def main():
if '-h' in sys.argv:
print_usage_message()
exit()
vectFileName = fn.create_prof_vect_name(sys.argv, True)
simMatFileName = fn.create_sim_mat_name(sys.argv)
predsFileName = fn.create_preds_name(sys.argv)
print(vectFileName)
print(simMatFileName)
print(predsFileName)
# Grab the ratings vector
if '-d' in sys.argv:
ratings = read.difficulty_rating_vect(vectFileName)
else:
ratings = read.overall_rating_vect(vectFileName)
# Assign similarity metric
sim_f = vp.inverse_euclidean_distance
if '-cos' in sys.argv:
sim_f = vp.cosine_similarity
elif '-pear' in sys.argv:
sim_f = vp.abs_pearson_correlation
# Set if weighted or not
weighted = True
if '-unweighted' in sys.argv:
weighted = False
# Grab predictions or create them if not available
predictions = read.knn_predictions(predsFileName)
if predictions is None:
simMat = read.similarity_matrix(simMatFileName)
if simMat is None:
wordVects = read.word_vects(vectFileName)
if wordVects is None:
print("Vector file " + vectFileName + " does not exist")
exit()
wordVects = vp.process_token_vectors(wordVects, sys.argv)
simMat = knn.get_similarity_matrix(wordVects, sim_f)
write.similarity_matrix(simMat, simMatFileName)
predictions = knn.knn_dataset(ratings, MaxK, simMat, weighted)
write.knn_predictions(predictions, predsFileName)
idxToPlot = None
if '-maxK' in sys.argv:
maxK = int(sys.argv[sys.argv.index('-maxK') + 1])
predictions = predictions[:, :maxK]
pidVect = read.pid_vect(vectFileName)
singleRevIdxs = vp.pids_to_idxs(pidVect,
read.pids_file(fn.PidsSingleRevFile))
smallLenIdxs = vp.pids_to_idxs(pidVect,
read.pids_file(fn.PidsSmallRevLenFile))
plotFileName = None
if '-save' in sys.argv:
plotFileName = fn.create_knn_accuracy_plot_name(sys.argv)
# Output results of the run
plot.knn_error(
predictions,
ratings,
title=plot.create_knn_error_title(sys.argv),
idxToPlot=[singleRevIdxs, smallLenIdxs],
subTitles=[
"Error with profs with one review",
"Error with profs with aggrigate review " +
"lengths one std div above the mean " + "review length or less"
],
saveFile=plotFileName)
