def rf_predict(input_dict):
from discomll.ensemble import distributed_random_forest
predictions_url = distributed_random_forest.predict(input_dict["dataset"],
fitmodel_url=input_dict["fitmodel_url"],
save_results=True)
return {"string": predictions_url}
def rf_predict(input_dict):
from discomll.ensemble import distributed_random_forest
predictions_url = distributed_random_forest.predict(
input_dict["dataset"],
fitmodel_url=input_dict["fitmodel_url"],
save_results=True)
return {"string": predictions_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
from disco.core import result_iterator
from discomll import dataset
from discomll.ensemble import distributed_random_forest
from discomll.utils import model_view
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_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)
print model_view.output_model(fit_model)
# predict training dataset
predictions = distributed_random_forest.predict(train, fit_model)
# output results
for k, v in result_iterator(predictions):
print k, v
# measure accuracy
ca = accuracy.measure(train, predictions)
print ca
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
]],
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_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)
print model_view.output_model(fit_model)
# predict training dataset
predictions = distributed_random_forest.predict(train, fit_model)
# output results
for k, v in result_iterator(predictions):
print k, v
# measure accuracy
ca = accuracy.measure(train, predictions)
print ca
from discomll import dataset
from discomll.ensemble import distributed_random_forest
train = dataset.Data(data_tag=["http://ropot.ijs.si/data/segmentation/train/xaaaaa.gz",
"http://ropot.ijs.si/data/segmentation/train/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(2, 21),
id_index=0,
y_index=1,
X_meta=["c" for i in range(2, 21)],
delimiter=",")
test = dataset.Data(data_tag=["http://ropot.ijs.si/data/segmentation/test/xaaaaa.gz",
"http://ropot.ijs.si/data/segmentation/test/xaaabj.gz"],
data_type="gzip",
generate_urls=True,
X_indices=range(2, 21),
id_index=0,
y_index=1,
X_meta=["c" for i in range(2, 21)],
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)
predictions = distributed_random_forest.predict(test, fit_model, diff=1)
print predictions
