src/ports/postgres/modules/crf/viterbi.sql_in

/* ----------------------------------------------------------------------- *//**
 *
 * @file viterbi.sql_in
 * @brief concatenate a set of input values into arrays to feed into viterbi c
 *  function and create a human readable view of the output
 * @date   February 2012
 *
 *
 *//* ----------------------------------------------------------------------- */

m4_include(`SQLCommon.m4')

/**
 * @brief This function creates the specified result_tbl containing top1 labels for the sequence.
 * @param segment_tbl Name of table containing all the testing sentences.
 * @param label_tbl Name of table containing all the labels in the label space.
 * @param result_tbl Name of table storing the best label sequence and the conditional probability.
*/

CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.vcrf_top1_table(
    segment_tbl     TEXT,
    label_tbl       TEXT,
    resulttbl_raw   TEXT,
    result_tbl      TEXT
) returns TEXT AS $$
PythonFunction(crf, viterbi, vcrf_top1_table)
$$ LANGUAGE plpythonu strict
m4_ifdef(`__HAS_FUNCTION_PROPERTIES__', `MODIFIES SQL DATA', `');

/**
 * @brief This function implements the Viterbi algorithm which takes the sentence to be label as input and return the top1 labeling for that sentence
 * @param marray Name of arrays containing m factors
 * @param rarray Name of arrays containing r factors
 * @param nlabel Total number of labels in the label space
 * @returns the top1 label sequence, the last two elements in the array is used to calculate the top1 probability
 */
CREATE OR REPLACE FUNCTION MADLIB_SCHEMA.vcrf_top1_label(mArray DOUBLE PRECISION[], rArray DOUBLE PRECISION[], nlabel int)
returns int[] as 'MODULE_PATHNAME' language c strict;


/**
 * @brief This function prepares the inputs for the c function 'vcrf_top1_label' and invoke the c function.
 * @param segment_tbl Name of table containing all the testing sentences.
 * @param factor_mtbl Name of table containing all the m factors.
 * @param factor_rtbl Name of table containing all the r factors.
 * @param label_tbl Name of table containing all the labels in the label space.
 * @param result_tbl Name of table to store the output
 * @returns the top1 label sequence, the last two elements in the array is used to calculate the top1 probability
 */

CREATE OR REPLACE FUNCTION
MADLIB_SCHEMA.vcrf_label(
    segment_tbl TEXT,
    factor_mtbl TEXT,
    factor_rtbl TEXT,
    label_tbl   TEXT,
    result_tbl TEXT
)   RETURNS TEXT AS $$
PythonFunction(crf, viterbi, vcrf_label)
$$ LANGUAGE plpythonu
m4_ifdef(`__HAS_FUNCTION_PROPERTIES__', `MODIFIES SQL DATA', `');