more

.devel/pytest/test_approx.py

@@ -14,7 +14,7 @@
     import rpy2
     from rpy2.robjects.packages import importr
     import rpy2.robjects.numpy2ri
-    rpy2.robjects.numpy2ri.activate()
+    #rpy2.robjects.numpy2ri.activate()
     stats = importr("stats")
     genie = importr("genie")
 except:

.devel/pytest/test_cache.py

@@ -10,7 +10,7 @@
     import rpy2
     from rpy2.robjects.packages import importr
     import rpy2.robjects.numpy2ri
-    rpy2.robjects.numpy2ri.activate()
+    #rpy2.robjects.numpy2ri.activate()
     stats = importr("stats")
     genie = importr("genie")
 except:

.devel/pytest/test_cvi.py

@@ -20,8 +20,8 @@ def test_cvi():
     try:
         import rpy2
         from rpy2.robjects.packages import importr
-        import rpy2.robjects.numpy2ri
-        rpy2.robjects.numpy2ri.activate()
+        from rpy2.robjects import numpy2ri
+        from rpy2.robjects import default_converter
 
         r_base = importr("base")
         lib_loc = r_base.Sys_getenv("R_LIBS_USER")[0]
@@ -33,54 +33,56 @@ def test_cvi():
         print("ImportError")
         return
 
-    for dataset in ["s1", "Aggregation", "unbalance", "h2mg_64_50"]:
-        X = np.loadtxt("%s/%s.data.gz" % (path,dataset), ndmin=2)
-        labels = np.loadtxt("%s/%s.labels0.gz" % (path,dataset), dtype=np.intp)
+    np_cv_rules = default_converter + numpy2ri.converter
+    with np_cv_rules.context():
+        for dataset in ["s1", "Aggregation", "unbalance", "h2mg_64_50"]:
+            X = np.loadtxt("%s/%s.data.gz" % (path,dataset), ndmin=2)
+            labels = np.loadtxt("%s/%s.labels0.gz" % (path,dataset), dtype=np.intp)
 
-        X = (X-X.mean(axis=0))/X.std(axis=None, ddof=1)
-        X += np.random.normal(0, 0.0001, X.shape)
+            X = (X-X.mean(axis=0))/X.std(axis=None, ddof=1)
+            X += np.random.normal(0, 0.0001, X.shape)
 
-        i1 = r_genieclust.calinski_harabasz_index(X, labels)[0]
-        i2 = genieclust.cluster_validity.calinski_harabasz_index(X, labels-1)
-        assert i1 == i2
+            i1 = r_genieclust.calinski_harabasz_index(X, labels)[0]
+            i2 = genieclust.cluster_validity.calinski_harabasz_index(X, labels-1)
+            assert i1 == i2
 
-        i1 = r_genieclust.negated_ball_hall_index(X, labels)[0]
-        i2 = genieclust.cluster_validity.negated_ball_hall_index(X, labels-1)
-        assert i1 == i2
+            i1 = r_genieclust.negated_ball_hall_index(X, labels)[0]
+            i2 = genieclust.cluster_validity.negated_ball_hall_index(X, labels-1)
+            assert i1 == i2
 
-        i1 = r_genieclust.negated_davies_bouldin_index(X, labels)[0]
-        i2 = genieclust.cluster_validity.negated_davies_bouldin_index(X, labels-1)
-        assert i1 == i2
+            i1 = r_genieclust.negated_davies_bouldin_index(X, labels)[0]
+            i2 = genieclust.cluster_validity.negated_davies_bouldin_index(X, labels-1)
+            assert i1 == i2
 
-        i1 = r_genieclust.negated_wcss_index(X, labels)[0]
-        i2 = genieclust.cluster_validity.negated_wcss_index(X, labels-1)
-        assert i1 == i2
+            i1 = r_genieclust.negated_wcss_index(X, labels)[0]
+            i2 = genieclust.cluster_validity.negated_wcss_index(X, labels-1)
+            assert i1 == i2
 
-        i1 = r_genieclust.silhouette_index(X, labels)[0]
-        i2 = genieclust.cluster_validity.silhouette_index(X, labels-1)
-        assert i1 == i2
+            i1 = r_genieclust.silhouette_index(X, labels)[0]
+            i2 = genieclust.cluster_validity.silhouette_index(X, labels-1)
+            assert i1 == i2
 
-        i1 = r_genieclust.silhouette_w_index(X, labels)[0]
-        i2 = genieclust.cluster_validity.silhouette_w_index(X, labels-1)
-        assert i1 == i2
+            i1 = r_genieclust.silhouette_w_index(X, labels)[0]
+            i2 = genieclust.cluster_validity.silhouette_w_index(X, labels-1)
+            assert i1 == i2
 
-        i1 = r_genieclust.generalised_dunn_index(X, labels, 4, 2)[0]
-        i2 = genieclust.cluster_validity.generalised_dunn_index(X, labels-1, 4, 2)
-        assert i1 == i2
+            i1 = r_genieclust.generalised_dunn_index(X, labels, 4, 2)[0]
+            i2 = genieclust.cluster_validity.generalised_dunn_index(X, labels-1, 4, 2)
+            assert i1 == i2
 
-        i1 = r_genieclust.wcnn_index(X, labels, 5)[0]
-        i2 = genieclust.cluster_validity.wcnn_index(X, labels-1, 5)
-        assert i1 == i2
+            i1 = r_genieclust.wcnn_index(X, labels, 5)[0]
+            i2 = genieclust.cluster_validity.wcnn_index(X, labels-1, 5)
+            assert i1 == i2
 
-        i1 = r_genieclust.dunnowa_index(X, labels, 10, "SMin:5", "Max")[0]
-        i2 = genieclust.cluster_validity.dunnowa_index(X, labels-1, 10, "SMin:5", "Max")
-        assert i1 == i2
+            i1 = r_genieclust.dunnowa_index(X, labels, 10, "SMin:5", "Max")[0]
+            i2 = genieclust.cluster_validity.dunnowa_index(X, labels-1, 10, "SMin:5", "Max")
+            assert i1 == i2
 
-        #double c_dunnowa_index
+            #double c_dunnowa_index
 
-        #double c_generalised_dunn_index
+            #double c_generalised_dunn_index
 
-        #double c_wcnn_index
+            #double c_wcnn_index
 
 
 

.devel/pytest/test_genie.py

@@ -9,8 +9,9 @@
 try:
     import rpy2
     from rpy2.robjects.packages import importr
-    import rpy2.robjects.numpy2ri
-    rpy2.robjects.numpy2ri.activate()
+    from rpy2.robjects import numpy2ri
+    from rpy2.robjects import default_converter
+    #rpy2.robjects.numpy2ri.activate()
     stats = importr("stats")
     genie = importr("genie")
 except:
@@ -39,69 +40,71 @@
 
 
 def __test_genie(metric='euclidean'):
-    for dataset in ["s1", "Aggregation", "unbalance", "h2mg_64_50", "bigger"]:#, "h2mg_1024_50", "t4_8k", "bigger"]:
-        if dataset == "bigger":
-            np.random.seed(123)
-            n = 10_000
-            d = 10
-            K = 2
-            X = np.random.normal(size=(n,d))
-            labels = np.random.choice(np.r_[0:K], n)
-        else:
-            X = np.loadtxt("%s/%s.data.gz" % (path,dataset), ndmin=2)
-            labels = np.loadtxt("%s/%s.labels0.gz" % (path,dataset), dtype=np.intp)-1
-
-        k = len(np.unique(labels[labels>=0]))
-
-        # center X + scale (NOT: standardize!)
-        X = (X-X.mean(axis=0))/X.std(axis=None, ddof=1)
-        X += np.random.normal(0, 0.0001, X.shape)
-
-        #t01 = time.time()
-        #hdbscan.RobustSingleLinkage().fit_predict(X)
-        #t11 = time.time()
-        #print("t_robustsl=%.3f" % (t11-t01), end="\t")
-
-        #t01 = time.time()
-        #hdbscan.HDBSCAN().fit_predict(X)
-        #t11 = time.time()
-        #print("t_hdbscan=%.3f" % (t11-t01), end="\t")
-
-        for g in [0.01, 0.3, 0.5, 0.7, 1.0]:
-            gc.collect()
-
-            #D = scipy.spatial.distance.pdist(X)
-            #D = scipy.spatial.distance.squareform(D)
-
-            print("%-20s g=%.2f n=%5d d=%2d"%(dataset,g,X.shape[0],X.shape[1]), end="\t")
-
-            t01 = time.time()
-            _res1 = genieclust.Genie(
-                k, gini_threshold=g, exact=True, affinity=metric, compute_full_tree=True)
-            res1 = _res1.fit_predict(X)+1
-            t11 = time.time()
-            print("t_py=%.3f" % (t11-t01), end="\t")
-
-            assert np.all(np.diff(_res1.distances_)>= 0.0)
-            assert len(np.unique(res1)) == k
-
-            if stats is not None and genie is not None and metric != 'cosine':
-                t02 = time.time()
-                res2 = stats.cutree(genie.hclust2(objects=X, d=metric, thresholdGini=g), k)
-                t12 = time.time()
-                print("t_r=%.3f" % (t12-t02), end="\t")
-                res2 = np.array(res2, np.intp)
-                assert len(np.unique(res2)) == k
-
-                ari = genieclust.compare_partitions.adjusted_rand_score(res1, res2)
-                print("ARI=%.3f" % ari, end="\t")
-                assert ari>1.0-1e-12
-
-                print("t_rel=%.3f" % ((t11-t01)/(t12-t02),), end="\t")
-
-
-            res1, res2 = None, None
-            print("")
+    np_cv_rules = default_converter + numpy2ri.converter
+    with np_cv_rules.context():
+        for dataset in ["s1", "Aggregation", "unbalance", "h2mg_64_50", "bigger"]:#, "h2mg_1024_50", "t4_8k", "bigger"]:
+            if dataset == "bigger":
+                np.random.seed(123)
+                n = 10_000
+                d = 10
+                K = 2
+                X = np.random.normal(size=(n,d))
+                labels = np.random.choice(np.r_[0:K], n)
+            else:
+                X = np.loadtxt("%s/%s.data.gz" % (path,dataset), ndmin=2)
+                labels = np.loadtxt("%s/%s.labels0.gz" % (path,dataset), dtype=np.intp)-1
+
+            k = len(np.unique(labels[labels>=0]))
+
+            # center X + scale (NOT: standardize!)
+            X = (X-X.mean(axis=0))/X.std(axis=None, ddof=1)
+            X += np.random.normal(0, 0.0001, X.shape)
+
+            #t01 = time.time()
+            #hdbscan.RobustSingleLinkage().fit_predict(X)
+            #t11 = time.time()
+            #print("t_robustsl=%.3f" % (t11-t01), end="\t")
+
+            #t01 = time.time()
+            #hdbscan.HDBSCAN().fit_predict(X)
+            #t11 = time.time()
+            #print("t_hdbscan=%.3f" % (t11-t01), end="\t")
+
+            for g in [0.01, 0.3, 0.5, 0.7, 1.0]:
+                gc.collect()
+
+                #D = scipy.spatial.distance.pdist(X)
+                #D = scipy.spatial.distance.squareform(D)
+
+                print("%-20s g=%.2f n=%5d d=%2d"%(dataset,g,X.shape[0],X.shape[1]), end="\t")
+
+                t01 = time.time()
+                _res1 = genieclust.Genie(
+                    k, gini_threshold=g, exact=True, affinity=metric, compute_full_tree=True)
+                res1 = _res1.fit_predict(X)+1
+                t11 = time.time()
+                print("t_py=%.3f" % (t11-t01), end="\t")
+
+                assert np.all(np.diff(_res1.distances_)>= 0.0)
+                assert len(np.unique(res1)) == k
+
+                if stats is not None and genie is not None and metric != 'cosine':
+                    t02 = time.time()
+                    res2 = stats.cutree(genie.hclust2(objects=X, d=metric, thresholdGini=g), k)
+                    t12 = time.time()
+                    print("t_r=%.3f" % (t12-t02), end="\t")
+                    res2 = np.array(res2, np.intp)
+                    assert len(np.unique(res2)) == k
+
+                    ari = genieclust.compare_partitions.adjusted_rand_score(res1, res2)
+                    print("ARI=%.3f" % ari, end="\t")
+                    assert ari>1.0-1e-12
+
+                    print("t_rel=%.3f" % ((t11-t01)/(t12-t02),), end="\t")
+
+
+                res1, res2 = None, None
+                print("")
 
 
 

.devel/pytest/test_inequality.py

@@ -39,19 +39,19 @@ def devergottini_ref(x):
                 x = np.random.random(n)*8 + 3
 
             xg1 = gini_index(np.array(x))
-            xg2 = gini_index(np.array(x, dtype=np.float_))
+            xg2 = gini_index(np.array(x, dtype=np.float64))
             xg3 = gini_ref(x)
             assert abs(xg1 - xg2) < 1e-9
             assert abs(xg1 - xg3) < 1e-9
 
             xb1 = bonferroni_index(np.array(x))
-            xb2 = bonferroni_index(np.array(x, dtype=np.float_))
+            xb2 = bonferroni_index(np.array(x, dtype=np.float64))
             xb3 = bonferroni_ref(x)
             assert abs(xb1 - xb2) < 1e-9
             assert abs(xb1 - xb3) < 1e-9
 
             xv1 = devergottini_index(np.array(x))
-            xv2 = devergottini_index(np.array(x, dtype=np.float_))
+            xv2 = devergottini_index(np.array(x, dtype=np.float64))
             xv3 = devergottini_ref(x)
             assert abs(xv1 - xv2) < 1e-9
             assert abs(xv1 - xv3) < 1e-9

.devel/pytest/test_warnerr.py

@@ -12,7 +12,7 @@
     import rpy2
     from rpy2.robjects.packages import importr
     import rpy2.robjects.numpy2ri
-    rpy2.robjects.numpy2ri.activate()
+    #rpy2.robjects.numpy2ri.activate()
     stats = importr("stats")
     genie = importr("genie")
 except ImportError:

.devel/sandbox_approx.py

@@ -23,7 +23,7 @@
 genie = importr("genie")
 import numpy as np
 import rpy2.robjects.numpy2ri
-rpy2.robjects.numpy2ri.activate()
+#rpy2.robjects.numpy2ri.activate()
 import time
 import gc
 np.random.seed(12345)

.devel/sandbox_parallel.py

@@ -13,7 +13,7 @@
 genieclustr = importr("genieclust")
 import numpy as np
 import rpy2.robjects.numpy2ri
-rpy2.robjects.numpy2ri.activate()
+#rpy2.robjects.numpy2ri.activate()
 
 
 verbose = False