def __init__(self,TRAINVALTEST_DENSE_X,TRAINVALTEST_DENSE_X_NAMES,\
TRAINVAL_SPARSE_X,TRAINVAL_SPARSE_X_NAMES,\
TEST_SPARSE_X,TEST_SPARSE_X_NAMES,\
UF_VW,ADF,TRAINVAL,UF_CSV,TRAINVAL_MERGE,\
TEST_MERGE,TEST,name='ffm',USE_TINY=False,RANDOMSTATE=2018):
super(FFM, self).__init__(
TRAINVALTEST_DENSE_X,TRAINVALTEST_DENSE_X_NAMES,\
TRAINVAL_SPARSE_X,TRAINVAL_SPARSE_X_NAMES,\
TEST_SPARSE_X,TEST_SPARSE_X_NAMES,\
UF_VW,ADF,TRAINVAL,UF_CSV,TRAINVAL_MERGE,\
TEST_MERGE,TEST,name,USE_TINY,RANDOMSTATE=2018)
'''In Ridge, only 'sag' solver can currently fit the intercept when X is sparse.'''
self.clf = xl.FFMModel(task='binary',
lr=0.2,
epoch=10,
reg_lambda=0.002,
metric='auc')
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
import numpy as np
import xlearn as xl
# param:
# 0. binary classification
# 1. learning rate: 0.2
# 2. epoch number: 10 (auto early-stop)
# 3. evaluation metric: accuracy
# 4. use sgd optimization method
ffm_model = xl.FFMModel(task='binary',
lr=0.2,
epoch=10,
reg_lambda=0.002,
metric='acc')
# Start to train
# Directly use string to specify data source
ffm_model.fit('../criteo_ctr/small_train.txt',
eval_set='../criteo_ctr/small_test.txt')
# print model weights
print(ffm_model.weights)
# Generate predictions
y_pred = ffm_model.predict('../criteo_ctr/small_test.txt')
nthread=None,
n_jobs=4,
alpha=1,
beta=1,
lambda_1=1,
lambda_2=1)
fmm_model = xl.FFMModel(model_type='ffm',
task='binary',
metric='auc',
block_size=500,
lr=0.2,
k=4,
reg_lambda=0.1,
init=0.1,
fold=1,
epoch=5,
stop_window=2,
opt='sgd',
nthread=None,
n_jobs=4,
alpha=1,
beta=1,
lambda_1=1,
lambda_2=1)
# Start to train
for model in [linear_model, fm_model, fmm_model]:
model.fit(X_train,
y_train,
fields=list(range(4)),
eval_set=[X_val, y_val],
is_lock_free=False)