TOPSIS-VK-102003295 1.0.0

A Python package implementing TOPSIS technique used to solve the multi criteria decision making problems.

TOPSIS-Python

Assignment 1 : UCS654 Predictive Analysis using Statistics

Author - Vardaan Khosla(102003295), TIET Patiala

What is TOPSIS

Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) originated in the 1980s as a multi-criteria decision making method. TOPSIS chooses the alternative of shortest Euclidean distance from the ideal solution, and greatest distance from the negative-ideal solution.

This is how we can use the developed package:

Topsis-VardaanKhosla-102003295 package can be run as follows:

In the Command Prompt type:

>> topsis input_data.csv "0.25,0.25,0.25,0.25" "+,+,-,+" output_data.csv

Sample dataset

The decision matrix (a) 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.The number of entries in the impacts and weights column must be equal to the number of columns starting from the 2nd column in the input dataset. For example, in this case there are 4 columns consisting of parameters which affect the decision making procedure. Each column will have an according weight and impact associated to it.

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 (w) is not already normalised will be normalised later in the code.

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

Output

The output will consist of the original csv file along with two additional columns Topsis Score and Rank.

Model  Topsis Score    Rank
-----  ------------    ----
  1    0.77221          2
  2    0.225599         5
  3    0.438897         4
  4    0.523878         3
  5    0.811389         1