def experiment_10(a):
concatenate={}
concatenate[111]=DATA_111_URL
concatenate[290]=DATA_290_URL
concatenate[896]=DATA_896_URL
data_table = load_data_table(concatenate[a])
##for the hierarchical
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
for ele in x:
singleton_list=HW3.hierarchical_clustering(singleton_list,ele)
distortion=0
for cluster in singleton_list:
distortion+=cluster.cluster_error(data_table)
if a==111:
y_111_H.append(distortion)
elif a==290:
y_290_H.append(distortion)
else:
y_896_H.append(distortion)
##K-means
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
for ele in x:
singleton_list=HW3.kmeans_clustering(singleton_list,ele,5)
distortion=0
for cluster in singleton_list:
distortion+=cluster.cluster_error(data_table)
if a==111:
y_111_K.append(distortion)
elif a==290:
y_290_K.append(distortion)
else:
y_896_K.append(distortion)
if a==111:
plt.plot(x,y_111_H)
plt.plot(x,y_111_K)
elif a==290:
plt.plot(x,y_290_H)
plt.plot(x,y_290_K)
else:
plt.plot(x,y_896_H)
plt.plot(x,y_896_K)
plt.xlabel('Number of the clusters ')
plt.ylabel('Total Distortion')
plt.legend(['Hierarchical Clustering','K-mean clustering'])
plt.title('Distortion comparison of two clustering method-'+str(a)+'counties')
plt.grid(True)
plt.savefig("HW3_"+str(a)+".png")
plt.show()
def run_example():
"""
Load a data table, compute a list of clusters and
plot a list of clusters
Set DESKTOP = True/False to use either matplotlib or simplegui
"""
data_table = load_data_table(DATA_3108_URL)
singleton_list = []
for line in data_table:
singleton_list.append(alg_cluster.Cluster(set([line[0]]), line[1], line[2], line[3], line[4]))
#cluster_list = sequential_clustering(singleton_list, 15)
#print "Displaying", len(cluster_list), "sequential clusters"
cluster_list = HW3.hierarchical_clustering(singleton_list, 15)
print "Displaying", len(cluster_list), "hierarchical clusters"
# cluster_list = HW3.kmeans_clustering(singleton_list,9, 5)
# print "Displaying", len(cluster_list), "k-means clusters"
#draw the clusters using matplotlib or simplegui
if DESKTOP:
alg_clusters_matplotlib.plot_clusters(data_table, cluster_list, False)
def test_mergeSort(self):
self.assertEqual(HW3.mergeSort(random_array), sorted_array)
def test_bubblesort(self):
self.assertEqual(HW3.bubblesort(random_array), sorted_array)
import sys
import os
import pathlib
p = pathlib.Path(os.getcwd())
p /= "../../../starter/lesson 7/Alex Shvab"
p = p.resolve()
sys.path.insert(0, str(p))
import HW3
x = int(input("Enter range of simple number: "))
HW3.simpl_numb(x + 1)
print((HW3.list))
import HW3
import pprint
documents = [{
"type": "passport",
"number": "2207",
"name": "Василий Гупкин"
}, {
"type": "invoice",
"number": "11-2",
"name": "Геннадий Покемонов"
}, {
"type": "insurance",
"number": "10006",
"name": "Аристарх Павлов"
}, {
"type": "insurance",
"number": "2"
}]
print(documents)
# print(HW3.get_owner(documents, '2'))
print(documents[0].keys())
if 'name' in documents[0].keys(): print('++')
print(HW3.get_owner(documents, '2'))
def test_bubblesort(self):
self.assertEqual(HW3.bubblesort(random_array), sorted_array)
def test_mergeSort(self):
self.assertEqual(HW3.mergeSort(random_array), sorted_array)
batch_size = 20
seq_length = 30
dropout = 0.3
learning_rate = 0.005
seed = 621
date = datetime.datetime.now().strftime("%d-%m-%y %H-%M-%S")
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
corpus = Corpus()
ids = corpus.get_data('data/train.txt', batch_size) # divide to batch size
valid_d = corpus.get_data('data/valid.txt', batch_size)
test_d = corpus.get_data('data/test.txt', batch_size)
vocab_size = len(corpus.dictionary)
num_batches = ids.size(1) // seq_length
model = HW3.RNNLM(vocab_size, embed_size, hidden_size, num_layers, dropout)
model.load_state_dict(torch.load(model_name,map_location=device))
model.eval()
torch.manual_seed(seed)
if torch.cuda.is_available():
torch.cuda.manual_seed(seed)
model.cuda()
else:
model.cpu()
# Set the random seed manually for reproducibility.
generate()
print(' ****** END of generative process ******')
import HW3 print(HW3.create_snp(3, 'ACGCTCGCTGAC'))
from matplotlib import pyplot
# Loop that gets a list of times for each type of sort
N = 10
trials = 4
merge_times = [0] * trials
bubble_times = [0] * trials
quick_times = [0] * trials
for i in range(0, trials):
random_array = range(1, N)
random.shuffle(random_array)
start_time = time.clock()
HW3.mergeSort(random_array)
merge_times[i] = time.clock() - start_time
random_array = range(1, N)
random.shuffle(random_array)
start_time = time.clock()
HW3.bubblesort(random_array)
bubble_times[i] = time.clock() - start_time
random_array = range(1, N)
random.shuffle(random_array)
start_time = time.clock()
random_array.sort()
quick_times[i] = time.clock() - start_time
