def wrf_fit(input_dict):
from discomll.ensemble import distributed_weighted_forest_rand
random_state = None if input_dict["seed"] == "None" else int(input_dict["seed"])
fitmodel_url = distributed_weighted_forest_rand.fit(input_dict["dataset"],
trees_per_chunk=input_dict["trees_per_subset"],
max_tree_nodes=input_dict["tree_nodes"],
num_medoids=input_dict["num_medoids"],
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 wrf_fit(input_dict):
from discomll.ensemble import distributed_weighted_forest_rand
random_state = None if input_dict["seed"] == "None" else int(
input_dict["seed"])
fitmodel_url = distributed_weighted_forest_rand.fit(
input_dict["dataset"],
trees_per_chunk=input_dict["trees_per_subset"],
max_tree_nodes=input_dict["tree_nodes"],
num_medoids=input_dict["num_medoids"],
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 disco.core import result_iterator
from discomll import dataset
from discomll.ensemble import distributed_weighted_forest_rand
from discomll.utils import accuracy
train = dataset.Data(data_tag=[
["http://archive.ics.uci.edu/ml/machine-learning-databases/breast-cancer-wisconsin/breast-cancer-wisconsin.data"]],
id_index=0,
X_indices=xrange(1, 10),
X_meta="http://ropot.ijs.si/data/datasets_meta/breastcancer_meta.csv",
y_index=10,
delimiter=",")
fit_model = distributed_weighted_forest_rand.fit(train, trees_per_chunk=3, max_tree_nodes=50, min_samples_leaf=5,
min_samples_split=10, class_majority=1,
measure="info_gain", num_medoids=10, accuracy=1, separate_max=True,
random_state=None, save_results=True)
# predict training dataset
predictions = distributed_weighted_forest_rand.predict(train, fit_model)
# output results
for k, v in result_iterator(predictions):
print k, v[0]
# measure accuracy
ca = accuracy.measure(train, predictions)
print ca
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_weighted_forest_rand.fit(train,
trees_per_chunk=3,
max_tree_nodes=50,
min_samples_leaf=10,
min_samples_split=5,
class_majority=1,
measure="info_gain",
num_medoids=10,
accuracy=1,
separate_max=True,
random_state=None,
save_results=True)
predict_url = distributed_weighted_forest_rand.predict(test, fit_model)
print predict_url