PgsFile 0.5.3__py3-none-any.whl → 0.5.5__py3-none-any.whl

PgsFile/PgsFile.py

@@ -3800,17 +3800,16 @@ def file_to_list_of_dicts(input_path, output_path):
 
 import liwc
 import json
-def perform_liwc_en(dic_path, file_path, output_excel_path):
+def perform_liwc_en(file_path, output_excel_path):
     '''
     Parameters
     ----------
-    dic_path : str
-        Path to the LIWC dictionary file.
     file_path : str
         Path to the raw text file.
     output_excel_path : str
         Path to the output Excel file.
     '''
+    dic_path = get_library_location("PgsFile")+"/PgsFile/models/dics/LIWC2015-English.dic" 
     parse, category_names = liwc.load_token_parser(dic_path)
     test = get_data_text(file_path)
     test_tokens = [w.lower() for w in word_tokenize2(test)]
@@ -3850,7 +3849,7 @@ def perform_liwc_en(dic_path, file_path, output_excel_path):
     df.to_excel(output_excel_path, 'sheet1', index=False)
 
 
-def perform_liwc_zh(dic_path, file_path, output_excel_path):
+def perform_liwc_zh(file_path, output_excel_path):
     '''
     Parameters
     ----------
@@ -3861,6 +3860,7 @@ def perform_liwc_zh(dic_path, file_path, output_excel_path):
     output_excel_path : str
         Path to the output Excel file.
     '''        
+    dic_path = get_library_location("PgsFile")+"/PgsFile/models/dics/LIWC2015-Chinese.json" 
     
     f=open(dic_path,"r")
     dicx=json.load(f)    
@@ -4322,3 +4322,41 @@ def append_result_only(prompts_dict, note=RESULT_ONLY_NOTE):
 # Apply it
 translation_prompts = append_result_only(raw_translation_prompts)
 
+
+def csv_to_json_append(csv_path: str, json_path: str) -> None:
+    """
+    Convert a CSV file into a list of dictionaries and append them into a JSON file.
+
+    Args:
+        csv_path (str): Path to the CSV file.
+        json_path (str): Path to the output JSON file.
+    """
+    
+    import pandas as pd
+    
+    # Load CSV into DataFrame
+    df = pd.read_csv(csv_path)
+
+    # Automatically get all columns, convert to list of dicts
+    data_list = df.to_dict(orient='records')
+
+    # Append each dict to JSON file
+    for record in data_list:
+        append_dict_to_json(json_path, record)
+
+    print(f"✅ Completed! Appended {len(data_list)} records to {json_path}")
+    
+def get_data_csv(csv_path: str) -> list[dict]:
+    """
+    Load a CSV file and return its rows as a list of dictionaries.
+    Column names are automatically detected.
+
+    Args:
+        csv_path (str): Path to the CSV file.
+
+    Returns:
+        list[dict]: A list of dictionaries, where each dict represents one row.
+    """
+    import pandas as pd
+    df = pd.read_csv(csv_path)
+    return df.to_dict(orient="records")    

PgsFile/__init__.py

@@ -11,7 +11,7 @@ from .PgsFile import conda_mirror_commands
 
 # 3. Text data retrieval
 from .PgsFile import get_data_text, get_data_lines, get_json_lines, get_tsv_lines
-from .PgsFile import get_data_excel, get_data_json, get_data_tsv, extract_misspelled_words_from_docx
+from .PgsFile import get_data_excel, get_data_json, get_data_tsv, get_data_csv, extract_misspelled_words_from_docx
 from .PgsFile import get_data_html_online, get_data_html_offline
 from .PgsFile import get_data_table_url, get_data_table_html_string
 from .PgsFile import mhtml2html
@@ -33,6 +33,7 @@ from .PgsFile import set_permanent_environment_variable
 from .PgsFile import delete_permanent_environment_variable
 from .PgsFile import get_env_variable, get_all_env_variables
 from .PgsFile import get_system_info
+from .PgsFile import csv_to_json_append
 
 # 6. Data cleaning
 from .PgsFile import BigPunctuation, StopTags, Special, yhd