topsis灵敏度分析代码

Topsis（Technique for Order of Preference by Similarity to Ideal Solution）是一种多属性决策分析方法，用于评估和排序一组候选方案。灵敏度分析是在Topsis方法中的一种技术，用于评估输入数据的变化对最终结果的影响程度。

以下是一个简单的Topsis灵敏度分析的代码示例：

import numpy as np

def topsis_sensitivity_analysis(data, weights):
    # Step 1: Normalize the data
    normalized_data = data / np.sqrt(np.sum(data**2, axis=0))

    # Step 2: Calculate the weighted normalized decision matrix
    weighted_normalized_data = normalized_data * weights

    # Step 3: Calculate the ideal and negative-ideal solutions
    ideal_solution = np.max(weighted_normalized_data, axis=0)
    negative_ideal_solution = np.min(weighted_normalized_data, axis=0)

    # Step 4: Calculate the Euclidean distances to the ideal and negative-ideal solutions
    distance_to_ideal = np.sqrt(np.sum((weighted_normalized_data - ideal_solution)**2, axis=1))
    distance_to_negative_ideal = np.sqrt(np.sum((weighted_normalized_data - negative_ideal_solution)**2, axis=1))

    # Step 5: Calculate the relative closeness to the ideal solution
    relative_closeness = distance_to_negative_ideal / (distance_to_ideal + distance_to_negative_ideal)

    return relative_closeness

# Example usage
data = np.array([[3, 4, 5], [2, 6, 8], [5, 7, 9], [1, 3, 2]])
weights = np.array([0.4, 0.3, 0.3])

sensitivity_analysis_result = topsis_sensitivity_analysis(data, weights)
print(sensitivity_analysis_result)

这段代码实现了Topsis灵敏度分析的基本步骤。首先，输入数据被归一化处理，然后根据权重计算加权归一化决策矩阵。接下来，计算理想解和负理想解，并计算每个方案到理想解和负理想解的欧氏距离。最后，根据欧氏距离计算相对接近度。