def test(self):
"""Function that tests all depths and method you want. Give it a tester object
Returns
-------
:self.train_err: numpy array of training errs (row: method, col: depth)
:self.test_err: numpy array of test errs (row: method, col: depth)
"""
# loop through methods and depths for each method
for i, method in enumerate(self.methods):
for j, d in enumerate(self.depths):
# initialize and make decision tree with specified depth and method
treeInit = None
dt = None
treeInit = decisionTree(self.dfTrain,
depth=d,
method=method,
numerical=self.numerical,
randTieBreak=self.tie)
print('Creating DT with depth limit: {} and method: {}...'.
format(d, method))
dt = run_ID3(treeInit)
print('Tree complete')
# get errors by applying the tree to both train and test sets
print('Applying the tree to train and test...')
self.train_err[i, j] = self._applyAndError(
dt, self.dfTrain, treeInit, numerical=self.numerical)
self.test_err[i, j] = self._applyAndError(
dt, self.dfTest, treeInit, numerical=self.numerical)
print('Applying complete\n')
print('Done\n')
return self.train_err, self.test_err
def _bagging_loop(self):
for t in range(self.T):
if (t) % np.round(self.T / 10) == 0:
self._bag_progress(t)
bootstrap = self.draw_with_replacement()
if self.small_sub:
tree_init = decisionTree(bootstrap,
numerical=self.numerical,
small_sub=self.small_sub,
globaldf=self.globaldf,
randForest=self.randForest,
Gsize=self.Gsize)
else:
tree_init = decisionTree(bootstrap,
numerical=self.numerical,
randForest=self.randForest,
Gsize=self.Gsize)
self.treesInit.append(tree_init)
run_ID3(tree_init)
self._calc_vote(tree_init, t, numerical=self.numerical)
if self.verbose:
print('100% done.\n')
def _AdaLoop(self, D):
print('Starting training...')
for t in range(self.T):
if (t) % np.round(self.T / 10) == 0:
self._progress(t)
stump_init = decisionTree(self.data,
numerical=True,
depth=self.depth,
weights=D)
run_ID3(stump_init)
self.learners_init.append(stump_init)
h_t = self._calc_vote(stump_init, t, D, numerical=True)
Dtp1 = self._update_weights(D, t, h_t)
D = Dtp1
print('Done training\n')
import matplotlib.pyplot as plt
import time
# %% importing the data and splitting it up
cols = list(pd.read_csv('car/data-desc.txt', skiprows=14))
train0 = pd.read_csv('car/train.csv', names=cols)
test0 = pd.read_csv('car/test.csv', names=cols)
attrTrain0 = np.array(train0.iloc[:, :-1])
attrTest0 = np.array(test0.iloc[:, :-1])
attrNames0 = cols[:-1]
labelsTrain0 = np.array(train0.iloc[:, -1])
labelsTest0 = np.array(test0.iloc[:, -1])
# %% training the ID3 algo for testing
carTreeInit = decisionTree(train0, method='entropy')
carTree = run_ID3(carTreeInit)
# %% applying the ID3 algo for testing
car_errinit = applyTree(carTree, test0, carTreeInit)
errs0, total_err0 = apply_ID3(car_errinit)
# %% making trees
tic = time.perf_counter()
methods = ['entropy', 'ME', 'gini']
datTrain0 = [attrTrain0, labelsTrain0, train0]
datTest0 = [attrTest0, labelsTest0, test0]
dfs = [train0, test0]
depths0 = len(attrNames0)
errinit = tester(methods, dfs, depths=depths0)
# %% importing the data
cols = [
'age', 'job', 'marital', 'education', 'default', 'balance', 'housing',
'loan', 'contact', 'day', 'month', 'duration', 'campaign', 'pdays',
'previous', 'poutcome', 'y'
]
train = pd.read_csv('bank/train.csv', names=cols)
test = pd.read_csv('bank/test.csv', names=cols)
train_no_unk = replace_unk(train.copy())
test_no_unk = replace_unk(test.copy())
# %% training the ID3 algo for testing
tic = time.perf_counter()
bankTreeInit = decisionTree(train, numerical=True)
bankTree = run_ID3(bankTreeInit)
# % applying the ID3 algo for testing
errinit = applyTree(bankTree, train, bankTreeInit, numerical=True)
errs, total_err = apply_ID3(errinit)
toc = time.perf_counter()
print('Time for bank code is {:0.4f} seconds.'.format(toc - tic))
# %% making trees
tic = time.perf_counter()
methods = ['entropy', 'ME', 'gini']
depths = len(train.columns) - 1
dfs = [train, test]
errinit = tester(methods, dfs, depths=depths, numerical=True)
# %%
def entropy(ps):
return -sum([p * np.log2(p) for p in ps])
# %% Training Data
# making the training data with columns as x1, x2, x3, x4
attributes = np.array([[0, 0, 0, 1, 0, 1, 0], [0, 1, 0, 0, 1, 1, 1],
[1, 0, 1, 0, 1, 0, 0], [0, 0, 1, 1, 0, 0, 1]]).T
# Boolean labels
y = np.array([0, 0, 1, 1, 0, 0, 0]).T
attrNames = [0, 1, 2, 3]
# %% run ID3 on 1a
init1 = decisionTree(attributes, attrNames, y, method='gini')
tree1 = run_ID3(init1)
# %% tennis data
attributes2 = np.array(
[['S', 'S', 'O', 'R', 'R', 'R', 'O', 'S', 'S', 'R', 'S', 'O', 'O', 'R'],
['H', 'H', 'H', 'M', 'C', 'C', 'C', 'M', 'C', 'M', 'M', 'M', 'H', 'M'],
['H', 'H', 'H', 'H', 'N', 'N', 'N', 'H', 'N', 'N', 'N', 'H', 'N', 'H'],
['W', 'S', 'W', 'W', 'W', 'S', 'S', 'W', 'W', 'W', 'S', 'S', 'W', 'S']]).T
y2 = np.array([0, 0, 1, 1, 1, 0, 1, 0, 1, 1, 1, 1, 1, 0]).T
attrNames2 = ['Outlook', 'Temp', 'Humidity', 'Wind']
init2 = decisionTree(attributes2, attrNames2, y2, method='ME')
tree2 = run_ID3(init2)
# %% ID3 on 3a