def testSimpleCase(self):
tree = DecisionTree()
tree.fit(simpleData)
for datum in simpleData:
self.assertEqual(datum[-1], tree.predict(datum))
tree.print()
def test(): X = [[1, 2, 0, 1, 0], [0, 1, 1, 0, 1], [1, 0, 0, 0, 1], [2, 1, 1, 0, 1], [1, 1, 0, 1, 1]] y = ['yes','yes','no','no','no'] decision_tree = DecisionTree(mode = 'C4.5') decision_tree.fit(X,y) res = decision_tree.predict(X) print res model_name = 'test.dt' decision_tree.saveModel(model_name) new_tree = DecisionTree() new_tree.loadModel(model_name) print new_tree.predict(X)
# zip categorical and non-categorical data together
train_data = np.concatenate((cat_data, non_cat_data), axis=1)
train_label = data[:, -1].astype(int)
validation_data = train_data[:200, :]
validation_label = train_label[:200]
train_data = train_data[:, :]
train_label = train_label[:]
test_data = np.concatenate((cat_data_test, non_cat_data_test), axis=1)
# decision tree
tree = DecisionTree(5, train_data.shape[0])
tree.train(train_data, train_label)
res = tree.predict(validation_data)
score = 0
for i in range(len(res)):
if res[i] == validation_label[i]:
score += 1
score /= len(res)
print(score)
# random forest
forest = RandomForest(100,5,train_data.shape[0],6)
forest.train(train_data, train_label)
res = forest.predict(validation_data)
score = 0
label2id = {'loss': 0, 'draw': 1, 'win': 2}
p2f = {'b': 0, 'x': 1, 'o': 2}
for line in fin:
line = line.strip().split(',')
label = label2id[line[-1]]
feature = np.array([p2f[p] for p in line[:-1]])
data.append((feature, label))
fin.close()
return data
data = read('connect-4.data')
x = np.array([d[0] for d in data])
y = np.array([d[1] for d in data])
#y = label_binarize(y, classes=list(range(3)))
kf = KFold(5, True)
all_f1 = []
for train_index, test_index in kf.split(x):
x_train, y_train, x_test, y_test = x[train_index], y[train_index], x[
test_index], y[test_index]
#x_train, x_test, y_train, y_test = train_test_split(x, y)
#print('training')
#model = OneVsRestClassifier(SVC(kernel='rbf'))
model = DecisionTree()
model.fit(x_train, y_train)
#print('testing')
y_pred = model.predict(x_test)
all_f1.append(f1_score(y_test, y_pred, average='macro'))
print(sum(all_f1) / 5)
# zip categorical and non-categorical data together
train_data = np.concatenate((cat_data, non_cat_data), axis=1)
train_label = data[:, -1].astype(int)
validation_data = train_data[:6000, :]
validation_label = train_label[:6000]
train_data = train_data[6000:,:]
train_label = train_label[6000:]
test_data = np.concatenate((cat_data_test,non_cat_data_test), axis=1)
# plot accuracy
accuracy = []
for i in range(40):
tree = DecisionTree(i,105)
tree.train(train_data,train_label)
res = tree.predict(validation_data)
score = 0
for i in range(len(res)):
if res[i] == validation_label[i]:
score += 1
score /= len(res)
accuracy.append(score)
plt.plot(accuracy)
plt.xlabel('depth')
plt.ylabel('accuracy')
plt.title('Accuracy vs. Decision Tree Depth')
plt.savefig('p6.png')
plt.show()
#decisionTree.LSID3(3)
#decisionTree.LSID3PathSample(2)
#decisionTree.LSID3MC(1, 0.1)
#decisionTree.BLSID3(1)
#decisionTree.BLSID3PathSample(1)
#decisionTree.LSID3Sequenced(2)
#decisionTree.IIDT(10, 0.5)
print("****Tree Data BEFORE Pruning****")
print("Tree Size - Number of Nodes:", decisionTree.size())
print("Number of Leafs:", decisionTree.getNumLeafs())
print("Tree Depth:", decisionTree.getTreeDepth())
testSetFile = open('SampleSets/test_set.csv')
testSetData = testSetFile.readlines()
testSetFile.close()
print("Prediction:", str(decisionTree.predict(testSetData) * 100) + "%")
#decisionTreePlot = DecisionTreePlot()
#decisionTreePlot.createDecisionTreePlot(decisionTree)
print("****Tree Data AFTER Pruning****")
validationSetFile = open('SampleSets/validation_set.csv')
validationSetData = validationSetFile.readlines()
validationSetFile.close()
decisionTree.prune(validationSetData)
print("Tree Size - Number of Nodes:", decisionTree.size())
print("Number of Leafs:", decisionTree.getNumLeafs())
print("Tree Depth:", decisionTree.getTreeDepth())
print("Prediction:", str(decisionTree.predict(testSetData) * 100) + "%")
#decisionTreePlot = DecisionTreePlot()
#decisionTreePlot.createDecisionTreePlot(decisionTree)
def testComplexCase(self):
tree = DecisionTree()
tree.fit(complexData)
for datum in complexData:
self.assertEqual(datum[-1], tree.predict(datum))
# Overcast = YES
self.assertEqual(
Label.YES,
tree.predict(
[Outlook.Overcast, Temperature.Hot, Humidity.High, Wind.Weak]))
self.assertEqual(
Label.YES,
tree.predict([
Outlook.Overcast, Temperature.Cool, Humidity.Normal,
Wind.Strong
]))
# Sunny + Normal = YES
self.assertEqual(
Label.YES,
tree.predict([
Outlook.Sunny, Temperature.Cool, Humidity.Normal, Wind.Strong
]))
self.assertEqual(
Label.YES,
tree.predict(
[Outlook.Sunny, Temperature.Hot, Humidity.Normal, Wind.Weak]))
# Sunny + High = NO
self.assertEqual(
Label.NO,
tree.predict(
[Outlook.Sunny, Temperature.Cool, Humidity.High, Wind.Strong]))
self.assertEqual(
Label.NO,
tree.predict(
[Outlook.Sunny, Temperature.Hot, Humidity.High, Wind.Weak]))
# Rain + Weak = Yes
self.assertEqual(
Label.YES,
tree.predict(
[Outlook.Rain, Temperature.Cool, Humidity.Normal, Wind.Weak]))
self.assertEqual(
Label.YES,
tree.predict(
[Outlook.Rain, Temperature.Hot, Humidity.High, Wind.Weak]))
# Rain + Strong = No
self.assertEqual(
Label.NO,
tree.predict(
[Outlook.Rain, Temperature.Cool, Humidity.Normal,
Wind.Strong]))
self.assertEqual(
Label.NO,
tree.predict(
[Outlook.Rain, Temperature.Hot, Humidity.High, Wind.Strong]))
tree.print()