import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns
import os
import locale
import sys
from pathlib import Path
# 解决中文乱码问题
try:
# 设置matplotlib中文显示
if os.name == 'nt': # Windows系统
plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'Arial Unicode MS']
else: # Mac/Linux系统
plt.rcParams['font.sans-serif'] = ['WenQuanYi Micro Hei', 'WenQuanYi Zen Hei', 'Arial Unicode MS']
plt.rcParams['axes.unicode_minus'] = False
plt.rcParams['font.size'] = 12
# 设置控制台编码
if hasattr(sys.stdout, 'encoding') and sys.stdout.encoding not in ['UTF-8', 'utf-8']:
try:
sys.stdout.reconfigure(encoding='utf-8')
except:
pass
print("中文显示设置完成")
except Exception as e:
print("中文设置错误:", e)
def enhanced_critic_weights(data,
target_indicators=None,
cost_indicators=None,
epsilon=1e-10):
"""
增强版CRITIC权重计算函数
"""
# 转换数据为NumPy数组
if isinstance(data, pd.DataFrame):
df = data.copy()
X = df.values.astype(np.float64)
columns = df.columns.tolist()
else:
X = np.asarray(data, dtype=np.float64)
columns = [f"Var_{i}" for i in range(X.shape[1])]
# 处理成本型指标
cost_col_indices = []
if cost_indicators:
for col in cost_indicators:
if col in columns:
cost_col_indices.append(columns.index(col))
# 处理靶心型指标
target_col_indices = []
if target_indicators:
for col, target_val in target_indicators.items():
if col in columns:
col_idx = columns.index(col)
# 计算绝对偏差 |x - target|
X[:, col_idx] = np.abs(X[:, col_idx] - target_val)
# 将靶心型指标视为成本型
if col_idx not in cost_col_indices:
cost_col_indices.append(col_idx)
target_col_indices.append(col_idx)
# 处理缺失值和无穷值
X = np.where(np.isnan(X), np.nanmean(X, axis=0), X)
X = np.where(np.isinf(X), np.nan, X)
X = np.where(np.isnan(X), np.nanmean(X, axis=0), X)
# 计算基本统计量
min_vals = np.nanmin(X, axis=0)
max_vals = np.nanmax(X, axis=0)
ranges = max_vals - min_vals
ranges[ranges < epsilon] = epsilon
# 标准化处理
Z = np.zeros_like(X)
for j in range(X.shape[1]):
if j in cost_col_indices:
Z[:, j] = (max_vals[j] - X[:, j]) / ranges[j]
else:
Z[:, j] = (X[:, j] - min_vals[j]) / ranges[j]
# 计算标准化值的和
standardized_sums = np.sum(Z, axis=0)
# 计算标准差
std_dev = np.std(Z, axis=0, ddof=1)
# 计算相关系数矩阵
corr_matrix = np.corrcoef(Z, rowvar=False)
# 计算冲突性
conflict = np.sum(1 - np.abs(corr_matrix), axis=1)
# 计算信息量
information = std_dev * conflict
# 计算权重
weights = information / np.sum(information)
# 整理结果信息
info = {
"columns": columns,
"std_dev": std_dev,
"conflict": conflict,
"information": information,
"target_col_indices": target_col_indices,
"cost_col_indices": cost_col_indices,
"standardized_sums": standardized_sums,
"standardized_data": Z
}
return weights, info
def stability_analysis_with_noise(data, critic_func, noise_levels=[0.01, 0.05, 0.1],
n_iter=100, **critic_kwargs):
"""
CRITIC权重稳定性分析
"""
# 计算原始权重
original_weights, original_info = critic_func(data, **critic_kwargs)
columns = original_info['columns']
# 初始化结果存储
stability_results = {
'noise_levels': noise_levels,
'original_weights': original_weights,
'weight_matrix': {},
'stability_stats': {}
}
# 对每个噪声水平进行分析
for noise_level in noise_levels:
weight_matrix = []
for i in range(n_iter):
# 复制原始数据
if isinstance(data, pd.DataFrame):
noisy_data = data.copy()
else:
noisy_data = data.copy()
# 为每列添加独立高斯噪声
for j, col in enumerate(columns):
if col in data.columns:
std_dev = np.std(data[col])
noise = np.random.normal(0, noise_level * std_dev, size=len(data))
noisy_data[col] += noise
# 计算带噪声数据的权重
weights, _ = critic_func(noisy_data, **critic_kwargs)
weight_matrix.append(weights)
# 转换为数组
weight_matrix = np.array(weight_matrix)
stability_results['weight_matrix'][noise_level] = weight_matrix
# 计算统计量
mean_weights = np.mean(weight_matrix, axis=0)
std_weights = np.std(weight_matrix, axis=0)
cv_weights = std_weights / np.where(mean_weights != 0, mean_weights, 1e-10) # 避免除零
# 创建DataFrame存储统计结果
stability_stats = pd.DataFrame({
'指标': columns,
'原始权重': original_weights,
'平均权重': mean_weights,
'标准差': std_weights,
'变异系数': cv_weights,
'噪声水平': noise_level
})
stability_results['stability_stats'][noise_level] = stability_stats
# 可视化结果
visualize_stability_results(stability_results)
# 保存报告
save_stability_report(stability_results, original_info)
return stability_results
def visualize_stability_results(results):
"""可视化稳定性分析结果 - 只绘制箱线图和热力图"""
try:
if os.name == 'nt': # Windows
title_font = {'family': 'SimHei', 'size': 16}
label_font = {'family': 'Microsoft YaHei', 'size': 14}
else: # Mac/Linux
title_font = {'family': 'WenQuanYi Micro Hei', 'size': 16}
label_font = {'family': 'WenQuanYi Zen Hei', 'size': 14}
except:
title_font = {'size': 16}
label_font = {'size': 14}
noise_levels = results['noise_levels']
columns = results['original_weights'].index if isinstance(results['original_weights'], pd.Series) else range(
len(results['original_weights']))
# 获取指标名称列表
if isinstance(columns, pd.Index):
indicator_names = columns.tolist()
else:
# 如果columns是数字索引，使用原始信息中的列名
indicator_names = results['stability_stats'][noise_levels[0]]['指标'].tolist()
color_palette = plt.cm.viridis(np.linspace(0, 1, len(noise_levels)))
# ===================================
# 1. 权重变化箱线图（独立图表）
# ===================================
plt.figure(figsize=(14, 8))
# 为每个噪声水平创建不同的颜色
for i, noise_level in enumerate(noise_levels):
weight_matrix = results['weight_matrix'][noise_level]
weight_changes = []
for j in range(weight_matrix.shape[1]):
orig_weight = results['original_weights'][j]
changes = (weight_matrix[:, j] - orig_weight) / orig_weight * 100
weight_changes.append(changes)
# 绘制箱线图 - 使用指标名称作为横坐标
positions = np.arange(len(indicator_names)) + i * 0.2
box = plt.boxplot(weight_changes, positions=positions,
widths=0.15, patch_artist=True,
boxprops=dict(facecolor=color_palette[i], alpha=0.7),
medianprops=dict(color='black', linewidth=1.5))
# 添加参考线、标签和标题
plt.axhline(y=0, color='r', linestyle='--', linewidth=1.5)
# 设置横坐标为指标名称
plt.xticks(np.arange(len(indicator_names)), indicator_names,
rotation=45, ha='right', fontproperties=label_font)
plt.xlabel('指标', fontproperties=label_font)
plt.ylabel('权重变化百分比 (%)', fontproperties=label_font)
plt.title('不同噪声水平下的权重变化', fontproperties=title_font)
# 创建自定义图例 - 放在右下角
legend_handles = [plt.Rectangle((0, 0), 1, 1, color=color_palette[i], alpha=0.7)
for i in range(len(noise_levels))]
legend_labels = [f'{level * 100:.0f}%噪声' for level in noise_levels]
# 将图例放在右下角并添加边框
plt.legend(legend_handles, legend_labels, title='噪声水平',
prop=label_font,
loc='lower right', # 放在右下角
bbox_to_anchor=(0.98, 0.02), # 精确控制位置
frameon=True, # 添加边框
framealpha=0.8, # 设置透明度
fontsize=11, # 字体大小
title_fontsize=12) # 标题字体大小
plt.grid(axis='y', linestyle='--', alpha=0.3)
# 调整布局以确保图例不遮挡
plt.tight_layout(rect=[0, 0, 1, 0.95]) # 调整布局区域
# 保存箱线图
try:
plt.savefig('权重变化箱线图.png', dpi=300, bbox_inches='tight')
print("权重变化箱线图已保存为 '权重变化箱线图.png'")
except Exception as e:
print(f"保存箱线图时出错: {e}")
# 显示或关闭当前图表
try:
plt.show()
except Exception as e:
print(f"显示箱线图时出错: {e}")
# 关闭当前图表
plt.close()
# ===================================
# 2. 变异系数热力图（独立图表）
# ===================================
plt.figure(figsize=(14, 8))
# 准备热力图数据
cv_matrix = []
for noise_level in noise_levels:
stats_df = results['stability_stats'][noise_level]
cv_matrix.append(stats_df['变异系数'].values)
cv_matrix = np.array(cv_matrix)
# 创建热力图
ax = sns.heatmap(cv_matrix, annot=True, fmt=".3f", cmap="coolwarm",
xticklabels=indicator_names, # 使用指标名称
yticklabels=[f'{level * 100:.0f}%' for level in noise_levels])
# 设置标签和标题
plt.setp(ax.get_xticklabels(), fontproperties=label_font, rotation=45, ha='right')
plt.setp(ax.get_yticklabels(), fontproperties=label_font)
plt.xlabel('指标', fontproperties=label_font)
plt.ylabel('噪声水平', fontproperties=label_font)
plt.title('权重变异系数热力图', fontproperties=title_font)
# 添加颜色条标签
cbar = ax.collections[0].colorbar
cbar.set_label('变异系数 (CV)', rotation=270, labelpad=20, fontproperties=label_font)
plt.tight_layout()
# 保存热力图
try:
plt.savefig('变异系数热力图.png', dpi=300, bbox_inches='tight')
print("变异系数热力图已保存为 '变异系数热力图.png'")
except Exception as e:
print(f"保存热力图时出错: {e}")
# 显示或关闭当前图表
try:
plt.show()
except Exception as e:
print(f"显示热力图时出错: {e}")
# 关闭当前图表
plt.close()
def save_stability_report(results, info):
"""保存稳定性分析报告"""
report = "CRITIC权重稳定性分析报告\n"
report += "=" * 80 + "\n\n"
# 1. 原始权重信息
report += "原始权重信息:\n"
report += "-" * 50 + "\n"
for i, col in enumerate(info['columns']):
report += f"{col}: {results['original_weights'][i]:.6f} "
report += f"(标准差: {info['std_dev'][i]:.4f}, "
report += f"冲突性: {info['conflict'][i]:.4f}, "
report += f"信息量: {info['information'][i]:.4f})\n"
# 2. 稳定性统计
report += "\n\n稳定性分析结果:\n"
report += "=" * 50 + "\n"
for noise_level in results['noise_levels']:
stats_df = results['stability_stats'][noise_level]
report += f"\n噪声水平: {noise_level * 100:.1f}%\n"
report += "-" * 40 + "\n"
report += f"{'指标':<20}{'原始权重':>12}{'平均权重':>12}{'标准差':>10}{'变异系数':>12}\n"
for _, row in stats_df.iterrows():
report += f"{row['指标']:<20}{row['原始权重']:>12.6f}{row['平均权重']:>12.6f}"
report += f"{row['标准差']:>10.6f}{row['变异系数']:>12.4f}\n"
# 3. 稳定性评估
report += "\n\n稳定性评估:\n"
report += "=" * 50 + "\n"
# 计算整体稳定性指标
overall_stability = {}
for noise_level in results['noise_levels']:
stats_df = results['stability_stats'][noise_level]
avg_cv = stats_df['变异系数'].mean()
max_cv = stats_df['变异系数'].max()
overall_stability[noise_level] = {
'平均变异系数': avg_cv,
'最大变异系数': max_cv
}
# 评估稳定性
if max_cv < 0.1:
stability_level = "极高稳定性"
elif max_cv < 0.2:
stability_level = "高稳定性"
elif max_cv < 0.3:
stability_level = "中等稳定性"
else:
stability_level = "低稳定性"
report += (f"噪声水平 {noise_level * 100:.1f}%: "
f"平均变异系数={avg_cv:.4f}, 最大变异系数={max_cv:.4f} → {stability_level}\n")
# 4. 关键指标稳定性分析
report += "\n关键指标稳定性分析:\n"
report += "-" * 50 + "\n"
# 找出权重最大的3个指标
top_indices = np.argsort(results['original_weights'])[-3:]
top_columns = [info['columns'][i] for i in top_indices]
for col in top_columns:
col_index = info['columns'].index(col)
cv_values = []
for noise_level in results['noise_levels']:
stats_df = results['stability_stats'][noise_level]
cv = stats_df[stats_df['指标'] == col]['变异系数'].values[0]
cv_values.append(cv)
avg_cv = np.mean(cv_values)
report += f"指标 '{col}' (权重={results['original_weights'][col_index]:.4f}): "
report += f"平均变异系数={avg_cv:.4f} → "
if avg_cv < 0.1:
report += "稳定性优异\n"
elif avg_cv < 0.2:
report += "稳定性良好\n"
elif avg_cv < 0.3:
report += "稳定性一般\n"
else:
report += "稳定性较差\n"
# 保存报告
try:
with open('CRITIC_稳定性分析报告.txt', 'w', encoding='utf-8') as f:
f.write(report)
print("稳定性分析报告已保存为 'CRITIC_稳定性分析报告.txt' (UTF-8编码)")
except:
try:
with open('CRITIC_稳定性分析报告.txt', 'w') as f:
f.write(report)
print("稳定性分析报告已保存为 'CRITIC_稳定性分析报告.txt' (系统默认编码)")
except Exception as e:
print(f"保存报告时出错: {e}")
print("\n" + "=" * 80)
print("CRITIC权重稳定性分析报告（控制台输出）")
print("=" * 80)
print(report)
def load_custom_data(file_path):
"""
加载自定义CSV数据文件
"""
try:
# 尝试多种常见编码
encodings = ['utf-8', 'gbk', 'latin1', 'iso-8859-1']
for encoding in encodings:
try:
data = pd.read_csv(file_path, encoding=encoding)
print(f"使用 {encoding} 编码成功加载数据")
return data
except UnicodeDecodeError:
continue
# 如果所有编码都失败，尝试自动检测
try:
import chardet
with open(file_path, 'rb') as f:
result = chardet.detect(f.read())
encoding = result['encoding']
data = pd.read_csv(file_path, encoding=encoding)
print(f"使用自动检测的 {encoding} 编码成功加载数据")
return data
except:
raise ValueError("无法确定文件编码，请手动指定")
except Exception as e:
print(f"加载文件时出错: {e}")
return None
def validate_data(data):
"""
验证数据质量
"""
if data is None:
return False
print("\n数据验证:")
print(f"- 数据维度: {data.shape[0]}行 × {data.shape[1]}列")
# 检查缺失值
missing_values = data.isnull().sum().sum()
if missing_values > 0:
print(f"- 警告: 发现 {missing_values} 个缺失值，将使用列均值填充")
# 检查非数值列
non_numeric_cols = data.select_dtypes(exclude=['number']).columns.tolist()
if non_numeric_cols:
print(f"- 错误: 发现非数值列: {non_numeric_cols}")
print(" 请确保所有列都是数值类型")
return False
# 检查列数
if len(data.columns) < 2:
print("- 错误: 数据至少需要2列指标")
return False
# 检查行数
if len(data) < 10:
print("- 警告: 数据行数较少 (<10)，结果可能不可靠")
return True
# 主程序入口
if __name__ == "__main__":
print("=" * 80)
print("CRITIC权重稳定性分析程序")
print("=" * 80)
# 1. 加载自定义CSV数据
data_file = "yingyu.csv" # 替换为您的CSV文件路径
custom_data = load_custom_data(data_file)
if custom_data is None:
print("无法加载数据，程序终止")
exit(1)
# 2. 验证数据质量
if not validate_data(custom_data):
print("数据验证失败，请修正数据后重试")
exit(1)
print("\n数据前5行预览:")
print(custom_data.head())
# 3. 指定指标类型
# 靶心型指标：字典形式 {指标列名: 目标值}
target_spec = {
"凝结水过冷度": 0, # 我们希望凝结水过冷度越接近0越好
"炉膛负压": -100 # 我们希望炉膛负压越接近-100越好
}
# 成本型指标：列表形式，值越小越好
cost_indicators = [
"低压缸排汽压力",
"发电机定子绕组温度",
"SO2",
"NOx",
"烟尘",
"供电煤耗率",
"厂用电率",
"CO2"
]
# 4. 确保指定的列名在数据中存在
all_columns = custom_data.columns.tolist()
missing_targets = [col for col in target_spec if col not in all_columns]
missing_costs = [col for col in cost_indicators if col not in all_columns]
if missing_targets:
print(f"警告: 以下靶心型指标在数据中不存在: {missing_targets}")
if missing_costs:
print(f"警告: 以下成本型指标在数据中不存在: {missing_costs}")
# 5. 计算原始权重
print("\n计算CRITIC权重中...")
weights, info = enhanced_critic_weights(
custom_data,
target_indicators=target_spec,
cost_indicators=cost_indicators
)
# 打印原始权重
print("\n原始权重分配：")
for col, weight in zip(info["columns"], weights):
print(f"{col}: {weight:.6f}")
# 6. 进行稳定性分析
print("\n进行稳定性分析...")
stability_results = stability_analysis_with_noise(
custom_data,
critic_func=enhanced_critic_weights,
noise_levels=[0.01, 0.03, 0.05], # 1%, 3%, 5%, 10%噪声
n_iter=50, # 迭代次数（可根据需要调整）
target_indicators=target_spec,
cost_indicators=cost_indicators
)
print("\n分析完成！")
print("结果已保存到:")
print("- 权重变化箱线图.png")
print("- 变异系数热力图.png")
print("- CRITIC_稳定性分析报告.txt")
我想让他生成的图片中的文字都是对应的英文，如何修改代码，请你修改好，横坐标的指标名字我已经在文件中替换为英文了，就是需要你把其他的中文内容变成英文
最新发布
本文解释了如何使用Pandas库正确地从CSV文件中读取数据并设置索引列，包括不同参数如index_col的使用方法及其可能导致的误解。
扫一扫
1519
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
