32 init(file, is_labelled, size);
38 if (parser.is_running())
45 ASSERT(index>=0 && index<current_num_features)
46 return current_sgvector.get_feature(index);
58 int32_t n=current_num_features;
60 current_num_features=num;
85 ASSERT(dim>=current_num_features)
87 return current_sgvector.dense_dot(alpha, vec, dim, b);
95 int32_t current_length = current_sgvector.num_feat_entries;
101 for (int32_t i=0; i<current_length; i++) {
102 if (current_vector[i].feat_index < vec2_len) {
116 int32_t current_length = current_sgvector.num_feat_entries;
122 for (int32_t i=0; i<current_length; i++) {
123 if (current_vector[i].feat_index < vec2_len) {
136 if (vec2_len < current_num_features)
138 SG_ERROR(
"dimension of vec (=%d) does not match number of features (=%d)\n",
139 vec2_len, current_num_features);
143 int32_t num_feat=current_sgvector.num_feat_entries;
149 for (int32_t i=0; i<num_feat; i++)
150 vec2[sv[i].feat_index]+= alpha*
CMath::abs(sv[i].entry);
154 for (int32_t i=0; i<num_feat; i++)
155 vec2[sv[i].feat_index]+= alpha*sv[i].entry;
164 if (vec2_len < current_num_features)
166 SG_ERROR(
"dimension of vec (=%d) does not match number of features (=%d)\n",
167 vec2_len, current_num_features);
171 int32_t num_feat=current_sgvector.num_feat_entries;
177 for (int32_t i=0; i<num_feat; i++)
178 vec2[sv[i].feat_index]+= alpha*
CMath::abs(sv[i].entry);
182 for (int32_t i=0; i<num_feat; i++)
183 vec2[sv[i].feat_index]+= alpha*sv[i].entry;
191 return current_sgvector.num_feat_entries;
197 int32_t current_length = current_sgvector.num_feat_entries;
204 for (int32_t i=0; i<current_length; i++)
205 sq += current_vector[i].entry * current_vector[i].entry;
217 get_vector().sort_features(
true);
219 ASSERT(old_ptr == current_sgvector.features);
231 if (current_sgvector.features)
243 parser.set_read_vector_and_label
247 #define GET_FEATURE_TYPE(f_type, sg_type) \
248 template<> EFeatureType CStreamingSparseFeatures<sg_type>::get_feature_type() const \
266 #undef GET_FEATURE_TYPE
270 void CStreamingSparseFeatures<T>::init()
274 current_num_features=-1;
280 void CStreamingSparseFeatures<T>::init(CStreamingFile* file,
285 has_labels = is_labelled;
288 parser.init(file, is_labelled, size);
289 parser.set_free_vector_after_release(
false);
295 if (!parser.is_running())
296 parser.start_parser();
308 int32_t current_length = 0;
312 ret_value = (bool) parser.get_next_example(current_vector,
324 current_num_features =
CMath::max(current_num_features, current_dimension);
333 return current_sgvector;
341 return current_label;
347 parser.finalize_example();
353 return current_num_features;
366 return current_num_features;
372 return current_sgvector.num_feat_entries;
virtual void set_vector_reader()
T sparse_dot(const SGSparseVector< T > &v)
int64_t get_num_nonzero_entries()
T get_feature(int32_t index)
#define SG_NOTIMPLEMENTED
virtual void add_to_dense_vec(float64_t alpha, float64_t *vec2, int32_t vec2_len, bool abs_val=false)
virtual void start_parser()
SGSparseVector< T > get_vector()
virtual int32_t get_num_features()
CStreamingSparseFeatures()
static T sparse_dot(T alpha, SGSparseVectorEntry< T > *avec, int32_t alen, SGSparseVectorEntry< T > *bvec, int32_t blen)
EFeatureClass
shogun feature class
virtual void reset_stream()
float32_t compute_squared()
A Streaming File access class.
virtual float32_t dot(CStreamingDotFeatures *df)
virtual int32_t get_nnz_features_for_vector()
virtual int32_t get_dim_feature_space() const
virtual void get_sparse_vector_and_label(SGSparseVectorEntry< bool > *&vector, int32_t &len, float64_t &label)
virtual CFeatures * duplicate() const
Streaming features that support dot products among other operations.
virtual int32_t get_num_vectors() const
virtual EFeatureClass get_feature_class() const
all of classes and functions are contained in the shogun namespace
virtual float64_t get_label()
void set_read_functions()
virtual void end_parser()
virtual void get_sparse_vector(SGSparseVectorEntry< bool > *&vector, int32_t &len)
template class SGSparseVectorEntry
virtual bool get_next_example()
int32_t set_num_features(int32_t num)
The class Features is the base class of all feature objects.
template class SGSparseVector The assumtion is that the stored SGSparseVectorEntry* vector is orde...
#define GET_FEATURE_TYPE(f_type, sg_type)
virtual void set_vector_and_label_reader()
int32_t get_num_dimensions()
T dense_dot(T alpha, T *vec, int32_t dim, T b)
This class implements streaming features with sparse feature vectors. The vector is represented as an...
virtual void release_example()
virtual ~CStreamingSparseFeatures()