0.1.200

PyPI/setup.cfg

@@ -1,7 +1,7 @@
 [metadata]
 # replace with your username:
 name = guan
-version = 0.1.193
+version = 0.1.200
 author = guanjihuan
 author_email = guanjihuan@163.com
 description = An open source python package

PyPI/src/guan.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: guan
-Version: 0.1.193
+Version: 0.1.200
 Summary: An open source python package
 Home-page: https://py.guanjihuan.com
 Author: guanjihuan

PyPI/src/guan/data_processing.py

@@ -11,6 +11,16 @@ def logging_with_day_and_time(content='', filename='time_logging', file_format='
        else:
            f2.write(datetime_today+' '+datetime_time+' '+str(content)+'\n')
 
+# 获取当前位置的 Unix 时间戳，并打印某段程序的运行时间
+def record_time_and_print_running_time(start_time=None):
+    import time
+    current_time = time.time()
+    if start_time == None:
+      print("\n--- 开始计时（第一个记录点）---\n")
+    else:
+      print(f"\n--- 自上一个记录点已运行: {current_time - start_time:.2f} 秒 ---\n")
+    return current_time
+
 # 使用该函数运行某个函数并获取函数计算时间（秒）
 def timer(function_name, *args, **kwargs):
     import time
@@ -88,7 +98,7 @@ def word_diff(a, b, print_show=1):
     jieba.setLogLevel(logging.ERROR)
     a_words = jieba.lcut(a)
     b_words = jieba.lcut(b)
-    sm = difflib.SequenceMatcher(None, a_words, b_words)
+    sm = difflib.SequenceMatcher(None, a_words, b_words, autojunk=False)
     result = []
     for tag, i1, i2, j1, j2 in sm.get_opcodes():
         if tag == "equal":
@@ -115,7 +125,7 @@ def word_diff_to_html(a, b, filename='diff_result', write_file=1):
     jieba.setLogLevel(logging.ERROR)
     a_words = jieba.lcut(a)
     b_words = jieba.lcut(b)
-    sm = difflib.SequenceMatcher(None, a_words, b_words)
+    sm = difflib.SequenceMatcher(None, a_words, b_words, autojunk=False)
     html_parts = []
     for tag, i1, i2, j1, j2 in sm.get_opcodes():
         if tag == "equal":
@@ -231,6 +241,42 @@ def standard_deviation_with_formula(data_array):
     std_result = np.sqrt(averaged_squared_data-averaged_data**2)
     return std_result
 
+# 使用公式计算皮尔逊相关系数
+def calculate_pearson_correlation(x_array, y_array):
+    import numpy as np
+    mean_x = np.mean(x_array)
+    mean_y = np.mean(y_array)
+    numerator = np.sum((x_array - mean_x) * (y_array - mean_y))
+    sum_sq_x = np.sum((x_array - mean_x) ** 2)
+    sum_sq_y = np.sum((y_array - mean_y) ** 2)
+    denominator = np.sqrt(sum_sq_x * sum_sq_y)
+    correlation = numerator / denominator
+    return correlation
+
+# 使用 scipy 计算皮尔逊相关系数和 p 值
+def calculate_pearson_correlation_with_scipy(x_array, y_array):
+    import scipy.stats
+    correlation, p_value = scipy.stats.pearsonr(x_array, y_array)
+    return correlation, p_value
+
+# 使用 scipy 计算多个数组的皮尔逊相关系数和 p 值的矩阵
+def calculate_correlation_matrix_for_multiple_arrays(multiple_arrays):
+    import scipy.stats
+    import numpy as np
+    num_arrays = len(multiple_arrays)
+    correlation_matrix = np.zeros((num_arrays, num_arrays))
+    p_value_matrix = np.zeros((num_arrays, num_arrays))
+    row_idx = 0
+    for array_1 in multiple_arrays:
+        col_idx = 0
+        for array_2 in multiple_arrays:
+            correlation, p_value = scipy.stats.pearsonr(array_1, array_2)
+            correlation_matrix[row_idx, col_idx] = correlation
+            p_value_matrix[row_idx, col_idx] = p_value
+            col_idx += 1
+        row_idx += 1
+    return correlation_matrix, p_value_matrix
+
 # 获取两个模式之间的字符串
 def get_string_between_two_patterns(original_string, start, end, include_start_and_end=0):
     import re
@@ -337,6 +383,14 @@ def run_programs_sequentially(program_files=['./a.py', './b.py'], execute='pytho
         end = time.time()
         print('Total running time = '+str((end-start)/60)+' min')
 
+# 根据 “.” 和 “。” 符号进行分句
+def split_text_into_sentences(text):
+    import re
+    pattern = r'(?<=[。])|(?<=\.)(?=\s|$)'
+    sentences = re.split(pattern, text)
+    sentence_array = [s.strip() for s in sentences if s.strip()]
+    return sentence_array
+
 # 根据一定的字符长度来分割文本
 def split_text(text, width=100):  
     split_text_list = [text[i:i+width] for i in range(0, len(text), width)]

PyPI/src/guan/file_reading_and_writing.py

@@ -471,7 +471,7 @@ def open_file(filename='a', file_format='.txt', mode='add'):
         f = open(filename+file_format, 'w', encoding='UTF-8')
     return f
 
-# 打印到TXT文件
+# 打印到TXT文件（补充内容）
 def print_to_file(*args, filename='print_result', file_format='.txt', print_on=True):
     if print_on==True:
         for arg in args:
@@ -483,7 +483,12 @@ def print_to_file(*args, filename='print_result', file_format='.txt', print_on=T
     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
+# 写入到文本文件（覆盖内容）
+def write_text_file(content, filename='a', file_format='.txt'):
+    with open(filename+file_format, 'w', encoding='UTF-8') as f:
+        f.write(content)
+
+# 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):

PyPI/src/guan/others.py

@@ -28,7 +28,18 @@ def combine_two_pdf_files(input_file_1='a.pdf', input_file_2='b.pdf', output_fil
     with open(output_file, 'wb') as combined_file:
         output_pdf.write(combined_file)
 
-# 使用pdfminer3k将PDF文件转成文本
+# 使用pdfplumber将PDF文件转成文本
+def pdf_to_text_with_pdfplumber(pdf_path):
+    import pdfplumber
+    with pdfplumber.open(pdf_path) as pdf:
+        all_text = []
+        for page in pdf.pages:
+            text = page.extract_text()
+            all_text.append(text)
+        content = "\n\n".join(all_text)
+        return content
+
+# 使用pdfminer3k将PDF文件转成文本（仅仅支持旧版本的 pdfminer3k）
 def pdf_to_text_with_pdfminer3k(pdf_path):
     from pdfminer.pdfparser import PDFParser, PDFDocument
     from pdfminer.pdfinterp import PDFResourceManager, PDFPageInterpreter
@@ -115,6 +126,29 @@ def get_links_from_pdf(pdf_path, link_starting_form=''):
                                 old = u['/A']['/URI']
     return links
 
+# 将某个文件夹中的某个类型的文本文件全部修改为另外一个编码，其他文件不变
+def convert_file_encoding_for_one_directory(source_directory, target_directory, file_formats=['.m'], src_encoding='utf-8', dst_encoding='gb18030'):
+    import os
+    import shutil
+    os.makedirs(target_directory, exist_ok=True)
+    for root, dirs, files in os.walk(source_directory):
+        rel_path = os.path.relpath(root, source_directory) 
+        target_subdir = os.path.join(target_directory, rel_path) if rel_path != '.' else target_directory
+        os.makedirs(target_subdir, exist_ok=True)
+        for file in files:
+            src_file = os.path.join(root, file)
+            dst_file = os.path.join(target_subdir, file)
+            if any(file.lower().endswith(ext.lower()) for ext in file_formats):
+                try:
+                    with open(src_file, 'r', encoding=src_encoding) as f:
+                        content = f.read()
+                    with open(dst_file, 'w', encoding=dst_encoding) as f:
+                        f.write(content)
+                except Exception as e:
+                    shutil.copy2(src_file, dst_file)
+            else:
+                shutil.copy2(src_file, dst_file)
+
 # 获取当前日期字符串
 def get_date(bar=True):
     import datetime
@@ -770,7 +804,7 @@ def creat_qrcode(data="https://www.guanjihuan.com", filename='a', file_format='.
     img = qrcode.make(data)
     img.save(filename+file_format)
 
-# 通过Sci-Hub网站下载文献
+# 通过Sci-Hub网站下载文献（该方法可能失效）
 def download_with_scihub(address=None, num=1):
     from bs4 import BeautifulSoup
     import re