pymcdm 1.0.3

Python library for Multi-Criteria Decision-Making

PyMCDM

Python 3 library for solving multi-criteria decision-making (MCDM) problems.

Installation

You can download and install pymcdm library using pip:

pip install pymcdm

Available methods

The library contains:

• MCDA methods:

  • TOPSIS
  • VIKOR
  • COPRAS
  • PROMETHEE I and II
  • COMET
  • SPOTIS

• Weighting methods:

  • Equal weights
  • Entropy method
  • Std method

• Normalization methods:

  • Linear
  • Max
  • Sum
  • Vector
  • Logarithmic

• Correlation coefficients:

  • Spearman
  • Pearson
  • Weighted Spearman
  • Rank Similarity Coefficient
  • Kendall Tau
  • Goodman and Kruskal Gamma

• Helpers

  • rankdata
  • rrankdata

Usage example

Here's a small example of how use this library to solve MCDM problem. For more examples with explanation see examples.

import numpy as np
from pymcdm.methods import TOPSIS
from pymcdm.helpers import rrankdata

# Define decision matrix (2 criteria, 4 alternative)
alts = np.array([
    [4, 4],
    [1, 5],
    [3, 2],
    [4, 2]
], dtype='float')

# Define weights and types
weights = np.array([0.5, 0.5])
types = np.array([1, -1])

# Create object of the method
topsis = TOPSIS()

# Determine preferences and ranking for alternatives
pref = topsis(alts, weights, types)
ranking = rrankdata(pref)

for r, p in zip(ranking, pref):
    print(r, p)

And the output of this example (numbers are rounded):

3 0.6126
4 0.0
2 0.7829
1 1.0