Created
June 9, 2014 14:53
-
-
Save abinashpanda/7a201f3fabb74e40dbf2 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <shogun/io/LineReader.h> | |
#include <shogun/io/Parser.h> | |
#include <shogun/lib/DelimiterTokenizer.h> | |
#include <shogun/lib/SGVector.h> | |
#include <shogun/lib/SGSparseVector.h> | |
#include <shogun/io/SGIO.h> | |
#include <shogun/base/init.h> | |
using namespace shogun; | |
void get_sparse_matrix( | |
FILE * file, | |
SGSparseVector<float64_t> * &mat_feat, | |
int32_t &num_feat, | |
int32_t &num_vec, | |
SGVector<int32_t> * &multilabel, | |
int32_t &num_classes) | |
{ | |
char m_delimiter_feat = ':'; | |
char m_delimiter_label = ','; | |
CDelimiterTokenizer * m_whitespace_tokenizer = new CDelimiterTokenizer( | |
true); | |
m_whitespace_tokenizer->delimiters[' '] = 1; | |
SG_REF(m_whitespace_tokenizer); | |
CDelimiterTokenizer * m_delimiter_feat_tokenizer = new CDelimiterTokenizer( | |
true); | |
m_delimiter_feat_tokenizer->delimiters[m_delimiter_feat] = 1; | |
SG_REF(m_delimiter_feat_tokenizer); | |
CDelimiterTokenizer * m_delimiter_label_tokenizer = new CDelimiterTokenizer( | |
true); | |
m_delimiter_label_tokenizer->delimiters[m_delimiter_label] = 1; | |
SG_REF(m_delimiter_label_tokenizer); | |
CDelimiterTokenizer * m_line_tokenizer = new CDelimiterTokenizer( | |
true); | |
m_line_tokenizer->delimiters['\n'] = 1; | |
SG_REF(m_line_tokenizer); | |
CParser * m_parser = new CParser(); | |
SG_REF(m_parser); | |
CLineReader * m_line_reader = new CLineReader( | |
file, | |
m_line_tokenizer); | |
SG_REF(m_line_reader); | |
SG_SPRINT(">>> Counting number of lines in the file...\n"); | |
num_vec = 0; | |
while (m_line_reader->has_next()) | |
{ | |
m_line_reader->skip_line(); | |
num_vec++; | |
} | |
m_line_reader->reset(); | |
SG_SPRINT("<<< Counting lines completed.\n"); | |
mat_feat = SG_MALLOC(SGSparseVector<float64_t>, num_vec); | |
multilabel = SG_MALLOC(SGVector<int32_t>, num_vec); | |
SG_UNREF(m_whitespace_tokenizer); SG_UNREF(m_delimiter_feat_tokenizer); | |
SG_UNREF(m_delimiter_label_tokenizer); SG_UNREF(m_line_tokenizer); | |
SG_UNREF(m_parser); SG_UNREF(m_line_reader); | |
} | |
int main(int argc, char ** argv) | |
{ | |
init_shogun_with_defaults(); | |
sg_io->set_loglevel(MSG_DEBUG); | |
FILE * file = fopen("sample.svm", "r"); | |
int32_t num_feat, num_vec, num_classes; | |
SGSparseVector<float64_t> * | |
mat_feat; | |
SGVector<int32_t> * multilabel; | |
get_sparse_matrix( | |
file, | |
mat_feat, | |
num_feat, | |
num_vec, | |
multilabel, | |
num_classes); | |
SG_SPRINT("Number of vectors/samples are = %d\n", num_vec); | |
exit_shogun(); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment