def model_view(request,input_dict,output_dict,widget):
from discomll.utils import model_view
import os.path
from mothra.settings import MEDIA_ROOT
from workflows.helpers import ensure_dir
folder = 'discomll_models'
tag_name = input_dict["fitmodel_url"]
tag = input_dict["fitmodel_url"].values()[0]
destination = MEDIA_ROOT+'/'+folder+"/"+tag[0][6:]+'.txt'
ensure_dir(destination)
if not os.path.isfile(destination): #file doesnt exists
model = model_view.output_model(tag_name)
f = open(destination,'w')
f.write(model)
f.close()
filename = folder+"/"+tag[0][6:]+'.txt'
output_dict['filename'] = filename
return render(request, 'visualizations/string_to_file.html',{'widget':widget,'input_dict':input_dict,'output_dict':output_dict})
def model_view(request, input_dict, output_dict, widget):
from discomll.utils import model_view
import os.path
from mothra.settings import MEDIA_ROOT
from workflows.helpers import ensure_dir
folder = 'discomll_models'
tag_name = input_dict["fitmodel_url"]
tag = input_dict["fitmodel_url"].values()[0]
destination = MEDIA_ROOT + '/' + folder + "/" + tag[0][6:] + '.txt'
ensure_dir(destination)
if not os.path.isfile(destination): #file doesnt exists
model = model_view.output_model(tag_name)
f = open(destination, 'w')
f.write(model)
f.close()
filename = folder + "/" + tag[0][6:] + '.txt'
output_dict['filename'] = filename
return render(request, 'visualizations/string_to_file.html', {
'widget': widget,
'input_dict': input_dict,
'output_dict': output_dict
})
from discomll.utils import model_view
# define training dataset
train = dataset.Data(data_tag=["test:breast_cancer_cont"],
data_type="chunk", # define data source - chunk data on ddfs
X_indices=xrange(0, 9), # define attribute indices
y_index=9, # define class index
delimiter=",")
# define test dataset
test = dataset.Data(data_tag=["test:breast_cancer_cont_test"],
data_type="chunk", # define data source - chunk data on ddfs
X_indices=xrange(0, 9), # define attribute indices
y_index=9, # define class index
delimiter=",")
# fit model on training dataset
fit_model = kmeans.fit(train, n_clusters=2, max_iterations=5, random_state=0)
# output model
model = model_view.output_model(fit_model)
print model
# predict test dataset
predictions = kmeans.predict(test, fit_model)
# output results
for k, v in result_iterator(predictions):
print k, v
from discomll import dataset
from discomll.classification import logistic_regression
from discomll.utils import model_view
# define training dataset
train = dataset.Data(data_tag=["test:ex4"],
data_type="chunk",
X_indices=xrange(0, 2),
y_index=2,
y_map=["0.0000000e+00", "1.0000000e+00"])
# fit model on training dataset
fit_model = logistic_regression.fit(train)
# output model
model = model_view.output_model(fit_model)
print model
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
from disco.core import result_iterator
from discomll import dataset
from discomll.ensemble import forest_distributed_decision_trees
from discomll.utils import model_view
train = dataset.Data(data_tag=[["http://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"]],
X_indices=xrange(0, 4),
X_meta="http://ropot.ijs.si/data/datasets_meta/iris_meta.csv",
y_index=4,
delimiter=",")
fit_model = forest_distributed_decision_trees.fit(train, trees_per_chunk=1, bootstrap=False, max_tree_nodes=50,
min_samples_leaf=2, min_samples_split=1, class_majority=1,
separate_max=True, measure="info_gain", accuracy=1, random_state=None,
save_results=True)
print model_view.output_model(fit_model)
# predict training dataset
predictions = forest_distributed_decision_trees.predict(train, fit_model)
# output results
for k, v in result_iterator(predictions):
print k, v[0]
