def rf_fit(input_dict):
from discomll.ensemble import distributed_random_forest
random_state = None if input_dict["seed"] == "None" else int(input_dict["seed"])
fitmodel_url = distributed_random_forest.fit(input_dict["dataset"],
trees_per_chunk=input_dict["trees_per_subset"],
max_tree_nodes=input_dict["tree_nodes"],
min_samples_leaf=input_dict["min_samples_leaf"],
min_samples_split=input_dict["min_samples_split"],
class_majority=input_dict["majority"],
measure=input_dict["measure"],
accuracy=input_dict["accuracy"],
separate_max=input_dict["separate_max"] == "true",
random_state=random_state,
save_results=True)
return {"fitmodel_url": fitmodel_url}
def rf_fit(input_dict):
from discomll.ensemble import distributed_random_forest
random_state = None if input_dict["seed"] == "None" else int(
input_dict["seed"])
fitmodel_url = distributed_random_forest.fit(
input_dict["dataset"],
trees_per_chunk=input_dict["trees_per_subset"],
max_tree_nodes=input_dict["tree_nodes"],
min_samples_leaf=input_dict["min_samples_leaf"],
min_samples_split=input_dict["min_samples_split"],
class_majority=input_dict["majority"],
measure=input_dict["measure"],
accuracy=input_dict["accuracy"],
separate_max=input_dict["separate_max"] == "true",
random_state=random_state,
save_results=True)
return {"fitmodel_url": fitmodel_url}
from discomll import dataset
from discomll.ensemble import distributed_random_forest
train = dataset.Data(data_tag=["http://ropot.ijs.si/data/lymphography/train/xaaaaa.gz",
"http://ropot.ijs.si/data/lymphography/train/xaaabj.gz"],
X_indices=range(2, 20),
data_type="gzip",
generate_urls=True,
id_index=0,
y_index=1,
X_meta=["d", "d", "d", "d", "d", "d", "d", "d", "c", "c", "d", "d", "d", "d", "d", "d", "d", "c"],
delimiter=",")
test = dataset.Data(data_tag=["http://ropot.ijs.si/data/lymphography/test/xaaaaa.gz",
"http://ropot.ijs.si/data/lymphography/test/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(2, 20),
id_index=0,
y_index=1,
X_meta=["d", "d", "d", "d", "d", "d", "d", "d", "c", "c", "d", "d", "d", "d", "d", "d", "d", "c"],
delimiter=",")
fit_model = distributed_random_forest.fit(train, trees_per_chunk=3, max_tree_nodes=50, min_samples_leaf=10,
min_samples_split=5, class_majority=1, measure="info_gain", accuracy=1,
separate_max=True, random_state=None, save_results=True)
predict_url = distributed_random_forest.predict(test, fit_model)
print predict_url
delimiter=",")
test = dataset.Data(data_tag=[
"http://ropot.ijs.si/data/lymphography/test/xaaaaa.gz",
"http://ropot.ijs.si/data/lymphography/test/xaaabj.gz"
],
data_type="gzip",
generate_urls=True,
X_indices=range(2, 20),
id_index=0,
y_index=1,
X_meta=[
"d", "d", "d", "d", "d", "d", "d", "d", "c", "c", "d",
"d", "d", "d", "d", "d", "d", "c"
],
delimiter=",")
fit_model = distributed_random_forest.fit(train,
trees_per_chunk=3,
max_tree_nodes=50,
min_samples_leaf=10,
min_samples_split=5,
class_majority=1,
measure="info_gain",
accuracy=1,
separate_max=True,
random_state=None,
save_results=True)
predict_url = distributed_random_forest.predict(test, fit_model)
print predict_url
