StreamingSparseFeatures.h

Go to the documentation of this file.

/*
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 3 of the License, or
 * (at your option) any later version.
 *
 * Written (W) 2011 Shashwat Lal Das
 * Copyright (C) 2011 Berlin Institute of Technology and Max-Planck-Society
 */
#ifndef _STREAMING_SPARSEFEATURES__H__
#define _STREAMING_SPARSEFEATURES__H__

#include <shogun/lib/common.h>
#include <shogun/mathematics/Math.h>
#include <shogun/features/streaming/StreamingDotFeatures.h>
#include <shogun/lib/DataType.h>
#include <shogun/io/streaming/InputParser.h>

namespace shogun
{
template <class T> class CStreamingSparseFeatures : public CStreamingDotFeatures
{
public:

    CStreamingSparseFeatures();

    CStreamingSparseFeatures(CStreamingFile* file,
                 bool is_labelled,
                 int32_t size);

    ~CStreamingSparseFeatures();

    virtual void set_vector_reader();

    virtual void set_vector_and_label_reader();

    virtual void start_parser();

    virtual void end_parser();

    virtual bool get_next_example();

    T get_feature(int32_t index);

    SGSparseVector<T> get_vector();

    virtual float64_t get_label();

    virtual void release_example();

    virtual void reset_stream();

    int32_t set_num_features(int32_t num);

    virtual int32_t get_dim_feature_space() const;

    virtual void expand_if_required(float32_t*& vec, int32_t &len);

    virtual void expand_if_required(float64_t*& vec, int32_t &len);

    virtual float32_t dot(CStreamingDotFeatures *df);

    static T sparse_dot(T alpha, SGSparseVectorEntry<T>* avec, int32_t alen, SGSparseVectorEntry<T>* bvec, int32_t blen);

    T dense_dot(T alpha, T* vec, int32_t dim, T b);

    virtual float64_t dense_dot(const float64_t* vec2, int32_t vec2_len);

    virtual float32_t dense_dot(const float32_t* vec2, int32_t vec2_len);

    virtual void add_to_dense_vec(float64_t alpha, float64_t* vec2, int32_t vec2_len, bool abs_val=false);

    virtual void add_to_dense_vec(float32_t alpha, float32_t* vec2, int32_t vec2_len, bool abs_val=false);

    int64_t get_num_nonzero_entries();

    float32_t compute_squared();

    void sort_features();

    virtual int32_t get_num_features();

    virtual int32_t get_nnz_features_for_vector();

    virtual EFeatureType get_feature_type() const;

    virtual EFeatureClass get_feature_class() const;
 
    virtual CFeatures* duplicate() const;

    inline virtual const char* get_name() const { return "StreamingSparseFeatures"; }

    virtual int32_t get_num_vectors() const;

    virtual int32_t get_size() const;

private:
    virtual void init();

    virtual void init(CStreamingFile *file, bool is_labelled, int32_t size);

protected:
    CInputParser< SGSparseVectorEntry<T> > parser;

    CStreamingFile* working_file;

    SGSparseVector<T> current_sgvector;

    SGSparseVectorEntry<T>* current_vector;

    index_t current_vec_index;

    float64_t current_label;

    int32_t current_length;

    int32_t current_num_features;
};

}
#endif // _STREAMING_SPARSEFEATURES__H__