def wine_net(seed, r, nn_type, options=None):
if nn_type is 'cat':
filename = '../resources/winequality/winequality-combined-cat.csv'
y_key = 'Reviews'
split_options = {'exclude-keys': ['quality']}
else:
filename = '../resources/winequality/winequality-combined.csv'
y_key = 'quality'
split_options = {'exclude-keys': []}
split_options['perc_sample'] = r
dir = 'nn-exports/wine/'
seed_dir = 'attempts/' + dir + str(seed) + '/'
np.random.seed(seed)
options = util.default(options, {})
class_types = util.myget(options, 'class_types', ['net'])
layers = util.myget(options, 'layers', [(5, 6)])
data = util.get_data(filename)
split_data = util.prep_data(data, y_key, split_options)
net_results = {}
for t in class_types:
for l in layers:
np.random.seed(seed)
start_time = datetime.datetime.now()
[train_results,
test_results] = train_and_test(seed_dir, split_data, t, l)
net_results[t + '_train'] = train_results
net_results[t + '_test'] = test_results
total_time = datetime.datetime.now() - start_time
write_results(seed, t, dir, train_results['error-perc'],
test_results['error-perc'], total_time,
len(split_data[0]), l, nn_type + '-')
pass
def breast_cancer_net(seed, r, options=None):
dir = 'nn-exports/breast_cancer/'
seed_dir = 'attempts/' + dir + str(seed) + '/'
np.random.seed(seed)
options = util.default(options, {})
class_types = util.myget(options, 'class_types', ['net'])
layers = util.myget(options, 'layers', [(5, 6)])
data = util.get_data('../resources/breast-cancer/wdbc.data.csv')
data = util.split_feature(data, 'diagnosis')
split_data = util.prep_data(
data, 'diagnosis_M', {
'exclude-keys': ['id', 'diagnosis_B', 'diagnosis'],
'perc_sample': r
})
net_results = {}
for t in class_types:
for l in layers:
np.random.seed(seed)
start_time = datetime.datetime.now()
[train_results,
test_results] = train_and_test(seed_dir, split_data, t, l)
net_results[t + '_train'] = train_results
net_results[t + '_test'] = test_results
total_time = datetime.datetime.now() - start_time
write_results(seed, t, dir, train_results['error-perc'],
test_results['error-perc'], total_time,
len(split_data[0]), l)
return net_results
def main():
filename = '../resources/winequality/winequality-combined.csv'
# filename = '../resources/winequality/dummy-data.csv'
exclude_column = 'quality'
# exclude_column = 'stuff3'
data = util.get_data(filename)
duplicated = data.loc[:, data.columns != exclude_column].duplicated()
print(duplicated.value_counts())
print(data.duplicated().value_counts())
data = data.sort_values(by=list(data.columns))
return duplicated
def wine_report_prep(level):
if level is 'cat':
filename = '../resources/winequality/winequality-combined-cat.csv'
y_key = 'Reviews'
split_options = {'exclude-keys': ['quality']}
else:
filename = '../resources/winequality/winequality-combined.csv'
y_key = 'quality'
split_options = {'exclude-keys': []}
data = util.get_data(filename)
return data, y_key, split_options
def main2():
filename = '../resources/winequality/winequality-combined.csv'
data = util.get_data(filename)
reviews = []
for i in data['quality']:
if i >= 1 and i <= 3:
reviews.append('1')
elif i >= 4 and i <= 7:
reviews.append('2')
elif i >= 8 and i <= 10:
reviews.append('3')
data['Reviews'] = reviews
data.to_csv('../resources/winequality/winequality-combined-cat.csv')
def breast_cancer_prep():
bc_data = util.get_data('../resources/breast-cancer/wdbc.data.csv')
bc_data = util.split_feature(bc_data, 'diagnosis')
return bc_data