Topsis-Satyam-101803324 1.0.5

This package can be used to calculate the topsis score of multiple component data and rank them accordingly

TOPSIS Package in Python

Submitted by: Satyam Verma

Roll no: 101803324

UCS538

---

TOPSIS

TOPSIS is an acronym that stands for ‘Technique of Order Preference Similarity to the Ideal Solution’ and is a pretty straightforward MCDA method. As the name implies, the method is based on finding an ideal and an anti-ideal solution and comparing the distance of each one of the alternatives to those.

---

How to use

The package Topsis-Satyam-101803324 can be run though the command line as follows:

>> pip install Topsis-Satyam-101803324

>>topsis data.csv "1,1,1,1" "+,+,-,+" result.csv

Sample Input

The decision matrix should be constructed with each row representing a Model alternative, and each column representing a criterion like Accuracy, R2, Root Mean Squared Error, Correlation, and many more.

Model	Correlation	R2	RMSE	Accuracy
M1	0.79	0.62	1.25	60.89
M2	0.66	0.44	2.89	63.07
M3	0.56	0.31	1.57	62.87
M4	0.82	0.67	2.68	70.19
M5	0.75	0.56	1.3	80.39

Weights `weights` is not already normalised will be normalised later in the code.

Information of benefit positive(+) or negative(-) impact criteria should be provided in impacts.

Output of this sample input

The output that will be generated from the following input data will be:

Model	Correlation	R2	RMSE	Accuracy	Topsis Score	Rank
M1	0.79	0.62	1.25	60.89	0.7722097345612788	2.0
M2	0.66	0.44	2.89	63.07	0.22559875426413367	5.0
M3	0.56	0.31	1.57	62.87	0.43889731728018605	4.0
M4	0.82	0.67	2.68	70.19	0.5238778712729114	3.0
M5	0.75	0.56	1.3	80.39	0.8113887082429979	1.0

The output file contains columns of input file along with two additional columns having **Topsis_score** and **Rank** . Here the ranks are given as rank 1 is the best solution according to the weights and impacts given and rank 5 is the worst solution.

---