def test_load_rb_wb_03():
data = load_rb_wb_03(num_instances=1)
known = {'_guid': 'aa5eff72-0572-4eff-a007-3def9a82ba5b',
'_human_cluster_label': '0', 'component0': {'b': 2.0, 'l': 2.0,
'r': 3.0, 't': 3.0,
'type': 'cube0'},
'component1': {'b': 2.0, 'l': 3.0, 'r': 4.0, 't': 3.0, 'type':
'cube0'}, 'component11': {'b': 3.0, 'l': 1.0, 'r':
4.0, 't': 4.0, 'type':
'ufoo0'}, 'component2':
{'b': 1.0, 'l': 2.0, 'r': 5.0, 't': 2.0, 'type': 'plat0'},
'component3': {'b': 0.0, 'l': 0.0, 'r': 5.0, 't': 1.0, 'type':
'rect0'}}
assert known == data[0]
def output_json(file="forest", size=100, prune=True, seed=50, burn=1):
random.seed(seed)
if file == "forest":
instances = ds.load_forest_fires()
variables = False
elif file == "voting":
instances = ds.load_congressional_voting()
variables = False
elif file == "iris":
instances = ds.load_iris()
variables = False
elif file == "mushroom":
instances = ds.load_mushroom()
variables = False
elif file == "rb_com_11":
instances = ds.load_rb_com_11()
variables = True
elif file == "rb_s_07":
instances = ds.load_rb_s_07()
variables = True
elif file == "rb_s_13":
instances = ds.load_rb_s_13()
variables = True
elif file == "rb_wb_03":
instances = ds.load_rb_wb_03()
variables = True
else:
instances = ds.load_forest_fires()
variables = False
random.shuffle(instances)
pprint.pprint(instances[0])
instances = instances[:size]
print(len(instances))
if variables:
variablizer = ObjectVariablizer()
instances = [variablizer.transform(t) for t in instances]
tree = TrestleTree()
tree.fit(instances, iterations=burn)
pprint.pprint(tree.root.output_json())
with open('output.js', 'w') as out:
out.write("var trestle_output = ")
out.write(json.dumps(tree.root.output_json()))
out.write(";")
def output_json(file="forest", size=100, prune=True, seed=50, burn=1):
random.seed(seed)
if file == "forest":
instances = ds.load_forest_fires()
variables = False
elif file == "voting":
instances = ds.load_congressional_voting()
variables = False
elif file == "iris":
instances = ds.load_iris()
variables = False
elif file == "mushroom":
instances = ds.load_mushroom()
variables = False
elif file == "rb_com_11":
instances = ds.load_rb_com_11()
variables = True
elif file == "rb_s_07":
instances = ds.load_rb_s_07()
variables = True
elif file == "rb_s_13":
instances = ds.load_rb_s_13()
variables = True
elif file == "rb_wb_03":
instances = ds.load_rb_wb_03()
variables = True
else:
instances = ds.load_forest_fires()
variables = False
random.shuffle(instances)
pprint.pprint(instances[0])
instances = instances[:size]
print(len(instances))
if variables:
variablizer = ObjectVariablizer()
instances = [variablizer.transform(t) for t in instances]
tree = TrestleTree()
tree.fit(instances, iterations=burn)
# pprint.pprint(tree.root.output_json())
with open('output.js', 'w') as out:
out.write("var trestle_output = ")
out.write(json.dumps(tree.root.output_json()))
out.write(";")
def test_load_rb_wb_03():
data = load_rb_wb_03(num_instances=1)
known = {
'_guid': 'aa5eff72-0572-4eff-a007-3def9a82ba5b',
'_human_cluster_label': '0',
'component0': {
'b': 2.0,
'l': 2.0,
'r': 3.0,
't': 3.0,
'type': 'cube0'
},
'component1': {
'b': 2.0,
'l': 3.0,
'r': 4.0,
't': 3.0,
'type': 'cube0'
},
'component11': {
'b': 3.0,
'l': 1.0,
'r': 4.0,
't': 4.0,
'type': 'ufoo0'
},
'component2': {
'b': 1.0,
'l': 2.0,
'r': 5.0,
't': 2.0,
'type': 'plat0'
},
'component3': {
'b': 0.0,
'l': 0.0,
'r': 5.0,
't': 1.0,
'type': 'rect0'
}
}
assert known == data[0]
from __future__ import print_function
from __future__ import unicode_literals
from __future__ import absolute_import
from __future__ import division
from random import shuffle
from sklearn.metrics import adjusted_rand_score
import matplotlib.pyplot as plt
from concept_formation.trestle import TrestleTree
from concept_formation.cluster import cluster
from concept_formation.datasets import load_rb_wb_03
from concept_formation.structure_mapper import ObjectVariablizer
towers = load_rb_wb_03()
shuffle(towers)
towers = towers[:30]
variablizer = ObjectVariablizer()
towers = [variablizer.transform(t) for t in towers]
tree = TrestleTree()
clusters = cluster(tree, towers, maxsplit=10)
human_labels = [tower['_human_cluster_label'] for tower in towers]
x = [num_splits for num_splits in range(1,len(clusters)+1)]
y = [adjusted_rand_score(human_labels, split) for split in clusters]
plt.plot(x, y, label="TRESTLE")
plt.title("TRESTLE Clustering Accuracy (Given Human Ground Truth)")
plt.ylabel("Adjusted Rand Index (Agreement Correcting for Chance)")
clusters = [cluster_split_search(tree, dataset, h, minsplit=1, maxsplit=40,
mod=False) for h in hueristics]
human_labels = [ds['_human_cluster_label'] for ds in dataset]
return [max(adjusted_rand_score(human_labels, huer), 0.01) for huer in
clusters]
x = np.arange(len(hueristics))
width = 0.3
hueristic_names = ['AIC', 'BIC', 'CU', 'AICc']
# for i in range(len(clusters)):
# hueristic_names[i] += '\nClusters='+str(len(set(clusters[i])))
b1 = plt.bar(x-width, calculate_aris(load_rb_wb_03()),
width, color='r', alpha=.8, align='center')
b2 = plt.bar(x, calculate_aris(load_rb_com_11()),
width, color='b', alpha=.8, align='center')
b3 = plt.bar(x+width, calculate_aris(load_rb_s_13()),
width, color='g', alpha=.8, align='center')
plt.legend((b1[0], b2[0], b3[0]), ('wb_03', 'com_11', 's_13'))
plt.title("TRESTLE Clustering Accuracy of Best Clustering by Different"
" Hueristics")
plt.ylabel("Adjusted Rand Index (Agreement Correcting for Chance)")
plt.ylim(0, 1)
plt.xlabel("Hueristic")
plt.xticks(x, hueristic_names)
plt.show()
from random import shuffle
from random import seed
from sklearn.metrics import adjusted_rand_score
import matplotlib.pyplot as plt
import numpy as np
from concept_formation.trestle import TrestleTree
from concept_formation.cluster import cluster_split_search
from concept_formation.cluster import AIC, BIC, AICc, CU
from concept_formation.datasets import load_rb_wb_03
from concept_formation.preprocessor import ObjectVariablizer
seed(5)
towers = load_rb_wb_03()
shuffle(towers)
towers = towers[:60]
variablizer = ObjectVariablizer()
towers = [variablizer.transform(t) for t in towers]
tree = TrestleTree()
tree.fit(towers)
hueristics = [AIC, BIC, CU, AICc]
clusters = [
cluster_split_search(tree, towers, h, minsplit=1, maxsplit=40, mod=False)
for h in hueristics
]
human_labels = [dataset['_human_cluster_label'] for dataset in dataset]
return [
max(adjusted_rand_score(human_labels, huer), 0.01) for huer in clusters
]
x = np.arange(len(hueristics))
width = 0.3
hueristic_names = ['AIC', 'BIC', 'CU', 'AICc']
# for i in range(len(clusters)):
# hueristic_names[i] += '\nClusters='+str(len(set(clusters[i])))
b1 = plt.bar(x - width,
calculate_aris(load_rb_wb_03()),
width,
color='r',
alpha=.8,
align='center')
b2 = plt.bar(x,
calculate_aris(load_rb_com_11()),
width,
color='b',
alpha=.8,
align='center')
b3 = plt.bar(x + width,
calculate_aris(load_rb_s_13()),
width,
color='g',
alpha=.8,