line-chart-visualization

Step1 数据加载与预处理（支持大文件Parquet转换与动态表头识别）。

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.cluster import KMeans
from sklearn.preprocessing import StandardScaler
import os
import re

# 设置中英文字体与图表美化
plt.rcParams['font.sans-serif'] = ['SimHei', 'WenQuanYi Zen Hei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False

file_path = 'input_data.xlsx'

# 处理大型Excel文件：统计总行数，若≥1万则转换为Parquet格式提升效率
xls = pd.ExcelFile(file_path)
total_rows = sum(pd.read_excel(xls, sheet_name=s, header=None).shape[0] for s in xls.sheet_names)

if total_rows >= 10000:
    parquet_path = "temp_converted_file.parquet"
    with pd.ExcelWriter(parquet_path, engine='pyarrow') as writer:
        for sheet in xls.sheet_names:
            df_sheet = pd.read_excel(xls, sheet_name=sheet, header=None)
            df_sheet.to_excel(writer, sheet_name=sheet, index=False, header=False)
    df = pd.read_excel(parquet_path, sheet_name='Sheet1', header=None)
else:
    df = pd.read_excel(file_path, sheet_name='Sheet1', header=None)

# 动态识别表头并提取数据
header_row_idx = None
target_cols = ['group_col', 'value_col1', 'value_col2'] # 占位示例列名