def eval():
print('Loading association matrix')
matrix = matrix_dict.Matrix_Dict()
matrix.read_matrix_from_file(MATRIX_FILE)
print('Evaluating')
scorer.evaluate_kbest_MeanReciprocalRank(matrix, corpora.GAME_SET_100_FILE,
EVAL_WORD_GAME100_FILE)
def build_and_eval():
utility.make_dir(OUTPUT_DIR)
print('Building lexicon')
poli_lexicon = list(lexicon.loadLexiconFromFile(corpora.DIZ_POLI_WORD_SORTED_FILE))
sost_lexicon = list(lexicon.loadLexiconFromFile(corpora.DIZIONARIO_SOSTANTIVI_AUGMENTED_PAISA_FILE))
agg_lexicon = list(lexicon.loadLexiconFromFile(corpora.DIZIONARIO_AGGETTIVI_AUGMENTED_PAISA_FILE))
lex_set = set(poli_lexicon+sost_lexicon+agg_lexicon)
lex_solution_set = set(sost_lexicon+agg_lexicon)
lexicon.printLexiconToFile(lex_set, LEX_FREQ_FILE)
lexicon.printLexiconToFile(lex_solution_set, SOLUTION_LEX_FREQ_FILE)
print('Computing coverage')
scorer.computeCoverageOfGameWordLex(lex_set, lex_solution_set, corpora.GAME_SET_100_FILE, COVERAGE_WORD_GAME100_FILE)
print('Building association matrix')
matrix = matrix_dict.Matrix_Dict(lex_set, lex_solution_set)
matrix.add_patterns_from_corpus(corpora.PAISA_RAW_INFO)
matrix.compute_association_scores()
matrix.write_matrix_to_file(MATRIX_FILE)
print('Eval')
scorer.evaluate_kbest_MeanReciprocalRank(matrix, corpora.GAME_SET_100_FILE, EVAL_WORD_GAME100_FILE)
scorer.evaluate_kbest_MeanReciprocalRank(matrix, corpora.NLP4FUN_DEV_TSV_v2_tv_FILE, EVAL_NLP4FUN_DEV_TV_FILE)
scorer.evaluate_kbest_MeanReciprocalRank(matrix, corpora.NLP4FUN_DEV_TSV_v2_bg_FILE, EVAL_NLP4FUN_DEV_BG_FILE)
def build_and_eval():
utility.make_dir(OUTPUT_DIR)
print('Building lexicon')
lex_set = lexicon.loadLexiconFromFile(corpora.DIZ_POLI_WORD_SORTED_FILE)
lexicon_freq = {w: 1 for w in lex_set}
#lex_solution_set = lexicon.loadLexiconFromFile(corpora.DIZIONARIO_BASE_SOSTANTIVI_FILE)
print('Lex size: {}'.format(len(lex_set)))
lexicon.printLexFreqToFile(lexicon_freq, LEX_FREQ_FILE)
print('Computing coverage')
scorer.computeCoverageOfGameWordLex(lexicon_freq,
corpora.GAME_SET_100_FILE,
COVERAGE_WORD_GAME100_FILE)
print('Building association matrix')
matrix = matrix_dict.Matrix_Dict(lex_set=lex_set) # lex_solution_set
matrix.add_patterns_from_corpus(corpora.PAISA_RAW_INFO)
matrix.add_patterns_from_corpus(corpora.DE_MAURO_POLIREMATICHE_INFO,
weight=DE_MAURO_WEIGHT)
corpora.addBigramFromPolirematicheInMatrix(matrix, DE_MAURO_WEIGHT)
matrix.compute_association_scores()
matrix.write_matrix_to_file(MATRIX_FILE)
print('Eval')
scorer.evaluate_kbest_MeanReciprocalRank(matrix, corpora.GAME_SET_100_FILE,
EVAL_WORD_GAME100_FILE)
def interactive_solver():
print('Loading association matrix')
matrix = matrix_dict.Matrix_Dict()
matrix.read_matrix_from_file(MATRIX_FILE)
scorer.interactive_solver(matrix)