Merge pull request #5 from clara-labs/feature/python3_cleanup

Feature/python3 cleanup
jasonlaska · Aug 20, 2017 · 7d7697c · 7d7697c
2 parents 3e20dec + 3c1d867
commit 7d7697c
Show file tree

Hide file tree

Showing 13 changed files with 429 additions and 374 deletions.
diff --git a/example-requirements.txt b/example-requirements.txt
@@ -0,0 +1,4 @@
+-r requirements.txt
+tabulate==0.7.7
+matplotlib==2.0.2
+seaborn==0.8
diff --git a/examples/document_clustering.py b/examples/document_clustering.py
@@ -13,9 +13,6 @@
 import logging
 from sklearn.cluster import KMeans
 
-import sys
-sys.path.append('../spherecluster')
-
 from spherecluster import SphericalKMeans
 from spherecluster import VonMisesFisherMixture
 

diff --git a/examples/make_sphere_graphic.py b/examples/make_sphere_graphic.py
@@ -1,10 +1,8 @@
+import sys
 import numpy as np
 from matplotlib import pyplot as plt
-from mpl_toolkits.mplot3d import Axes3D
-import seaborn
-
-import sys
-sys.path.append('../spherecluster')
+from mpl_toolkits.mplot3d import Axes3D  # NOQA
+import seaborn  # NOQA
 
 from spherecluster import sample_vMF
 
@@ -19,22 +17,31 @@
 
 Xs = []
 for nn in range(n_clusters):
-  new_X = sample_vMF(mus[nn], kappas[nn], num_points_per_class)
-  Xs.append(new_X.T)
+    new_X = sample_vMF(mus[nn], kappas[nn], num_points_per_class)
+    Xs.append(new_X.T)
 
 
 fig = plt.figure(figsize=(8, 6))
-ax = fig.add_subplot(1, 1, 1, aspect='equal', projection='3d',
-        adjustable='box-forced', xlim=[-1.1, 1.1], ylim=[-1.1, 1.1],
-        zlim=[-1.1, 1.1])
+ax = fig.add_subplot(
+    1, 1, 1, aspect='equal', projection='3d',
+    adjustable='box-forced', xlim=[-1.1, 1.1], ylim=[-1.1, 1.1],
+    zlim=[-1.1, 1.1]
+)
 
 colors = ['b', 'r', 'g']
 for nn in range(n_clusters):
-  ax.scatter(Xs[nn][0, :], Xs[nn][1, :], Xs[nn][2, :], c=colors[nn])
-  ax.hold(True)
+    ax.scatter(Xs[nn][0, :], Xs[nn][1, :], Xs[nn][2, :], c=colors[nn])
+    ax.hold(True)
 
 ax.set_aspect('equal')
 plt.axis('off')
 plt.show()
 
-raw_input()
+def r_input(val=None):
+    val = val or ''
+    if sys.version_info[0] >= 3:
+        return eval(input(val))
+
+    return raw_input(val)
+
+r_input()
diff --git a/examples/small_mix.py b/examples/small_mix.py
@@ -1,11 +1,9 @@
+import sys
 import numpy as np
 from matplotlib import pyplot as plt
 from sklearn.cluster import KMeans
 from sklearn import metrics
 
-import sys
-sys.path.append('../spherecluster')
-
 from spherecluster import SphericalKMeans
 from spherecluster import VonMisesFisherMixture
 from spherecluster import sample_vMF
@@ -19,13 +17,22 @@
 Provides a basic smell test that the algoriths are performing as intended.
 '''
 
+
+def r_input(val=None):
+    val = val or ''
+    if sys.version_info[0] >= 3:
+        return eval(input(val))
+
+    return raw_input(val)
+
+
 ###############################################################################
 # Generate small-mix dataset
 mu_0 = np.array([-0.251, -0.968])
 mu_1 = np.array([0.399, 0.917])
 mus = [mu_0, mu_1]
-kappa_0 = 8 # concentration parameter
-kappa_1 = 2 # concentration parameter
+kappa_0 = 8  # concentration parameter
+kappa_1 = 2  # concentration parameter
 kappas = [kappa_0, kappa_1]
 num_points_per_class = 100
 
@@ -184,46 +191,45 @@
 plt.show()
 
 
-print 'mu 0: {}'.format(mu_0)
-print 'mu 0: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_0_idx], km_mu_0_error, km_mu_0_error_norm)
-print 'mu 0: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_0_idx], skm_mu_0_error)
-print 'mu 0: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_0_idx], vmf_soft_mu_0_error)
-print 'mu 0: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_0_idx], vmf_hard_mu_0_error)
+print('mu 0: {}'.format(mu_0))
+print('mu 0: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_0_idx], km_mu_0_error, km_mu_0_error_norm))
+print('mu 0: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_0_idx], skm_mu_0_error))
+print('mu 0: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_0_idx], vmf_soft_mu_0_error))
+print('mu 0: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_0_idx], vmf_hard_mu_0_error))
 
-print '---'
-print 'mu 1: {}'.format(mu_1)
-print 'mu 1: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_1_idx], km_mu_1_error, km_mu_1_error_norm)
-print 'mu 1: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_1_idx], skm_mu_1_error)
-print 'mu 1: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_1_idx], vmf_soft_mu_1_error)
-print 'mu 1: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_1_idx], vmf_hard_mu_1_error)
+print('---')
+print('mu 1: {}'.format(mu_1))
+print('mu 1: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_1_idx], km_mu_1_error, km_mu_1_error_norm))
+print('mu 1: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_1_idx], skm_mu_1_error))
+print('mu 1: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_1_idx], vmf_soft_mu_1_error))
+print('mu 1: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_1_idx], vmf_hard_mu_1_error))
 
 
-print '---'
-print 'true kappas {}'.format(kappas)
-print 'vmf-soft kappas {}'.format(vmf_soft.concentrations_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]])
-print 'vmf-hard kappas {}'.format(vmf_hard.concentrations_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]])
+print('---')
+print('true kappas {}'.format(kappas))
+print('vmf-soft kappas {}'.format(vmf_soft.concentrations_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]]))
+print('vmf-hard kappas {}'.format(vmf_hard.concentrations_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]]))
 
-print '---'
-print 'vmf-soft weights {}'.format(vmf_soft.weights_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]])
-print 'vmf-hard weights {}'.format(vmf_hard.weights_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]])
+print('---')
+print('vmf-soft weights {}'.format(vmf_soft.weights_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]]))
+print('vmf-hard weights {}'.format(vmf_hard.weights_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]]))
 
-print '---'
+print('---')
 print("Homogeneity: %0.3f (k-means)" % metrics.homogeneity_score(labels, km.labels_))
 print("Homogeneity: %0.3f (spherical k-means)" % metrics.homogeneity_score(labels, skm.labels_))
 print("Homogeneity: %0.3f (vmf-soft)" % metrics.homogeneity_score(labels, vmf_soft.labels_))
 print("Homogeneity: %0.3f (vmf-hard)" % metrics.homogeneity_score(labels, vmf_hard.labels_))
 
-print '---'
+print('---')
 print("Completeness: %0.3f (k-means)" % metrics.completeness_score(labels, km.labels_))
 print("Completeness: %0.3f (spherical k-means)" % metrics.completeness_score(labels, skm.labels_))
 print("Completeness: %0.3f" % metrics.completeness_score(labels, vmf_soft.labels_))
 print("Completeness: %0.3f" % metrics.completeness_score(labels, vmf_hard.labels_))
 
-print '---'
+print('---')
 print("V-measure: %0.3f (k-means)" % metrics.v_measure_score(labels, km.labels_))
 print("V-measure: %0.3f (spherical k-means)" % metrics.v_measure_score(labels, skm.labels_))
 print("V-measure: %0.3f (vmf-soft)" % metrics.v_measure_score(labels, vmf_soft.labels_))
 print("V-measure: %0.3f (vmf-hard)" % metrics.v_measure_score(labels, vmf_hard.labels_))
 
-
-raw_input()
+r_input()
diff --git a/examples/small_mix_3d.py b/examples/small_mix_3d.py
@@ -1,19 +1,24 @@
+import sys
 import numpy as np
 from matplotlib import pyplot as plt
 from mpl_toolkits.mplot3d import Axes3D
 from sklearn.cluster import KMeans
 from sklearn import metrics
 
-import sys
-sys.path.append('../spherecluster')
-
 from spherecluster import SphericalKMeans
 from spherecluster import VonMisesFisherMixture
 from spherecluster import sample_vMF
 
 plt.ion()
 
 
+def r_input(val=None):
+    val = val or ''
+    if sys.version_info[0] >= 3:
+        return eval(input(val))
+
+    return raw_input(val)
+
 
 ###############################################################################
 # Generate small-mix dataset
@@ -22,8 +27,8 @@
 mu_1 = np.array([0.399, 0.917, 0.713])
 mu_1 = mu_1 / np.linalg.norm(mu_1)
 mus = [mu_0, mu_1]
-kappa_0 = 8 # concentration parameter
-kappa_1 = 2 # concentration parameter
+kappa_0 = 8  # concentration parameter
+kappa_1 = 2  # concentration parameter
 kappas = [kappa_0, kappa_1]
 num_points_per_class = 300
 
@@ -166,46 +171,45 @@
 plt.show()
 
 
-print 'mu 0: {}'.format(mu_0)
-print 'mu 0: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_0_idx], km_mu_0_error, km_mu_0_error_norm)
-print 'mu 0: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_0_idx], skm_mu_0_error)
-print 'mu 0: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_0_idx], vmf_soft_mu_0_error)
-print 'mu 0: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_0_idx], vmf_hard_mu_0_error)
+print('mu 0: {}'.format(mu_0))
+print('mu 0: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_0_idx], km_mu_0_error, km_mu_0_error_norm))
+print('mu 0: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_0_idx], skm_mu_0_error))
+print('mu 0: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_0_idx], vmf_soft_mu_0_error))
+print('mu 0: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_0_idx], vmf_hard_mu_0_error))
 
-print '---'
-print 'mu 1: {}'.format(mu_1)
-print 'mu 1: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_1_idx], km_mu_1_error, km_mu_1_error_norm)
-print 'mu 1: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_1_idx], skm_mu_1_error)
-print 'mu 1: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_1_idx], vmf_soft_mu_1_error)
-print 'mu 1: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_1_idx], vmf_hard_mu_1_error)
+print('---')
+print('mu 1: {}'.format(mu_1))
+print('mu 1: {} (kmeans), error={} ({})'.format(km.cluster_centers_[km_mu_1_idx], km_mu_1_error, km_mu_1_error_norm))
+print('mu 1: {} (spherical kmeans), error={}'.format(skm.cluster_centers_[skm_mu_1_idx], skm_mu_1_error))
+print('mu 1: {} (vmf-soft), error={}'.format(vmf_soft.cluster_centers_[vmf_soft_mu_1_idx], vmf_soft_mu_1_error))
+print('mu 1: {} (vmf-hard), error={}'.format(vmf_hard.cluster_centers_[vmf_hard_mu_1_idx], vmf_hard_mu_1_error))
 
 
-print '---'
-print 'true kappas {}'.format(kappas)
-print 'vmf-soft kappas {}'.format(vmf_soft.concentrations_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]])
-print 'vmf-hard kappas {}'.format(vmf_hard.concentrations_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]])
+print('---')
+print('true kappas {}'.format(kappas))
+print('vmf-soft kappas {}'.format(vmf_soft.concentrations_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]]))
+print('vmf-hard kappas {}'.format(vmf_hard.concentrations_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]]))
 
-print '---'
-print 'vmf-soft weights {}'.format(vmf_soft.weights_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]])
-print 'vmf-hard weights {}'.format(vmf_hard.weights_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]])
+print('---')
+print('vmf-soft weights {}'.format(vmf_soft.weights_[[vmf_soft_mu_0_idx, vmf_soft_mu_1_idx]]))
+print('vmf-hard weights {}'.format(vmf_hard.weights_[[vmf_hard_mu_0_idx, vmf_hard_mu_1_idx]]))
 
-print '---'
+print('---')
 print("Homogeneity: %0.3f (k-means)" % metrics.homogeneity_score(labels, km.labels_))
 print("Homogeneity: %0.3f (spherical k-means)" % metrics.homogeneity_score(labels, skm.labels_))
 print("Homogeneity: %0.3f (vmf-soft)" % metrics.homogeneity_score(labels, vmf_soft.labels_))
 print("Homogeneity: %0.3f (vmf-hard)" % metrics.homogeneity_score(labels, vmf_hard.labels_))
 
-print '---'
+print('---')
 print("Completeness: %0.3f (k-means)" % metrics.completeness_score(labels, km.labels_))
 print("Completeness: %0.3f (spherical k-means)" % metrics.completeness_score(labels, skm.labels_))
 print("Completeness: %0.3f" % metrics.completeness_score(labels, vmf_soft.labels_))
 print("Completeness: %0.3f" % metrics.completeness_score(labels, vmf_hard.labels_))
 
-print '---'
+print('---')
 print("V-measure: %0.3f (k-means)" % metrics.v_measure_score(labels, km.labels_))
 print("V-measure: %0.3f (spherical k-means)" % metrics.v_measure_score(labels, skm.labels_))
 print("V-measure: %0.3f (vmf-soft)" % metrics.v_measure_score(labels, vmf_soft.labels_))
 print("V-measure: %0.3f (vmf-hard)" % metrics.v_measure_score(labels, vmf_hard.labels_))
 
-
-raw_input()
+r_input()
diff --git a/requirements.txt b/requirements.txt
@@ -1,7 +1,4 @@
-scikit-learn==0.17.1
-tabulate==0.7.5
-matplotlib==1.4.3
-seaborn==0.6.0
-pytest==2.9.2
+scikit-learn==0.19.0
+pytest==3.2.1
 numpy
-scipy
+scipy
diff --git a/setup.py b/setup.py
@@ -7,24 +7,25 @@
 
 
 try:
-    import numpy
+    import numpy  # NOQA
 except ImportError:
     print('numpy is required during installation')
     sys.exit(1)
 
 try:
-    import scipy
+    import scipy  # NOQA
 except ImportError:
     print('scipy is required during installation')
     sys.exit(1)
 
-setup(name='spherecluster',
-      version='0.1.2',
-      description='Clustering on the unit hypersphere in scikit-learn.',
-      author='Jason Laska',
-      author_email='[email protected]',
-      packages=find_packages(),
-      install_requires=INSTALL_REQUIRES,
-      url='https://github.com/clara-labs/spherecluster',
-      license='MIT',
-      )
+setup(
+    name='spherecluster',
+    version='0.1.5',
+    description='Clustering on the unit hypersphere in scikit-learn.',
+    author='Jason Laska',
+    author_email='[email protected]',
+    packages=find_packages(),
+    install_requires=INSTALL_REQUIRES,
+    url='https://github.com/clara-labs/spherecluster',
+    license='MIT',
+)
diff --git a/spherecluster/__init__.py b/spherecluster/__init__.py
@@ -1,3 +1,4 @@
+from __future__ import absolute_import
 from .spherical_kmeans import SphericalKMeans
 from .von_mises_fisher_mixture import VonMisesFisherMixture
 from .util import sample_vMF
@@ -6,4 +7,4 @@
     'SphericalKMeans',
     'VonMisesFisherMixture',
     'sample_vMF',
-]
+]