def genetic_tree_optimization(n_trees, n_iter, depth, X, labels, oblique, X_valid, y_valid, CR=0.95, l = 1):
clf = RandomForestClassifier(n_estimators = n_trees, max_depth=depth, random_state=0, min_samples_leaf= 4)
clf.fit(X, labels)
random_trees = clf.estimators_
trees = []
best_loss = np.inf
best_tree = None
for tree in random_trees:
T = ClassificationTree(oblique = oblique)
T.initialize_from_CART(X, labels, tree)
tao_opt(T, X, labels)
trees.append(T)
ClassificationTree.build_idxs_of_subtree(X, range(len(labels)), T.tree[0], oblique)
#ClassificationTree.restore_tree(T)
#multi_optimize_tao(trees, X, labels)
best_loss = np.inf
best_tree = None
for i in range(n_iter):
print("Iter: ", i)
#multi_optimize_evolution(trees, X, labels, CR)
for tree in trees:
#optimize_evolution(tree, trees, X, labels, X_valid, y_valid, CR)
trial = mutation(tree, trees, CR, X, labels, depth)
tao_opt(trial, X, labels)
trial_loss = regularized_loss(trial.tree[0], X, labels, X_valid, y_valid, range(len(labels)), oblique, l=l)
loss = regularized_loss(tree.tree[0], X, labels, X_valid, y_valid, range(len(labels)), oblique, l=l)
if trial_loss < loss:
tree = trial
#print("migliore")
if loss < best_loss:
best_loss = loss
best_tree = tree
print ("best loss: ", best_loss)
print("loss train best: ", 1-ClassificationTree.misclassification_loss(best_tree.tree[0], X, labels, range(len(labels)), oblique))
print("loss valid: ", 1-ClassificationTree.misclassification_loss(best_tree.tree[0], X_valid, y_valid, range(len(y_valid)), oblique))
print("ritorno loss train best: ", 1-ClassificationTree.misclassification_loss(best_tree.tree[0], X, labels, range(len(labels)), oblique))
print("ritono loss valid: ", 1-ClassificationTree.misclassification_loss(best_tree.tree[0], X_valid, y_valid, range(len(y_valid)), oblique))
return best_tree, best_loss
def optimize_evolution(tree, trees, X, labels, X_valid, y_valid, CR):
trial = ClassificationTree.copy_tree(tree)
'''
n_nodes = len(X[0])/(2**tree.depth - 1)
if n_nodes < 1:
n_nodes = 1
p = np.random.uniform()
for node in nodes:
if p < CR and not node.is_leaf:
node.feature = np.random.randint(0, len(X[0]))
node.threshold = np.random.uniform(np.min(X[node.feature]),np.max(X[node.feature]))
'''
crossover(trial, trees, CR, X)
ClassificationTree.build_idxs_of_subtree(X, range(len(labels)), trial.tree[0], oblique)
#partners = random.sample(trees, 2)
#optimize_crossover(trial, ClassificationTree.copy_tree(partners[0]), ClassificationTree.copy_tree(partners[1]), depth, X, labels, oblique)
tao_opt(trial, X, labels)
loss = regularized_loss(trial.tree[0], X, labels, X_valid, y_valid, range(len(labels)), oblique)
#Se il nuovo individuo è migliore del padre li scambio
if loss < regularized_loss(tree.tree[0], X, labels, X_valid, y_valid, range(len(labels)), oblique):
#if loss < ClassificationTree.misclassification_loss(tree.tree[0], X, labels, range(len(labels)), oblique):
tree = trial