def evaluate_all_systems(p_dictoffolderpaths, p_run_all_systems=True):
if p_run_all_systems:
Task1.execute_system('')
Task2.execute_system('')
Task3A.execute_system('')
Task3B.execute_system('')
print "Evaluating all systems..."
create_directory(ldirpath)
lquerydict = get_given_queries_in_dict(CACM_QUERY_FILE + FILE_EXT)
lquerydict = get_sorted_dict(lquerydict)
lallsystemsmeanvaluesdict = {}
lallsystemsavgprecisionvaluesdict = {}
for lkey, lvalue in p_dictoffolderpaths.iteritems():
lsystemname = get_system_name(lkey)
print "Evaluating system: " + lsystemname
lsystemmeanvaluesdict = {}
ldictofavgprecisionvalues = {}
llistofprecisionandrecallvalues = [
"Query Id,DocId,Rank,Precision,Recall"
]
llistofpatkvalues = ["Query Id,P@5,P@20"]
evaluate_system(
lvalue, # results folder path to evaluate
lquerydict, # dictionary containing all queries with query id
lsystemmeanvaluesdict, # dictionary to hold the mean values for all systems
ldictofavgprecisionvalues, # dictionary to hold avg precision values of systems
llistofprecisionandrecallvalues, # results of precision recall values for all queries
llistofpatkvalues # list to hold pat5 and pat20 values for all queries for this system
) # evaluate_system..
lallsystemsmeanvaluesdict[lkey] = lsystemmeanvaluesdict
# ldictofavgprecisionvalues = get_sorted_dict(ldictofavgprecisionvalues)
lallsystemsavgprecisionvaluesdict[lkey] = ldictofavgprecisionvalues
# print "Writing Precision and Recall values for system: " + lsystemname
llfilename = ldirpath + "/" + FILE_FOR_PRECISON_RECALL_RESULTS_OF_SYSTEM + "_" + lsystemname + CSV_FILE_EXT
create_file(llfilename, '')
convert_data_from_collection_to_file(llfilename,
llistofprecisionandrecallvalues)
# print "Writing P@5 and P@20 values for system: " + lsystemname
llfilename = ldirpath + "/" + FILE_FOR_PATK_RESULTS_OF_SYSTEM + "_" + lsystemname + CSV_FILE_EXT
create_file(llfilename, '')
convert_data_from_collection_to_file(llfilename, llistofpatkvalues)
# print "Writing mean values to file"
llistofmeanvalues = ["System,MAP,MRR,P@5,P@20"]
for lkey, lvalue in lallsystemsmeanvaluesdict.iteritems():
lsystemname = get_system_name(lkey)
lstr = lsystemname + "," + str(lvalue[MAP_CONST]) + "," + str(lvalue[MRR_CONST]) + \
"," + str(lvalue[PAT5_CONST]) + "," + str(lvalue[PAT20_CONST])
llistofmeanvalues.append(lstr)
lfilename = ldirpath + "/" + FILE_FOR_ALL_SYSTEMS_MEAN_VALUES + CSV_FILE_EXT
create_file(lfilename, '')
convert_data_from_collection_to_file(lfilename, llistofmeanvalues)
# print "Writing average precision values to file"
llistavgprecisionresults = ["System,Query Id,Average Precision"]
for lkey, lvalue in lallsystemsavgprecisionvaluesdict.iteritems():
lsystemname = get_system_name(lkey)
for ljkey, ljvalue in lvalue.iteritems():
lstr = lsystemname + "," + str(ljkey) + "," + str(ljvalue)
llistavgprecisionresults.append(lstr)
lfilename = ldirpath + "/" + FILE_FOR_ALL_SYSTEMS_AVG_PRECISION_VALUES + CSV_FILE_EXT
create_file(lfilename, '')
convert_data_from_collection_to_file(lfilename, llistavgprecisionresults)
# print "Run t-tests for models"
run_tests_for_models(lallsystemsavgprecisionvaluesdict, len(lquerydict))
# read command line params for stemmed data file
lstemmeddatafile = CACM_STEM_FILE + FILE_EXT
if len(input_arguments) > 2:
lstemmeddatafile = input_arguments[2]
# Tokenize raw text
tokenize_raw_data(ldatafilesdir)
# Write given queries to a file
create_directory(DIR_FOR_OUTPUT_FILES)
write_given_queries_to_file(
CACM_QUERY_FILE + FILE_EXT,
DIR_FOR_OUTPUT_FILES + "/" + FILE_FOR_QUERIES + FILE_EXT)
Task1.execute_system(ldatafilesdir)
Task2.execute_system(ldatafilesdir)
Task3A.execute_system(ldatafilesdir)
Task3B.execute_system(lstemmeddatafile)
ldictoffolderpaths = {}
ldictoffolderpaths[
1] = DIR_FOR_OUTPUT_FILES + "/" + TASK1_CONST + "/" + DIR_FOR_BM25_OUTPUT
ldictoffolderpaths[
2] = DIR_FOR_OUTPUT_FILES + "/" + TASK1_CONST + "/" + DIR_FOR_TFIDF_OUTPUT
ldictoffolderpaths[3] = LUCENE + "/" + LUCENE_RESULTS
ldictoffolderpaths[
4] = DIR_FOR_OUTPUT_FILES + "/" + TASK2_CONST + "/" + DIR_FOR_BM25_OUTPUT
ldictoffolderpaths[
5] = DIR_FOR_OUTPUT_FILES + "/" + TASK2_CONST + "/" + DIR_FOR_TFIDF_OUTPUT
ldictoffolderpaths[
6] = DIR_FOR_OUTPUT_FILES + "/" + TASK3A_CONST + "/" + DIR_FOR_BM25_OUTPUT