def test_som():
cur = enable_connection()
companies_data = data_fetch.get_data(cur)
companies_names = data_fetch.get_names(cur)
#print(companies_data.shape)
#print(companies_data)
most_similar_companies = similarity_func(companies_data[13], companies_data, companies_names, 5)
#print(most_similar_companies)
print(list(most_similar_companies.values()))
for company_id, company_distance in most_similar_companies.items():
#print(company_id)
print(companies_names[int(company_id)])
print(company_distance)
#print(companies_names[list(most_similar_companies.keys())])
# c1 = np.random.rand(50, 3)/5
# c2 = (0.6, 0.1, 0.05) + np.random.rand(50, 3)/5
# c3 = (0.4, 0.1, 0.7) + np.random.rand(50, 3)/5
# data = np.float32(np.concatenate((c1, c2, c3)))
# fig = plt.figure()
# ax = Axes3D(fig)
# ax.scatter(data[:, 0], data[:, 1], data[:, 2], c=colors)
# labels = range(150)
dim_multiplier = 2
n_rows, n_columns = companies_data.shape[0] * dim_multiplier, \
companies_data.shape[1] * dim_multiplier
som = somoclu.Somoclu(n_columns, n_rows, maptype="toroid",
compactsupport=False)
colors = ["red"] * 60
colors.extend(["green"] * 60)
colors.extend(["blue"] * 61)
unit_labels = range(181)
som.train(companies_data, epochs=1)
som.view_umatrix(bestmatches=True, labels=companies_names)
activation_map = som.get_surface_state()
# bestmatchs = som.get_bmus(activation_map)
# print(activation_map)
# print(bestmatchs)
# #print(som.activation_map)
# som.view_component_planes()
plt.savefig('pic8.png')
criterion = boundary_distance_BCE
elif LOSS_NUM == 4:
print("Using distance weighted Dice")
criterion = boundary_distance_dice
elif LOSS_NUM == 5:
print("Using Lovasz")
criterion = lovasz_hinge_loss
elif LOSS_NUM == 6:
criterion = lovasz_hinge
# Pick optimizer
optimizer = Adam(model.parameters(), lr=LR)
print("Reading data")
all_data, labels, img_name, class_labels = get_data(num_points_fetch)
all_data = all_data / 255.0
print("Loaded data")
if LOSS_NUM == 3 or LOSS_NUM == 4:
print("calculating weights")
obj = DistToBoundary(labels)
rowWts, colWts = obj.computeWeights()
weights = 5 * np.exp(-(rowWts + colWts)/50.0)
# Split data into train and test
test_data = all_data[train_num_pts:]
test_label = labels[train_num_pts:]
all_data = all_data[:train_num_pts]
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import cross_validate
from data_fetch import get_data
data_sets = [
"Breast Cancer", "Blood Transfusion", "Diabetes", "Credit Scores",
"Oil Spill"
]
##################### Set varibles ###########################
dataset = data_sets[0] # pick data set
FOLDS = 5 # set # of folds for cross validation
clf = RandomForestClassifier() # choose classifier
#################### Get data ###########################
features, labels = get_data(dataset)
################### Fit classifier ###########################
result = cross_validate(clf, features, labels, cv=FOLDS)
################### Display result ###########################
print("Cv results")
for res in result["test_score"]:
print(res)