def test_rf_regression_float64(large_reg, datatype):
X, y = large_reg
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.8,
random_state=0)
X_train = X_train.astype(datatype[0])
y_train = y_train.astype(datatype[0])
X_test = X_test.astype(datatype[1])
y_test = y_test.astype(datatype[1])
# Initialize, fit and predict using cuML's
# random forest classification model
cuml_model = curfr()
cuml_model.fit(X_train, y_train)
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype[0])
# sklearn random forest classification model
# initialization, fit and predict
if X.shape[0] < 500000:
sk_model = skrfr(max_depth=16, random_state=10)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype[0])
assert cu_r2 >= (sk_r2 - 0.09)
# predict using cuML's GPU based prediction
fil_preds = cuml_model.predict(X_test,
predict_model="GPU",
convert_dtype=True)
fil_preds = np.reshape(fil_preds, np.shape(cu_preds))
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype[0])
assert fil_r2 >= (cu_r2 - 0.02)
def test_rf_regression_sparse(special_reg, datatype, fil_sparse_format, algo):
use_handle = True
num_treees = 50
X, y = special_reg
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X, y, train_size=0.8,
random_state=0)
# Create a handle for the cuml model
handle, stream = get_handle(use_handle, n_streams=1)
# Initialize and fit using cuML's random forest regression model
cuml_model = curfr(n_bins=16, split_criterion=2,
min_rows_per_node=2, random_state=123, n_streams=1,
n_estimators=num_treees, handle=handle, max_leaves=-1,
max_depth=40, accuracy_metric='mse')
cuml_model.fit(X_train, y_train)
# predict using FIL
if ((not fil_sparse_format or algo == 'tree_reorg' or
algo == 'batch_tree_reorg') or
fil_sparse_format == 'not_supported'):
with pytest.raises(ValueError):
fil_preds = cuml_model.predict(X_test, predict_model="GPU",
fil_sparse_format=fil_sparse_format,
algo=algo)
else:
fil_preds = cuml_model.predict(X_test, predict_model="GPU",
fil_sparse_format=fil_sparse_format,
algo=algo)
fil_preds = np.reshape(fil_preds, np.shape(y_test))
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype)
fil_model = cuml_model.convert_to_fil_model()
input_type = 'numpy'
fil_model_preds = fil_model.predict(X_test,
output_type=input_type)
fil_model_preds = np.reshape(fil_model_preds, np.shape(y_test))
fil_model_r2 = r2_score(y_test, fil_model_preds,
convert_dtype=datatype)
assert fil_r2 == fil_model_r2
tl_model = cuml_model.convert_to_treelite_model()
assert num_treees == tl_model.num_trees
assert X.shape[1] == tl_model.num_features
# Initialize, fit and predict using
# sklearn's random forest regression model
if X.shape[0] < 1000: # mode != "stress":
sk_model = skrfr(n_estimators=50, max_depth=40,
min_samples_split=2,
random_state=10)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype)
assert fil_r2 >= (sk_r2 - 0.07)
def test_rf_regression(
special_reg, datatype, max_features, max_samples, n_bins
):
use_handle = True
X, y = special_reg
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=0.8, random_state=0
)
# Create a handle for the cuml model
handle, stream = get_handle(use_handle, n_streams=1)
# Initialize and fit using cuML's random forest regression model
cuml_model = curfr(
max_features=max_features,
max_samples=max_samples,
n_bins=n_bins,
split_criterion=2,
min_samples_leaf=2,
random_state=123,
n_streams=1,
n_estimators=50,
handle=handle,
max_leaves=-1,
max_depth=16,
accuracy_metric="mse",
)
cuml_model.fit(X_train, y_train)
# predict using FIL
fil_preds = cuml_model.predict(X_test, predict_model="GPU")
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
fil_preds = np.reshape(fil_preds, np.shape(cu_preds))
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype)
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype)
# Initialize, fit and predict using
# sklearn's random forest regression model
if X.shape[0] < 1000: # mode != "stress"
sk_model = skrfr(
n_estimators=50,
max_depth=16,
min_samples_split=2,
max_features=max_features,
random_state=10,
)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype)
assert fil_r2 >= (sk_r2 - 0.07)
assert fil_r2 >= (cu_r2 - 0.02)
def test_rf_regression_float64(large_reg, datatype):
X, y = large_reg
X_train, X_test, y_train, y_test = train_test_split(
X, y, train_size=0.8, random_state=0
)
X_train = X_train.astype(datatype[0])
y_train = y_train.astype(datatype[0])
X_test = X_test.astype(datatype[1])
y_test = y_test.astype(datatype[1])
# Initialize, fit and predict using cuML's
# random forest classification model
cuml_model = curfr()
cuml_model.fit(X_train, y_train)
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype[0])
# sklearn random forest classification model
# initialization, fit and predict
if X.shape[0] < 500000:
sk_model = skrfr(max_depth=16, random_state=10)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype[0])
assert cu_r2 >= (sk_r2 - 0.09)
# predict using cuML's GPU based prediction
if datatype[0] == np.float32:
fil_preds = cuml_model.predict(
X_test, predict_model="GPU", convert_dtype=True
)
fil_preds = np.reshape(fil_preds, np.shape(cu_preds))
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype[0])
assert fil_r2 >= (cu_r2 - 0.02)
# because datatype[0] != np.float32 or datatype[0] != datatype[1]
# display warning when GPU-predict cannot be used and revert to CPU-predict
elif datatype[1] == np.float64:
with warnings.catch_warnings(record=True) as w:
warnings.simplefilter("always")
fil_preds = cuml_model.predict(
X_test, predict_model="GPU"
)
assert("GPU based predict only accepts "
"np.float32 data. The model was "
"trained on np.float64 data hence "
"cannot use GPU-based prediction! "
"\nDefaulting to CPU-based Prediction. "
"\nTo predict on float-64 data, set "
"parameter predict_model = 'CPU'"
in str(w[-1].message))
def test_rf_regression(datatype, split_algo, rows_sample,
n_info, mode, ncols, max_features):
use_handle = True
if mode == 'unit':
X, y = make_regression(n_samples=100, n_features=ncols,
n_informative=n_info,
random_state=123)
elif mode == 'quality':
X, y = fetch_california_housing(return_X_y=True)
else:
X, y = make_regression(n_samples=100000, n_features=ncols,
n_informative=n_info,
random_state=123)
train_rows = np.int32(X.shape[0]*0.8)
X_test = np.asarray(X[train_rows:, :]).astype(datatype)
y_test = np.asarray(y[train_rows:, ]).astype(datatype)
X_train = np.asarray(X[0:train_rows, :]).astype(datatype)
y_train = np.asarray(y[0:train_rows, ]).astype(datatype)
# Create a handle for the cuml model
handle, stream = get_handle(use_handle, n_streams=8)
# Initialize and fit using cuML's random forest regression model
cuml_model = curfr(max_features=max_features, rows_sample=rows_sample,
n_bins=16, split_algo=split_algo, split_criterion=2,
min_rows_per_node=2,
n_estimators=50, handle=handle, max_leaves=-1,
max_depth=16, accuracy_metric='mse')
cuml_model.fit(X_train, y_train)
# predict using FIL
fil_preds = cuml_model.predict(X_test, predict_model="GPU")
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds)
fil_r2 = r2_score(y_test, fil_preds)
# Initialize, fit and predict using
# sklearn's random forest regression model
sk_model = skrfr(n_estimators=50, max_depth=16,
min_samples_split=2, max_features=max_features,
random_state=10)
sk_model.fit(X_train, y_train)
sk_predict = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_predict)
print(fil_r2, cu_r2, sk_r2)
assert fil_r2 >= (cu_r2 - 0.02)
assert fil_r2 >= (sk_r2 - 0.07)
def test_rf_regression_float64(datatype, column_info, nrows, convert_dtype):
ncols, n_info = column_info
X, y = make_regression(n_samples=nrows,
n_features=ncols,
n_informative=n_info,
random_state=123)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.8,
random_state=0)
X_train = X_train.astype(datatype[0])
y_train = y_train.astype(datatype[0])
X_test = X_test.astype(datatype[1])
y_test = y_test.astype(datatype[1])
# Initialize, fit and predict using cuML's
# random forest classification model
cuml_model = curfr()
cuml_model.fit(X_train, y_train)
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype[0])
# sklearn random forest classification model
# initialization, fit and predict
if nrows < 500000:
sk_model = skrfr(max_depth=16, random_state=10)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype[0])
assert cu_r2 >= (sk_r2 - 0.09)
# predict using cuML's GPU based prediction
if datatype[0] == np.float32 and convert_dtype:
fil_preds = cuml_model.predict(X_test,
predict_model="GPU",
convert_dtype=convert_dtype)
fil_preds = np.reshape(fil_preds, np.shape(cu_preds))
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype[0])
assert fil_r2 >= (cu_r2 - 0.02)
else:
with pytest.raises(TypeError):
fil_preds = cuml_model.predict(X_test,
predict_model="GPU",
convert_dtype=convert_dtype)
def test_rf_regression(datatype, use_handle, split_algo,
n_info, mode, ncols,
rows_sample):
if mode == 'unit':
X, y = make_regression(n_samples=30, n_features=ncols,
n_informative=n_info,
random_state=123)
elif mode == 'quality':
X, y = fetch_california_housing(return_X_y=True)
else:
X, y = make_regression(n_samples=100000, n_features=ncols,
n_informative=n_info,
random_state=123)
train_rows = np.int32(X.shape[0]*0.8)
X_test = np.asarray(X[train_rows:, :]).astype(datatype)
y_test = np.asarray(y[train_rows:, ]).astype(datatype)
X_train = np.asarray(X[0:train_rows, :]).astype(datatype)
y_train = np.asarray(y[0:train_rows, ]).astype(datatype)
# Create a handle for the cuml model
handle, stream = get_handle(use_handle)
# Initialize, fit and predict using cuML's
# random forest classification model
cuml_model = curfr(max_features=1.0, rows_sample=rows_sample,
n_bins=8, split_algo=split_algo, split_criterion=2,
min_rows_per_node=2,
n_estimators=50, handle=handle, max_leaves=-1,
max_depth=25, accuracy_metric='mse')
cuml_model.fit(X_train, y_train)
cu_mse = cuml_model.score(X_test, y_test)
if mode != 'stress':
# sklearn random forest classification model
# initialization, fit and predict
sk_model = skrfr(n_estimators=50, max_depth=50,
min_samples_split=2, max_features=1.0,
random_state=10)
sk_model.fit(X_train, y_train)
sk_predict = sk_model.predict(X_test)
sk_mse = mean_squared_error(y_test, sk_predict)
# compare the accuracy of the two models
assert cu_mse <= (sk_mse + 0.07)
def test_rf_regression_default(datatype, column_info, nrows):
ncols, n_info = column_info
X, y = make_regression(n_samples=nrows,
n_features=ncols,
n_informative=n_info,
random_state=123)
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.8,
random_state=0)
# Initialize, fit and predict using cuML's
# random forest classification model
cuml_model = curfr()
cuml_model.fit(X_train, y_train)
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype)
# predict using FIL
fil_preds = cuml_model.predict(X_test, predict_model="GPU")
fil_preds = np.reshape(fil_preds, np.shape(cu_preds))
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype)
# score function should be equivalent
score_mse = cuml_model.score(X_test, y_test, predict_model="GPU")
sk_mse = mean_squared_error(y_test, fil_preds)
assert sk_mse == pytest.approx(score_mse)
# Initialize, fit and predict using
# sklearn's random forest regression model
if nrows < 500000:
sk_model = skrfr(max_depth=16, random_state=10)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype)
# XXX Accuracy gap exists with default parameters, requires
# further investigation for next release
assert fil_r2 >= (sk_r2 - 0.08)
assert fil_r2 >= (cu_r2 - 0.02)
def test_rf_regression(datatype, split_algo, mode, column_info, max_features,
rows_sample):
ncols, n_info = column_info
use_handle = True
if mode == 'unit':
X, y = make_regression(n_samples=500,
n_features=ncols,
n_informative=n_info,
random_state=123)
elif mode == 'quality':
X, y = fetch_california_housing(return_X_y=True)
else:
X, y = make_regression(n_samples=100000,
n_features=ncols,
n_informative=n_info,
random_state=123)
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.8,
random_state=0)
# Create a handle for the cuml model
handle, stream = get_handle(use_handle, n_streams=1)
# Initialize and fit using cuML's random forest regression model
cuml_model = curfr(max_features=max_features,
rows_sample=rows_sample,
n_bins=16,
split_algo=split_algo,
split_criterion=2,
min_rows_per_node=2,
seed=123,
n_streams=1,
n_estimators=50,
handle=handle,
max_leaves=-1,
max_depth=16,
accuracy_metric='mse')
cuml_model.fit(X_train, y_train)
# predict using FIL
fil_preds = cuml_model.predict(X_test, predict_model="GPU")
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype)
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype)
# Initialize, fit and predict using
# sklearn's random forest regression model
if mode != "stress":
sk_model = skrfr(n_estimators=50,
max_depth=16,
min_samples_split=2,
max_features=max_features,
random_state=10)
sk_model.fit(X_train, y_train)
sk_predict = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_predict, convert_dtype=datatype)
assert fil_r2 >= (sk_r2 - 0.07)
assert fil_r2 >= (cu_r2 - 0.02)
def test_rf_regression_sparse(datatype, split_algo, mode, column_info,
max_features, rows_sample, fil_sparse_format,
algo):
ncols, n_info = column_info
use_handle = True
num_treees = 50
if mode == 'unit':
X, y = make_regression(n_samples=500,
n_features=ncols,
n_informative=n_info,
random_state=123)
elif mode == 'quality':
X, y = fetch_california_housing(return_X_y=True)
else:
X, y = make_regression(n_samples=100000,
n_features=ncols,
n_informative=n_info,
random_state=123)
X = X.astype(datatype)
y = y.astype(datatype)
X_train, X_test, y_train, y_test = train_test_split(X,
y,
train_size=0.8,
random_state=0)
# Create a handle for the cuml model
handle, stream = get_handle(use_handle, n_streams=1)
# Initialize and fit using cuML's random forest regression model
cuml_model = curfr(max_features=max_features,
rows_sample=rows_sample,
n_bins=16,
split_algo=split_algo,
split_criterion=2,
min_rows_per_node=2,
seed=123,
n_streams=1,
n_estimators=num_treees,
handle=handle,
max_leaves=-1,
max_depth=40,
accuracy_metric='mse')
cuml_model.fit(X_train, y_train)
cu_preds = cuml_model.predict(X_test, predict_model="CPU")
cu_r2 = r2_score(y_test, cu_preds, convert_dtype=datatype)
# predict using FIL
if ((not fil_sparse_format or algo == 'tree_reorg'
or algo == 'batch_tree_reorg')
or fil_sparse_format == 'not_supported'):
with pytest.raises(ValueError):
fil_preds = cuml_model.predict(X_test,
predict_model="GPU",
fil_sparse_format=fil_sparse_format,
algo=algo)
else:
fil_preds = cuml_model.predict(X_test,
predict_model="GPU",
fil_sparse_format=fil_sparse_format,
algo=algo)
fil_preds = np.reshape(fil_preds, np.shape(cu_preds))
fil_r2 = r2_score(y_test, fil_preds, convert_dtype=datatype)
fil_model = cuml_model.convert_to_fil_model()
input_type = 'numpy'
fil_model_preds = fil_model.predict(X_test, output_type=input_type)
fil_model_preds = np.reshape(fil_model_preds, np.shape(cu_preds))
fil_model_r2 = r2_score(y_test,
fil_model_preds,
convert_dtype=datatype)
assert fil_r2 == fil_model_r2
tl_model = cuml_model.convert_to_treelite_model()
assert num_treees == tl_model.num_trees
assert ncols == tl_model.num_features
del tl_model
# Initialize, fit and predict using
# sklearn's random forest regression model
if mode != "stress":
sk_model = skrfr(n_estimators=50,
max_depth=40,
min_samples_split=2,
max_features=max_features,
random_state=10)
sk_model.fit(X_train, y_train)
sk_preds = sk_model.predict(X_test)
sk_r2 = r2_score(y_test, sk_preds, convert_dtype=datatype)
assert fil_r2 >= (sk_r2 - 0.07)
assert fil_r2 >= (cu_r2 - 0.02)
