1]
return title, stock_data
# 绘制股票图
def plot_stock_line(date_array, opening_array, closing_array, high_array, low_array, lw_open_close=6, lw_high_low=2, xlabel='date', ylabel='price', title='', fontsize=20, labelsize=20, adjust_bottom=0.2, adjust_left=0.2, fontfamily='Times New Roman'):
import guan
plt, fig, ax = guan.import_plt_and_start_fig_ax(adjust_bottom=adjust_bottom, adjust_left=adjust_left, labelsize=labelsize, fontfamily=fontfamily)
if fontfamily=='Times New Roman':
ax.set_title(title, fontsize=fontsize, fontfamily='Times New Roman')
ax.set_xlabel(xlabel, fontsize=fontsize, fontfamily='Times New Roman')
ax.set_ylabel(ylabel, fontsize=fontsize, fontfamily='Times New Roman')
else:
ax.set_title(title, fontsize=fontsize)
ax.set_xlabel(xlabel, fontsize=fontsize)
ax.set_ylabel(ylabel, fontsize=fontsize)
for i0 in range(len(date_array)):
if opening_array[i0] <= closing_array[i0]:
ax.vlines(date_array[i0], opening_array[i0], closing_array[i0], linestyle='-', color='red', lw=lw_open_close)
ax.vlines(date_array[i0], low_array[i0], high_array[i0], color='red', linestyle='-', lw=lw_high_low)
else:
ax.vlines(date_array[i0], opening_array[i0], closing_array[i0], linestyle='-', color='green', lw=lw_open_close)
ax.vlines(date_array[i0], low_array[i0], high_array[i0], color='green', linestyle='-', lw=lw_high_low)
plt.show()
plt.close('all')
# Guan软件包的使用统计（仅仅统计装机数和import次数）
def statistics_of_guan_package(function_name=None):
import guan
try:
import socket
datetime_date = guan.get_date()
datetime_time = guan.get_time()
current_version = guan.get_current_version('guan')
client_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
client_socket.settimeout(0.5)
client_socket.connect(('socket.guanjihuan.com', 12345))
mac_address = guan.get_mac_address()
if function_name == None:
message = {
'server': 'py.guanjihuan.com',
'date': datetime_date,
'time': datetime_time,
'version': current_version,
'MAC_address': mac_address,
}
else:
message = {
'server': 'py.guanjihuan.com',
'date': datetime_date,
'time': datetime_time,
'version': current_version,
'MAC_address': mac_address,
'function_name': function_name
}
import json
send_message = json.dumps(message)
client_socket.send(send_message.encode())
client_socket.close()
except:
pass
# Guan软件包升级检查和提示（如果无法连接或者版本为最新，那么均没有提示）
def notification_of_upgrade(timeout=5):
try:
import guan
latest_version = guan.get_latest_version(package_name='guan', timeout=timeout)
current_version = guan.get_current_version('guan')
if latest_version != None and current_version != None:
if latest_version != current_version:
print('升级提示：您当前使用的版本是 guan-'+current_version+'，目前已经有最新版本 guan-'+latest_version+'。您可以通过以下命令对软件包进行升级：pip install --upgrade guan -i https://pypi.python.org/simple 或 pip install --upgrade guan')
except:
pass

378
PyPI/src/guan/file_reading_and_writing.py
View File

@@ -35,138 +35,6 @@ def load_txt_data(filename):
data = np.loadtxt(filename+'.txt') data = np.loadtxt(filename+'.txt')
return data return data
# 如果不存在文件夹，则新建文件夹
def make_directory(directory='./test'):
import os
if not os.path.exists(directory):
os.makedirs(directory)
# 如果不存在文件，则新建空文件
def make_file(file_path='./a.txt'):
import os
if not os.path.exists(file_path):
with open(file_path, 'w') as f:
pass
# 打开文件用于写入，默认为新增内容
def open_file(filename='a', file_format='.txt', mode='add'):
if mode == 'add':
f = open(filename+file_format, 'a', encoding='UTF-8')
elif mode == 'overwrite':
f = open(filename+file_format, 'w', encoding='UTF-8')
return f
def print_to_file(*args, filename='print_result', file_format='.txt', print_on=True):
if print_on==True:
for arg in args:
print(arg, end=' ')
print()
f = open(filename+file_format, 'a', encoding='UTF-8')
for arg in args:
f.write(str(arg)+' ')
f.write('\n')
f.close()
# 读取文本文件内容。如果文件不存在，返回空字符串
def read_text_file(file_path='./a.txt', make_file=None):
import os
if not os.path.exists(file_path):
if make_file != None:
with open(file_path, 'w') as f:
pass
return ''
else:
with open(file_path, 'r') as f:
content = f.read()
return content
# 获取目录中的所有文件名
def get_all_filenames_in_directory(directory='./', file_format=None, show_root_path=0, sort=1, include_subdirectory=1):
import os
file_list = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
if file_format == None:
if show_root_path == 0:
file_list.append(files[i0])
else:
file_list.append(root+'/'+files[i0])
else:
if file_format in files[i0]:
if show_root_path == 0:
file_list.append(files[i0])
else:
file_list.append(root+'/'+files[i0])
if include_subdirectory != 1:
break
if sort == 1:
file_list = sorted(file_list)
return file_list
# 获取文件夹中某种文本类型的文件以及读取所有内容
def read_text_files_in_directory(directory='./', file_format='.md'):
import os
file_list = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
if file_format in files[i0]:
file_list.append(root+'/'+files[i0])
content_array = []
for file in file_list:
with open(file, 'r', encoding='UTF-8') as f:
content_array.append(f.read())
return file_list, content_array
# 在多个文本文件中查找关键词
def find_words_in_multiple_files(words, directory='./', file_format='.md'):
import guan
file_list, content_array = guan.read_text_files_in_directory(directory=directory, file_format=file_format)
num_files = len(file_list)
file_list_with_words = []
for i0 in range(num_files):
if words in content_array[i0]:
file_list_with_words.append(file_list[i0])
return file_list_with_words
# 复制一份文件
def copy_file(old_file='./a.txt', new_file='./b.txt'):
import shutil
shutil.copy(old_file, new_file)
# 打开文件，替代某字符串
def open_file_and_replace_str(file_path='./a.txt', old_str='', new_str=''):
import guan
content = guan.read_text_file(file_path=file_path)
content = content.replace(old_str, new_str)
f = guan.open_file(filename=file_path, file_format='', mode='overwrite')
f.write(content)
f.close()
# 复制一份文件，然后再替代某字符串
def copy_file_and_replace_str(old_file='./a.txt', new_file='./b.txt', old_str='', new_str=''):
import guan
guan.copy_file(old_file=old_file, new_file=new_file)
content = guan.read_text_file(file_path=new_file)
content = content.replace(old_str, new_str)
f = guan.open_file(filename=new_file, file_format='', mode='overwrite')
f.write(content)
f.close()
# 拼接两个PDF文件
def combine_two_pdf_files(input_file_1='a.pdf', input_file_2='b.pdf', output_file='combined_file.pdf'):
import PyPDF2
output_pdf = PyPDF2.PdfWriter()
with open(input_file_1, 'rb') as file1:
pdf1 = PyPDF2.PdfReader(file1)
for page in range(len(pdf1.pages)):
output_pdf.add_page(pdf1.pages[page])
with open(input_file_2, 'rb') as file2:
pdf2 = PyPDF2.PdfReader(file2)
for page in range(len(pdf2.pages)):
output_pdf.add_page(pdf2.pages[page])
with open(output_file, 'wb') as combined_file:
output_pdf.write(combined_file)
# 读取文件中的一维数据（一行一组x和y） # 读取文件中的一维数据（一行一组x和y）
def read_one_dimensional_data(filename='a', file_format='.txt'): def read_one_dimensional_data(filename='a', file_format='.txt'):
import numpy as np import numpy as np
@@ -375,6 +243,124 @@ def write_two_dimensional_data_without_xy_array_and_without_opening_file(matrix,
f.write(str(element)+' ') f.write(str(element)+' ')
f.write('\n') f.write('\n')
# 如果不存在文件夹，则新建文件夹
def make_directory(directory='./test'):
import os
if not os.path.exists(directory):
os.makedirs(directory)
# 如果不存在文件，则新建空文件
def make_file(file_path='./a.txt'):
import os
if not os.path.exists(file_path):
with open(file_path, 'w') as f:
pass
# 打开文件用于写入，默认为新增内容
def open_file(filename='a', file_format='.txt', mode='add'):
if mode == 'add':
f = open(filename+file_format, 'a', encoding='UTF-8')
elif mode == 'overwrite':
f = open(filename+file_format, 'w', encoding='UTF-8')
return f
# 打印到TXT文件
def print_to_file(*args, filename='print_result', file_format='.txt', print_on=True):
if print_on==True:
for arg in args:
print(arg, end=' ')
print()
f = open(filename+file_format, 'a', encoding='UTF-8')
for arg in args:
f.write(str(arg)+' ')
f.write('\n')
f.close()
# 读取文本文件内容。如果文件不存在，返回空字符串
def read_text_file(file_path='./a.txt', make_file=None):
import os
if not os.path.exists(file_path):
if make_file != None:
with open(file_path, 'w') as f:
pass
return ''
else:
with open(file_path, 'r') as f:
content = f.read()
return content
# 获取目录中的所有文件名
def get_all_filenames_in_directory(directory='./', file_format=None, show_root_path=0, sort=1, include_subdirectory=1):
import os
file_list = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
if file_format == None:
if show_root_path == 0:
file_list.append(files[i0])
else:
file_list.append(root+'/'+files[i0])
else:
if file_format in files[i0]:
if show_root_path == 0:
file_list.append(files[i0])
else:
file_list.append(root+'/'+files[i0])
if include_subdirectory != 1:
break
if sort == 1:
file_list = sorted(file_list)
return file_list
# 获取文件夹中某种文本类型的文件以及读取所有内容
def read_text_files_in_directory(directory='./', file_format='.md'):
import os
file_list = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
if file_format in files[i0]:
file_list.append(root+'/'+files[i0])
content_array = []
for file in file_list:
with open(file, 'r', encoding='UTF-8') as f:
content_array.append(f.read())
return file_list, content_array
# 在多个文本文件中查找关键词
def find_words_in_multiple_files(words, directory='./', file_format='.md'):
import guan
file_list, content_array = guan.read_text_files_in_directory(directory=directory, file_format=file_format)
num_files = len(file_list)
file_list_with_words = []
for i0 in range(num_files):
if words in content_array[i0]:
file_list_with_words.append(file_list[i0])
return file_list_with_words
# 复制一份文件
def copy_file(old_file='./a.txt', new_file='./b.txt'):
import shutil
shutil.copy(old_file, new_file)
# 打开文件，替代某字符串
def open_file_and_replace_str(file_path='./a.txt', old_str='', new_str=''):
import guan
content = guan.read_text_file(file_path=file_path)
content = content.replace(old_str, new_str)
f = guan.open_file(filename=file_path, file_format='', mode='overwrite')
f.write(content)
f.close()
# 复制一份文件，然后再替代某字符串
def copy_file_and_replace_str(old_file='./a.txt', new_file='./b.txt', old_str='', new_str=''):
import guan
guan.copy_file(old_file=old_file, new_file=new_file)
content = guan.read_text_file(file_path=new_file)
content = content.replace(old_str, new_str)
f = guan.open_file(filename=new_file, file_format='', mode='overwrite')
f.write(content)
f.close()
# 改变当前的目录位置 # 改变当前的目录位置
def change_directory_by_replacement(current_key_word='code', new_key_word='data'): def change_directory_by_replacement(current_key_word='code', new_key_word='data'):
import os import os
@@ -384,3 +370,131 @@ def change_directory_by_replacement(current_key_word='code', new_key_word='data'
if os.path.exists(data_path) == False: if os.path.exists(data_path) == False:
os.makedirs(data_path) os.makedirs(data_path)
os.chdir(data_path) os.chdir(data_path)
# 查找文件名相同的文件
def find_repeated_file_with_same_filename(directory='./', ignored_directory_with_words=[], ignored_file_with_words=[], num=1000):
import os
from collections import Counter
file_list = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
file_list.append(files[i0])
for word in ignored_directory_with_words:
if word in root:
file_list.remove(files[i0])
for word in ignored_file_with_words:
if word in files[i0]:
try:
file_list.remove(files[i0])
except:
pass
count_file = Counter(file_list).most_common(num)
repeated_file = []
for item in count_file:
if item[1]>1:
repeated_file.append(item)
return repeated_file
# 统计各个子文件夹中的文件数量
def count_file_in_sub_directory(directory='./', sort=0, reverse=1, print_show=1, smaller_than_num=None):
import os
import numpy as np
dirs_list = []
for root, dirs, files in os.walk(directory):
if dirs != []:
for i0 in range(len(dirs)):
dirs_list.append(root+'/'+dirs[i0])
count_file_array = []
for sub_dir in dirs_list:
file_list = []
for root, dirs, files in os.walk(sub_dir):
for i0 in range(len(files)):
file_list.append(files[i0])
count_file = len(file_list)
count_file_array.append(count_file)
if sort == 0:
if print_show == 1:
if smaller_than_num == None:
print(sub_dir)
print(count_file)
print()
else:
if count_file<smaller_than_num:
print(sub_dir)
print(count_file)
print()
if sort == 0:
sub_directory = dirs_list
num_in_sub_directory = count_file_array
if sort == 1:
sub_directory = []
num_in_sub_directory = []
if reverse == 1:
index_array = np.argsort(count_file_array)[::-1]
else:
index_array = np.argsort(count_file_array)
for i0 in index_array:
sub_directory.append(dirs_list[i0])
num_in_sub_directory.append(count_file_array[i0])
if print_show == 1:
if smaller_than_num == None:
print(dirs_list[i0])
print(count_file_array[i0])
print()
else:
if count_file_array[i0]<smaller_than_num:
print(dirs_list[i0])
print(count_file_array[i0])
print()
return sub_directory, num_in_sub_directory
# 在多个子文件夹中产生必要的文件，例如 readme.md
def creat_necessary_file(directory, filename='readme', file_format='.md', content='', overwrite=None, ignored_directory_with_words=[]):
import os
directory_with_file = []
ignored_directory = []
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
if root not in directory_with_file:
directory_with_file.append(root)
if files[i0] == filename+file_format:
if root not in ignored_directory:
ignored_directory.append(root)
if overwrite == None:
for root in ignored_directory:
directory_with_file.remove(root)
ignored_directory_more =[]
for root in directory_with_file:
for word in ignored_directory_with_words:
if word in root:
if root not in ignored_directory_more:
ignored_directory_more.append(root)
for root in ignored_directory_more:
directory_with_file.remove(root)
for root in directory_with_file:
os.chdir(root)
f = open(filename+file_format, 'w', encoding="utf-8")
f.write(content)
f.close()
# 删除特定文件名的文件（谨慎使用）
def delete_file_with_specific_name(directory, filename='readme', file_format='.md'):
import os
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
if files[i0] == filename+file_format:
os.remove(root+'/'+files[i0])
# 将所有文件移到根目录（谨慎使用）
def move_all_files_to_root_directory(directory):
import os
import shutil
for root, dirs, files in os.walk(directory):
for i0 in range(len(files)):
shutil.move(root+'/'+files[i0], directory+'/'+files[i0])
for i0 in range(100):
for root, dirs, files in os.walk(directory):
try:
os.rmdir(root)
except:
pass

22
PyPI/src/guan/machine_learning.py
View File

@@ -382,3 +382,25 @@ def pca_of_data(data, n_components=None, standard=1):
data_transformed = pca.fit_transform(data_scaled) data_transformed = pca.fit_transform(data_scaled)
explained_variance_ratio = pca.explained_variance_ratio_ explained_variance_ratio = pca.explained_variance_ratio_
return data_transformed, explained_variance_ratio return data_transformed, explained_variance_ratio
# 通过定义计算R^2（基于实际值和预测值，数值有可能小于0）
def calculate_R2_with_definition(y_true_array, y_pred_array):
import numpy as np
y_mean = np.mean(y_true_array)
SS_tot = np.sum((y_true_array - y_mean) ** 2)
SS_res = np.sum((y_true_array - y_pred_array) ** 2)
R2 = 1 - (SS_res / SS_tot)
return R2
# 通过sklearn计算R^2，和上面定义的计算结果一致
def calculate_R2_with_sklearn(y_true_array, y_pred_array):
from sklearn.metrics import r2_score
R2 = r2_score(y_true_array, y_pred_array)
return R2
# 通过scipy计算线性回归后的R^2（基于线性回归模型，范围在0和1之间）
def calculate_R2_after_linear_regression_with_scipy(y_true_array, y_pred_array):
from scipy import stats
slope, intercept, r_value, p_value, std_err = stats.linregress(y_true_array, y_pred_array)
R2 = r_value**2
return R2

711
PyPI/src/guan/others.py
View File

@@ -1,711 +0,0 @@
# Module: others
# 获取软件包的本机版本
def get_current_version(package_name='guan'):
import importlib.metadata
try:
current_version = importlib.metadata.version(package_name)
return current_version
except:
return None
# 获取Python软件包的最新版本
def get_latest_version(package_name='guan', timeout=5):
import requests
url = f"https://pypi.org/pypi/{package_name}/json"
try:
response = requests.get(url, timeout=timeout)
except:
return None
if response.status_code == 200:
data = response.json()
latest_version = data["info"]["version"]
return latest_version
else:
return None
# 获取包含某个字符的进程PID值
def get_PID_array(name):
import subprocess
command = "ps -ef | grep "+name
result = subprocess.run(command, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
if result.returncode == 0:
ps_ef = result.stdout
import re
ps_ef_1 = re.split(r'\n', ps_ef)
id_running_array = []
for ps_ef_item in ps_ef_1:
if ps_ef_item != '':
ps_ef_2 = re.split(r'\s+', ps_ef_item)
id_running_array.append(ps_ef_2[1])
return id_running_array
# 每日git commit次数的统计
def statistics_of_git_commits(print_show=0, str_or_datetime='str'):
import subprocess
import collections
since_date = '100 year ago'
result = subprocess.run(
['git', 'log', f'--since={since_date}', '--pretty=format:%ad', '--date=short'],
stdout=subprocess.PIPE,
text=True)
commits = result.stdout.strip().split('\n')
counter = collections.Counter(commits)
daily_commit_counts = dict(sorted(counter.items()))
date_array = []
commit_count_array = []
for date, count in daily_commit_counts.items():
if print_show == 1:
print(f"{date}: {count} commits")
if str_or_datetime=='datetime':
import datetime
date_array.append(datetime.datetime.strptime(date, "%Y-%m-%d"))
elif str_or_datetime=='str':
date_array.append(date)
commit_count_array.append(count)
return date_array, commit_count_array
# 将文件目录结构写入Markdown文件
def write_file_list_in_markdown(directory='./', filename='a', reverse_positive_or_negative=1, starting_from_h1=None, banned_file_format=[], hide_file_format=None, divided_line=None, show_second_number=None, show_third_number=None):
import os
f = open(filename+'.md', 'w', encoding="utf-8")
filenames1 = os.listdir(directory)
u0 = 0
for filename1 in filenames1[::reverse_positive_or_negative]:
filename1_with_path = os.path.join(directory,filename1)
if os.path.isfile(filename1_with_path):
if os.path.splitext(filename1)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename1)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename1)[0])+'\n\n')
else:
u0 += 1
if divided_line != None and u0 != 1:
f.write('--------\n\n')
if starting_from_h1 == None:
f.write('#')
f.write('# '+str(filename1)+'\n\n')
filenames2 = os.listdir(filename1_with_path)
i0 = 0
for filename2 in filenames2[::reverse_positive_or_negative]:
filename2_with_path = os.path.join(directory, filename1, filename2)
if os.path.isfile(filename2_with_path):
if os.path.splitext(filename2)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename2)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename2)[0])+'\n\n')
else:
i0 += 1
if starting_from_h1 == None:
f.write('#')
if show_second_number != None:
f.write('## '+str(i0)+'. '+str(filename2)+'\n\n')
else:
f.write('## '+str(filename2)+'\n\n')
j0 = 0
filenames3 = os.listdir(filename2_with_path)
for filename3 in filenames3[::reverse_positive_or_negative]:
filename3_with_path = os.path.join(directory, filename1, filename2, filename3)
if os.path.isfile(filename3_with_path):
if os.path.splitext(filename3)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename3)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename3)[0])+'\n\n')
else:
j0 += 1
if starting_from_h1 == None:
f.write('#')
if show_third_number != None:
f.write('### ('+str(j0)+') '+str(filename3)+'\n\n')
else:
f.write('### '+str(filename3)+'\n\n')
filenames4 = os.listdir(filename3_with_path)
for filename4 in filenames4[::reverse_positive_or_negative]:
filename4_with_path = os.path.join(directory, filename1, filename2, filename3, filename4)
if os.path.isfile(filename4_with_path):
if os.path.splitext(filename4)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename4)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename4)[0])+'\n\n')
else:
if starting_from_h1 == None:
f.write('#')
f.write('#### '+str(filename4)+'\n\n')
filenames5 = os.listdir(filename4_with_path)
for filename5 in filenames5[::reverse_positive_or_negative]:
filename5_with_path = os.path.join(directory, filename1, filename2, filename3, filename4, filename5)
if os.path.isfile(filename5_with_path):
if os.path.splitext(filename5)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename5)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename5)[0])+'\n\n')
else:
if starting_from_h1 == None:
f.write('#')
f.write('##### '+str(filename5)+'\n\n')
filenames6 = os.listdir(filename5_with_path)
for filename6 in filenames6[::reverse_positive_or_negative]:
filename6_with_path = os.path.join(directory, filename1, filename2, filename3, filename4, filename5, filename6)
if os.path.isfile(filename6_with_path):
if os.path.splitext(filename6)[1] not in banned_file_format:
if hide_file_format == None:
f.write('+ '+str(filename6)+'\n\n')
else:
f.write('+ '+str(os.path.splitext(filename6)[0])+'\n\n')
else:
if starting_from_h1 == None:
f.write('#')
f.write('###### '+str(filename6)+'\n\n')
f.close()
# 从网页的标签中获取内容
def get_html_from_tags(link, tags=['title', 'h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'li', 'a']):
from bs4 import BeautifulSoup
import urllib.request
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
html = urllib.request.urlopen(link).read().decode('utf-8')
soup = BeautifulSoup(html, features="lxml")
all_tags = soup.find_all(tags)
content = ''
for tag in all_tags:
text = tag.get_text().replace('\n', '')
if content == '':
content = text
else:
content = content + '\n\n' + text
return content
# 从HTML中获取所有的链接
def get_links_from_html(html_link, links_with_text=0):
from bs4 import BeautifulSoup
import urllib.request
import ssl
ssl._create_default_https_context = ssl._create_unverified_context
html = urllib.request.urlopen(html_link).read().decode('utf-8')
soup = BeautifulSoup(html, features="lxml")
a_tags = soup.find_all('a')
if links_with_text == 0:
link_array = [tag.get('href') for tag in a_tags if tag.get('href')]
return link_array
else:
link_array_with_text = [(tag.get('href'), tag.text) for tag in a_tags if tag.get('href')]
return link_array_with_text
# 检查链接的有效性
def check_link(url, timeout=3, allow_redirects=True):
import requests
try:
response = requests.head(url, timeout=timeout, allow_redirects=allow_redirects)
if response.status_code == 200:
return True
else:
return False
except requests.exceptions.RequestException:
return False
# 检查链接数组中链接的有效性
def check_link_array(link_array, timeout=3, allow_redirects=True, try_again=0, print_show=1):
import guan
failed_link_array0 = []
for link in link_array:
if link=='#' or guan.check_link(link, timeout=timeout, allow_redirects=allow_redirects):
pass
else:
failed_link_array0.append(link)
if print_show:
print(link)
failed_link_array = []
if try_again:
if print_show:
print('\nTry again:\n')
for link in failed_link_array0:
if link=='#' or guan.check_link(link, timeout=timeout, allow_redirects=allow_redirects):
pass
else:
failed_link_array.append(link)
if print_show:
print(link)
else:
failed_link_array = failed_link_array0
return failed_link_array
# 生成二维码
def creat_qrcode(data="https://www.guanjihuan.com", filename='a', file_format='.png'):
import qrcode
img = qrcode.make(data)
img.save(filename+file_format)
# 将PDF文件转成文本
def pdf_to_text(pdf_path):
from pdfminer.pdfparser import PDFParser, PDFDocument
from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
from pdfminer.converter import PDFPageAggregator
from pdfminer.layout import LAParams, LTTextBox
from pdfminer.pdfinterp import PDFTextExtractionNotAllowed
import logging
logging.Logger.propagate = False
logging.getLogger().setLevel(logging.ERROR)
praser = PDFParser(open(pdf_path, 'rb'))
doc = PDFDocument()
praser.set_document(doc)
doc.set_parser(praser)
doc.initialize()
if not doc.is_extractable:
raise PDFTextExtractionNotAllowed
else:
rsrcmgr = PDFResourceManager()
laparams = LAParams()
device = PDFPageAggregator(rsrcmgr, laparams=laparams)
interpreter = PDFPageInterpreter(rsrcmgr, device)
content = ''
for page in doc.get_pages():
interpreter.process_page(page)
layout = device.get_result()
for x in layout:
if isinstance(x, LTTextBox):
content = content + x.get_text().strip()
return content
# 获取PDF文件页数
def get_pdf_page_number(pdf_path):
import PyPDF2
pdf_file = open(pdf_path, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)
num_pages = len(pdf_reader.pages)
return num_pages
# 获取PDF文件指定页面的内容
def pdf_to_txt_for_a_specific_page(pdf_path, page_num=1):
import PyPDF2
pdf_file = open(pdf_path, 'rb')
pdf_reader = PyPDF2.PdfReader(pdf_file)
num_pages = len(pdf_reader.pages)
for page_num0 in range(num_pages):
if page_num0 == page_num-1:
page = pdf_reader.pages[page_num0]
page_text = page.extract_text()
pdf_file.close()
return page_text
# 获取PDF文献中的链接。例如: link_starting_form='https://doi.org'
def get_links_from_pdf(pdf_path, link_starting_form=''):
import PyPDF2
import re
reader = PyPDF2.PdfReader(pdf_path)
pages = len(reader.pages)
i0 = 0
links = []
for page in range(pages):
pageSliced = reader.pages[page]
pageObject = pageSliced.get_object()
if '/Annots' in pageObject.keys():
ann = pageObject['/Annots']
old = ''
for a in ann:
u = a.get_object()
if '/A' in u.keys():
if '/URI' in u['/A']:
if re.search(re.compile('^'+link_starting_form), u['/A']['/URI']):
if u['/A']['/URI'] != old:
links.append(u['/A']['/URI'])
i0 += 1
old = u['/A']['/URI']
return links
# 通过Sci-Hub网站下载文献
def download_with_scihub(address=None, num=1):
from bs4 import BeautifulSoup
import re
import requests
import os
if num==1 and address!=None:
address_array = [address]
else:
address_array = []
for i in range(num):
address = input('\nInput：')
address_array.append(address)
for address in address_array:
r = requests.post('https://sci-hub.st/', data={'request': address})
print('\nResponse：', r)
print('Address：', r.url)
soup = BeautifulSoup(r.text, features='lxml')
pdf_URL = soup.embed['src']
# pdf_URL = soup.iframe['src'] # This is a code line of history version which fails to get pdf URL.
if re.search(re.compile('^https:'), pdf_URL):
pass
else:
pdf_URL = 'https:'+pdf_URL
print('PDF address：', pdf_URL)
name = re.search(re.compile('fdp.*?/'),pdf_URL[::-1]).group()[::-1][1::]
print('PDF name：', name)
print('Directory：', os.getcwd())
print('\nDownloading...')
r = requests.get(pdf_URL, stream=True)
with open(name, 'wb') as f:
for chunk in r.iter_content(chunk_size=32):
f.write(chunk)
print('Completed!\n')
if num != 1:
print('All completed!\n')
# 将字符串转成音频
def str_to_audio(str='hello world', filename='str', rate=125, voice=1, read=1, save=0, compress=0, bitrate='16k', print_text=0):
import pyttsx3
import guan
if print_text==1:
print(str)
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[voice].id)
engine.setProperty("rate", rate)
if save==1:
engine.save_to_file(str, filename+'.wav')
engine.runAndWait()
print('Wav file saved!')
if compress==1:
import os
os.rename(filename+'.wav', 'temp.wav')
guan.compress_wav_to_mp3('temp.wav', output_filename=filename+'.mp3', bitrate=bitrate)
os.remove('temp.wav')
if read==1:
engine.say(str)
engine.runAndWait()
# 将txt文件转成音频
def txt_to_audio(txt_path, rate=125, voice=1, read=1, save=0, compress=0, bitrate='16k', print_text=0):
import pyttsx3
import guan
f = open(txt_path, 'r', encoding ='utf-8')
text = f.read()
if print_text==1:
print(text)
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[voice].id)
engine.setProperty("rate", rate)
if save==1:
import re
filename = re.split('[/,\\\]', txt_path)[-1][:-4]
engine.save_to_file(text, filename+'.wav')
engine.runAndWait()
print('Wav file saved!')
if compress==1:
import os
os.rename(filename+'.wav', 'temp.wav')
guan.compress_wav_to_mp3('temp.wav', output_filename=filename+'.mp3', bitrate=bitrate)
os.remove('temp.wav')
if read==1:
engine.say(text)
engine.runAndWait()
# 将PDF文件转成音频
def pdf_to_audio(pdf_path, rate=125, voice=1, read=1, save=0, compress=0, bitrate='16k', print_text=0):
import pyttsx3
import guan
text = guan.pdf_to_text(pdf_path)
text = text.replace('\n', ' ')
if print_text==1:
print(text)
engine = pyttsx3.init()
voices = engine.getProperty('voices')
engine.setProperty('voice', voices[voice].id)
engine.setProperty("rate", rate)
if save==1:
import re
filename = re.split('[/,\\\]', pdf_path)[-1][:-4]
engine.save_to_file(text, filename+'.wav')
engine.runAndWait()
print('Wav file saved!')
if compress==1:
import os
os.rename(filename+'.wav', 'temp.wav')
guan.compress_wav_to_mp3('temp.wav', output_filename=filename+'.mp3', bitrate=bitrate)
os.remove('temp.wav')
if read==1:
engine.say(text)
engine.runAndWait()
# 将wav音频文件压缩成MP3音频文件
def compress_wav_to_mp3(wav_path, output_filename='a.mp3', bitrate='16k'):
# Note: Beside the installation of pydub, you may also need download FFmpeg on http://www.ffmpeg.org/download.html and add the bin path to the environment variable.
from pydub import AudioSegment
sound = AudioSegment.from_mp3(wav_path)
sound.export(output_filename,format="mp3",bitrate=bitrate)
# 将WordPress导出的XML格式文件转换成多个MarkDown格式的文件
def convert_wordpress_xml_to_markdown(xml_file='./a.xml', convert_content=1, replace_more=[]):
import xml.etree.ElementTree as ET
import re
tree = ET.parse(xml_file)
root = tree.getroot()
for item in root.findall('.//item'):
title = item.find('title').text
content = item.find('.//content:encoded', namespaces={'content': 'http://purl.org/rss/1.0/modules/content/'}).text
if convert_content == 1:
content = re.sub(r'<!--.*?-->', '', content)
content = content.replace('<p>', '')
content = content.replace('</p>', '')
content = content.replace('<ol>', '')
content = content.replace('</ol>', '')
content = content.replace('<ul>', '')
content = content.replace('</ul>', '')
content = content.replace('<strong>', '')
content = content.replace('</strong>', '')
content = content.replace('</li>', '')
content = content.replace('<li>', '+ ')
content = content.replace('</h3>', '')
content = re.sub(r'<h2.*?>', '## ', content)
content = re.sub(r'<h3.*?>', '### ', content)
content = re.sub(r'<h4.*?>', '#### ', content)
for replace_item in replace_more:
content = content.replace(replace_item, '')
for _ in range(100):
content = content.replace('\n\n\n', '\n\n')
else:
pass
markdown_content = f"# {title}\n{content}"
markdown_file_path = f"{title}.md"
cleaned_filename = re.sub(r'[/:*?"<>|\'\\]', ' ', markdown_file_path)
with open(cleaned_filename, 'w', encoding='utf-8') as md_file:
md_file.write(markdown_content)
# 凯利公式
def kelly_formula(p, b, a=1):
f=(p/a)-((1-p)/b)
return f
# 获取所有股票
def all_stocks():
import numpy as np
import akshare as ak
stocks = ak.stock_zh_a_spot_em()
title = np.array(stocks.columns)
stock_data = stocks.values
return title, stock_data
# 获取所有股票的代码
def all_stock_symbols():
import guan
title, stock_data = guan.all_stocks()
stock_symbols = stock_data[:, 1]
return stock_symbols
# 股票代码的分类
def stock_symbols_classification():
import guan
import re
stock_symbols = guan.all_stock_symbols()
# 上交所主板
stock_symbols_60 = []
for stock_symbol in stock_symbols:
find_600 = re.findall(r'^600', stock_symbol)
find_601 = re.findall(r'^601', stock_symbol)
find_603 = re.findall(r'^603', stock_symbol)
find_605 = re.findall(r'^605', stock_symbol)
if find_600 != [] or find_601 != [] or find_603 != [] or find_605 != []:
stock_symbols_60.append(stock_symbol)
# 深交所主板
stock_symbols_00 = []
for stock_symbol in stock_symbols:
find_000 = re.findall(r'^000', stock_symbol)
find_001 = re.findall(r'^001', stock_symbol)
find_002 = re.findall(r'^002', stock_symbol)
find_003 = re.findall(r'^003', stock_symbol)
if find_000 != [] or find_001 != [] or find_002 != [] or find_003 != []:
stock_symbols_00.append(stock_symbol)
# 创业板
stock_symbols_30 = []
for stock_symbol in stock_symbols:
find_300 = re.findall(r'^300', stock_symbol)
find_301 = re.findall(r'^301', stock_symbol)
if find_300 != [] or find_301 != []:
stock_symbols_30.append(stock_symbol)
# 科创板
stock_symbols_68 = []
for stock_symbol in stock_symbols:
find_688 = re.findall(r'^688', stock_symbol)
find_689 = re.findall(r'^689', stock_symbol)
if find_688 != [] or find_689 != []:
stock_symbols_68.append(stock_symbol)
# 新三板
stock_symbols_8_4 = []
for stock_symbol in stock_symbols:
find_82 = re.findall(r'^82', stock_symbol)
find_83 = re.findall(r'^83', stock_symbol)
find_87 = re.findall(r'^87', stock_symbol)
find_88 = re.findall(r'^88', stock_symbol)
find_430 = re.findall(r'^430', stock_symbol)
find_420 = re.findall(r'^420', stock_symbol)
find_400 = re.findall(r'^400', stock_symbol)
if find_82 != [] or find_83 != [] or find_87 != [] or find_88 != [] or find_430 != [] or find_420 != [] or find_400 != []:
stock_symbols_8_4.append(stock_symbol)
# 检查遗漏的股票代码
stock_symbols_others = []
for stock_symbol in stock_symbols:
if stock_symbol not in stock_symbols_60 and stock_symbol not in stock_symbols_00 and stock_symbol not in stock_symbols_30 and stock_symbol not in stock_symbols_68 and stock_symbol not in stock_symbols_8_4:
stock_symbols_others.others.append(stock_symbol)
return stock_symbols_60, stock_symbols_00, stock_symbols_30, stock_symbols_68, stock_symbols_8_4, stock_symbols_others
# 股票代码各个分类的数量
def statistics_of_stock_symbols_classification():
import guan
stock_symbols_60, stock_symbols_00, stock_symbols_30, stock_symbols_68, stock_symbols_8_4, stock_symbols_others = guan.stock_symbols_classification()
num_stocks_60 = len(stock_symbols_60)
num_stocks_00 = len(stock_symbols_00)
num_stocks_30 = len(stock_symbols_30)
num_stocks_68 = len(stock_symbols_68)
num_stocks_8_4 = len(stock_symbols_8_4)
num_stocks_others= len(stock_symbols_others)
return num_stocks_60, num_stocks_00, num_stocks_30, num_stocks_68, num_stocks_8_4, num_stocks_others
# 从股票代码获取股票名称
def find_stock_name_from_symbol(symbol='000002'):
import guan
title, stock_data = guan.all_stocks()
for stock in stock_data:
if symbol in stock:
stock_name = stock[2]
return stock_name
# 市值排序
def sorted_market_capitalization(num=10):
import numpy as np
import guan
title, stock_data = guan.all_stocks()
new_stock_data = []
for stock in stock_data:
if np.isnan(float(stock[9])):
continue
else:
new_stock_data.append(stock)
new_stock_data = np.array(new_stock_data)
list_index = np.argsort(new_stock_data[:, 17])
list_index = list_index[::-1]
if num == None:
num = len(list_index)
sorted_array = []
for i0 in range(num):
stock_symbol = new_stock_data[list_index[i0], 1]
stock_name = new_stock_data[list_index[i0], 2]
market_capitalization = new_stock_data[list_index[i0], 17]/1e8
sorted_array.append([i0+1, stock_symbol, stock_name, market_capitalization])
return sorted_array
# 美股市值排序
def sorted_market_capitalization_us(num=10):
import akshare as ak
import numpy as np
stocks = ak.stock_us_spot_em()
stock_data = stocks.values
new_stock_data = []
for stock in stock_data:
if np.isnan(float(stock[9])):
continue
else:
new_stock_data.append(stock)
new_stock_data = np.array(new_stock_data)
list_index = np.argsort(new_stock_data[:, 9])
list_index = list_index[::-1]
if num == None:
num = len(list_index)
sorted_array = []
for i0 in range(num):
stock_symbol = new_stock_data[list_index[i0], 15]
stock_name = new_stock_data[list_index[i0], 1]
market_capitalization = new_stock_data[list_index[i0], 9]/1e8
sorted_array.append([i0+1, stock_symbol, stock_name, market_capitalization])
return sorted_array
# 获取单个股票的历史数据
def history_data_of_one_stock(symbol='000002', period='daily', start_date="19000101", end_date='21000101'):
# period = 'daily'
# period = 'weekly'
# period = 'monthly'
import numpy as np
import akshare as ak
stock = ak.stock_zh_a_hist(symbol=symbol, period=period, start_date=start_date, end_date=end_date)
title = np.array(stock.columns)
stock_data = stock.values[::-1]
return title, stock_data
# 绘制股票图
def plot_stock_line(date_array, opening_array, closing_array, high_array, low_array, lw_open_close=6, lw_high_low=2, xlabel='date', ylabel='price', title='', fontsize=20, labelsize=20, adjust_bottom=0.2, adjust_left=0.2, fontfamily='Times New Roman'):
import guan
plt, fig, ax = guan.import_plt_and_start_fig_ax(adjust_bottom=adjust_bottom, adjust_left=adjust_left, labelsize=labelsize, fontfamily=fontfamily)
if fontfamily=='Times New Roman':
ax.set_title(title, fontsize=fontsize, fontfamily='Times New Roman')
ax.set_xlabel(xlabel, fontsize=fontsize, fontfamily='Times New Roman')
ax.set_ylabel(ylabel, fontsize=fontsize, fontfamily='Times New Roman')
else:
ax.set_title(title, fontsize=fontsize)
ax.set_xlabel(xlabel, fontsize=fontsize)
ax.set_ylabel(ylabel, fontsize=fontsize)
for i0 in range(len(date_array)):
if opening_array[i0] <= closing_array[i0]:
ax.vlines(date_array[i0], opening_array[i0], closing_array[i0], linestyle='-', color='red', lw=lw_open_close)
ax.vlines(date_array[i0], low_array[i0], high_array[i0], color='red', linestyle='-', lw=lw_high_low)
else:
ax.vlines(date_array[i0], opening_array[i0], closing_array[i0], linestyle='-', color='green', lw=lw_open_close)
ax.vlines(date_array[i0], low_array[i0], high_array[i0], color='green', linestyle='-', lw=lw_high_low)
plt.show()
plt.close('all')
# Guan软件包的使用统计（仅仅统计装机数和import次数）
def statistics_of_guan_package(function_name=None):
import guan
try:
import socket
datetime_date = guan.get_date()
datetime_time = guan.get_time()
current_version = guan.get_current_version('guan')
client_socket = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
client_socket.settimeout(0.5)
client_socket.connect(('socket.guanjihuan.com', 12345))
mac_address = guan.get_mac_address()
if function_name == None:
message = {
'server': 'py.guanjihuan.com',
'date': datetime_date,
'time': datetime_time,
'version': current_version,
'MAC_address': mac_address,
}
else:
message = {
'server': 'py.guanjihuan.com',
'date': datetime_date,
'time': datetime_time,
'version': current_version,
'MAC_address': mac_address,
'function_name': function_name
}
import json
send_message = json.dumps(message)
client_socket.send(send_message.encode())
client_socket.close()
except:
pass
# # Guan软件包升级检查和提示（如果无法连接或者版本为最新，那么均没有提示）
# def notification_of_upgrade(timeout=5):
# try:
# import guan
# latest_version = guan.get_latest_version(package_name='guan', timeout=timeout)
# current_version = guan.get_current_version('guan')
# if latest_version != None and current_version != None:
# if latest_version != current_version:
# print('升级提示：您当前使用的版本是 guan-'+current_version+'，目前已经有最新版本 guan-'+latest_version+'。您可以通过以下命令对软件包进行升级：pip install --upgrade guan -i https://pypi.python.org/simple 或 pip install --upgrade guan')
# except:
# pass