101 lines
3.7 KiB
Plaintext
101 lines
3.7 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 1,
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Updated data saved to raw_data_s.csv\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import re\n",
|
|
"\n",
|
|
"# Load the data_mapping CSV file\n",
|
|
"data_mapping_file_path = '../../data_import/raw_data.csv' # Adjust this path to your actual file location\n",
|
|
"data_mapping_file_path = 'raw_data_add_tag.csv' # Adjust this path to your actual file location\n",
|
|
"data_mapping = pd.read_csv(data_mapping_file_path, dtype=str)\n",
|
|
"\n",
|
|
"# Backup the original tag_description\n",
|
|
"data_mapping['org_tag_description'] = data_mapping['tag_description']\n",
|
|
"\n",
|
|
"# Ensure all values in the 'tag_description' column are strings\n",
|
|
"data_mapping['tag_description'] = data_mapping['tag_description'].fillna('').astype(str)\n",
|
|
"data_mapping['tag_description'] = data_mapping['tag_description'].str.replace(r'[()]', ' ', regex=True)\n",
|
|
"\n",
|
|
"# Function to find tokens containing numbers\n",
|
|
"def find_tokens_with_numbers(description):\n",
|
|
" tokens = description.split() # Tokenize by spaces\n",
|
|
" number_tokens = [token for token in tokens if re.search(r'\\d', token)]\n",
|
|
" return number_tokens\n",
|
|
"\n",
|
|
"# Function to process tokens\n",
|
|
"def process_token(token):\n",
|
|
" # Step 1: Replace '_' or '-' adjacent to numbers with spaces\n",
|
|
" token = re.sub(r'(_|-)(?=\\d)', ' ', token)\n",
|
|
" token = re.sub(r'(?<=\\d)(_|-)', ' ', token)\n",
|
|
"\n",
|
|
" # Step 2: Insert spaces between letters and numbers where no separator exists\n",
|
|
" token = re.sub(r'([A-Za-z])(\\d+)', r'\\1 \\2', token)\n",
|
|
" token = re.sub(r'(\\d+)([A-Za-z])', r'\\1 \\2', token)\n",
|
|
"\n",
|
|
" # Step 3: Handle cases like \"NO.1\" or \"No.1\" to become \"No. 1\"\n",
|
|
" token = re.sub(r'([A-Za-z]+)\\.(\\d+)', r'\\1. \\2', token)\n",
|
|
"\n",
|
|
" # Clean multiple spaces and strip\n",
|
|
" token = re.sub(r'\\s+', ' ', token).strip()\n",
|
|
" return token\n",
|
|
"\n",
|
|
"# Apply the process to each row in the 'tag_description' column\n",
|
|
"for index, row in data_mapping.iterrows():\n",
|
|
" original_description = row['tag_description']\n",
|
|
" number_tokens = find_tokens_with_numbers(original_description)\n",
|
|
"\n",
|
|
" # Process each token containing numbers\n",
|
|
" processed_tokens = [process_token(token) for token in number_tokens]\n",
|
|
"\n",
|
|
" # Replace the original tokens with processed tokens in the tag_description\n",
|
|
" new_description = original_description\n",
|
|
" for original_token, processed_token in zip(number_tokens, processed_tokens):\n",
|
|
" new_description = new_description.replace(original_token, processed_token)\n",
|
|
"\n",
|
|
" # Update the data_mapping with the modified description\n",
|
|
" data_mapping.at[index, 'tag_description'] = new_description\n",
|
|
"\n",
|
|
"# Save the updated data_mapping to a new CSV file\n",
|
|
"output_file_path = 'raw_data_s.csv'\n",
|
|
"data_mapping.to_csv(output_file_path, index=False, encoding='utf-8-sig')\n",
|
|
"\n",
|
|
"print(f\"Updated data saved to {output_file_path}\")\n"
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "torch",
|
|
"language": "python",
|
|
"name": "python3"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.10.14"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 2
|
|
}
|