def load_lda_parameters(mdl_cfg):
dictionary_file = mdl_cfg['CORPUS']['dict_file']
path_index_file = mdl_cfg['CORPUS']['path_index_file']
lda_mdl_file = mdl_cfg['LDA']['lda_model_file']
lda_cos_index_file = mdl_cfg['LDA']['lda_cos_index_file']
if nexists(dictionary_file) and nexists(path_index_file):
lda_file_path_index = load_file_paths_index(path_index_file)
lda_dictionary = load_dictionary(dictionary_file)
if nexists(lda_mdl_file) and nexists(lda_cos_index_file):
lda_mdl, lda_index = load_lda_variables(lda_mdl_file, lda_cos_index_file)
lda_theta_file = mdl_cfg['LDA']['lda_theta_file']
lda_theta = np.loadtxt(lda_theta_file) # loads the LDA theta from the model theta file
num_docs, num_topics = lda_theta.shape
min_lda_theta = np.min(np.min(lda_theta))
print 'LDA-theta is loaded: # of documents:', num_docs, \
'# of topics:', num_topics, 'min(Theta):', min_lda_theta
lda_beta_file = mdl_cfg['LDA']['lda_beta_file']
lda_beta = np.loadtxt(lda_beta_file) # loads the LDA theta from the model theta file
num_topics, vocab_size = lda_beta.shape
min_lda_beta = np.min(np.min(lda_beta))
print 'LDA-beta is loaded: # of topics:', num_topics, \
'# of terms in the vocabulary:', vocab_size, \
'min(Bheta):', min_lda_beta
print
return lda_dictionary, lda_mdl, lda_index, lda_file_path_index, lda_theta, lda_beta
def load_lsi_parameters(mdl_cfg):
dictionary_file = mdl_cfg['CORPUS']['dict_file']
path_index_file = mdl_cfg['CORPUS']['path_index_file']
lsi_mdl_file = mdl_cfg['LSI']['lsi_model_file']
lsi_cos_index_file = mdl_cfg['LSI']['lsi_cos_index_file']
if nexists(dictionary_file) and nexists(path_index_file):
lsi_file_path_index = load_file_paths_index(path_index_file)
lsi_dictionary = load_dictionary(dictionary_file)
if nexists(lsi_mdl_file) and nexists(lsi_cos_index_file):
lsi_mdl, lsi_index = load_lsi_variables(lsi_mdl_file, lsi_cos_index_file)
return lsi_dictionary, lsi_mdl, lsi_index, lsi_file_path_index
def load_tm(mdl_cfg):
dictionary_file = mdl_cfg['CORPUS']['dict_file']
path_index_file = mdl_cfg['CORPUS']['path_index_file']
lda_mdl_file = mdl_cfg['LDA']['lda_model_file']
lda_cos_index_file = mdl_cfg['LDA']['lda_cos_index_file']
if nexists(dictionary_file) and nexists(path_index_file):
lda_file_path_index = load_file_paths_index(path_index_file)
lda_dictionary = load_dictionary(dictionary_file)
if nexists(lda_mdl_file) and nexists(lda_cos_index_file):
lda_mdl, lda_index = load_lda_variables(lda_mdl_file, lda_cos_index_file)
return lda_dictionary, lda_mdl, lda_index, lda_file_path_index
def eval_ranking_methods(file_prefix, config_file,
test_directory,
tm_query,
limit = 1000,
img_extension = '.eps'):
lucene_query = 'all:(%s)' % tm_query # search in all fields
print 'Lucene query:', lucene_query
print 'TM query:', tm_query
positive_dir = os.path.join(test_directory, "1") # TRUE positive documents
TOP_K_TOPICS = 5 # the number topics used for Topic-LDA
rocs_file_name = '%s-ROCs' % file_prefix + img_extension
rocs_img_title = '' # %s: ROC curves' % file_prefix
roc_labels = ['Lucene ranking',
'Keyword-LDA ranking' ,
'Keyword-LDA * Lucene ranking',
'Topic-LDA ranking' ,
'Topic-LDA * Lucene Ranking',
'Keyword-LSI ranking']
line_styles = ['ro-','kx-','b+-','c^-','yv-.','gd-']
#---------------------------------------------- Reads the configuration file
mdl_cfg = read_config(config_file)
#------------ Checks whether the keywords are there in the corpus dictionary
dictionary = load_dictionary(mdl_cfg['CORPUS']['dict_file'])
valid_tokens = 0
for token in tm_query.split():
if token.strip() not in dictionary.values():
print token, "is not in the corpus vocabulary. Hence, this word will be ignored from the topic search."
else:
valid_tokens += 1
if valid_tokens == 0:
print 'None of the tokens exist in the dictionary. Exiting topic search!'
exit()
#------------------------------------------------------------- Lucene search
print 'Lucene ranking'
lu_docs = search_li(lucene_query, limit, mdl_cfg)
lu_docs_dict, lu_docs_list = lu_append_nonresp(lu_docs, test_directory)
lu_res = convert_to_roc_format(lu_docs_list, positive_dir)
print
#---------------------------------------------------------------- LDA search
# Loads the LDA model
lda_dictionary, lda_mdl, lda_index, lda_file_path_index, lda_theta, lda_beta = load_lda_parameters(mdl_cfg)
# To display the LDA model topics based on the
# increasing order of entropy
# print_lda_topics_on_entropy(lda_mdl, file_name='%s-topic-words.csv' % file_prefix, topn=50)
# Gets the dominant topics from the LDA model
dominant_topics = get_dominant_query_topics(tm_query, lda_dictionary, lda_mdl, TOP_K_TOPICS)
dominant_topics_idx = [idx for (idx, _) in dominant_topics] # get the topic indices
print 'LDA (w/ keywords) ranking'
lda_docs = search_tm(tm_query, limit, lda_dictionary, lda_mdl, lda_index, lda_file_path_index)
lda_res = convert_to_roc_format(lda_docs, positive_dir)
# plot_doc_class_predictions(lda_res, '%s-Keyword-LDA' % file_prefix, img_extension)
print 'LDA (w/ keywords) * Lucene ranking'
lu_tm_docs = fuse_lucene_tm_scores(lu_docs_dict, lda_docs)
lda_lu_res = convert_to_roc_format(lu_tm_docs, positive_dir)
# plot_doc_class_predictions(lda_lu_res, '%s-Keyword-LDA-Lucene' % file_prefix, img_extension)
print 'LDA (w/ query topics) ranking'
lda_tts_docs = search_tm_topics(dominant_topics_idx, limit, lda_file_path_index, lda_theta)
lda_tts_res = convert_to_roc_format(lda_tts_docs, positive_dir)
# plot_doc_class_predictions(lda_tts_res, '%s-Topic-LDA' % file_prefix, img_extension)
print 'LDA (w/ query topics) * Lucene Ranking'
final_docs_tts = fuse_lucene_tm_scores(lu_docs_dict, lda_tts_docs)
lda_tts_lu_res = convert_to_roc_format(final_docs_tts, positive_dir)
# plot_doc_class_predictions(lda_tts_lu_res, '%s-Topic-LDA-Lucene' % file_prefix, img_extension)
#---------------------------------------------------------------- LSI search
print 'LSI (w/ keywords) ranking'
lsi_docs = search_lsi(tm_query, limit, mdl_cfg)
lsi_res = convert_to_roc_format(lsi_docs, positive_dir)
## Plot ROC curves
results_list = [lu_res,
lda_res, lda_lu_res,
lda_tts_res, lda_tts_lu_res,
lsi_res]
roc_data_list = [ROCData(result, linestyle=line_styles[idx])
for idx, result in enumerate(results_list)]
plot_multiple_roc(roc_data_list, title=rocs_img_title,
labels=roc_labels, include_baseline=True,
file_name=rocs_file_name)
