updated_weight_vector = weight_vector + modified_feature_vector
return updated_weight_vector
def get_predicted_value(weight_vector, feature_vector):
dot_product_value = np.dot(weight_vector, feature_vector)
predicted_value = 1 if dot_product_value >= 0 else -1
return predicted_value
if __name__ == '__main__':
import create_feature_vectors
# Train on the training set to get weight vector
print("Running with last trained weight vector")
(feature_vector_list_training,
is_spam_list_training,
vocabulary_list) = create_feature_vectors.run('./output_data/training_set')
(weight_vector,
total_number_of_misclassifications,
number_of_runs) = perceptron_train(
feature_vector_list_training, is_spam_list_training,
display_intermediate_steps=True)
print('Total number of misclassifications: ' + str(total_number_of_misclassifications))
print('Number of runs: ' + str(number_of_runs))
# Verify error on the training set
error = perceptron_test(weight_vector, feature_vector_list_training, is_spam_list_training)
print('Error on training set: ' + error)
# Verify error on the validation set
(feature_vector_list_validation,
os.makedirs(output_directory)
else:
os.makedirs(output_directory)
# Run Script for ps1 (Perceptron Implementation)
import split_training_data
import create_feature_vectors
import perceptron
# Part 1: Split Training data into training and validation set
split_training_data.run()
# Part 2: Transform each email in the training set into a feature vector
(feature_vector_list_training,
is_spam_list_training,
vocabulary_list) = create_feature_vectors.run('./output_data/training_set')
# Part 3/4: Train the data on the training set and return the last weight vector. Test the percent
# error when this weight is run on the validation set
print('\n=========================================================================================')
print('Problem 4:')
(weight_vector,
total_number_of_misclassifications,
number_of_runs) = perceptron.perceptron_train(feature_vector_list_training, is_spam_list_training)
(feature_vector_list_validation,
is_spam_list_validation,
_) = create_feature_vectors.run('./output_data/validation_set', vocabulary_list)
training_set_error = perceptron.perceptron_test(
weight_vector, feature_vector_list_training, is_spam_list_training)
