You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
190 lines
7.3 KiB
190 lines
7.3 KiB
import os
|
|
import openpyxl
|
|
import re
|
|
|
|
# 文件路径
|
|
input_file = r'D:\计量经济学\计量实验资料及作业要求\计量实验资料及作业要求\图文帖子实验数据（新）.xlsx'
|
|
output_file = r'D:\计量经济学\计量实验资料及作业要求\计量实验资料及作业要求\UGC回归数据.xlsx'
|
|
|
|
print("========================================")
|
|
print(" 处理所有数据")
|
|
print("========================================")
|
|
print(f"输入文件: {input_file}")
|
|
print(f"输出文件: {output_file}")
|
|
print()
|
|
|
|
# 检查文件是否存在
|
|
if not os.path.exists(input_file):
|
|
print("错误: 输入文件不存在！")
|
|
exit(1)
|
|
|
|
print(f"输入文件大小: {os.path.getsize(input_file) / 1024:.2f} KB")
|
|
|
|
# 读取原始数据
|
|
try:
|
|
print("正在读取原始数据...")
|
|
wb_input = openpyxl.load_workbook(input_file)
|
|
ws_input = wb_input.active
|
|
|
|
print(f"工作表名称: {ws_input.title}")
|
|
print(f"最大行数: {ws_input.max_row}")
|
|
print(f"最大列数: {ws_input.max_column}")
|
|
|
|
# 识别列
|
|
print("\n识别列...")
|
|
headers = []
|
|
helpfull_col = None
|
|
comment_count_col = None
|
|
comment_cols = []
|
|
|
|
for col in range(1, ws_input.max_column + 1):
|
|
header = ws_input.cell(row=1, column=col).value
|
|
headers.append(header)
|
|
|
|
if header:
|
|
header_str = str(header).lower()
|
|
if 'helpfull' in header_str or 'helpful' in header_str:
|
|
helpfull_col = col
|
|
print(f"找到 Y 列 (helpfull): 列 {col}")
|
|
elif '评论总数' in str(header) or '帖子评论总数' in str(header):
|
|
comment_count_col = col
|
|
print(f"找到 X1 列 (评论总数): 列 {col}")
|
|
elif '评论' in str(header) and any(str(i) in str(header) for i in range(1, 6)):
|
|
comment_cols.append(col)
|
|
print(f"找到评论列 {len(comment_cols)}: 列 {col} - {header}")
|
|
|
|
print(f"\n共找到 {len(comment_cols)} 个评论列")
|
|
|
|
# 创建新的输出文件
|
|
print("\n创建新的输出文件...")
|
|
wb_output = openpyxl.Workbook()
|
|
ws_output = wb_output.active
|
|
|
|
# 写入表头
|
|
headers_output = ['Y', 'X1', 'X2', 'X3', 'X4', 'X5', 'X6']
|
|
for i, header in enumerate(headers_output, 1):
|
|
ws_output.cell(row=1, column=i, value=header)
|
|
|
|
# 计算并填充数据
|
|
print("\n计算并填充数据...")
|
|
total_rows = ws_input.max_row - 1
|
|
print(f"总数据行数: {total_rows}")
|
|
|
|
for row in range(2, ws_input.max_row + 1):
|
|
if row % 1000 == 0:
|
|
print(f"处理到第 {row-1} 行...")
|
|
|
|
# Y (UGC有用性)
|
|
if helpfull_col:
|
|
y_value = ws_input.cell(row=row, column=helpfull_col).value
|
|
y_value = float(y_value) if y_value else 0
|
|
else:
|
|
y_value = 0
|
|
ws_output.cell(row=row, column=1, value=y_value)
|
|
|
|
# X1 (评论数量)
|
|
if comment_count_col:
|
|
x1_value = ws_input.cell(row=row, column=comment_count_col).value
|
|
x1_value = float(x1_value) if x1_value else 0
|
|
else:
|
|
x1_value = 0
|
|
ws_output.cell(row=row, column=2, value=x1_value)
|
|
|
|
# 计算评论相关指标
|
|
comment_lengths = []
|
|
comment_complexities = []
|
|
comment_sentiments = []
|
|
comment_richness = []
|
|
|
|
for col in comment_cols:
|
|
content = str(ws_input.cell(row=row, column=col).value)
|
|
if content and content != 'None' and content != 'nan':
|
|
# X2: 评论长度（剔空格后的字符数）
|
|
length = len(content.replace(' ', ''))
|
|
comment_lengths.append(length)
|
|
|
|
# X3: 评论复杂度（按空格拆分的分词数）
|
|
complexity = len(content.split())
|
|
comment_complexities.append(complexity)
|
|
|
|
# X5: 内容情感性（正面=1、中性=0、负面=-1）
|
|
positive_words = ['好', '棒', '优秀', '喜欢', '满意', '赞', 'positive', 'good', 'great', 'excellent']
|
|
negative_words = ['差', '糟糕', '不好', '失望', '不满', 'negative', 'bad', 'terrible', 'poor']
|
|
|
|
sentiment = 0
|
|
lower_content = content.lower()
|
|
|
|
if any(word in lower_content for word in positive_words):
|
|
sentiment = 1
|
|
elif any(word in lower_content for word in negative_words):
|
|
sentiment = -1
|
|
comment_sentiments.append(sentiment)
|
|
|
|
# X6: 信息丰富度（含数字/链接/表情各1分，满分3分）
|
|
richness = 0
|
|
if re.search(r'\d', content):
|
|
richness += 1
|
|
if re.search(r'http[s]?://', content):
|
|
richness += 1
|
|
if re.search(r'[\u2600-\u27BF]|[:;][-]?[)D]', content):
|
|
richness += 1
|
|
comment_richness.append(richness)
|
|
|
|
# X2: 评论长度平均值
|
|
x2_value = sum(comment_lengths) / len(comment_lengths) if comment_lengths else 0
|
|
ws_output.cell(row=row, column=3, value=x2_value)
|
|
|
|
# X3: 评论复杂度平均值
|
|
x3_value = sum(comment_complexities) / len(comment_complexities) if comment_complexities else 0
|
|
ws_output.cell(row=row, column=4, value=x3_value)
|
|
|
|
# X4: 评论可读性（X2/X3，X3为0时记0）
|
|
x4_value = x2_value / x3_value if x3_value > 0 else 0
|
|
ws_output.cell(row=row, column=5, value=x4_value)
|
|
|
|
# X5: 内容情感性平均值
|
|
x5_value = sum(comment_sentiments) / len(comment_sentiments) if comment_sentiments else 0
|
|
ws_output.cell(row=row, column=6, value=x5_value)
|
|
|
|
# X6: 信息丰富度平均值
|
|
x6_value = sum(comment_richness) / len(comment_richness) if comment_richness else 0
|
|
ws_output.cell(row=row, column=7, value=x6_value)
|
|
|
|
# 保存文件
|
|
print("\n保存文件...")
|
|
wb_output.save(output_file)
|
|
|
|
print(f"文件已成功保存: {output_file}")
|
|
print(f"文件大小: {os.path.getsize(output_file) / 1024:.2f} KB")
|
|
print(f"处理完成，共 {total_rows} 行数据")
|
|
|
|
# 验证文件
|
|
print("\n验证文件...")
|
|
if os.path.exists(output_file):
|
|
print("文件保存成功！")
|
|
# 重新打开文件检查
|
|
wb_check = openpyxl.load_workbook(output_file)
|
|
ws_check = wb_check.active
|
|
print(f"输出文件行数: {ws_check.max_row - 1}")
|
|
print(f"输出文件列数: {ws_check.max_column}")
|
|
|
|
# 显示前5行数据
|
|
print("\n前5行数据:")
|
|
for row in range(1, min(6, ws_check.max_row + 1)):
|
|
row_data = []
|
|
for col in range(1, ws_check.max_column + 1):
|
|
value = ws_check.cell(row=row, column=col).value
|
|
row_data.append(value)
|
|
print(f"行 {row}: {row_data}")
|
|
else:
|
|
print("文件保存失败！")
|
|
|
|
print()
|
|
print("========================================")
|
|
print(" 任务完成")
|
|
print("========================================")
|
|
|
|
except Exception as e:
|
|
print(f"处理文件时出错: {str(e)}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
|