numo-libsvm 0.4.0 → 0.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: '098e529149ba06f54fc8c4949afa2051dd62f856'
-  data.tar.gz: b86c22820135dff7f95c34dfe6517f89d451156f
+  metadata.gz: 4366bf85268dddd0d9717790646f16ba73bfcc5f
+  data.tar.gz: 8bb7e4a8a79b86f4f60c73f7087af628e3d9751f
 SHA512:
-  metadata.gz: 8d3ed02591f622d50203c6552671ebcfa26ead1cf86816e0ae166548981409ef8b6b14bce2a0123e9d3f1abcaf121b52c49e7ee4110ebc3e4a0f4224902c388a
-  data.tar.gz: 56595713d0dccca3f953ee7583f90ca6fb63d83eedb0d6f2878caaacf6c8db859628f82c88e95b5062eabb85316bbe034fa716b86aebd07fc5f414a5f1ccda77
+  metadata.gz: 3beb968e572a1750522d85081feddd124464b4961e03578635b68afab00e69c9003323f5d7e1f983865ceb14842ec733bbe082b3f58fc630b45812a6b4a81692
+  data.tar.gz: a07ff40e86e815fbe11445a7919c8350dd51471e152dcc783e0e71cb641635e8d7dd9e6476c40ee8a60acfe85adfc1125731359b3bf72d7a4222d9dd8ee1def9

data/CHANGELOG.md

@@ -1,3 +1,6 @@
+# 0.5.0
+- Fix to use LIBSVM sparce vector representation for internal processing.
+
 # 0.4.0
 - Add verbose parameter to output learning process messages.
 - Several documentation improvements.

data/ext/numo/libsvm/converter.c

@@ -132,31 +132,65 @@ VALUE svm_nodes_to_nary(struct svm_node** const support_vecs, const int n_suppor
   return v;
 }
 
-struct svm_node** nary_to_svm_nodes(VALUE model_val)
+struct svm_node** nary_to_svm_nodes(VALUE nary_val)
 {
-  int i, j;
-  int n_rows, n_cols;
-  narray_t* model_nary;
-  double* model_pt;
+  int i, j, k;
+  int n_rows, n_cols, n_nonzero_cols;
+  narray_t* nary;
+  double* nary_pt;
   struct svm_node** support_vecs;
 
-  if (model_val == Qnil) return NULL;
+  if (nary_val == Qnil) return NULL;
 
-  GetNArray(model_val, model_nary);
-  n_rows = (int)NA_SHAPE(model_nary)[0];
-  n_cols = (int)NA_SHAPE(model_nary)[1];
+  GetNArray(nary_val, nary);
+  n_rows = (int)NA_SHAPE(nary)[0];
+  n_cols = (int)NA_SHAPE(nary)[1];
 
-  model_pt = (double*)na_get_pointer_for_read(model_val);
+  nary_pt = (double*)na_get_pointer_for_read(nary_val);
   support_vecs = ALLOC_N(struct svm_node*, n_rows);
   for (i = 0; i < n_rows; i++) {
-    support_vecs[i] = ALLOC_N(struct svm_node, n_cols + 1);
+    n_nonzero_cols = 0;
     for (j = 0; j < n_cols; j++) {
-      support_vecs[i][j].index = j + 1;
-      support_vecs[i][j].value = model_pt[i * n_cols + j];
+      if (nary_pt[i * n_cols + j] != 0) {
+        n_nonzero_cols++;
+      }
+    }
+    support_vecs[i] = ALLOC_N(struct svm_node, n_nonzero_cols + 1);
+    for (j = 0, k = 0; j < n_cols; j++) {
+      if (nary_pt[i * n_cols + j] != 0) {
+        support_vecs[i][k].index = j + 1;
+        support_vecs[i][k].value = nary_pt[i * n_cols + j];
+        k++;
+      }
     }
-    support_vecs[i][n_cols].index = -1;
-    support_vecs[i][n_cols].value = 0.0;
+    support_vecs[i][n_nonzero_cols].index = -1;
+    support_vecs[i][n_nonzero_cols].value = 0.0;
   }
 
   return support_vecs;
 }
+
+struct svm_node* dbl_vec_to_svm_node(double* const arr, int const size)
+{
+  int i, j;
+  int n_nonzero_elements;
+  struct svm_node* node;
+
+  n_nonzero_elements = 0;
+  for (i = 0; i < size; i++) {
+    if (arr[i] != 0.0) n_nonzero_elements++;
+  }
+
+  node = ALLOC_N(struct svm_node, n_nonzero_elements + 1);
+  for (i = 0, j = 0; i < size; i++) {
+    if (arr[i] != 0.0) {
+      node[j].index = i + 1;
+      node[j].value = arr[i];
+      j++;
+    }
+  }
+  node[n_nonzero_elements].index = -1;
+  node[n_nonzero_elements].value = 0.0;
+
+  return node;
+}

data/ext/numo/libsvm/converter.h

@@ -14,6 +14,7 @@ double* nary_to_dbl_vec(VALUE vec_val);
 VALUE dbl_mat_to_nary(double** const mat, int const n_rows, int const n_cols);
 double** nary_to_dbl_mat(VALUE mat_val);
 VALUE svm_nodes_to_nary(struct svm_node** const support_vecs, const int n_support_vecs);
-struct svm_node** nary_to_svm_nodes(VALUE model_val);
+struct svm_node** nary_to_svm_nodes(VALUE nary_val);
+struct svm_node* dbl_vec_to_svm_node(double* const arr, int const size);
 
 #endif /* NUMO_LIBSVM_CONVERTER_H */

data/ext/numo/libsvm/libsvmext.c

@@ -254,9 +254,10 @@ VALUE predict(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_hash)
   size_t y_shape[1];
   VALUE y_val;
   double* y_pt;
-  int i, j;
+  int i, j, k;
   int n_samples;
   int n_features;
+  int n_nonzero_features;
 
   /* Obtain C data structures. */
   if (CLASS_OF(x_val) != numo_cDFloat) {
@@ -285,18 +286,12 @@ VALUE predict(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_hash)
   x_pt = (double*)na_get_pointer_for_read(x_val);
 
   /* Predict values. */
-  x_nodes = ALLOC_N(struct svm_node, n_features + 1);
-  x_nodes[n_features].index = -1;
-  x_nodes[n_features].value = 0.0;
   for (i = 0; i < n_samples; i++) {
-    for (j = 0; j < n_features; j++) {
-      x_nodes[j].index = j + 1;
-      x_nodes[j].value = (double)x_pt[i * n_features + j];
-    }
+    x_nodes = dbl_vec_to_svm_node(&x_pt[i * n_features], n_features);
     y_pt[i] = svm_predict(model, x_nodes);
+    xfree(x_nodes);
   }
 
-  xfree(x_nodes);
   xfree_svm_model(model);
   xfree_svm_parameter(param);
 
@@ -368,34 +363,22 @@ VALUE decision_function(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_h
 
   /* Predict values. */
   if (model->param.svm_type == ONE_CLASS || model->param.svm_type == EPSILON_SVR || model->param.svm_type == NU_SVR) {
-    x_nodes = ALLOC_N(struct svm_node, n_features + 1);
-    x_nodes[n_features].index = -1;
-    x_nodes[n_features].value = 0.0;
     for (i = 0; i < n_samples; i++) {
-      for (j = 0; j < n_features; j++) {
-        x_nodes[j].index = j + 1;
-        x_nodes[j].value = (double)x_pt[i * n_features + j];
-      }
+      x_nodes = dbl_vec_to_svm_node(&x_pt[i * n_features], n_features);
       svm_predict_values(model, x_nodes, &y_pt[i]);
+      xfree(x_nodes);
     }
-    xfree(x_nodes);
   } else {
     y_cols = (int)y_shape[1];
     dec_values = ALLOC_N(double, y_cols);
-    x_nodes = ALLOC_N(struct svm_node, n_features + 1);
-    x_nodes[n_features].index = -1;
-    x_nodes[n_features].value = 0.0;
     for (i = 0; i < n_samples; i++) {
-      for (j = 0; j < n_features; j++) {
-        x_nodes[j].index = j + 1;
-        x_nodes[j].value = (double)x_pt[i * n_features + j];
-      }
+      x_nodes = dbl_vec_to_svm_node(&x_pt[i * n_features], n_features);
       svm_predict_values(model, x_nodes, dec_values);
+      xfree(x_nodes);
       for (j = 0; j < y_cols; j++) {
         y_pt[i * y_cols + j] = dec_values[j];
       }
     }
-    xfree(x_nodes);
     xfree(dec_values);
   }
 
@@ -463,20 +446,14 @@ VALUE predict_proba(VALUE self, VALUE x_val, VALUE param_hash, VALUE model_hash)
 
     /* Predict values. */
     probs = ALLOC_N(double, model->nr_class);
-    x_nodes = ALLOC_N(struct svm_node, n_features + 1);
-    x_nodes[n_features].index = -1;
-    x_nodes[n_features].value = 0.0;
     for (i = 0; i < n_samples; i++) {
-      for (j = 0; j < n_features; j++) {
-        x_nodes[j].index = j + 1;
-        x_nodes[j].value = (double)x_pt[i * n_features + j];
-      }
+      x_nodes = dbl_vec_to_svm_node(&x_pt[i * n_features], n_features);
       svm_predict_probability(model, x_nodes, probs);
+      xfree(x_nodes);
       for (j = 0; j < model->nr_class; j++) {
         y_pt[i * model->nr_class + j] = probs[j];
       }
     }
-    xfree(x_nodes);
     xfree(probs);
   }
 

data/ext/numo/libsvm/svm_problem.c

@@ -29,9 +29,12 @@ struct svm_problem* dataset_to_svm_problem(VALUE x_val, VALUE y_val)
   narray_t* x_nary;
   double* x_pt;
   double* y_pt;
-  int i, j;
+  int i, j, k;
   int n_samples;
   int n_features;
+  int n_nonzero_features;
+  int is_padded;
+  int last_feature_id;
 
   GetNArray(x_val, x_nary);
   n_samples = (int)NA_SHAPE(x_nary)[0];
@@ -43,14 +46,40 @@ struct svm_problem* dataset_to_svm_problem(VALUE x_val, VALUE y_val)
   problem->l = n_samples;
   problem->x = ALLOC_N(struct svm_node*, n_samples);
   problem->y = ALLOC_N(double, n_samples);
+
+  is_padded = 0;
   for (i = 0; i < n_samples; i++) {
-    problem->x[i] = ALLOC_N(struct svm_node, n_features + 1);
+    n_nonzero_features = 0;
     for (j = 0; j < n_features; j++) {
-      problem->x[i][j].index = j + 1;
-      problem->x[i][j].value = x_pt[i * n_features + j];
+      if (x_pt[i * n_features + j] != 0.0) {
+        n_nonzero_features += 1;
+        last_feature_id = j + 1;
+      }
+    }
+    if (is_padded == 0 && last_feature_id == n_features) {
+      is_padded = 1;
+    }
+    if (is_padded == 1) {
+      problem->x[i] = ALLOC_N(struct svm_node, n_nonzero_features + 1);
+    } else {
+      problem->x[i] = ALLOC_N(struct svm_node, n_nonzero_features + 2);
+    }
+    for (j = 0, k = 0; j < n_features; j++) {
+      if (x_pt[i * n_features + j] != 0.0) {
+        problem->x[i][k].index = j + 1;
+        problem->x[i][k].value = (double)x_pt[i * n_features + j];
+        k++;
+      }
+    }
+    if (is_padded == 1) {
+      problem->x[i][n_nonzero_features].index = -1;
+      problem->x[i][n_nonzero_features].value = 0.0;
+    } else {
+      problem->x[i][n_nonzero_features].index = n_features;
+      problem->x[i][n_nonzero_features].value = 0.0;
+      problem->x[i][n_nonzero_features + 1].index = -1;
+      problem->x[i][n_nonzero_features + 1].value = 0.0;
     }
-    problem->x[i][n_features].index = -1;
-    problem->x[i][n_features].value = 0.0;
     problem->y[i] = y_pt[i];
   }
 

data/lib/numo/libsvm/version.rb

@@ -3,6 +3,6 @@
 module Numo
   module Libsvm
     # The version of Numo::Libsvm you are using.
-    VERSION = '0.4.0'
+    VERSION = '0.5.0'
   end
 end

data/numo-libsvm.gemspec

@@ -33,6 +33,12 @@ Gem::Specification.new do |spec|
   spec.require_paths = ['lib']
   spec.extensions    = ['ext/numo/libsvm/extconf.rb']
 
+  spec.metadata      = {
+    'homepage_uri' => 'https://github.com/yoshoku/numo-libsvm',
+    'source_code_uri' => 'https://github.com/yoshoku/numo-libsvm',
+    'documentation_uri' => 'https://yoshoku.github.io/numo-libsvm/doc/'
+  }
+
   spec.add_runtime_dependency 'numo-narray', '~> 0.9.1'
   spec.add_development_dependency 'bundler', '~> 2.0'
   spec.add_development_dependency 'rake', '~> 10.0'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: numo-libsvm
 version: !ruby/object:Gem::Version
-  version: 0.4.0
+  version: 0.5.0
 platform: ruby
 authors:
 - yoshoku
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2019-09-01 00:00:00.000000000 Z
+date: 2019-09-23 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: numo-narray
@@ -122,7 +122,10 @@ files:
 homepage: https://github.com/yoshoku/numo-libsvm
 licenses:
 - BSD-3-Clause
-metadata: {}
+metadata:
+  homepage_uri: https://github.com/yoshoku/numo-libsvm
+  source_code_uri: https://github.com/yoshoku/numo-libsvm
+  documentation_uri: https://yoshoku.github.io/numo-libsvm/doc/
 post_install_message: 
 rdoc_options: []
 require_paths: