def prepare_avg_param(filename, param_name, ommit_first=True):
data = load(filename)
max_epoch = max(d['epochs'] for d in data['many_results']) + 1
many_accuracies = [d['test_accuracies'] for d in data['many_results']]
alligned_many_accuracies = [
elem + [elem[-1]] * (max_epoch - len(elem)) for elem in many_accuracies
]
avg_accuracies = np.asarray(alligned_many_accuracies).sum(
axis=0) / len(alligned_many_accuracies)
if ommit_first:
# TODO
avg_accuracies = avg_accuracies[1:].round(4)
max_epoch -= 1
elapsed_times = [
d['elapsed_times'] if 'elapsed_times' in d else None
for d in data['many_results']
]
avg_times = calc_avg_duration(elapsed_times) if all(
elapsed_times) else None
return {
param_name: data[param_name],
'avg_accuracies': avg_accuracies,
'max_epoch': max_epoch,
'activation': data['activation'] if 'activation' in data else '',
'avg_times': avg_times,
'use_adagrad': data['use_adagrad'] if 'use_adagrad' in data else False,
'draw_type': data['draw_type'] if 'draw_type' in data else 'uniform',
'momentum_param': data['momentum_param']
}
def test_calc_prediction_accuracy():
loaded_weights = load(filename='test_once_sigmoid_alpha_0.04_batch_100_draw_range_0.001_hidden_neurones_50_'
'test_accuracy_0.968.pkl')['weights']
_, _, test_data = load_data_wrapper("../data")
test_data = add_bias(data=test_data)
te_in, te_out = test_data
weights_tested = loaded_weights[0]
assert(calc_prediction_accuracy(SIGMOID.activation, *weights_tested, te_in, te_out) == 0.101)
weights_tested = loaded_weights[-1]
assert(calc_prediction_accuracy(SIGMOID.activation, *weights_tested, te_in, te_out) == 0.9687)
def test_mlp():
loaded_data = load_data_wrapper("../data")
loaded_result = load(filename='test_once_sigmoid_alpha_0.05_batch_100_draw_range_0.2_hidden_neurones_15_mom_0.5_'
'accuracy_0.7321.pkl')
np.random.seed(0)
result = mlp(data=loaded_data, activation=SIGMOID, alpha=0.05, batch_size=100, draw_range=0.2,
hidden_neurones=15, worse_result_limit=1, momentum_param=0.5, use_adagrad=False, images_len_divider=250)
for (w11 , w12), (w21, w22) in zip(loaded_result['weights'], result['weights']):
assert(np.allclose(a=w11, b=w21))
assert(np.allclose(a=w12, b=w22))
assert (len(loaded_result['weights']) == len(result['weights']))
def prepare(filename):
data = load(filename)
data['activation'] = 'sigmoid'
str_to_find = '_simulation_'
index = filename.find(str_to_find) + len(str_to_find)
new_filename = f'{filename[:index]}sigmoid_{filename[index:]}'
# data = load(filename)
# hidden_neurones = 'hidden_neurones'
# data[hidden_neurones] = 50
# str_to_find = '_draw_range_'
# index = filename.find(str_to_find) + len(str_to_find) + 4
# new_filename = f'{filename[:index]}hidden_neurones_50_{filename[index:]}'
# save(data=data, filename=new_filename)
print("'" + new_filename + "',")
def execute(self, inputs=None) -> any:
return loader.load(self.cu, file=self.file)
from loader import loader
if __name__ == "__main__":
loader.load()
def load(): from loader import loader loader.load()
# # goodF = [
# # 'hidden_neurones_simulation_alpha_0.04_batch_100_draw_range_0.2_hidden_neurones_15_avg_epochs_22.6_times_5.pkl',
# # 'hidden_neurones_simulation_alpha_0.04_batch_100_draw_range_0.2_hidden_neurones_25_avg_epochs_20.6_times_5.pkl',
# # 'hidden_neurones_simulation_alpha_0.04_batch_100_draw_range_0.2_hidden_neurones_75_avg_epochs_26.0_times_5.pkl',
# # 'hidden_neurones_simulation_alpha_0.04_batch_100_draw_range_0.2_hidden_neurones_100_avg_epochs_31.2_times_5.pkl',
# # ]
# #
#
# for f in files:
# prepare(f)
# print(load('once_relu_alpha_0.003_batch_10_draw_range_0.2_hidden_neurones_50.pkl'))
print(
load(
'hidden_neurones4_simulation_relu_alpha_0.01_batch_5_draw_range_0.2_hidden_neurones_25_avg_epochs_16.0_times_5.pkl'
))
# def calc_avg_times(input):
# max_len = max(len(sub_list) for sub_list in input)
# result_acc = [0] * max_len
# divider_acc = [0] * max_len
# for sub_list in input:
# for i in range(len(sub_list)):
# result_acc[i] += sub_list[i]
# divider_acc[i] += 1
# return [result_acc[i] / divider_acc[i] for i in range(max_len)]
#
# a = [[1, 3], [2, 4, 6, 9], [], [-1]]
# print(calc_avg_times(a))
def load():
from loader import loader
loader.load(app.config)