def test_model_n_trees_non_positive():
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update({"n_trees": 0})
model = CascadeForestClassifier(**case_kwargs)
with pytest.raises(ValueError) as excinfo:
model._set_n_trees(0)
assert "should be strictly positive." in str(excinfo.value)
def test_model_n_trees_invalid():
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update({"n_trees": [42]})
model = CascadeForestClassifier(**case_kwargs)
with pytest.raises(ValueError) as excinfo:
model._set_n_trees(0)
assert "Invalid value for n_trees." in str(excinfo.value)
def test_model_n_trees_auto():
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update({"n_trees": "auto"})
model = CascadeForestClassifier(**case_kwargs)
n_trees = model._set_n_trees(0)
assert n_trees == 100
n_trees = model._set_n_trees(2)
assert n_trees == 300
n_trees = model._set_n_trees(10)
assert n_trees == 500
def test_model_invalid_training_params(param):
case_kwargs = copy.deepcopy(toy_kwargs)
case_kwargs.update(param[1])
model = CascadeForestClassifier(**case_kwargs)
with pytest.raises(ValueError) as excinfo:
model.fit(X_train, y_train)
if param[0] == 0:
assert "max_layers" in str(excinfo.value)
elif param[0] == 1:
assert "n_tolerant_rounds" in str(excinfo.value)
elif param[0] == 2:
assert "delta " in str(excinfo.value)
def test_custom_estimator_missing_fit():
class tmp_estimator:
def __init__(self):
pass
model = CascadeForestClassifier()
with pytest.raises(AttributeError) as excinfo:
model.set_estimator([tmp_estimator()])
assert "The `fit` method of estimator" in str(excinfo.value)
with pytest.raises(AttributeError) as excinfo:
model.set_predictor(tmp_estimator())
assert "The `fit` method of the predictor" in str(excinfo.value)
def test_model_workflow_in_memory():
"""Run the workflow of deep forest with in-memory mode."""
case_kwargs = copy.deepcopy(kwargs)
case_kwargs.update({"partial_mode": False})
model = CascadeForestClassifier(**case_kwargs)
model.fit(X_train, y_train)
# Predictions before saving
y_pred_before = model.predict(X_test)
# Save and Reload
model.save(save_dir)
model = CascadeForestClassifier(**case_kwargs)
model.load(save_dir)
# Make sure the same predictions before and after model serialization
y_pred_after = model.predict(X_test)
assert_array_equal(y_pred_before, y_pred_after)
shutil.rmtree(save_dir)
def test_model_sample_weight():
"""Run the workflow of deep forest with a local buffer."""
case_kwargs = copy.deepcopy(kwargs)
# Training without sample_weight
model = CascadeForestClassifier(**case_kwargs)
model.fit(X_train, y_train)
y_pred_no_sample_weight = model.predict(X_test)
# Training with equal sample_weight
model = CascadeForestClassifier(**case_kwargs)
sample_weight = np.ones(y_train.size)
model.fit(X_train, y_train, sample_weight=sample_weight)
y_pred_equal_sample_weight = model.predict(X_test)
# Make sure the same predictions with None and equal sample_weight
assert_array_equal(y_pred_no_sample_weight, y_pred_equal_sample_weight)
model = CascadeForestClassifier(**case_kwargs)
sample_weight = np.where(y_train == 0, 0.1, y_train)
model.fit(X_train, y_train, sample_weight=y_train)
y_pred_skewed_sample_weight = model.predict(X_test)
# Make sure the different predictions with None and equal sample_weight
assert_raises(AssertionError, assert_array_equal,
y_pred_skewed_sample_weight, y_pred_equal_sample_weight)
model.clean() # clear the buffer
def test_model_workflow_partial_mode():
"""Run the workflow of deep forest with a local buffer."""
case_kwargs = copy.deepcopy(kwargs)
case_kwargs.update({"partial_mode": True})
model = CascadeForestClassifier(**case_kwargs)
model.fit(X_train, y_train)
# Predictions before saving
y_pred_before = model.predict(X_test)
# Save and Reload
model.save(save_dir)
model = CascadeForestClassifier(**case_kwargs)
model.load(save_dir)
# Predictions after loading
y_pred_after = model.predict(X_test)
# Make sure the same predictions before and after model serialization
assert_array_equal(y_pred_before, y_pred_after)
model.clean() # clear the buffer
shutil.rmtree(save_dir)
def test_model_properties_after_fitting():
"""Check the model properties after fitting a deep forest model."""
model = CascadeForestClassifier(**toy_kwargs)
model.fit(X_train, y_train)
assert len(model) == model.n_layers_
assert model[0] is model._get_layer(0)
with pytest.raises(ValueError) as excinfo:
model._get_layer(model.n_layers_)
assert "The layer index should be in the range" in str(excinfo.value)
with pytest.raises(RuntimeError) as excinfo:
model._set_layer(0, None)
assert "already exists in the internal container" in str(excinfo.value)
with pytest.raises(ValueError) as excinfo:
model._get_binner(model.n_layers_ + 1)
assert "The binner index should be in the range" in str(excinfo.value)
with pytest.raises(RuntimeError) as excinfo:
model._set_binner(0, None)
assert "already exists in the internal container" in str(excinfo.value)
def test_model_input_label_encoder():
"""Test if the model behaves the same with and without label encoding."""
# Load data
X, y = load_digits(return_X_y=True)
y_as_str = np.char.add("label_", y.astype(str))
# Train model on integer labels. Labels should look like: 1, 2, 3, ...
model = CascadeForestClassifier(**toy_kwargs)
model.fit(X, y)
y_pred_int_labels = model.predict(X)
# Train model on string labels. Labels should look like: "label_1", "label_2", "label_3", ...
model = CascadeForestClassifier(**toy_kwargs)
model.fit(X, y_as_str)
y_pred_str_labels = model.predict(X)
# Check if the underlying data are the same
y_pred_int_labels_as_str = np.char.add("label_",
y_pred_int_labels.astype(str))
assert_array_equal(y_pred_str_labels, y_pred_int_labels_as_str)
# Clean up buffer
model.clean()
def test_model_properties_after_fitting():
"""Check the model properties after fitting a deep forest model."""
model = CascadeForestClassifier(**toy_kwargs)
model.fit(X_train, y_train)
assert len(model) == model.n_layers_
assert model[0] is model._get_layer(0)
with pytest.raises(ValueError) as excinfo:
model._get_layer(model.n_layers_)
assert "The layer index should be in the range" in str(excinfo.value)
with pytest.raises(RuntimeError) as excinfo:
model._set_layer(0, None)
assert "already exists in the internal container" in str(excinfo.value)
with pytest.raises(ValueError) as excinfo:
model._get_binner(model.n_layers_ + 1)
assert "The binner index should be in the range" in str(excinfo.value)
with pytest.raises(RuntimeError) as excinfo:
model._set_binner(0, None)
assert "already exists in the internal container" in str(excinfo.value)
# Test the hook on forest estimator
assert (model.get_forest(0, 0, "rf") is
model._get_layer(0).estimators_["0-0-rf"].estimator_)
with pytest.raises(ValueError) as excinfo:
model.get_forest(model.n_layers_, 0, "rf")
assert "`layer_idx` should be in the range" in str(excinfo.value)
with pytest.raises(ValueError) as excinfo:
model.get_forest(0, model.n_estimators, "rf")
assert "`est_idx` should be in the range" in str(excinfo.value)
with pytest.raises(ValueError) as excinfo:
model.get_forest(0, 0, "Unknown")
assert "`forest_type` should be one of" in str(excinfo.value)
x, y, random_state=1, train_size=0.99, test_size=0.01)
#划分数据与标签（验证集）
valx, valy = np.split(valdata, indices_or_sections=(10, ),
axis=1) #valx为数据，valy为标签
valx = valx[:, 0:10] #选取前n个波段作为特征
train_data = train_data.astype(np.uint8)
test_data = test_data.astype(np.uint8)
train_label = train_label.astype(np.uint8)
test_label = test_label.astype(np.uint8)
#验证集
valx = valx.astype(np.uint8)
valy = valy.astype(np.uint8)
classification = CascadeForestClassifier(max_depth=5,
n_trees=100,
n_jobs=6,
use_predictor="forest")
classification.fit(train_data, train_label.ravel())
prediction = classification.predict_proba(valx)
probability = [prob[1] for prob in prediction]
pre_class = []
for i in probability:
if i > 0.5:
pre_class.append(1)
else:
pre_class.append(0)
prediction = prediction[:, 1]
pred = classification.predict(valx)
def test_custom_base_estimator_wrong_estimator_type():
model = CascadeForestClassifier()
with pytest.raises(ValueError) as excinfo:
model.set_estimator(42)
assert "estimators should be a list" in str(excinfo.value)
def test_custom_cascade_layer_workflow_partial_mode():
model = CascadeForestClassifier(partial_mode=True)
n_estimators = 4
estimators = [DecisionTreeClassifier() for _ in range(n_estimators)]
model.set_estimator(estimators) # set custom base estimators
predictor = DecisionTreeClassifier()
model.set_predictor(predictor)
model.fit(X_train, y_train)
y_pred_before = model.predict(X_test)
# Save and Reload
model.save(save_dir)
model = CascadeForestClassifier()
model.load(save_dir)
# Predictions after loading
y_pred_after = model.predict(X_test)
# Make sure the same predictions before and after model serialization
assert_array_equal(y_pred_before, y_pred_after)
model.clean() # clear the buffer
shutil.rmtree(save_dir)
df_sum_y = pd.DataFrame(sum_y.T, columns=['Class', 'Sum'], index=None)
print('\n', df_sum_y)
# Apply SMOTE 生成 fake data
sm = SMOTE(k_neighbors=args.kneighbors,
random_state=args.randomseed,
n_jobs=-1)
x_resampled, y_resampled = sm.fit_sample(X, y)
# after over sampleing 读取分类信息并返回数量
np_resampled_y = np.asarray(np.unique(y_resampled, return_counts=True))
df_resampled_y = pd.DataFrame(np_resampled_y.T, columns=['Class', 'Sum'])
print("\nNumber of samples after over sampleing:\n{0}\n".format(
df_resampled_y))
# 初始化 classifier
clf = CascadeForestClassifier(random_state=args.randomseed)
print("\nClassifier parameters:")
print(clf.get_params())
print("\nSMOTE parameters:")
print(sm.get_params())
print("\n")
# 使用SMOTE后数据进行训练
clf.fit(x_resampled, y_resampled)
# 预测测试集
y_pred = clf.predict(X_test)
# 输出测试集统计结果
if (num_categories > 2):
model_evaluation(num_categories, y_test, y_pred)
else:
import numpy as np
from sklearn.datasets import load_iris
from sklearn.metrics import accuracy_score
from deepforest import CascadeForestClassifier
from sklearn.model_selection import train_test_split
X, y = load_iris(return_X_y=True)
X = np.array(X)
y = np.array(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = CascadeForestClassifier()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)
acc = accuracy_score(y_test, y_pred) * 100
print("Accuracy: {:.3f} %".format(acc))
df_sum_y = pd.DataFrame(sum_y.T, columns=['Class', 'Sum'], index=None)
print('\n', df_sum_y)
# Apply SMOTE 生成 fake data
sm = SMOTE(k_neighbors=args.kneighbors,
random_state=args.randomseed,
n_jobs=-1)
x_resampled, y_resampled = sm.fit_sample(X, y)
# after over sampleing 读取分类信息并返回数量
np_resampled_y = np.asarray(np.unique(y_resampled, return_counts=True))
df_resampled_y = pd.DataFrame(np_resampled_y.T, columns=['Class', 'Sum'])
print("\nNumber of samples after over sampleing:\n{0}\n".format(
df_resampled_y))
# 初始化 classifier
clf = CascadeForestClassifier(random_state=args.randomseed)
print("\nClassifier parameters:")
print(clf.get_params())
print("\nSMOTE parameters:")
print(sm.get_params())
print("\n")
# 交叉验证
y_pred_resampled = cross_val_predict(clf,
x_resampled,
y_resampled,
cv=args.kfolds,
n_jobs=-1,
verbose=0)
# 通过 index 去除 fake data
y_pred = y_pred_resampled[0:X.shape[0]]
records = []
for idx, random_state in enumerate(random_states):
msg = "Currently processing {} with trial {}..."
print(msg.format(dataset, idx))
model = CascadeForestClassifier(
n_bins=n_bins,
bin_subsample=bin_subsample,
max_layers=max_layers,
criterion=criterion,
n_estimators=n_estimators,
n_trees=n_trees,
max_depth=max_depth,
min_samples_leaf=min_samples_leaf,
use_predictor=use_predictor,
predictor=predictor,
n_tolerant_rounds=n_tolerant_rounds,
partial_mode=partial_mode,
delta=delta,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
)
tic = time.time()
model.fit(X_train, y_train)
toc = time.time()
training_time = toc - tic
tic = time.time()
# feature_names
X, y = shap.datasets.iris()
# print("X", X.head())
# print("y", y)
feature_names = X.columns
X = np.array(X)
y = np.array(y)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
model = CascadeForestClassifier(backend="sklearn")
model.fit(X_train, y_train)
forest = model.get_forest(0, 0, "rf")
explainer = shap.TreeExplainer(forest)
shap_values = explainer.shap_values(X_test)
# shap_values = np.array(explainer.shap_values(X_train))
# print(shap_values.shape)
# print(shap_values[2].shape)
# shap.summary_plot(shap_values[2], X_train)
#
#
# clf = RandomForestClassifier(n_estimators=100)
# clf.fit(X_train, y_train)
# explainer = shap.TreeExplainer(clf)
def test_classifier_custom_cascade_layer_workflow_in_memory():
model = CascadeForestClassifier()
n_estimators = 4
estimators = [DecisionTreeClassifier() for _ in range(n_estimators)]
model.set_estimator(estimators) # set custom base estimators
predictor = DecisionTreeClassifier()
model.set_predictor(predictor)
model.fit(X_train_clf, y_train_clf)
y_pred_before = model.predict(X_test_clf)
# Save and Reload
model.save(save_dir)
model = CascadeForestClassifier()
model.load(save_dir)
# Predictions after loading
y_pred_after = model.predict(X_test_clf)
# Make sure the same predictions before and after model serialization
assert_array_equal(y_pred_before, y_pred_after)
assert (model.get_estimator(0, 0, "custom") is
model._get_layer(0).estimators_["0-0-custom"].estimator_)
model.clean() # clear the buffer
shutil.rmtree(save_dir)
def test_model_workflow_in_memory(backend):
"""Run the workflow of deep forest with in-memory mode."""
case_kwargs = copy.deepcopy(kwargs)
case_kwargs.update({"partial_mode": False})
case_kwargs.update({"backend": backend})
model = CascadeForestClassifier(**case_kwargs)
model.fit(X_train, y_train)
# Test feature_importances_
if backend == "sklearn":
model.get_layer_feature_importances(0)
else:
with pytest.raises(RuntimeError) as excinfo:
model.get_layer_feature_importances(0)
assert "Please use the sklearn backend" in str(excinfo.value)
# Predictions before saving
y_pred_before = model.predict(X_test)
# Save and Reload
model.save(save_dir)
model = CascadeForestClassifier(**case_kwargs)
model.load(save_dir)
# Make sure the same predictions before and after model serialization
y_pred_after = model.predict(X_test)
assert_array_equal(y_pred_before, y_pred_after)
shutil.rmtree(save_dir)
import shap import numpy as np from deepforest import CascadeForestClassifier from sklearn.model_selection import train_test_split # load JS visualization code to notebook shap.initjs() X, y = shap.datasets.iris() X = np.array(X) y = np.array(y) X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2) model = CascadeForestClassifier() model.fit(X_train, y_train) explainer = shap.TreeExplainer(model)
