def main():
pm = path_manager()
selected_dbs = select_db(pm.find_folders(pm.get_databases_dir()))
for database in selected_dbs:
# TODO fix this band-aid when i get a f**k
if database[0] != 'all':
db = prepare_db(database[0], pm)
else:
print(
"we don't support that shit right now\nit's a feature, not a bug :)"
)
sys.exit()
# BEGIN classification FFNN
if db.get_dataset_type() == 'classification':
# BEGIN preprocessing
process_data.FFNN_encoding(db)
# (1) First layer (input layer) has 1 node per attribute.
# (2) Hidden layers has arbitrary number of nodes.
# (3) Output layer has 1 node per possible classification.
layer_sizes = [
len(db.get_attr()) - 1, 50,
len(db.get_class_list())
]
# This number is arbitrary.
# TODO Tune this per dataset
learning_rate = .3
ffnn = FFNN(layer_sizes, db.get_data(), db.get_dataset_type(),
learning_rate)
sys.exit()
# BEGIN regression FFNN
elif db.get_dataset_type() == 'regression':
process_data.FFNN_encoding(db)
# (1) First layer (input layer) has 1 node per attribute.
# (2) Hidden layers has arbitrary number of nodes.
# (3) Output layer has 1 node, just some real number.
layer_sizes = [len(db.get_attr()) - 1, 50, 1]
# machine's learning rate
# learning_rate = .60
# Forest fire's learning rate
learning_rate = .01
ffnn = FFNN(layer_sizes, db.get_data(), db.get_dataset_type(),
learning_rate)
sys.exit()
else:
print('Database type invalid. Type = ' + db.get_dataset_type())
import Cost_Functions as cf
from FFNN import FFNN
from path_manager import pathManager as path_manager
import numpy as np
import os.path
import prepare_data
import shared_functions as sf
import pso
pm = path_manager()
selected_dbs = prepare_data.select_db(pm.find_folders(pm.get_databases_dir()))
db = prepare_data.prepare_db(selected_dbs[0], pm)
process_data.shuffle_all(db.get_data(), 1)
process_data.FFNN_encoding(db)
half_idx = int(len(db.get_data()) * .5)
# FFNN stuff
# BEGIN classification FFNN
if db.get_dataset_type() == 'classification':
# (1) First layer (input layer) has 1 node per attribute.
# (2) Hidden layers has arbitrary number of nodes.
# (3) Output layer has 1 node per possible classification.
layer_sizes = [
len(db.get_attr()) - 1, # (1)
5,
5, # (2)
len(db.get_class_list())
def main():
pm = path_manager()
selected_dbs = select_db(pm.find_folders(pm.get_databases_dir()))
for database in selected_dbs:
# NOTE OUTPUT WILL WRITE TO A FILE, AS DEFINED BELOW:
# MAKE SURE TO CREATE THIS DIRECTORY BEFORE YOU RUN, AND YOU CAN
# SHOW THE FILE THAT'S CREATED IN THE VIDEO FOR OUTPUT
filename = "../output/kmedoids/" + database + "_output.txt"
output_file = open(filename, "w+")
db = prepare_db(database, pm)
k_nn = knn(5, db.get_dataset_type(), db.get_classifier_col(),
db.get_classifier_attr_cols())
classes = db.get_class_list() if db.get_dataset_type(
) == 'classification' else []
class_count = len(
classes) if db.get_dataset_type() == 'classification' else 1
X = process_data.shuffle_all(db.get_data(), 1)
y = np.array(db.get_data())[:, db.get_classifier_col()]
# RUN K-MEDOIDS ------------------------------------------------------------
print("RUNNING K-MEDOIDS")
kc = kcluster(10, 10, db.get_data(), db.get_classifier_attr_cols(),
'k-medoids')
indices = kc.get_medoids()
centers = [db.get_data()[i] for i in indices]
rbf = RBF(len(centers), class_count, output_file, 25)
rbf.fit(X, centers, y, db.get_dataset_type(), classes)
print("INITIAL WEIGHTS: ", rbf.weights)
output_file.write("INITIAL WEIGHTS: \n")
output_file.write(str(rbf.weights) + "\n")
print("CENTERS: ", centers)
output_file.write("FINAL WEIGHTS: \n")
output_file.write(str(rbf.weights) + "\n")
output_file.write("FINAL TESTS: \n")
rbf.test(X, db.get_dataset_type(), y, centers, classes)
print("FINALS WEIGHTS:")
print(rbf.weights)
# ----------------------------------------------------------------------------
# BEGIN classification FFNN
if db.get_dataset_type() == 'classification':
# BEGIN preprocessing
process_data.FFNN_encoding(db)
# (1) First layer (input layer) has 1 node per attribute.
# (2) Hidden layers has arbitrary number of nodes.
# (3) Output layer has 1 node per possible classification.
layer_sizes = [len(db.get_attr()), 10,
len(db.get_class_list())] # (3)
# This number is arbitrary.
# NOTICE: Tune this per dataset
learning_rate = .5
ffnn = FFNN(layer_sizes, db.get_dataset_type(), db_name,
db.get_data(), learning_rate)
# BEGIN regression FFNN
elif db.get_dataset_type() == 'regression':
process_data.FFNN_encoding(db)
# (1) First layer (input layer) has 1 node per attribute.
# (2) Hidden layers has arbitrary number of nodes.
# (3) Output layer has 1 node, just some real number.
layer_sizes = [len(db.get_attr()) - 1, 5, 5, 1]
learning_rate = .0001
ffnn = FFNN(layer_sizes, db.get_dataset_type(), db_name,
db.get_data(), learning_rate)
else:
print('Database type invalid. Type = ' + db.get_dataset_type())