nlpertools 1.0.10__py3-none-any.whl → 1.0.11__py3-none-any.whl

nlpertools/__init__.py

@@ -4,6 +4,7 @@
 from .algo.kmp import *
 from .data_structure.base_structure import *
 from .draw import *
+from .dataprocess.dp_main import *
 from .dataprocess import *
 from .io.dir import *
 from .io.file import *
@@ -20,4 +21,4 @@ from .cli import *
 from .llm import *
 
 
-__version__ = "1.0.10"
+__version__ = "1.0.11"

nlpertools/cli.py

@@ -2,7 +2,7 @@ import argparse
 import os
 import uuid
 import sys
-from .dataprocess import startwith
+from .dataprocess.dp_main import startwith
 
 
 def run_git_command(command):
@@ -17,7 +17,7 @@ def run_git_command(command):
         info = os.system(command)
         print(str(info))
         # 检查命令执行结果，若未出现错误则认为执行成功
-        if not startwith(str(info), ["fatal", "error", "128", "1"]):
+        if (not startwith(str(info), ["fatal", "error", "128", "1"])) and "fatal" not in str(info):
             print("success")
             print(f"success info : ##{info}##")
             break
@@ -25,7 +25,7 @@ def run_git_command(command):
 
 def get_mac_address():
     mac = uuid.UUID(int=uuid.getnode()).hex[-12:]
-    mac_address = ":".join([mac[e:e + 2] for e in range(0, 11, 2)])
+    mac_address = ":".join([mac[e : e + 2] for e in range(0, 11, 2)])
     print("mac address 不一定准确")
     print(mac_address)
     return mac_address
@@ -33,6 +33,7 @@ def get_mac_address():
 
 def get_2af_value(key):
     import pyotp
+
     """
     key应该是7位的
     """
@@ -65,15 +66,11 @@ def start_gpu_usage_notify_client():
     from plyer import notification
     import time
 
-    SERVER_URL = 'http://127.0.0.1:5000/notify'  # 服务器的 API 地址
+    SERVER_URL = "http://127.0.0.1:5000/notify"  # 服务器的 API 地址
 
     def notify(text):
         # 使用 plyer 发送通知
-        notification.notify(
-            title='远程通知',
-            message=text,
-            timeout=10  # 10秒的通知显示时间
-        )
+        notification.notify(title="远程通知", message=text, timeout=10)  # 10秒的通知显示时间
 
     """定时轮询服务器获取通知"""
     while True:
@@ -94,12 +91,12 @@ def start_gpu_usage_notify_client():
 
 def main():
     parser = argparse.ArgumentParser(description="CLI tool for git operations and other functions.")
-    parser.add_argument('git_command', nargs='*', help='Any git command (e.g., push, pull)')
-    parser.add_argument('--mac_address', action='store_true', help='Get the MAC address.')
-    parser.add_argument('--get_2fa', action='store_true', help='Get the 2fa value.')
-    parser.add_argument('--get_2fa_key', type=str, help='Get the 2fa value.')
-    parser.add_argument('--monitor_gpu_cli', action='store_true', help='monitor gpu cli')
-    parser.add_argument('--monitor_gpu_ser', action='store_true', help='monitor gpu ser')
+    parser.add_argument("git_command", nargs="*", help="Any git command (e.g., push, pull)")
+    parser.add_argument("--mac_address", action="store_true", help="Get the MAC address.")
+    parser.add_argument("--get_2fa", action="store_true", help="Get the 2fa value.")
+    parser.add_argument("--get_2fa_key", type=str, help="Get the 2fa value.")
+    parser.add_argument("--monitor_gpu_cli", action="store_true", help="monitor gpu cli")
+    parser.add_argument("--monitor_gpu_ser", action="store_true", help="monitor gpu ser")
 
     args = parser.parse_args()
 
@@ -121,5 +118,5 @@ def main():
         print("No operation specified.")
 
 
-if __name__ == '__main__':
-    main()
+if __name__ == "__main__":
+    main()

nlpertools/dataprocess/__init__.py

@@ -0,0 +1 @@
+from .dedupl import *

nlpertools/dataprocess/dedupl.py

@@ -0,0 +1,9 @@
+# 根据字段对一个元素为dict的list去重
+def deduplicate_dict_list(dict_list: list, key: str) -> list:
+    seen = set()
+    result = []
+    for d in dict_list:
+        if key in d and d[key] not in seen:
+            seen.add(d[key])
+            result.append(d)
+    return result

nlpertools/{dataprocess.py → dataprocess/dp_main.py}

@@ -8,7 +8,7 @@ from typing import List
 import numpy as np
 
 # from . import DB_CONFIG_FILE # cannot import name 'DB_CONFIG_FILE' from partially initialized module 'nlpertools'
-from .utils.package import *
+from ..utils.package import *
 
 main_special_characters = string.punctuation + string.digits + string.whitespace
 other_special_characters = (

nlpertools/io/dir.py

@@ -3,6 +3,7 @@
 # @Author  : youshu.Ji
 import os
 from pathlib import Path
+from typing import overload,Literal,Union
 
 
 # dir ----------------------------------------------------------------------
@@ -45,15 +46,34 @@ def get_filename(path, suffix=True) -> str:
         filename = filename.split('.')[0]
     return filename
 
-
-def listdir(dir_name, including_dir=True):
-    filenames = os.listdir(dir_name)
+"""
+因为os.listdir无法支持Path类型，虽然是bytelikepath,但是传入Path后只会返回字符串
+且无法只返回文件名
+故重新实现
+"""
+@overload
+def listdir(dir_name: Path, including_dir: Literal[True]) -> list[Path]: ...
+@overload
+def listdir(dir_name: str, including_dir: Literal[True]) -> list[str]: ...
+@overload
+def listdir(dir_name: Path, including_dir: Literal[False] = False) -> list[str]: ...
+@overload
+def listdir(dir_name: str, including_dir: Literal[False] = False) -> list[str]: ...
+
+def listdir(dir_name: Union[Path, str], including_dir: bool = False) -> list[Path] | list[str]:
+    """
+    including_dir=True -> list[Path] or list[str]
+    including_dir=False -> list[str]
+    """
+    filenames = os.listdir(str(dir_name))
     if including_dir:
-        return [os.path.join(dir_name, filename) for filename in filenames]
+        if isinstance(dir_name, Path):
+            return [dir_name / filename for filename in filenames]
+        else:
+            return [os.path.join(dir_name, filename) for filename in filenames]
     else:
         return list(filenames)
 
-
 def listdir_yield(dir_name, including_dir=True):
     filenames = os.listdir(dir_name)
     for filename in filenames:

nlpertools/io/file.py

@@ -5,8 +5,11 @@ import codecs
 import json
 import pickle
 import random
-from itertools import (takewhile, repeat)
+from itertools import takewhile, repeat
+from typing import Optional
+from pathlib import Path
 import pandas as pd
+
 # import omegaconf
 # import yaml
 from ..utils.package import *
@@ -15,18 +18,18 @@ LARGE_FILE_THRESHOLD = 1e5
 
 
 def safe_filename(filename: str) -> str:
-    for char in ['\\', '/', ':', '*', '?', '"', '<', '>', '|']:
-        filename = filename.replace(char, '_')
+    for char in ["\\", "/", ":", "*", "?", '"', "<", ">", "|"]:
+        filename = filename.replace(char, "_")
     return filename
 
 
 def read_yaml(path, omega=False):
     if omega:
         return omegaconf.OmegaConf.load(path)
-    return yaml.load(codecs.open(path, encoding='utf-8'), Loader=yaml.FullLoader)
+    return yaml.load(codecs.open(path, encoding="utf-8"), Loader=yaml.FullLoader)
 
 
-def _merge_file(filelist, save_filename, shuffle=False):
+def merge_file(filelist, save_filename, shuffle=False):
     contents = []
     for file in filelist:
         content = readtxt_list_all_strip(file)
@@ -43,9 +46,9 @@ def iter_count(file_name):
     author: unknown
     """
     buffer = 1024 * 1024
-    with codecs.open(file_name, 'r', 'utf-8') as f:
+    with codecs.open(file_name, "r", "utf-8") as f:
         buf_gen = takewhile(lambda x: x, (f.read(buffer) for _ in repeat(None)))
-        return sum(buf.count('\n') for buf in buf_gen)
+        return sum(buf.count("\n") for buf in buf_gen)
 
 
 # 需要加入进度条的函数包括
@@ -57,24 +60,24 @@ load_from_json
 
 
 # 读txt文件 一次全读完 返回list 去换行
-def readtxt_list_all_strip(path, encoding='utf-8') -> list:
+def readtxt_list_all_strip(path, encoding="utf-8") -> list:
     file_line_num = iter_count(path)
     lines = []
-    with codecs.open(path, 'r', encoding) as r:
+    with codecs.open(path, "r", encoding) as r:
         if file_line_num > LARGE_FILE_THRESHOLD:
             iter_obj = tqdm(enumerate(r.readlines()), total=file_line_num)
         else:
             iter_obj = enumerate(r.readlines())
 
         for ldx, line in iter_obj:
-            lines.append(line.strip('\n').strip("\r"))
+            lines.append(line.strip("\n").strip("\r"))
         return lines
 
 
 # 读txt 一次读一行 最后返回list
 def readtxt_list_each(path) -> list:
     lines = []
-    with codecs.open(path, 'r', 'utf-8') as r:
+    with codecs.open(path, "r", "utf-8") as r:
         line = r.readline()
         while line:
             lines.append(line)
@@ -82,11 +85,11 @@ def readtxt_list_each(path) -> list:
     return lines
 
 
-def readtxt_list_each_strip(path) -> list:
+def readtxt_list_each_strip(path: Optional[str | Path]):
     """
     yield方法
     """
-    with codecs.open(path, 'r', 'utf-8') as r:
+    with codecs.open(path, "r", "utf-8") as r:
         line = r.readline()
         while line:
             yield line.strip("\n").strip("\r")
@@ -95,51 +98,51 @@ def readtxt_list_each_strip(path) -> list:
 
 # 读txt文件 一次全读完 返回list
 def readtxt_list_all(path) -> list:
-    with codecs.open(path, 'r', 'utf-8') as r:
+    with codecs.open(path, "r", "utf-8") as r:
         lines = r.readlines()
         return lines
 
 
 # 读byte文件 读成一条string
 def readtxt_byte(path, encoding="utf-8") -> str:
-    with codecs.open(path, 'rb') as r:
+    with codecs.open(path, "rb") as r:
         lines = r.read()
         lines = lines.decode(encoding)
-        return lines.replace('\r', '')
+        return lines.replace("\r", "")
 
 
 # 读txt文件 读成一条string
-def readtxt_string(path, encoding="utf-8") -> str:
-    with codecs.open(path, 'r', encoding) as r:
+def read_text(path, encoding="utf-8") -> str:
+    with codecs.open(path, "r", encoding) as r:
         lines = r.read()
-        return lines.replace('\r', '')
+        return lines.replace("\r", "")
 
 
 # 写txt文件覆盖
-def writetxt_w(txt, path, r='w'):
-    with codecs.open(path, r, 'utf-8') as w:
+def writetxt_w(txt, path, r="w"):
+    with codecs.open(path, r, "utf-8") as w:
         w.writelines(txt)
 
 
 # 写txt文件追加
 def writetxt_a(txt, path):
-    with codecs.open(path, 'a', 'utf-8') as w:
+    with codecs.open(path, "a", "utf-8") as w:
         w.writelines(txt)
 
 
 def writetxt(txt, path, encoding="utf-8"):
-    with codecs.open(path, 'w', encoding) as w:
+    with codecs.open(path, "w", encoding) as w:
         w.write(txt)
 
 
 def writetxt_wb(txt, path):
-    with codecs.open(path, 'wb') as w:
+    with codecs.open(path, "wb") as w:
         w.write(txt)
 
 
 # 写list 覆盖
 def writetxt_w_list(list, path, num_lf=1):
-    with codecs.open(path, 'w', "utf-8") as w:
+    with codecs.open(path, "w", "utf-8") as w:
         for i in list:
             w.write(i)
             w.write("\n" * num_lf)
@@ -147,7 +150,7 @@ def writetxt_w_list(list, path, num_lf=1):
 
 # 写list 追加
 def writetxt_a_list(list, path, num_lf=2):
-    with codecs.open(path, 'a', "utf-8") as w:
+    with codecs.open(path, "a", "utf-8") as w:
         for i in list:
             w.write(i)
             w.write("\n" * num_lf)
@@ -158,7 +161,7 @@ def save_to_json(content, path):
         json.dump(content, w, ensure_ascii=False, indent=1)
 
 
-def load_from_json(path):
+def load_from_json(path: Optional[str | Path]):
     with codecs.open(path, "r", "utf-8") as r:
         content = json.load(r)
         return content
@@ -167,60 +170,60 @@ def load_from_json(path):
 # 读txt文件 读成一条string if gb2312
 def readtxt_string_all_encoding(path):
     try:
-        with codecs.open(path, 'rb', "utf-8-sig") as r:
+        with codecs.open(path, "rb", "utf-8-sig") as r:
             lines = r.read()
             return lines
     except:
         try:
-            with codecs.open(path, 'rb', "utf-8") as r:
+            with codecs.open(path, "rb", "utf-8") as r:
                 lines = r.reacd()
                 return lines
         except:
             try:
-                with codecs.open(path, 'rb', "big5") as r:
+                with codecs.open(path, "rb", "big5") as r:
                     lines = r.read()
                     return lines
             except:
                 print(path)
-                with codecs.open(path, 'rb', "gb2312", errors='ignore') as r:
+                with codecs.open(path, "rb", "gb2312", errors="ignore") as r:
                     lines = r.read()
                     return lines
 
 
 def readtxt_list_all_encoding(path):
     try:
-        with codecs.open(path, 'rb', "utf-8-sig") as r:
+        with codecs.open(path, "rb", "utf-8-sig") as r:
             lines = r.readlines()
             return lines
     except:
         try:
-            with codecs.open(path, 'rb', "utf-8") as r:
+            with codecs.open(path, "rb", "utf-8") as r:
                 lines = r.readlines()
                 return lines
         except:
             try:
-                with codecs.open(path, 'rb', "big5") as r:
+                with codecs.open(path, "rb", "big5") as r:
                     lines = r.readlines()
                     return lines
             except:
-                with codecs.open(path, 'rb', "gb2312", errors='ignore') as r:
+                with codecs.open(path, "rb", "gb2312", errors="ignore") as r:
                     lines = r.readlines()
                     return lines
 
 
 # line by line
 def save_to_jsonl(corpus, path):
-    with open(path, 'w', encoding='utf-8') as wt:
+    with open(path, "w", encoding="utf-8") as wt:
         for i in corpus:
             wt.write(json.dumps(i, ensure_ascii=False))
-            wt.write('\n')
+            wt.write("\n")
 
 
 # line by line
 def load_from_jsonl(path):
     file_line_num = iter_count(path)
     if file_line_num > 1e5:
-        with open(path, 'r', encoding='utf-8') as rd:
+        with open(path, "r", encoding="utf-8") as rd:
             corpus = []
             while True:
                 line = rd.readline()
@@ -230,7 +233,7 @@ def load_from_jsonl(path):
                     break
         return corpus
     else:
-        with open(path, 'r', encoding='utf-8') as rd:
+        with open(path, "r", encoding="utf-8") as rd:
             corpus = []
             while True:
                 line = rd.readline()
@@ -242,20 +245,20 @@ def load_from_jsonl(path):
 
 
 def save_pkl(data, path):
-    with open(path, 'wb') as f:
+    with open(path, "wb") as f:
         pickle.dump(data, f)
 
 
 def load_pkl(path):
-    with open(path, 'rb') as f:
+    with open(path, "rb") as f:
         data = pickle.load(f)
     return data
 
 
 def save_to_csv(df, save_path, index_flag=False):
-    with open(save_path, 'wb+') as csvfile:
+    with open(save_path, "wb+") as csvfile:
         csvfile.write(codecs.BOM_UTF8)
-    df.to_csv(save_path, mode='a', index=index_flag)
+    df.to_csv(save_path, mode="a", index=index_flag)
 
 
 def save_to_mongo():

nlpertools/llm/__init__.py

@@ -0,0 +1,3 @@
+from .call_llm_once import *
+from .infer import *
+from .price import *

nlpertools/llm/call_llm_once.py

@@ -1,7 +1,6 @@
-from ..io.file import readtxt_string, read_yaml
+from ..io.file import read_yaml
 from tqdm import tqdm
 import os
-from openai import Openai
 from typing import Optional, Union
 
 """
@@ -9,8 +8,38 @@ from typing import Optional, Union
 """
 
 
+def call_once_stream(
+    client, input: Optional[Union[str, list]], model_name: str = "qwen3-0626-e4", max_tokens: int = 8192, temperature=0.2
+) -> str:
+    """
+    调用LLM模型进行一次推理
+    :param prompt: 输入的提示文本
+    :param model_name: 模型名称
+    :param max_tokens: 最大输出token数
+    :return: 模型的输出文本
+    """
+    from openai import OpenAI
+
+    if isinstance(input, str):
+        message = [{"role": "user", "content": input}]
+    elif isinstance(input, list):
+        message = input
+
+    completion = client.chat.completions.create(model=model_name, messages=message, max_tokens=max_tokens, stream=True)
+    text = ""
+    for chunk in completion:
+        if chunk.choices:
+            c = chunk.choices[0].delta.content or ""
+            text += c
+            print(c, end="")
+        else:
+            print()
+            print(chunk.usage)
+    return text
+
+
 def call_once(
-    client: Openai, input: Optional[Union[str, list]], model_name: str = "qwen3-0626-e4", max_tokens: int = 8192
+    client, input: Optional[Union[str, list]], model_name: str = "qwen3-0626-e4", max_tokens: int = 8192, temperature=0.8
 ) -> str:
     """
     调用LLM模型进行一次推理
@@ -19,12 +48,13 @@ def call_once(
     :param max_tokens: 最大输出token数
     :return: 模型的输出文本
     """
+    from openai import OpenAI
 
     if isinstance(input, str):
         message = [{"role": "user", "content": input}]
     elif isinstance(input, list):
         message = input
 
-    response = client.chat.completions.create(model=model_name, messages=message, max_tokens=max_tokens)
+    response = client.chat.completions.create(model=model_name, messages=message, max_tokens=max_tokens,temperature=temperature)
 
     return response.choices[0].message.content

nlpertools/llm/infer.py

@@ -1,7 +1,7 @@
 import os
 from tqdm import tqdm
-from openai import OpenAI
 import concurrent.futures
+import itertools
 
 
 INFER_PARAS = {
@@ -15,14 +15,17 @@ INFER_PARAS = {
 
 
 def parse_infer_data(infer_data: list):
+    # 解释一下为什么要[][]，因为message本来就必须得是[]
     if isinstance(infer_data[0], str):
-        message = [{"role": "user", "content": i} for i in infer_data]
+        message = [[{"role": "user", "content": i}] for i in infer_data]
     elif isinstance(infer_data[0], list):
         message = infer_data
     return message
 
 
-def common_api_infer_func(model_name, infer_data: list, infer_paras, client: OpenAI):
+def common_api_infer_func(model_name, infer_data: list, infer_paras, client):
+    from openai import OpenAI
+
     """
     infer_data: list of messages/prompt
     """
@@ -31,16 +34,58 @@ def common_api_infer_func(model_name, infer_data: list, infer_paras, client: Ope
     def get_response(model_name, messages, infer_paras):
         responses = []
         infer_times = infer_paras.get("infer_times", 1)
+
         for _ in range(infer_times):
             # 使用OpenAI API进行推理
-            response = client.chat.completions.create(model=model_name, messages=messages, **infer_paras)
+            response = client.chat.completions.create(
+                model=model_name,
+                messages=messages,
+                temperature=infer_paras.get("temperature", 0.7),
+                max_tokens=infer_paras.get("max_tokens", 8192),
+            )
             text = response.choices[0].message.content
             responses.append({"text": text})
         return responses
 
     with concurrent.futures.ThreadPoolExecutor(16) as executor:
         futures = [executor.submit(get_response, model_name, message, infer_paras) for message in messages]
-        results = [future.result() for future in concurrent.futures.as_completed(futures)]
+        # results = [future.result() for future in tqdm(concurrent.futures.as_completed(futures))] # 乱序
+        results = [future.result() for future in tqdm(futures)]
+
+    return results
+
+
+def common_api_infer_func_multi_client(model_name, infer_data: list, infer_paras, clients: list):
+    """
+    infer_data: list of messages/prompt
+    """
+    messages = parse_infer_data(infer_data)
+    iter_cycle = itertools.cycle(clients)
+
+    def get_response(model_name, messages, infer_paras):
+        client = next(iter_cycle)
+        # print(client.base_url)
+        responses = []
+        infer_times = infer_paras.get("infer_times", 1)
+        for _ in range(infer_times):
+            # 使用OpenAI API进行推理
+            try:
+                response = client.chat.completions.create(
+                    model=model_name,
+                    messages=messages,
+                    temperature=infer_paras.get("temperature", 0.7),
+                    max_tokens=infer_paras.get("max_tokens", 8192),
+                )
+                text = response.choices[0].message.content
+            except Exception as e:
+                print(e.__str__())
+                text = ""
+            responses.append({"text": text})
+        return responses
+
+    with concurrent.futures.ThreadPoolExecutor(128) as executor:
+        futures = [executor.submit(get_response, model_name, message, infer_paras) for message in messages]
+        results = [future.result() for future in tqdm(futures)]
 
     return results
 

nlpertools/other.py

@@ -3,7 +3,6 @@
 # @Author  : youshu.Ji
 import itertools
 import os
-import re
 import string
 import subprocess
 import threading
@@ -13,7 +12,10 @@ import math
 import datetime
 import difflib
 import psutil
+import sys
+
 from .io.file import writetxt_w_list, writetxt_a
+
 # import numpy as np
 # import psutil
 # import pyquery as pq
@@ -25,9 +27,9 @@ from .io.file import writetxt_w_list, writetxt_a
 # from win32evtlogutil import langid
 from .utils.package import *
 
-CHINESE_PUNCTUATION = list('，。；：‘’“”！？《》「」【】<>（）、')
-ENGLISH_PUNCTUATION = list(',.;:\'"!?<>()')
-OTHER_PUNCTUATION = list('!@#$%^&*')
+CHINESE_PUNCTUATION = list("，。；：‘’“”！？《》「」【】<>（）、")
+ENGLISH_PUNCTUATION = list(",.;:'\"!?<>()")
+OTHER_PUNCTUATION = list("!@#$%^&*")
 
 
 def setup_logging(log_file):
@@ -40,11 +42,23 @@ def setup_logging(log_file):
     logging.basicConfig(
         filename=log_file,
         level=logging.INFO,
-        format='%(asctime)s - %(levelname)s - %(message)s',
-        datefmt='%Y-%m-%d %H:%M:%S'
+        format="%(asctime)s - %(levelname)s - %(message)s",
+        datefmt="%Y-%m-%d %H:%M:%S",
     )
 
 
+def stop():
+    sys.exit()
+
+
+def exit():
+    sys.exit()
+
+
+def round2(num):
+    return round(num * 100, 2)
+
+
 def get_diff_parts(str1, str2):
     # 创建一个 SequenceMatcher 对象
     matcher = difflib.SequenceMatcher(None, str1, str2)
@@ -52,7 +66,7 @@ def get_diff_parts(str1, str2):
     # 获取差异部分
     diff_parts = []
     for tag, i1, i2, j1, j2 in matcher.get_opcodes():
-        if tag == 'replace' or tag == 'delete' or tag == 'insert':
+        if tag == "replace" or tag == "delete" or tag == "insert":
             diff_parts.append((tag, str1[i1:i2], str2[j1:j2]))
 
     return diff_parts
@@ -62,8 +76,9 @@ def run_cmd_with_timeout(cmd, timeout):
     """
     https://juejin.cn/post/7391703459803086848
     """
-    process = subprocess.Popen(cmd, shell=True, encoding="utf-8", errors="ignore", stdout=subprocess.PIPE,
-                               stderr=subprocess.PIPE)
+    process = subprocess.Popen(
+        cmd, shell=True, encoding="utf-8", errors="ignore", stdout=subprocess.PIPE, stderr=subprocess.PIPE
+    )
     res = [None]
 
     def target():
@@ -144,8 +159,11 @@ def print_three_line_table(df):
             border-bottom: (third_line_px)px solid black;
         }
     </style>"""
-    style = style.replace("(first_line_px)", first_line_px).replace("(second_line_px)", second_line_px).replace(
-        "(third_line_px)", third_line_px)
+    style = (
+        style.replace("(first_line_px)", first_line_px)
+        .replace("(second_line_px)", second_line_px)
+        .replace("(third_line_px)", third_line_px)
+    )
     # 将 CSS 样式和 HTML 表格结合起来
     html = f"{style}{html_table}"
     print(html)
@@ -153,7 +171,7 @@ def print_three_line_table(df):
     # 将 HTML 保存到文件中
     with open(temp_file_path, "w") as f:
         f.write(html)
-    webbrowser.open('file://' + os.path.realpath(temp_file_path))
+    webbrowser.open("file://" + os.path.realpath(temp_file_path))
 
 
 def jprint(obj, depth=0):
@@ -178,6 +196,7 @@ def print_split(sign="=", num=20, char: str = None):
 
 def seed_everything():
     import torch
+
     # seed everything
     seed = 7777777
     np.random.seed(seed)
@@ -192,22 +211,23 @@ def sent_email(mail_user, mail_pass, receiver, title, content, attach_path=None)
     from email.mime.text import MIMEText
     from email.mime.application import MIMEApplication
 
-    mail_host = 'smtp.qq.com'
+    mail_host = "smtp.qq.com"
     mail_user = mail_user
     mail_pass = mail_pass
     sender = mail_user
 
     message = MIMEMultipart()
-    message.attach(MIMEText(content, 'plain', 'utf-8'))
+    message.attach(MIMEText(content, "plain", "utf-8"))
     if attach_path:
-        attachment = MIMEApplication(open(attach_path, 'rb').read())
-        attachment["Content-Type"] = 'application/octet-stream'
-        attachment.add_header('Content-Dispositon', 'attachment',
-                              filename=('utf-8', '', attach_path))  # 注意：此处basename要转换为gbk编码，否则中文会有乱码。
+        attachment = MIMEApplication(open(attach_path, "rb").read())
+        attachment["Content-Type"] = "application/octet-stream"
+        attachment.add_header(
+            "Content-Dispositon", "attachment", filename=("utf-8", "", attach_path)
+        )  # 注意：此处basename要转换为gbk编码，否则中文会有乱码。
         message.attach(attachment)
-    message['Subject'] = title
-    message['From'] = sender
-    message['To'] = receiver
+    message["Subject"] = title
+    message["From"] = sender
+    message["To"] = receiver
 
     try:
         smtp_obj = smtplib.SMTP()
@@ -215,9 +235,9 @@ def sent_email(mail_user, mail_pass, receiver, title, content, attach_path=None)
         smtp_obj.login(mail_user, mail_pass)
         smtp_obj.sendmail(sender, receiver, message.as_string())
         smtp_obj.quit()
-        print('send email success')
+        print("send email success")
     except smtplib.SMTPException as e:
-        print('send failed', e)
+        print("send failed", e)
 
 
 def convert_np_to_py(obj):
@@ -247,12 +267,12 @@ def camel_to_snake(s: str) -> str:
     :param s: camel case variable
     :return:
     """
-    return reduce(lambda x, y: x + ('_' if y.isupper() else '') + y, s).lower()
+    return reduce(lambda x, y: x + ("_" if y.isupper() else "") + y, s).lower()
 
 
 # other ----------------------------------------------------------------------
 # 统计词频
-def calc_word_count(list_word, mode, path='tempcount.txt', sort_id=1, is_reverse=True):
+def calc_word_count(list_word, mode, path="tempcount.txt", sort_id=1, is_reverse=True):
     word_count = {}
     for key in list_word:
         if key not in word_count:
@@ -260,20 +280,20 @@ def calc_word_count(list_word, mode, path='tempcount.txt', sort_id=1, is_reverse
         else:
             word_count[key] += 1
     word_dict_sort = sorted(word_count.items(), key=lambda x: x[sort_id], reverse=is_reverse)
-    if mode == 'w':
+    if mode == "w":
         for key in word_dict_sort:
-            writetxt_a(str(key[0]) + '\t' + str(key[1]) + '\n', path)
-    elif mode == 'p':
+            writetxt_a(str(key[0]) + "\t" + str(key[1]) + "\n", path)
+    elif mode == "p":
         for key in word_dict_sort:
-            print(str(key[0]) + '\t' + str(key[1]))
-    elif mode == 'u':
+            print(str(key[0]) + "\t" + str(key[1]))
+    elif mode == "u":
         return word_dict_sort
 
 
 # 字典去重
 def dupl_dict(dict_list, key):
     new_dict_list, value_set = [], []
-    print('去重中...')
+    print("去重中...")
     for i in tqdm(dict_list):
         if i[key] not in value_set:
             new_dict_list.append(i)
@@ -288,9 +308,9 @@ def multi_thread_run(_task, data):
 
 
 def del_special_char(sentence):
-    special_chars = ['\ufeff', '\xa0', '\u3000', '\xa0', '\ue627']
+    special_chars = ["\ufeff", "\xa0", "\u3000", "\xa0", "\ue627"]
     for i in special_chars:
-        sentence = sentence.replace(i, '')
+        sentence = sentence.replace(i, "")
     return sentence
 
 
@@ -306,20 +326,20 @@ def spider(url):
     :param url:
     :return:
     """
-    if 'baijiahao' in url:
+    if "baijiahao" in url:
         content = requests.get(url)
         # print(content.text)
         html = pq.PyQuery(content.text)
-        title = html('.index-module_articleTitle_28fPT').text()
-        res = html('.index-module_articleWrap_2Zphx').text().rstrip('举报/反馈')
-        return '{}\n{}'.format(title, res)
+        title = html(".index-module_articleTitle_28fPT").text()
+        res = html(".index-module_articleWrap_2Zphx").text().rstrip("举报/反馈")
+        return "{}\n{}".format(title, res)
 
 
 def eda(sentence):
-    url = 'https://x.x.x.x:x/eda'
+    url = "https://x.x.x.x:x/eda"
     json_data = dict({"sentence": sentence})
     res = requests.post(url, json=json_data)
-    return res.json()['eda']
+    return res.json()["eda"]
 
 
 def find_language(text):
@@ -353,8 +373,8 @@ def print_prf(y_true, y_pred, label=None):
     for i in range(len(label)):
         res = []
         for k in result:
-            res.append('%.5f' % k[i])
-        print('{}: {} {} {}'.format(label[i], *res[:3]))
+            res.append("%.5f" % k[i])
+        print("{}: {} {} {}".format(label[i], *res[:3]))
 
 
 def print_cpu():
@@ -375,14 +395,16 @@ def squeeze_list(high_dim_list):
 
 def unsqueeze_list(flatten_list, each_element_len):
     # 该函数是错的，被split_list替代了
-    two_dim_list = [flatten_list[i * each_element_len:(i + 1) * each_element_len] for i in
-                    range(len(flatten_list) // each_element_len)]
+    two_dim_list = [
+        flatten_list[i * each_element_len : (i + 1) * each_element_len]
+        for i in range(len(flatten_list) // each_element_len)
+    ]
     return two_dim_list
 
 
 def split_list(input_list, chunk_size):
     # 使用列表推导式将列表分割成二维数组
-    return [input_list[i:i + chunk_size] for i in range(0, len(input_list), chunk_size)]
+    return [input_list[i : i + chunk_size] for i in range(0, len(input_list), chunk_size)]
 
 
 def auto_close():
@@ -392,6 +414,7 @@ def auto_close():
     import pyautogui as pg
     import time
     import os
+
     cmd = 'schtasks /create /tn shut /tr "shutdown -s -f" /sc once /st 23:30'
     os.system(cmd)
     while 1:
@@ -405,10 +428,13 @@ def tf_idf(corpus, save_path):
     vectorizer = CountVectorizer()  # 该类会将文本中的词语转换为词频矩阵，矩阵元素a[i][j] 表示j词在i类文本下的词频
     transformer = TfidfTransformer()  # 该类会统计每个词语的tf-idf权值
     tfidf = transformer.fit_transform(
-        vectorizer.fit_transform(corpus))  # 第一个fit_transform是计算tf-idf，第二个fit_transform是将文本转为词频矩阵
+        vectorizer.fit_transform(corpus)
+    )  # 第一个fit_transform是计算tf-idf，第二个fit_transform是将文本转为词频矩阵
     word = vectorizer.get_feature_names()  # 获取词袋模型中的所有词语
     weight = tfidf.toarray()  # 将tf-idf矩阵抽取出来，元素a[i][j]表示j词在i类文本中的tf-idf权重
-    for i in range(len(weight)):  # 打印每类文本的tf-idf词语权重，第一个for遍历所有文本，第二个for便利某一类文本下的词语权重
+    for i in range(
+        len(weight)
+    ):  # 打印每类文本的tf-idf词语权重，第一个for遍历所有文本，第二个for便利某一类文本下的词语权重
         for j in range(len(word)):
             getword = word[j]
             getvalue = weight[i][j]
@@ -418,7 +444,7 @@ def tf_idf(corpus, save_path):
                 else:
                     tfidfdict.update({getword: getvalue})
     sorted_tfidf = sorted(tfidfdict.items(), key=lambda d: d[1], reverse=True)
-    to_write = ['{} {}'.format(i[0], i[1]) for i in sorted_tfidf]
+    to_write = ["{} {}".format(i[0], i[1]) for i in sorted_tfidf]
     writetxt_w_list(to_write, save_path, num_lf=1)
 
 
@@ -427,7 +453,7 @@ class GaussDecay(object):
     当前只实现了时间的，全部使用默认值
     """
 
-    def __init__(self, origin='2022-08-02', scale='90d', offset='5d', decay=0.5, task="time"):
+    def __init__(self, origin="2022-08-02", scale="90d", offset="5d", decay=0.5, task="time"):
         self.origin = origin
         self.task = task
         self.scale, self.offset = self.translate(scale, offset)
@@ -451,7 +477,7 @@ class GaussDecay(object):
     @staticmethod
     def translated_minus(field_value):
         origin = datetime.datetime.now()
-        field_value = datetime.datetime.strptime(field_value, '%Y-%m-%d %H:%M:%S')
+        field_value = datetime.datetime.strptime(field_value, "%Y-%m-%d %H:%M:%S")
         return (origin - field_value).days
 
     def calc_exp(self):
@@ -469,13 +495,13 @@ class GaussDecay(object):
         :return:
         """
         numerator = max(0, (abs(self.translated_minus(field_value)) - self.offset)) ** 2
-        sigma_square = -1 * self.scale ** 2 / (2 * math.log(self.decay, math.e))
+        sigma_square = -1 * self.scale**2 / (2 * math.log(self.decay, math.e))
         denominator = 2 * sigma_square
         s = math.exp(-1 * numerator / denominator)
         return round(self.time_coefficient * s + self.related_coefficient * raw_score, 7)
 
 
-if __name__ == '__main__':
+if __name__ == "__main__":
     gauss_decay = GaussDecay()
     res = gauss_decay.calc_gauss(raw_score=1, field_value="2021-05-29 14:31:13")
     print(res)

nlpertools/utils/package.py

@@ -37,20 +37,19 @@ def lazy_import(importer_name, to_import):
     module = importlib.import_module(importer_name)
     import_mapping = {}
     for name in to_import:
-        importing, _, binding = name.partition(' as ')
+        importing, _, binding = name.partition(" as ")
         if not binding:
-            _, _, binding = importing.rpartition('.')
+            _, _, binding = importing.rpartition(".")
         import_mapping[binding] = importing
 
     def __getattr__(name):
         if name not in import_mapping:
-            message = f'module {importer_name!r} has no attribute {name!r}'
+            message = f"module {importer_name!r} has no attribute {name!r}"
             raise AttributeError(message)
         importing = import_mapping[name]
         # imortlib.import_module() implicitly sets submodules on this module as
         # appropriate for direct imports.
-        imported = importlib.import_module(importing,
-                                           module.__spec__.parent)
+        imported = importlib.import_module(importing, module.__spec__.parent)
         setattr(module, name, imported)
         return imported
 
@@ -75,15 +74,15 @@ KafkaConsumer = try_import("kafka", "KafkaConsumer")
 np = try_import("numpy", None)
 plt = try_import("matplotlib", "pyplot")
 WordNetLemmatizer = try_import("nltk.stem", "WordNetLemmatizer")
-metrics = try_import("sklearn", "metrics")
+# metrics = try_import("sklearn", "metrics")
 requests = try_import("requests", None)
 pq = try_import("pyquery", None)
-CountVectorizer = try_import("sklearn.feature_extraction.text", "CountVectorizer")
-precision_recall_fscore_support = try_import("sklearn.metrics", "precision_recall_fscore_support")
+# CountVectorizer = try_import("sklearn.feature_extraction.text", "CountVectorizer")
+# precision_recall_fscore_support = try_import("sklearn.metrics", "precision_recall_fscore_support")
 tqdm = try_import("tqdm", "tqdm")
 # TODO 自动导出langid和win32evtlogutil输出有bug
 langid = try_import("langid", None)
 win32evtlogutil = try_import("win32evtlogutil", None)
-TfidfTransformer = try_import("sklearn.feature_extraction.text", "TfidfTransformer")
+# TfidfTransformer = try_import("sklearn.feature_extraction.text", "TfidfTransformer")
 yaml = try_import("yaml", None)
-omegaconf = try_import("omegaconf", None)
+omegaconf = try_import("omegaconf", None)

nlpertools/wrapper.py

@@ -7,16 +7,18 @@ import time
 from functools import wraps
 import asyncio
 
+
 def fn_async_timer(function):
     """
     针对异步函数的装饰器
     """
+
     @wraps(function)
     async def function_timer(*args, **kwargs):
         t0 = time.time()
         result = await function(*args, **kwargs)
         t1 = time.time()
-        print('[finished {func_name} in {time:.2f}s]'.format(func_name=function.__name__, time=t1 - t0))
+        print("[finished {func_name} in {time:.2f}s]".format(func_name=function.__name__, time=t1 - t0))
         return result
 
     return function_timer
@@ -36,14 +38,14 @@ def fn_timer(async_func=False, analyse=False):
             t0 = time.time()
             result = await asyncio.create_task(func(*args, **kwargs))
             t1 = time.time()
-            print('[finished {func_name} in {time:.2f}s]'.format(func_name=func.__name__, time=t1 - t0))
+            print("[finished {func_name} in {time:.2f}s]".format(func_name=func.__name__, time=t1 - t0))
             return result
 
         def func_time(*args, **kwargs):
             t0 = time.time()
             result = func(*args, **kwargs)
             t1 = time.time()
-            print('[finished {func_name} in {time:.2f}s]'.format(func_name=func.__name__, time=t1 - t0))
+            print("[finished {func_name} in {time:.2f}s]".format(func_name=func.__name__, time=t1 - t0))
             return result
 
         def func_time_analyse(*args, **kwargs):
@@ -114,7 +116,7 @@ def fn_try(parameter):
                 return result
             except Exception as e:
                 msg = "报错！"
-                print('[func_name: {func_name} {msg}]'.format(func_name=function.__name__, msg=msg))
+                print("[func_name: {func_name} {msg}]".format(func_name=function.__name__, msg=msg))
                 parameter["msg"] = parameter["msg"].format(str(e))
                 return parameter
             finally:

{nlpertools-1.0.10.dist-info → nlpertools-1.0.11.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: nlpertools
-Version: 1.0.10
+Version: 1.0.11
 Summary: A small package about small basic IO operation when coding
 Home-page: https://github.com/lvzii/nlpertools
 Author: youshuJi
@@ -64,6 +64,8 @@ json_data = nlpertools.load_from_json('res.json')
 ```bash
 ## git, 连接github不稳定的时候非常有用
 ncli git pull
+## 带有参数时，加上--以避免-u被解析
+ncli -- git push -u origin main
 
 # 生成pypi双因素认证的实时密钥(需要提供key)
 ncli --get_2fa --get_2fa_key your_key

{nlpertools-1.0.10.dist-info → nlpertools-1.0.11.dist-info}/RECORD

@@ -1,20 +1,19 @@
-nlpertools/__init__.py,sha256=3tjuCeGz_Q2DAGXn2K6n58YEQ8dpwGx4yg_rh_npw9M,502
-nlpertools/cli.py,sha256=LlHZV9x9ZeqC9rILG4aYmNM2PymdkzYVc7lcbu1tMRw,3615
+nlpertools/__init__.py,sha256=VnH7GWVSTcV010_kD4VtsOAwIjzhe8prax8Wj17uc20,537
+nlpertools/cli.py,sha256=uCIUkiBXqTWJaxSQd5MlliGcTfxWzymo1UyQ3z_uhak,3612
 nlpertools/data_client.py,sha256=esX8lUQrTui4uVkqPfhpHVok7Eq6ywpuemKjLeqoglc,14674
-nlpertools/dataprocess.py,sha256=3ayCZAFc5t-Ov06oenRhMoGmnQrmCy-gtPhswecjEa4,23451
 nlpertools/default_db_config.yml,sha256=E1K9k_xzXVlsf-HJQh8kyHXHYuvTpD12jD4Hfe5rUk8,606
 nlpertools/get_2fa.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nlpertools/ml.py,sha256=fjI-WMM1lRnOnRFfTLEGplUx_Uamgr2gfmoAvGlgF7E,18994
 nlpertools/movie.py,sha256=rkyOnAXdsbWfMSbi1sE1VNRT7f66Hp9BnZsN_58Afmw,897
 nlpertools/nlpertools_config.yml,sha256=ksXejxFs7pxR47tNAsrN88_4gvq9PCA2ZMO07H-dJXY,26
 nlpertools/open_api.py,sha256=uyTY00OUlM57Cn0Wm0yZXcIS8vAszy9rKnDMBEWfWJM,1744
-nlpertools/other.py,sha256=WWUPwdBkRQrWpsmAMOYBm6GFFnKlyN1ANlFx5bLkj8s,15125
+nlpertools/other.py,sha256=LaNZRQ8wWJqZP6Gycq7eThEqcGXIANg7WzT6nh5QiKQ,15262
 nlpertools/pic.py,sha256=13aaFJh3USGYGs4Y9tAKTvWjmdQR4YDjl3LlIhJheOA,9906
 nlpertools/plugin.py,sha256=LB7j9GdoQi6TITddH-6EglHlOa0WIHLUT7X5vb_aIZY,1168
 nlpertools/reminder.py,sha256=wiXwZQmxMck5vY3EvG8_oakP3FAdjGTikAIOiTPUQrs,2977
 nlpertools/utils_for_nlpertools.py,sha256=SJqjfMc2Vd8ZCqzQiJCkSxjJxEKzvEUgAgbhKPtC6ww,3583
 nlpertools/vector_index_demo.py,sha256=CSCzXD13bUIo9AG-bjen668H10B02HFU1Kbxakvrs68,2924
-nlpertools/wrapper.py,sha256=xQ7UUAAqSEaRJweoZyGSTjM4B3FQNLl5Gou968Sl_hA,4348
+nlpertools/wrapper.py,sha256=8ReHv7LrBGX6wHma8rf_EhFPg0FJNoDjbn4p0O2UHzs,4350
 nlpertools/algo/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nlpertools/algo/ac.py,sha256=4BSiJdG8-S78w_KRqvGOkYjxuTDRiBsskRv-6Doi7oE,422
 nlpertools/algo/bit_ops.py,sha256=l14-j5VOqrab80CA_uBs1AiAJbzJUJH9dJXc7O9F5d0,501
@@ -24,15 +23,18 @@ nlpertools/algo/template.py,sha256=9vsHr4g3jZZ5KVU_2I9i97o8asRXq-8pSaCXIv0sHeM,2
 nlpertools/algo/union.py,sha256=0l7lGZbw1qIfW1z5TE8Oo3tybL1bKIP5rzpa5ZT-vLQ,249
 nlpertools/data_structure/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nlpertools/data_structure/base_structure.py,sha256=gVUvJZ5jsCAswRETTpMwcEjLKoageWiTuCKNEwIWKWk,2641
+nlpertools/dataprocess/__init__.py,sha256=YPBPsZ8vAoMS6GJ7GlCqj01Cx1q8dDARc_gW-ysORyk,21
+nlpertools/dataprocess/dedupl.py,sha256=WIBOrM6LfX3txcDa0xF7rqeBIpfqwrDBgepa6bavpt0,289
+nlpertools/dataprocess/dp_main.py,sha256=iyDsmKzUx5lD8EUNwkWIlTGKVQQDVx8p3pXFv2_kR64,23452
 nlpertools/draw/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nlpertools/draw/draw.py,sha256=19dskkr0wrgczxPJnphEszliwYshEh5SjD8Zz07nlk0,2615
 nlpertools/draw/math_func.py,sha256=0NQ22Dfi9DFG6Bg_hXnCT27w65-dqpOOIgZX7oUIW-Q,881
 nlpertools/io/__init__.py,sha256=YMuKtC2Ddh5dL5MvXjyUKYOOuqzFYUhBPFaP2kyFG9I,68
-nlpertools/io/dir.py,sha256=FPY62COQN8Ji72pk0dYRoXkrORYaUlybKNcL4474uUI,2263
-nlpertools/io/file.py,sha256=mLWl09IEi0rWPN4tTq3LwdYMvAjj4e_QsjEMhufuPPo,7192
-nlpertools/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-nlpertools/llm/call_llm_once.py,sha256=vswnPDZmDZO2Gz2U1m7X7OhaCHUkyVnEzDy4g7CQhVU,856
-nlpertools/llm/infer.py,sha256=u9DbopRY1-xQymcNGucsnVwo9Bgyrqg2ncWlK1f00rA,2483
+nlpertools/io/dir.py,sha256=jpJuCwLeBInr03iCSUfffmlchWShZ2Cjq38n0D0dILI,3106
+nlpertools/io/file.py,sha256=NF1xV5iazl86-TDdMQJ-LLrqCnuW29uuFb_NA55YNr4,7274
+nlpertools/llm/__init__.py,sha256=SdbGjzhu1lCeq55mC0tgsah9yzVxvvNrWMf2z8kDEoQ,71
+nlpertools/llm/call_llm_once.py,sha256=W0J2Ab8dHnVZ8q_KgfTKbee7NlJnA-ewjsne80ALLXY,1793
+nlpertools/llm/infer.py,sha256=q7asgwdJwo27d6rdBNQLys_bPEF0g-UNDKjt3S-Ltvs,4133
 nlpertools/llm/price.py,sha256=8zzEaLrbGiDUbTFSnuBGAduiSfDVXQUk4Oc_lE6eJFw,544
 nlpertools/monitor/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 nlpertools/monitor/gpu.py,sha256=M59O6i0hlew7AzXZlaVZqbZA5IR93OhBY2WI0-T_HtY,531
@@ -41,13 +43,13 @@ nlpertools/template/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSu
 nlpertools/utils/__init__.py,sha256=YMuKtC2Ddh5dL5MvXjyUKYOOuqzFYUhBPFaP2kyFG9I,68
 nlpertools/utils/lazy.py,sha256=SAeHLjxsYhpKWvcQKjs2eY0Nn5n3CJlqtxOLVOe1WjQ,29280
 nlpertools/utils/log_util.py,sha256=ftJDoTOtroLH-LadOygZljeyltOQn0D2Xb5x7Td1Qdg,428
-nlpertools/utils/package.py,sha256=wLg_M8j7Y6ReRjWHWCWoZJHrzEwuAr9TyG2jvb7OQCo,3261
+nlpertools/utils/package.py,sha256=8TLbrD3nmukpJw9lSpHHbUYK74qyAaSM_jUrCJOG6mo,3227
 nlpertools/utils/package_v1.py,sha256=sqgFb-zbTdMd5ziJLY6YUPqR49qUNZjxBH35DnyR5Wg,3542
 nlpertools/utils/package_v2.py,sha256=WOcsguWfUd4XSAfmPgCtL8HtUbqJ6GRSMHb0OsB47r0,3932
-nlpertools-1.0.10.dist-info/licenses/LICENSE,sha256=SBcMozykvTbZJ--MqSiKUmHLLROdnr25V70xCQgEwqw,11331
+nlpertools-1.0.11.dist-info/licenses/LICENSE,sha256=SBcMozykvTbZJ--MqSiKUmHLLROdnr25V70xCQgEwqw,11331
 nlpertools_helper/__init__.py,sha256=obxRUdZDctvcvK_iA1Dx2HmQFMlMzJto-xDPryq1lJ0,198
-nlpertools-1.0.10.dist-info/METADATA,sha256=z6WqwEQxdq4xOF3Pw8QXMcrckcMTYfaeRyEqs0aM428,3304
-nlpertools-1.0.10.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-nlpertools-1.0.10.dist-info/entry_points.txt,sha256=XEazQ4vUwJMoMAgAwk1Lq4PRQGklPkPBaFkiP0zN_JE,45
-nlpertools-1.0.10.dist-info/top_level.txt,sha256=_4q4MIFvMr4cAUbhWKWYdRXIXsF4PJDg4BUsZvgk94s,29
-nlpertools-1.0.10.dist-info/RECORD,,
+nlpertools-1.0.11.dist-info/METADATA,sha256=3KXxqbO2wWDMXLmnZJm2RvETybvIMekPelhSxE_ovKk,3386
+nlpertools-1.0.11.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+nlpertools-1.0.11.dist-info/entry_points.txt,sha256=XEazQ4vUwJMoMAgAwk1Lq4PRQGklPkPBaFkiP0zN_JE,45
+nlpertools-1.0.11.dist-info/top_level.txt,sha256=_4q4MIFvMr4cAUbhWKWYdRXIXsF4PJDg4BUsZvgk94s,29
+nlpertools-1.0.11.dist-info/RECORD,,