def classify(config, text):
""" Text classification
"""
# Preprocess: transform text to frequency
prepro = Preprocessing(**config)
mat = prepro.loading_single_doc(text, 'doc_freq', config['threshold'])
# Initialize only 3 algorithms at the moment
ml = MachineLearning(**config)
# Perform prediction
# Naive Bayes
nb_algo = ml.NiaveBayes()
nb_model = nb_algo.load_model()
nb_prediction = nb_algo.predict(nb_model, [mat])
# ANN
nn_algo = ml.NeuralNetwork(hidden_layer_sizes=(250, 100),\
learning_rate=0.012, momentum=0.5, random_state=0, max_iter=200, activation='tanh')
nn_model = nn_algo.load_model()
nn_prediction = nn_algo.predict(nn_model, [mat])
# DT
dt_algo = ml.DecisionTree(criterion='gini',
prune='depth',
max_depth=30,
min_criterion=0.05)
dt_model = dt_algo.load_model()
#norm_mat = prepro.normalize_dataset(np.array([mat])) # use with decision tree only
#norm_mat = prepro.normalize_dataset(np.array([mat])) # use with decision tree only
#dt_prediction = dt_algo.predict(dt_model, norm_mat)
dt_prediction = dt_algo.predict(dt_model, np.array([mat]))
# Get the best labe outputed by BN, NN, DT
nb_label = ml.to_label(nb_prediction, config['label_match'])
nn_label = ml.to_label(nn_prediction, config['label_match'])
dt_label = ml.to_label(dt_prediction, config['label_match'])
# Prepare results of:
# (1) Naive Bayes (2) Neural Network (3) Decision Tree
result = {'NB': nb_label, 'NN': nn_label, 'DT': dt_label}
return result
dataset_matrix = prepro.loading_data(config['text_dir'], 'doc_freq', 'all',
1)
#load dataset from file (feature data)
filename = "doc_freq_1.csv"
dataset_path = FileUtil.dataset_path(config, filename)
dataset_sample = FileUtil.load_csv(dataset_path)
prepro_time = time.time() - whole_st
ml = MachineLearning(**config)
# choose your algorithm
nb_algo = ml.NiaveBayes()
nn_algo = ml.NeuralNetwork(hidden_layer_sizes=(250, 100),
learning_rate=0.012,
momentum=0.5,
random_state=0,
max_iter=200,
activation='tanh')
dt_algo = ml.DecisionTree(criterion='gini',
prune='depth',
max_depth=30,
min_criterion=0.05)
nb_result = perform_algo(ml, nb_algo, dataset_sample)
nn_result = perform_algo(ml, nn_algo, dataset_sample)
dt_result = perform_algo(ml, dt_algo, dataset_sample)
print(nb_result, nn_result, dt_result)
total_execution_time = time.time() - whole_st
def get_results(path_textfile, params, config, start_time):
"""
This function performs features extraction from client's data source\
Train model based on extracted features
Get Accuracy of each algorithm (e.g: Naive Bayes, Neural Network) based on\
evaluation criteria e.g: LOO, 5 folds or 10 folds
"""
# Store config for next use
config = config
is_unicode = config.get('is_unicode', None)
config['is_unicode'] = True if is_unicode != None else False
#logfile = '/Users/lion/Documents/py-workspare/slash-ml/logfile.log'
#logging.basicConfig(filename=logfile, level=logging.DEBUG)
config['passion'] = "passion"
# Perform features extraction
is_successful_fextract = MLManager.extract_features(
path_textfile, config)
#is_successful_fextract = True
if is_successful_fextract:
whole_st = time.time()
prepro = Preprocessing(**config)
# preposessing
params_prepro = params['PR']
dataset_matrix = prepro.loading_data(config['text_dir'], params_prepro['method'],\
'all', params_prepro['threshold'])
# Remove sub-directory from "data/dataset/text"
FileUtil.remove_file(config['text_dir'], ignore_errors=True)
#load dataset from file (feature data)
filename = "doc_freq_" + str(params_prepro['threshold']) + ".csv"
dataset_path = FileUtil.dataset_path(config, filename)
dataset_sample = FileUtil.load_csv(dataset_path)
prepro_time = time.time() - whole_st
ml = MachineLearning(**config)
# choose your algorithm
nb_algo = ml.NiaveBayes()
params_nn = params['NN']
nn_algo = ml.NeuralNetwork(hidden_layer_sizes=params_nn['hidden_layer_sizes'],\
learning_rate=params_nn['learning_rate'], momentum=params_nn['momentum'],\
random_state=params_nn['random_state'], max_iter=params_nn['max_iter'],\
activation=params_nn['activation'])
params_dt = params['DT']
dt_algo = ml.DecisionTree(criterion=params_dt['criterion'], prune='depth',\
max_depth=params_dt['max_depth'], min_criterion=params_dt['min_criterion'])
nb_result = MLManager.perform_algo(ml, nb_algo, dataset_sample)
nn_result = MLManager.perform_algo(ml, nn_algo, dataset_sample)
dt_result = MLManager.perform_algo(ml, dt_algo, dataset_sample)
print(nb_result, nn_result, dt_result)
total_execution_time = time.time() - whole_st
result = {
'com_time': round(total_execution_time, 2),
'text_extract_time': round(prepro_time, 2),
'figure_on_testing_data': {
'NB': nb_result['acc'],
'NN': nn_result['acc'],
'DT': dt_result['acc'],
},
'figure_on_training_data': {
'NB': nb_result['acc_train'],
'NN': nn_result['acc_train'],
'DT': dt_result['acc_train'],
},
'on_testing_data': {
'NB': {
'accuracy': nb_result['acc'],
'time': nb_result['exec_time']
},
'NN': {
'accuracy': nn_result['acc'],
'time': nn_result['exec_time']
},
'DT': {
'accuracy': dt_result['acc'],
'time': dt_result['exec_time']
},
},
'on_training_data': {
'NB': {
'accuracy': nb_result['acc_train'],
'time': nb_result['exec_time']
},
'NN': {
'accuracy': nn_result['acc_train'],
'time': nn_result['exec_time']
},
'DT': {
'accuracy': dt_result['acc_train'],
'time': dt_result['exec_time']
},
}
}
return result