def predict_wine_quality(table, n):
#Make the continous varibles discrete
disc = Discretize()
disc.method = discretize.EqualWidth(n=n)
table = disc(table)
#Define domain
feature_vars = list(table.domain[1:])
class_label_var = table.domain[0]
wine_domain = Domain(feature_vars, class_label_var)
table = Table.from_table(domain=wine_domain, source=table)
#Construct learner and print results
tree_learner = NNClassificationLearner(hidden_layer_sizes=(10, ),
max_iter=4000)
eval_results = CrossValidation(table, [tree_learner], k=10)
print("Accuracy of cross validation: {:.3f}".format(
scoring.CA(eval_results)[0]))
print("AUC: {:.3f}".format(scoring.AUC(eval_results)[0]))
def test_NN_classification_predict_single_instance(self):
lrn = NNClassificationLearner()
clf = lrn(self.iris)
for ins in self.iris[::20]:
clf(ins)
_, _ = clf(ins, clf.ValueProbs)
def test_NN_classification(self):
results = CrossValidation(self.iris, [NNClassificationLearner()], k=3)
ca = CA(results)
self.assertGreater(ca, 0.8)
self.assertLess(ca, 0.99)
wine_domain = Domain(feature_vars, class_label_var)
data_table = Table.from_table(domain=wine_domain, source=raw_data_table)
Table.save(data_table, "data_table normal2.csv")
def normalize_table(table_to_process):
norm = Normalize(norm_type=Normalize.NormalizeBySpan)
norm.transform_class = False
norm_data_table = norm(table_to_process)
norm_data_table.shuffle()
return norm_data_table
#Normalise the feature values
norm_data_table = normalize_table(data_table)
print("Applying learner on total data records {}".format(len(norm_data_table)))
#Create a NN classifier learner
then = datetime.datetime.now()
ann_learner = NNClassificationLearner(hidden_layer_sizes=(10, ),max_iter=4000 )
ann_classifier = ann_learner(norm_data_table)
#Do the 10 folds cross validation
eval_results = CrossValidation(norm_data_table, [ann_learner], k=10)
now = datetime.datetime.now()
tdelta = now - then
print("Processing completed after: {} ".format(tdelta))
#Accuracy and area under (receiver operating characteristic, ROC) curve (AUC)
print("Accuracy: {:.3f}".format(scoring.CA(eval_results)[0]))
print("AUC: {:.3f}".format(scoring.AUC(eval_results)[0]))
#Remove minority classes
value_counts = pd.Series(raw_data_table[:,0]).value_counts()[pd.Series(raw_data_table[:,0]).value_counts() > 10]
value_counts1 = pd.Series(raw_data_table[:,0]).value_counts()[pd.Series(raw_data_table[:,0]).value_counts() < 10]
from Orange.classification import NNClassificationLearner
from Orange.evaluation import CrossValidation, scoring
data_tab = Table('iris')
feature_vars = list(data_tab.domain[:-1])
class_label_var = data_tab.domain[len(data_tab.domain) - 1]
iris_domain = Domain(feature_vars, class_label_var)
data_tab = Table.from_table(domain=iris_domain, source=data_tab)
print("DOMAIN: %s \nVARIABLES: %s \nATTRIBUTES: %s \nCLASS_VAR: %s" %
(data_tab.domain, data_tab.domain.variables, data_tab.domain.attributes,
data_tab.domain.class_var))
print(len(data_tab))
tree_learner = NNClassificationLearner(hidden_layer_sizes=(10, ),
max_iter=1750)
#Accuracy of cross validation: 0.953
#AUC: 0.991
eval_results = CrossValidation(data_tab, [tree_learner], k=10)
print("Accuracy of cross validation: {:.3f}".format(
scoring.CA(eval_results)[0]))
print("AUC: {:.3f}".format(scoring.AUC(eval_results)[0]))
#####################TASK 3##########################
tree_learner2 = NNClassificationLearner(hidden_layer_sizes=(10, ),
max_iter=2000,
verbose=True,
solver="sgd",
learning_rate_init=3,
learning_rate="invscaling",
power_t=0.3)
def test_NN_classification(self):
results = CrossValidation(self.iris, [NNClassificationLearner()], k=3)
self.assertGreater(CA(results), 0.90)