Adapt python examples to new transformer api

shogun-toolbox · Jun 8, 2018 · 6636bf4 · 6636bf4
1 parent 203f260
commit 6636bf4
Show file tree

Hide file tree

Showing 18 changed files with 57 additions and 85 deletions.
diff --git a/examples/undocumented/python/distance_canberraword.py b/examples/undocumented/python/distance_canberraword.py
@@ -17,17 +17,15 @@ def distance_canberraword (fm_train_dna=traindna,fm_test_dna=testdna,order=3,gap
 	charfeat.set_features(fm_train_dna)
 	feats_train=StringWordFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	preproc=SortWordString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
+	preproc = SortWordString()
+	preproc.fit(feats_train)
+	feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(DNA)
 	charfeat.set_features(fm_test_dna)
 	feats_test=StringWordFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	feats_test = preproc.apply(feats_test)
 
 	distance=CanberraWordDistance(feats_train, feats_train)
 

diff --git a/examples/undocumented/python/distance_hammingword.py b/examples/undocumented/python/distance_hammingword.py
@@ -21,16 +21,14 @@ def distance_hammingword (fm_train_dna=traindna,fm_test_dna=testdna,
 	feats_train=StringWordFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
 	preproc=SortWordString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
+	preproc.fit(feats_train)
+	feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(DNA)
 	charfeat.set_features(fm_test_dna)
 	feats_test=StringWordFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	feats_test = preproc.apply(feats_test)
 
 	distance=HammingWordDistance(feats_train, feats_train, use_sign)
 

diff --git a/examples/undocumented/python/distance_manhattenword.py b/examples/undocumented/python/distance_manhattenword.py
@@ -11,16 +11,14 @@ def distance_manhattenword (train_fname=traindna,test_fname=testdna,order=3,gap=
 	charfeat=StringCharFeatures(CSVFile(train_fname), DNA)
 	feats_train=StringWordFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	preproc=SortWordString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
+	preproc = SortWordString()
+	preproc.fit(feats_train)
+	feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(CSVFile(test_fname), DNA)
 	feats_test=StringWordFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	feats_test = preproc.apply(feats_test)
 
 	distance=ManhattanWordDistance(feats_train, feats_train)
 

diff --git a/examples/undocumented/python/kernel_comm_ulong_string.py b/examples/undocumented/python/kernel_comm_ulong_string.py
@@ -16,18 +16,15 @@ def kernel_comm_ulong_string (fm_train_dna=traindat,fm_test_dna=testdat, order=3
 	charfeat.set_features(fm_train_dna)
 	feats_train=StringUlongFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	preproc=SortUlongString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
-
+	preproc = SortUlongString()
+	preproc.fit(feats_train)
+	feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(DNA)
 	charfeat.set_features(fm_test_dna)
 	feats_test=StringUlongFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	feats_test = preproc.apply(feats_test)
 
 	use_sign=False
 

diff --git a/examples/undocumented/python/kernel_comm_word_string.py b/examples/undocumented/python/kernel_comm_word_string.py
@@ -16,17 +16,15 @@ def kernel_comm_word_string (fm_train_dna=traindat, fm_test_dna=testdat, order=3
 	charfeat.set_features(fm_train_dna)
 	feats_train=StringWordFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	preproc=SortWordString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
+	preproc = SortWordString()
+	preproc.fit(feats_train)
+	feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(DNA)
 	charfeat.set_features(fm_test_dna)
 	feats_test=StringWordFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	feats_test = preproc.apply(feats_test)
 
 	kernel=CommWordStringKernel(feats_train, feats_train, use_sign)
 

diff --git a/examples/undocumented/python/kernel_weighted_comm_word_string.py b/examples/undocumented/python/kernel_weighted_comm_word_string.py
@@ -14,16 +14,14 @@ def kernel_weighted_comm_word_string (fm_train_dna=traindat,fm_test_dna=testdat,
 	charfeat=StringCharFeatures(fm_train_dna, DNA)
 	feats_train=StringWordFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	preproc=SortWordString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
+	preproc = SortWordString()
+	preproc.fit(feats_train)
+	feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(fm_test_dna, DNA)
 	feats_test=StringWordFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	feats_test = preproc.apply(feats_test)
 
 	use_sign=False
 	kernel=WeightedCommWordStringKernel(feats_train, feats_train, use_sign)

diff --git a/examples/undocumented/python/preprocessor_dimensionreductionpreprocessor.py b/examples/undocumented/python/preprocessor_dimensionreductionpreprocessor.py
@@ -21,8 +21,8 @@ def preprocessor_dimensionreductionpreprocessor (data, k):
 	converter.set_k(k)
 
 	preprocessor = DimensionReductionPreprocessor(converter)
-	preprocessor.init(features)
-	preprocessor.apply_to_feature_matrix(features)
+	preprocessor.fit(features)
+	features = preprocessor.apply(features)
 
 	return features
 

diff --git a/examples/undocumented/python/preprocessor_fisherlda.py b/examples/undocumented/python/preprocessor_fisherlda.py
@@ -17,9 +17,9 @@ def preprocessor_fisherlda (data, labels, method):
 	sg_features = RealFeatures(data)
 	sg_labels = MulticlassLabels(labels)
 
-	preprocessor=FisherLda(method)
-	preprocessor.fit(sg_features, sg_labels, 1)
-	yn=preprocessor.apply_to_feature_matrix(sg_features)
+	preprocessor=FisherLda(1, method)
+	preprocessor.fit(sg_features, sg_labels)
+	yn = preprocessor.apply(sg_features).get_real_matrix('feature_matrix')
 
 	return yn
 

diff --git a/examples/undocumented/python/preprocessor_kernelpca.py b/examples/undocumented/python/preprocessor_kernelpca.py
@@ -16,9 +16,9 @@ def preprocessor_kernelpca (data, threshold, width):
 	kernel = GaussianKernel(features,features,width)
 
 	preprocessor = KernelPCA(kernel)
-	preprocessor.init(features)
+	preprocessor.fit(features)
 	preprocessor.set_target_dim(2)
-	preprocessor.apply_to_feature_matrix(features)
+	features = preprocessor.apply(features)
 
 	return features
 

diff --git a/examples/undocumented/python/preprocessor_logplusone.py b/examples/undocumented/python/preprocessor_logplusone.py
@@ -16,13 +16,10 @@ def preprocessor_logplusone (fm_train_real=traindat,fm_test_real=testdat,width=1
 	feats_train=RealFeatures(fm_train_real)
 	feats_test=RealFeatures(fm_test_real)
 
-	preproc=LogPlusOne()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
-
+	preproc = LogPlusOne()
+	preproc.fit(feats_train)
+        feats_train = preproc.apply(feats_train)
+        feats_test = preproc.apply(feats_test)
 
 	kernel=Chi2Kernel(feats_train, feats_train, width, size_cache)
 

diff --git a/examples/undocumented/python/preprocessor_normone.py b/examples/undocumented/python/preprocessor_normone.py
@@ -17,11 +17,9 @@ def preprocessor_normone (fm_train_real=traindat,fm_test_real=testdat,width=1.4,
 	feats_test=RealFeatures(fm_test_real)
 
 	preprocessor=NormOne()
-	preprocessor.init(feats_train)
-	feats_train.add_preprocessor(preprocessor)
-	feats_train.apply_preprocessor()
-	feats_test.add_preprocessor(preprocessor)
-	feats_test.apply_preprocessor()
+	preprocessor.fit(feats_train)
+        feats_train = preprocessor.apply(feats_train)
+        feats_test = preprocessor.apply(feats_test)
 
 	kernel=Chi2Kernel(feats_train, feats_train, width, size_cache)
 

diff --git a/examples/undocumented/python/preprocessor_pca.py b/examples/undocumented/python/preprocessor_pca.py
@@ -13,8 +13,8 @@ def preprocessor_pca (data):
 	features = RealFeatures(data)
 
 	preprocessor = PCA()
-	preprocessor.init(features)
-	preprocessor.apply_to_feature_matrix(features)
+	preprocessor.fit(features)
+	features = preprocessor.apply(features)
 
 	return features
 

diff --git a/examples/undocumented/python/preprocessor_prunevarsubmean.py b/examples/undocumented/python/preprocessor_prunevarsubmean.py
@@ -16,11 +16,9 @@ def preprocessor_prunevarsubmean (fm_train_real=traindat,fm_test_real=testdat,wi
 	feats_test=RealFeatures(fm_test_real)
 
 	preproc=PruneVarSubMean()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	preproc.fit(feats_train)
+        feats_train = preproc.apply(feats_train)
+        feats_test = preproc.apply(feats_test)
 
 	kernel=Chi2Kernel(feats_train, feats_train, width, size_cache)
 

diff --git a/examples/undocumented/python/preprocessor_randomfouriergausspreproc.py b/examples/undocumented/python/preprocessor_randomfouriergausspreproc.py
@@ -19,11 +19,9 @@ def preprocessor_randomfouriergausspreproc (fm_train_real=traindat,fm_test_real=
 	feats_test=RealFeatures(fm_test_real)
 
 	preproc=RandomFourierGaussPreproc()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	preproc.fit(feats_train)
+        feats_train = preproc.apply(feats_train)
+        feats_test = preproc.apply(feats_test)
 
 	kernel=Chi2Kernel(feats_train, feats_train, width, size_cache)
 

diff --git a/examples/undocumented/python/preprocessor_sortulongstring.py b/examples/undocumented/python/preprocessor_sortulongstring.py
@@ -24,12 +24,10 @@ def preprocessor_sortulongstring (fm_train_dna=traindna,fm_test_dna=testdna,orde
 	feats_test=StringUlongFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
 
-	preproc=SortUlongString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+	preproc = SortUlongString()
+	preproc.fit(feats_train)
+        feats_train = preproc.apply(feats_train)
+        feats_test = preproc.apply(feats_test)
 
 	kernel=CommUlongStringKernel(feats_train, feats_train, use_sign)
 

diff --git a/examples/undocumented/python/preprocessor_sortwordstring.py b/examples/undocumented/python/preprocessor_sortwordstring.py
@@ -16,16 +16,14 @@ def preprocessor_sortwordstring (fm_train_dna=traindna,fm_test_dna=testdna,order
 	charfeat=StringCharFeatures(fm_train_dna, DNA)
 	feats_train=StringWordFeatures(charfeat.get_alphabet())
 	feats_train.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	preproc=SortWordString()
-	preproc.init(feats_train)
-	feats_train.add_preprocessor(preproc)
-	feats_train.apply_preprocessor()
+	preproc = SortWordString()
+	preproc.fit(feats_train)
+        feats_train = preproc.apply(feats_train)
 
 	charfeat=StringCharFeatures(fm_test_dna, DNA)
 	feats_test=StringWordFeatures(charfeat.get_alphabet())
 	feats_test.obtain_from_char(charfeat, order-1, order, gap, reverse)
-	feats_test.add_preprocessor(preproc)
-	feats_test.apply_preprocessor()
+        feats_test = preproc.apply(feats_test)
 
 	kernel=CommWordStringKernel(feats_train, feats_train, use_sign)
 

diff --git a/examples/undocumented/python/serialization_string_kernels.py b/examples/undocumented/python/serialization_string_kernels.py
@@ -105,9 +105,8 @@ def get_spectrum_features(data, order=3, gap=0, reverse=True):
     feat = StringWordFeatures(charfeat.get_alphabet())
     feat.obtain_from_char(charfeat, order-1, order, gap, reverse)
     preproc = SortWordString()
-    preproc.init(feat)
-    feat.add_preprocessor(preproc)
-    feat.apply_preprocessor()
+    preproc.fit(feat)
+    feat = preproc.apply(feat)
 
     return feat
 

diff --git a/examples/undocumented/python/tests_check_commwordkernel_memleak.py b/examples/undocumented/python/tests_check_commwordkernel_memleak.py
@@ -66,9 +66,8 @@ def tests_check_commwordkernel_memleak (num, order, gap, reverse):
 		#trainudat.io.set_loglevel(MSG_DEBUG)
 		pre = SortWordString()
 		#pre.io.set_loglevel(MSG_DEBUG)
-		pre.init(trainudat)
-		trainudat.add_preprocessor(pre)
-		trainudat.apply_preprocessor()
+		pre.fit(trainudat)
+		trainudat = pre.apply(trainudat)
 		spec = CommWordStringKernel(10, False)
 		spec.set_normalizer(IdentityKernelNormalizer())
 		spec.init(trainudat, trainudat)