def setUp(self):
"""Set up test data.
"""
self.restaurant = {
'restaurants': [0] * 6 + [1] * 6,
'split_patrons': [[0, 0], [1, 1, 1, 1], [1, 1, 0, 0, 0, 0]],
'split_food_type': [[0, 1], [0, 1], [0, 0, 1, 1], [0, 0, 1, 1]]
}
self.dataset = dt.load_csv('part23_data.csv')
self.train_features, self.train_classes = self.dataset
def a1():
dataset = dt.load_csv('challenge_train.csv',class_index=0)
train_features,train_classes= dataset
sums=0
for _ in range(10):
tree2=dt.ChallengeClassifier()
tree2.fit(train_features,train_classes)
a=tree2.classify(train_features)
for i in range(len(train_classes)):
if a[i]==train_classes[i]:
sums+=1
print(sums/10/len(train_classes))
def a2():
dataset = dt.load_csv('challenge_train.csv',class_index=0)
train_features,train_classes= dataset
sums=0
for _ in range(5):
tree2=dt.RandomForest(10,5,0.8,0.8)
tree2.fit(train_features,train_classes)
a=tree2.classify(train_features)
for i in range(len(train_classes)):
if a[i]==train_classes[i]:
sums+=1
print(sums/5/len(train_classes))
def setUp(self):
#Set up test data.
#
#print("in setup")
self.restaurant = {'restaurants': [0] * 6 + [1] * 6,
'split_patrons': [[0, 0],
[1, 1, 1, 1],
[1, 1, 0, 0, 0, 0]],
'split_food_type': [[0, 1],
[0, 1],
[0, 0, 1, 1],
[0, 0, 1, 1]]}
self.dataset = dt.load_csv('challenge_train.csv', class_index = 0)
#self.dataset = dt.load_csv('part23_data.csv', class_index = -1)
self.train_features, self.train_classes = self.dataset
def test_clf(params):
dataset = dt.load_csv('challenge_train.csv', 0)
# pdb.set_trace()
train_features, train_classes = dataset
folds = dt.generate_k_folds(dataset, 5)
accuracy = []
for idx, fold in enumerate(folds):
training_set, test_set = fold
clf = dt.ChallengeClassifier(**params)
clf.fit(training_set[0], training_set[1])
preds = clf.classify(test_set[0])
accuracy.append(dt.accuracy(preds, test_set[1]))
# print("Fold %d" %idx)
# print("accuracy %f" %(dt.accuracy(preds, test_set[1])))
# print("precision %f" %(dt.precision(preds, test_set[1])))
# print("recall %f" %(dt.recall(preds, test_set[1])))
print(params, np.mean(accuracy))
def setUp(self):
"""Set up test data.
"""
self.vector = dt.Vectorization()
self.data = dt.load_csv('vectorize.csv', 1)