def main():
'''
Runs cross validation on the input Twitter data.
'''
args = parser.parse_args()
# Extract the data for LDA and divide into 10 folds
dm = DataManager(args.train_path, 'twitter')
if settings.DEBUG: print("Loading data...")
# Time the process of loading in the data.
start = time.perf_counter()
# Load the data (possibly from the cache, if it exists)
dm.load_data(args.cache_path)
# The number of folds is passed in as a command-line arg
dm.divide_into_folds(args.num_folds)
end = time.perf_counter()
if settings.DEBUG:
print(
f"Preparing the data (loading, dividing into folds) took {end-start:0.4f} seconds."
)
# Initialize the best k and best likelihood, along with the list of k values to try
best_k = None
best_likelihood = -float("inf")
# Get the list of topic numbers to try as a command line arg too.
possible_k_values = args.topic_numbers
# Store the results to the result path. Add the headers if the file doesn't exist yet.
if not os.path.exists(args.results_path):
fout = open(args.results_path, "w")
out_writer = csv.writer(fout)
out_writer.writerow([
"Model", "k", "Average Likelihood", "Number of Documents", "Source"
])
else:
fout = open(args.results_path, "w")
out_writer = csv.writer(fout)
# Run cross validation once for each parameter value
for k in possible_k_values:
if settings.DEBUG: print(f"Trying k={k} components...")
# We will create a list of accuracies for each validation set
likelihoods = []
for i in range(dm.get_num_folds()):
if settings.DEBUG:
print(f" Iteration {i+1}/{dm.get_num_folds()}")
# Update the validation fold.
dm.set_validation(i)
# Retrieve the training data and validation set.
train, validate = get_data_for_LDA(dm)
start = time.perf_counter()
# Train the model with the param choice.
lda_model = run_LDA_for_CV(train, k)
# Compute the resulting accuracy on the validation set.
likelihood = lda_model.score(validate)
end = time.perf_counter()
if settings.DEBUG: print(f" likelihood = {likelihood}")
if settings.DEBUG:
print(f" Training took {end-start:0.4f} seconds.")
likelihoods.append(likelihood)
avg_likelihood = sum(likelihoods) / len(likelihoods)
out_writer.writerow([
"LDA", k, avg_likelihood,
len(dm.get_all_fold_data()), settings.TWITTER_DIR
])
if settings.DEBUG: print(f" avg_likelihood = {avg_likelihood}")
if avg_likelihood > best_likelihood:
best_likelihood = avg_likelihood
best_k = k
print(
f"Best average likelihood found was {best_likelihood} with parameter value k={best_k}"
)
fout.close()
