def test_kmeans_breastcancer(self):
# python -m unittest tests_clustering.Tests_Clustering.test_kmeans_breastcancer
from discomll.clustering import kmeans
from sklearn.cluster import KMeans
max_iter = 10
clusters = 2
random_seed = 2
x_train, _, x_test, _ = datasets.breastcancer_disc()
train_data, test_data = datasets.breastcancer_disc_discomll()
kmeans2 = KMeans(n_clusters=clusters, max_iter=max_iter, n_init=1, random_state=random_seed).fit(x_train)
centroids1 = kmeans2.cluster_centers_
predictions1 = kmeans2.predict(x_test)
centroids_url = kmeans.fit(train_data,
n_clusters=clusters,
max_iterations=max_iter,
random_state=random_seed)
predictions_url = kmeans.predict(test_data, centroids_url)
predictions2 = [v[0] for k, v in result_iterator(predictions_url)]
centroids2 = [v["x"] for k, v in result_iterator(centroids_url["kmeans_fitmodel"])]
centroids2[0], centroids2[1] = centroids2[1], centroids2[0]
self.assertTrue(np.allclose(centroids1, centroids2))
def test_kmeans_iris(self):
# python -m unittest tests_clustering.Tests_Clustering.test_kmeans_iris
from discomll.clustering import kmeans
from sklearn.cluster import KMeans
max_iter = 10
clusters = 3
random_seed = 0
x_train, y_train, x_test, y_test = datasets.iris()
train_data, test_data = datasets.iris_discomll()
sk_kmeans = KMeans(n_clusters=clusters, max_iter=max_iter, n_init=1, random_state=random_seed).fit(x_train)
centroids1 = sk_kmeans.cluster_centers_
# predictions1 = sk_kmeans.predict(x_test)
centroids_url = kmeans.fit(train_data,
n_clusters=clusters,
max_iterations=max_iter,
random_state=random_seed)
predictions_url = kmeans.predict(test_data, centroids_url)
# predictions2 = [v[1] for k,v in result_iterator(predictions_url)]
centroids2 = [v["x"] for k, v in result_iterator(centroids_url["kmeans_fitmodel"])]
centroids2[0], centroids2[2] = centroids2[2], centroids2[0]
self.assertTrue(np.allclose(centroids1, centroids2))
def test_kmeans_breastcancer(self):
# python -m unittest tests_clustering.Tests_Clustering.test_kmeans_breastcancer
from discomll.clustering import kmeans
from sklearn.cluster import KMeans
max_iter = 10
clusters = 2
random_seed = 2
x_train, _, x_test, _ = datasets.breastcancer_disc()
train_data, test_data = datasets.breastcancer_disc_discomll()
kmeans2 = KMeans(n_clusters=clusters,
max_iter=max_iter,
n_init=1,
random_state=random_seed).fit(x_train)
centroids1 = kmeans2.cluster_centers_
predictions1 = kmeans2.predict(x_test)
centroids_url = kmeans.fit(train_data,
n_clusters=clusters,
max_iterations=max_iter,
random_state=random_seed)
predictions_url = kmeans.predict(test_data, centroids_url)
predictions2 = [v[0] for k, v in result_iterator(predictions_url)]
centroids2 = [
v["x"]
for k, v in result_iterator(centroids_url["kmeans_fitmodel"])
]
centroids2[0], centroids2[1] = centroids2[1], centroids2[0]
self.assertTrue(np.allclose(centroids1, centroids2))
def test_kmeans_iris(self):
# python -m unittest tests_clustering.Tests_Clustering.test_kmeans_iris
from discomll.clustering import kmeans
from sklearn.cluster import KMeans
max_iter = 10
clusters = 3
random_seed = 0
x_train, y_train, x_test, y_test = datasets.iris()
train_data, test_data = datasets.iris_discomll()
sk_kmeans = KMeans(n_clusters=clusters,
max_iter=max_iter,
n_init=1,
random_state=random_seed).fit(x_train)
centroids1 = sk_kmeans.cluster_centers_
# predictions1 = sk_kmeans.predict(x_test)
centroids_url = kmeans.fit(train_data,
n_clusters=clusters,
max_iterations=max_iter,
random_state=random_seed)
predictions_url = kmeans.predict(test_data, centroids_url)
# predictions2 = [v[1] for k,v in result_iterator(predictions_url)]
centroids2 = [
v["x"]
for k, v in result_iterator(centroids_url["kmeans_fitmodel"])
]
centroids2[0], centroids2[2] = centroids2[2], centroids2[0]
self.assertTrue(np.allclose(centroids1, centroids2))
def kmeans_fit(input_dict):
from discomll.clustering import kmeans
fitmodel_url = kmeans.fit(input_dict["dataset"],
n_clusters=input_dict["clusters"],
max_iterations=input_dict["itr"],
save_results=True)
return {"fitmodel_url": fitmodel_url}
def kmeans_fit(input_dict):
from discomll.clustering import kmeans
fitmodel_url = kmeans.fit(input_dict["dataset"],
n_clusters = input_dict["clusters"],
max_iterations = input_dict["itr"],
save_results = True)
return {"fitmodel_url" : fitmodel_url}
def kmeans_fit(input_dict):
from discomll.clustering import kmeans
random_state = None if input_dict["seed"] == "None" else int(input_dict["seed"])
fitmodel_url = kmeans.fit(input_dict["dataset"],
n_clusters=input_dict["clusters"],
max_iterations=input_dict["itr"],
random_state=random_state,
save_results=True)
return {"fitmodel_url": fitmodel_url}
def kmeans_fit(input_dict):
from discomll.clustering import kmeans
random_state = None if input_dict["seed"] == "None" else int(
input_dict["seed"])
fitmodel_url = kmeans.fit(input_dict["dataset"],
n_clusters=input_dict["clusters"],
max_iterations=input_dict["itr"],
random_state=random_state,
save_results=True)
return {"fitmodel_url": fitmodel_url}
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.clustering import kmeans
train = dataset.Data(data_tag=[
"http://ropot.ijs.si/data/linear/train/xaaaaa.gz",
"http://ropot.ijs.si/data/linear/train/xaaabj.gz"
],
data_type="gzip",
generate_urls=True,
X_indices=range(1, 22),
id_index=0,
delimiter=",")
test = dataset.Data(data_tag=[
"http://ropot.ijs.si/data/linear/test/xaaaaa.gz",
"http://ropot.ijs.si/data/linear/test/xaaabj.gz"
],
data_type="gzip",
generate_urls=True,
X_indices=range(1, 22),
id_index=0,
delimiter=",")
fit_model = kmeans.fit(train, n_clusters=5, max_iterations=10, random_state=0)
predictions = kmeans.predict(test, fit_model)
print predictions