Remove pyemd in favor of scipy (#37)

* Remove pyemd in favor of scipy

* Bump python version to 3.8 in actions and setup

* Fix python version for YAML

Per actions/setup-python#160

.github/workflows/manual-build.yml

@@ -11,7 +11,7 @@ jobs:
     timeout-minutes: 20
     strategy:
       matrix:
-        python-version: [ 3.8, 3.9 ]
+        python-version: [ 3.8, '3.10' ]
 
     steps:
       - name: Checkout branch

.github/workflows/publish_pypi.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.7]
+        python-version: [3.8]
 
     steps:
       - uses: actions/checkout@v2

.github/workflows/unit-build.yml

@@ -16,7 +16,7 @@ jobs:
     timeout-minutes: 15
     strategy:
       matrix:
-        python-version: [ 3.8, 3.9 ]
+        python-version: [ 3.8, 3.9, '3.10' ]
 
     steps:
     - uses: actions/checkout@v3

golem/metrics/mmd.py

@@ -1,10 +1,12 @@
 import itertools
 import numpy as np
 from scipy.linalg import toeplitz
-import pyemd
+from scipy.stats import wasserstein_distance
 
 
 def emd(x, y, distance_scaling=1.0):
+    """Earth's mover distance (or Wasserstein metric)
+     between 2 probability distributions."""
     support_size = max(len(x), len(y))
     d_mat = toeplitz(range(support_size)).astype(np.float64)
     distance_mat = d_mat / distance_scaling
@@ -17,7 +19,7 @@ def emd(x, y, distance_scaling=1.0):
     elif len(y) < len(x):
         y = np.hstack((y, [0.0] * (support_size - len(y))))
 
-    emd_value = pyemd.emd(x, y, distance_mat)
+    emd_value = wasserstein_distance(x, y, distance_mat)
     return emd_value
 
 

requirements.txt

@@ -27,6 +27,3 @@ hyperopt>=0.2.7
 # Tests
 pytest>=6.2.0
 testfixtures>=6.18.0
-
-# Examples
-pyemd

setup.py

@@ -14,7 +14,7 @@
 
 README = Path(HERE, 'README_en.rst').read_text(encoding='utf-8')
 URL = 'https://github.com/aimclub/GOLEM'
-REQUIRES_PYTHON = '>=3.7'
+REQUIRES_PYTHON = '>=3.8'
 LICENSE = 'BSD 3-Clause'
 
 
@@ -53,8 +53,8 @@ def _get_requirements(req_name: str):
     },
     classifiers=[
         'License :: OSI Approved :: BSD License',
-        'Programming Language :: Python :: 3.7',
         'Programming Language :: Python :: 3.8',
         'Programming Language :: Python :: 3.9'
+        'Programming Language :: Python :: 3.10'
     ],
 )