histogram-visualization

Step 1 加载数据并进行预处理，配置中文字体与环境参数

import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
import re

# 设置中文字体，兼容不同环境
plt.rcParams['font.sans-serif'] = ['SimHei', 'WenQuanYi Zen Hei', 'DejaVu Sans']
plt.rcParams['axes.unicode_minus'] = False

# 加载数据并处理合并单元格
file_path = 'input_data.xlsx'
df = pd.read_excel(file_path)
df.ffill(inplace=True) # 处理可能的合并单元格空值

# 统一重命名列名以便于程序化处理
original_columns = df.columns.tolist()
df.columns = [f'col_{i+1}' for i in range(df.shape[1])]

print(f"数据形状: {df.shape}")
print(f"原始列映射: {dict(zip(df.columns, original_columns))}")

Step 2 生成多子图箱线图，直观展示各维度数据的分布特征与统计量

# 计算子图布局
num_cols = len(df.columns)
rows = (num_cols + 2) // 3
fig, axes = plt.subplots(rows, 3, figsize=(18, 5 * rows))
fig.suptitle('数据分布维度分析', fontsize=16, fontweight='bold')
axes_flat = axes.flatten()

for i, column in enumerate(df.columns):
    data_series = df[column].dropna()
    if pd.api.types.is_numeric_dtype(data_series):
        axes_flat[i].boxplot(data_series, patch_artist=True,
                            boxprops=dict(facecolor='lightblue', alpha=0.7),
                            medianprops=dict(color='red', linewidth=2))