def test_forest():
#加载数据
train_set = pd.read_csv('./data_set/seeds.csv')
data_set = np.array(train_set)
X = data_set[:, :-1]
y = data_set[:, -1]
train_X, test_X, train_y, y_true = train_test_split(X,
y,
test_size=1 / 3.,
random_state=7)
# 加载模型
rf_model = RandomForestClassifier(n_estimators=3,
criterion='gini',
max_features='sqrt',
max_depth=20)
rf_model.fit(train_X, train_y) #创建决策树集合
print('rf_model.predict...begin...')
pre_result = rf_model.predict(test_X)
print('训练数据的预测概率向量：')
print(pre_result)
print('真实标签 ：')
print(y_true)
print('训练数据的预测准确度：')
print(accuracy_score(y_true, pre_result))
def grid_search_RF():
dataset = datasets.load_digits()
X_train, X_test, y_train, y_test = train_test_split(dataset['data'], dataset['target'], test_size=0.3, random_state=0)
trees_num_list = [16, 32, 64, 128] # ランダムフォレストに含まれる決定木の個数の候補
bootstrap_list = [0.1, 0.3, 0.5, 0.7, 0.9] # ブートストラップ法で復元するデータ量の元のデータ量に対する割合の候補
best_acc = 0
best_trees_num = None
best_bootstrap = None
with tqdm(total=len(trees_num_list)*len(bootstrap_list), desc='Progress') as pbar:
for trees_num in trees_num_list:
for bootstrap in bootstrap_list:
random_forest = RandomForestClassifier(trees_num=trees_num, max_depth=5, bootstrap=bootstrap)
random_forest.fit(X_train, y_train)
acc = random_forest.accuracy_score(X_test, y_test)
if acc > best_acc:
best_acc = acc
best_trees_num = trees_num
best_bootstrap = bootstrap
pbar.update(1)
print('best acc : {:.4f} best trees_num : {} best bootstrap : {}'.format(best_acc, best_trees_num, best_bootstrap))
return best_trees_num, best_bootstrap
def compare_performance(trees_num, max_depth, bootstrap):
dataset = datasets.load_digits()
X_train, X_test, y_train, y_test = train_test_split(dataset['data'], dataset['target'], test_size=0.3, random_state=0)
# 決定木
print('##### 決定木の性能 #####')
decision_tree = DecisionTreeClassifier(max_depth=max_depth)
dt_lr_start = time.time() # 学習開始時間を記録
decision_tree.fit(X_train, y_train)
dt_lr_time = time.time() - dt_lr_start # 学習時間
dt_est_start = time.time() # 推論開始時間を記録
y_est = decision_tree.predict(X_test)
dt_est_time = time.time() - dt_est_start # 推論時間
print('学習時間 : {:.6f} [sec] 推論時間 : {:.6f} [sec]'.format(dt_lr_time, dt_est_time))
dt_train_accuracy = decision_tree.accuracy_score(X_train, y_train)
dt_test_accuracy = decision_tree.accuracy_score(X_test, y_test)
print('train accuracy : {:.4f} test_accuracy : {:.4f}'.format(dt_train_accuracy, dt_test_accuracy))
# ランダムフォレスト
print('##### ランダムフォレストの性能 #####')
random_forest = RandomForestClassifier(trees_num=trees_num, max_depth=max_depth, bootstrap=bootstrap)
rf_lr_start = time.time() # 学習開始時間を記録
random_forest.fit(X_train, y_train)
rf_lr_time = time.time() - rf_lr_start # 学習時間
rf_est_start = time.time() # 推論開始時間を記録
y_est = random_forest.predict(X_test)
rf_est_time = time.time() - rf_est_start # 推論時間
print('学習時間 : {:.6f} [sec] 推論時間 : {:.6f} [sec]'.format(rf_lr_time, rf_est_time))
rf_train_accuracy = random_forest.accuracy_score(X_train, y_train)
rf_test_accuracy = random_forest.accuracy_score(X_test, y_test)
print('train accuracy : {:.4f} test_accuracy : {:.4f}'.format(rf_train_accuracy, rf_test_accuracy))
def test_rf_classification():
iris = datasets.load_iris()
X, y = iris.data, iris.target
print (X.shape, y.shape)
train_X, train_y, test_X, test_y = split_train_test(X, y)
print (train_X.shape, train_y.shape, test_X.shape, test_y.shape)
clf = RandomForestClassifier(n_estimators=100)
clf.fit(train_X, train_y)
preds = clf.predict(test_X)
accuracy = cal_accuracy(test_y, preds)
print ('accuracy: ', accuracy)
def compare_depth():
dataset = datasets.load_digits()
X_train, X_test, y_train, y_test = train_test_split(dataset['data'], dataset['target'], test_size=0.3, random_state=0)
# ランダムフォレストに関して、最良のハイパーパラメータを調べる
trees_num, bootstrap = grid_search_RF()
# 決定木の深度の制限を変えて、調べる
depth_list = [i for i in range(21)] # 深さの制限0~20まで調べる
dt_train_acc_list = []
dt_test_acc_list = []
rf_train_acc_list = []
rf_test_acc_list = []
for depth in tqdm(depth_list):
print('***** max_depth = {} *****'.format(depth))
# 決定木
decision_tree = DecisionTreeClassifier(max_depth=depth)
decision_tree.fit(X_train, y_train)
dt_train_accuracy = decision_tree.accuracy_score(X_train, y_train)
dt_test_accuracy = decision_tree.accuracy_score(X_test, y_test)
# accuracyをリストに追加
dt_train_acc_list.append(dt_train_accuracy)
dt_test_acc_list.append(dt_test_accuracy)
print('決定木 train accuracy : {:.4f} test_accuracy : {:.4f}'.format(dt_train_accuracy, dt_test_accuracy))
# ランダムフォレスト
random_forest = RandomForestClassifier(trees_num=trees_num, max_depth=depth, bootstrap=bootstrap)
random_forest.fit(X_train, y_train)
rf_train_accuracy = random_forest.accuracy_score(X_train, y_train)
rf_test_accuracy = random_forest.accuracy_score(X_test, y_test)
# accuracyをリストに追加
rf_train_acc_list.append(rf_train_accuracy)
rf_test_acc_list.append(rf_test_accuracy)
print('ランダムフォレスト train accuracy : {:.4f} test_accuracy : {:.4f}'.format(rf_train_accuracy, rf_test_accuracy))
# グラフの描画
plt.plot(depth_list, dt_train_acc_list, label='Decision Tree - train accuracy', color='r')
plt.plot(depth_list, dt_test_acc_list, label='Decision Tree - test accuracy', color='g')
plt.plot(depth_list, rf_train_acc_list, label='Random Forest - train accuracy', color='y')
plt.plot(depth_list, rf_test_acc_list, label='Random Forest - test accuracy', color='b')
plt.xlabel('Max Depth')
plt.ylabel('Accuracy')
plt.xlim(0, 20)
plt.xticks(np.arange(0, 21, 2))
plt.ylim(0, 1.0)
plt.legend(loc='lower right')
plt.title('Max Depth of Decision Trees and Accuracy')
# グラフを保存
plt.savefig('figures/mnist/max_depth_&_accuracy.png')
def train_and_predict(x_train, y_train, x_test, x_val, y_val):
""" Interface to train and test the new/improved decision tree.
This function is an interface for training and testing the new/improved
decision tree classifier.
x_train and y_train should be used to train your classifier, while
x_test should be used to test your classifier.
x_val and y_val may optionally be used as the validation dataset.
You can just ignore x_val and y_val if you do not need a validation dataset.
Args:
x_train (numpy.ndarray): Training instances, numpy array of shape (N, K)
N is the number of instances
K is the number of attributes
y_train (numpy.ndarray): Class labels, numpy array of shape (N, )
Each element in y is a str
x_test (numpy.ndarray): Test instances, numpy array of shape (M, K)
M is the number of test instances
K is the number of attributes
x_val (numpy.ndarray): Validation instances, numpy array of shape (L, K)
L is the number of validation instances
K is the number of attributes
y_val (numpy.ndarray): Class labels of validation set, numpy array of shape (L, )
"""
#######################################################################
# ** TASK 4.2: COMPLETE THIS FUNCTION **
#######################################################################
# TODO: Train new classifier
forest = RandomForestClassifier()
# Forest is trained on the best hyperparameter set
forest.update_hyperparameters(feature_sel=True,
cross_val=False,
max_tree_depth=13,
min_sample_size=2,
num_trees=20)
forest.fit(x_train, y_train)
# set up an empty (M, ) numpy array to store the predicted labels
# feel free to change this if needed
# TODO: Make predictions on x_test using new classifier
predictions = forest.predict(x_test)
# return result on best classifier option
# remember to change this if you rename the variable
return predictions
def main():
dataset = datasets.load_iris()
X_train, X_test, y_train, y_test = train_test_split(dataset['data'],
dataset['target'],
test_size=0.3,
random_state=0)
# 決定木の深度の制限が1~3、制限なしの各場合について調べる
depth_list = [1, 2, 3, None]
for depth in depth_list:
print('######### max_depth = {} #########'.format(depth))
# 全ての特徴量を使用したときの精度、学習時間、推論時間、汎化性能を調べる
# 決定木
decision_tree = DecisionTreeClassifier(max_depth=depth)
dt_lr_start = time.time() # 学習開始時間を記録
decision_tree.fit(X_train, y_train)
dt_lr_time = time.time() - dt_lr_start # 学習時間
dt_est_start = time.time() # 推論開始時間を記録
y_est = decision_tree.predict(X_test)
dt_est_time = time.time() - dt_est_start # 推論時間
print('決定木 学習時間 : {:.6f} [sec] 推論時間 : {:.6f} [sec]'.format(
dt_lr_time, dt_est_time))
dt_train_accuracy = decision_tree.accuracy_score(X_train, y_train)
dt_test_accuracy = decision_tree.accuracy_score(X_test, y_test)
print('決定木 train accuracy : {:.4f} test_accuracy : {:.4f}'.
format(dt_train_accuracy, dt_test_accuracy))
# ランダムフォレスト
random_forest = RandomForestClassifier(max_depth=depth)
rf_lr_start = time.time() # 学習開始時間を記録
random_forest.fit(X_train, y_train)
rf_lr_time = time.time() - rf_lr_start # 学習時間
rf_est_start = time.time() # 推論開始時間を記録
y_est = random_forest.predict(X_test)
rf_est_time = time.time() - rf_est_start # 推論時間
print('ランダムフォレスト 学習時間 : {:.6f} [sec] 推論時間 : {:.6f} [sec]'.
format(rf_lr_time, rf_est_time))
rf_train_accuracy = random_forest.accuracy_score(X_train, y_train)
rf_test_accuracy = random_forest.accuracy_score(X_test, y_test)
print(
'ランダムフォレスト train accuracy : {:.4f} test_accuracy : {:.4f}'
.format(rf_train_accuracy, rf_test_accuracy))
# 使用する特徴量を2つ(Petal legth, Petal width)に絞って、二次元で可視化
visualize('decision_tree', max_depth=depth)
visualize('random_forest', max_depth=depth)
def random_forest_classification(self, train_data):
train_X = train_data[:, :-1]
train_y = train_data[:, -1]
print("train_X ......type.....")
print(type(train_X))
self.k_class_ = list(set(train_y)) #
rf_model = RandomForestClassifier(n_estimators=10,
criterion='gini',
max_features='sqrt',
max_depth=20)
rf_model.fit(train_X, train_y)
# 保存模型
self.rf_model = rf_model
save_model_rf_model(rf_model)
def test_random_foerst_fit_predict(self):
model = RandomForestClassifier(n_estimators=100)
features = np.array([
[0, 0],
[0, 0],
[0, 1],
[0, 1],
[0, 1],
[1, 0],
[1, 0],
[1, 0],
[1, 1],
[1, 1],
[1, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 1],
[0, 1],
[1, 0],
[1, 0],
[1, 0],
[1, 1],
[1, 1],
[1, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 1],
[0, 1],
[1, 0],
[1, 0],
[1, 0],
[1, 1],
[1, 1],
[1, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 1],
[0, 1],
[1, 0],
[1, 0],
[1, 0],
[1, 1],
[1, 1],
[1, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 1],
[0, 1],
[1, 0],
[1, 0],
[1, 0],
[1, 1],
[1, 1],
[1, 1],
[0, 0],
[0, 0],
[0, 1],
[0, 1],
[0, 1],
[1, 0],
[1, 0],
[1, 0],
[1, 1],
[1, 1],
[1, 1],
])
labels = np.array([
0,
0,
1,
1,
1,
1,
1,
1,
0,
0,
0,
0,
0,
1,
1,
1,
1,
1,
1,
0,
0,
0,
0,
0,
1,
1,
1,
1,
1,
1,
0,
0,
0,
0,
0,
1,
1,
1,
1,
1,
1,
0,
0,
0,
0,
0,
1,
1,
1,
1,
1,
1,
0,
0,
0,
0,
0,
1,
1,
1,
1,
1,
1,
0,
0,
0,
])
model.fit(features, labels)
"""
for tree in model._models:
print("=================================")
from pprint import pprint
pprint(tree._node)
for tree in model._models:
print(tree.predict(np.array([[0, 0], [0, 1], [1, 0], [1, 1]])))
"""
predictions = model.predict(np.array([[0, 0], [0, 1], [1, 0], [1, 1]]))
self.assertEqual(predictions.tolist(), [0, 1, 1, 0])
print(f"10 tree Random Forest Validation Accuracy, ",
f"with feature selection and sampling: {acc_val_4}")
results = np.asarray([acc_val_1, acc_val_2, acc_val_3, acc_val_4])
print(f"Best result was achieved with setup {np.argmax(results) + 1}")
"""
# 4.2.4 starts here
# Trees start following the best tree model from improvement 1
forest.update_hyperparameters(feature_sel=True,
cross_val=False,
max_tree_depth=13,
min_sample_size=3,
num_trees=10)
forest.fit(x_train, y_train)
pred_val = forest.predict(x_val)
acc_val_5 = metrics.accuracy(pred_val, y_val)
print(f"10 Best Tree Random Forest Validation Accuracy, ",
f"with feature selection and sampling: {acc_val_5}")
# start by tuning the trees used
param_space = {
"max_tree_depth": [x for x in range(13, 15)],
"min_sample_size": [y for y in range(2, 4)],
"num_trees": [10, 20]
}
best_param = metrics.grid_search(forest,
x_train,
y_train,