Compute TOPSIS scores and rank alternatives from a decision matrix.
npx skills add https://github.com/SPIRAL-EDWIN/MCM-ICM-2601000 --skill topsis-scorer
Please help me install this Agent Skill. Skill: topsis-scorer Source: https://github.com/SPIRAL-EDWIN/MCM-ICM-2601000/tree/main/.github/skills/topsis-scorer Command: npx skills add https://github.com/SPIRAL-EDWIN/MCM-ICM-2601000 --skill topsis-scorer
TOPSIS scores provide a principled way to rank alternatives by measuring their distance from the Positive and Negative Ideal Solutions, enabling objective decision making across multiple criteria.
Run the topsis-scorer on your dataset by supplying a DataFrame, a weights vector, and an optional list of negative_indicators to obtain ranked results.
High-intent search queries and answers about installing and using this skill.
To rank alternatives with TOPSIS, supply a pandas DataFrame decision matrix, a weights vector, and an optional negative_indicators list. The scorer computes distances from ideal solutions to produce ranked results.
TOPSIS handles benefit and cost criteria by measuring each alternative's distance from the Positive and Negative Ideal Solutions. You define cost criteria using the negative_indicators list to reverse their impact.
Yes, you can compare vendor proposals by price, quality, and delivery time in Python. The scorer uses numpy and pandas to process the decision matrix and output a ranked list of options.
Yes, you need numpy and pandas installed in your Python environment to calculate TOPSIS scores. These dependencies handle the underlying matrix operations and data manipulation required by the scorer.
The best way to apply weights for ranking options is passing a weights vector alongside your decision matrix to the TOPSIS scorer. This normalizes the criteria and calculates the relative closeness for sorting.
Use TOPSIS when you need objective decision making across multiple criteria with mixed benefits and costs. It provides a principled ranking by evaluating the geometric distance of alternatives from ideal solutions.
SPIRAL-EDWINComputes entropy-based weights for decision criteria and optionally adjusts polarity for negative indicators.
lyndonklCompare named alternatives against weighted criteria to generate ranked outcomes.
andikarachmanPreprocess raw data into clean, analysis-ready datasets with pandas and numpy.
oyjs1989Automate multi-criteria decision analysis with AHP, weighted scoring, and TOPSIS.
