def KNearestNeighbourController(training_paths, training_labels, test_paths=None, test_labels=None, k=1, tf_idf=False):
"""
Controller function to co-ordinate the K-Nearest neighbour algorithm
"""
# Returns the text per file and their labels once and for all
training_text_dict = readTextFromFilePaths(training_paths)
# If this is a validation run, we need to keep one book aside at a time and send
# the rest of the them to create the training vectors
if not test_paths:
# Creating the vectors for the training set. This includes all but one book
# which will be used for validation
for validation_file in training_text_dict:
print("Validation being done on: {0}".format(validation_file))
# Creating the training vectors and validation vectors from the training dictionary
vectors, _ = createTrainingVectors(training_text_dict)
# Performing tf-idf transform on all the vectors
tfidf_transform_dict = tfIdfTransform(vectors) if tf_idf else vectors
# Separating the validation vector from the training one
validation_vector = tfidf_transform_dict.pop(validation_file)
training_vectors = tfidf_transform_dict
# Finding the nearest neighbours by passing in a manual k
nearest_neighbours = findNearestNeighbour(training_vectors, validation_vector, k)
# Finding the genre with the concept of voting by neighbours
genre = detectClassOfTestSet(nearest_neighbours, training_labels, k)
print(
"Known label: {0} Calculated Label: {1}".format(training_labels.get(validation_file, "Unknown"), genre)
)
# Else clause gets activated in case the run is a final test run
else:
# Creating the training vectors from the training dictionary
vectors, zero_vector = createTrainingVectors(training_text_dict)
# Finding the genre of a test file one file at a time
for test_file_path in test_paths:
test_file = test_file_path.split("/")[-1]
print("\nTest file is : {0}".format(test_file))
# Creating the set of tokens for the test file
test_text_dict = readTextFromFilePaths([test_file_path])
# Running k nearest neighbours algorithms
genre = runKNearestNeighbours(vectors, test_text_dict, test_file, training_labels, zero_vector, k, tf_idf)
print("Known label: {0} Calculated Label: {1}".format(test_labels.get(test_file, "Unknown"), genre))
if tf_idf:
vectors.pop(test_file)
def runKNearestNeighbours(
training_vectors, tokenized_test_file, test_file, training_labels, zero_vector, k, tf_idf=False
):
# Creating the test vector with only those tokens that were a part of the training set
training_vectors[test_file] = createTestVectors(tokenized_test_file[test_file], zero_vector)
# Performing tf-idf transform on all the vectors
tfidf_transform_dict = tfIdfTransform(training_vectors) if tf_idf else training_vectors
# Seperating the test vector from the training vectors
test_vector = tfidf_transform_dict.pop(test_file)
training_vectors = tfidf_transform_dict
# Finding the nearest neighbours by passing in a manual k
nearest_neighbours = findNearestNeighbour(training_vectors, test_vector, k)
# Running k nearest neighbours algorithms
genre = detectClassOfTestSet(nearest_neighbours, training_labels, k)
return genre
