def create_tree_result(dir_path: str, tree: DpNode, pred_labels: np.ndarray,
ground_truth: np.ndarray, col_node_id_map):
if not os.path.exists(dir_path):
os.makedirs(dir_path)
f = open(f"{dir_path}/results.txt", "wt")
f.write(
f"NMI: {nmi(pred_labels, ground_truth, average_method='arithmetic')}\n"
)
acc, acc_confusion = cluster_acc(pred_labels, ground_truth)
f.write(f"ACC: {acc} confusion (ground truth \ prediction):\n")
f.write(f"{acc_confusion}\n")
f.write("\n\n")
f.write(f"Dendrogram Purity: {dendrogram_purity(tree, ground_truth)}\n")
lp = leaf_purity(tree, ground_truth)
f.write(f"Leaf Purity: Avg:{lp[0]:1.3} std:{lp[1]:1.3}\n")
col_nod_str = "\t".join([
f"{x[0]}:{x[1]}"
for x in sorted(list(col_node_id_map.items()), key=lambda x: x[0])
])
f.write(f"{col_nod_str}\n")
f.write("\n\n")
tree_str = tree2string(tree, "children", "node_id")
f.write(f"{tree_str} \n")
f.write("\n\n")
f.write(_label_distribution(tree, ground_truth))
f.close()
def run_experiment(ae_model_path):
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(f"Working now on {ae_model_path.name}")
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
new_seed = random.randint(0, 1000)
logger.info(f"Seed value for this is: {new_seed}")
set_random_seed(new_seed)
ae_module = stacked_ae(pt_data.shape[1], [500, 500, 2000, 10],
weight_initalizer=torch.nn.init.xavier_normal_,
activation_fn=lambda x: F.relu(x),
loss_fn=None,
optimizer_fn=None)
model_data = torch.load(ae_model_path, map_location='cpu')
ae_module.load_state_dict(model_data)
ae_module = ae_module.cuda()
# Get embedded data
embedded_data = None
for batch_data in torch.utils.data.DataLoader(pt_data,
batch_size=256,
shuffle=False):
embedded_batch_np = ae_module.forward(
batch_data.cuda())[0].detach().cpu().numpy()
if embedded_data is None:
embedded_data = embedded_batch_np
else:
embedded_data = np.concatenate([embedded_data, embedded_batch_np],
0)
del ae_module
# Perform k-means
k_means_labels = k_means(embedded_data, n_clusters, n_init=20)[1]
k_means_nmi_value = nmi(gold_labels,
k_means_labels,
average_method='arithmetic')
k_means_acc_value = cluster_acc(gold_labels, k_means_labels)[0]
result_file = Path(f"{result_dir}/results_ae_kmeans_{dataset_name}.txt")
result_file_exists = result_file.exists()
f = open(result_file, "a+")
if not result_file_exists:
f.write("#\"ae_model_name\"\t\"NMI\"\t\"ACC\"\n")
f.write(
f"{ae_model_path.name}\t{k_means_nmi_value}\t{k_means_acc_value}\n")
f.close()
def evaluate(train_round_idx, ae_module, cluster_module):
test_loader = torch.utils.data.DataLoader(
torch.utils.data.TensorDataset(pt_data), batch_size=256)
pred_labels = np.zeros(pt_data.shape[0], dtype=np.int)
index = 0
n_batches = 0
for batch_data in test_loader:
batch_data = batch_data[0].cuda()
n_batches += 1
batch_size = batch_data.shape[0]
embedded_data, reconstructed_data = ae_module.forward(batch_data)
labels = cluster_module.prediction_hard_np(embedded_data)
pred_labels[index:index + batch_size] = labels
index = index + batch_size
nmi_value = nmi(gold_labels, pred_labels, average_method='arithmetic')
acc_value = cluster_acc(gold_labels, pred_labels)[0]
logger.info(
f"{train_round_idx} Evaluation: NMI: {nmi_value} ACC: {acc_value}")
return nmi_value, acc_value
def run_experiment(ae_model_path):
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(f"Working now on {ae_model_path.name}")
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
new_seed = random.randint(0, 1000)
logger.info(f"Seed value for this is: {new_seed}")
set_random_seed(new_seed)
ae_module = stacked_ae(pt_data.shape[1], [500, 500, 2000, 10],
weight_initalizer=torch.nn.init.xavier_normal_,
activation_fn=lambda x: F.relu(x),
loss_fn=None,
optimizer_fn=None)
model_data = torch.load(ae_model_path, map_location='cpu')
ae_module.load_state_dict(model_data)
ae_module = ae_module.cuda()
# Get embedded data
embedded_data = None
for batch_data in torch.utils.data.DataLoader(pt_data,
batch_size=256,
shuffle=False):
embedded_batch_np = ae_module.forward(
batch_data.cuda())[0].detach().cpu().numpy()
if embedded_data is None:
embedded_data = embedded_batch_np
else:
embedded_data = np.concatenate([embedded_data, embedded_batch_np],
0)
del ae_module
# bisecting k-means:
tree = bisection(n_leaf_nodes_final, embedded_data)
bisec_labels = predict_by_tree(tree, embedded_data, n_clusters)
bisec_tree = predict_id_tree(tree, embedded_data)
bisec_km_nmi = nmi(gold_labels, bisec_labels, average_method='arithmetic')
bisec_km_acc = cluster_acc(bisec_labels, gold_labels)[0]
bisec_km_purity = dendrogram_purity(bisec_tree, gold_labels)
lp = leaf_purity(bisec_tree, gold_labels)
leaf_purity_value = f"{lp[0]:1.3}\t({lp[1]:1.3})"
result_file = Path(f"{result_dir}/results_ae_biseckm_{dataset_name}.txt")
result_file_exists = result_file.exists()
f = open(result_file, "a+")
if not result_file_exists:
f.write(
"#\"ae_model_name\"\t\"NMI\"\t\"ACC\"\t\"Dendrogram_Purity\"\t\"Leaf_Purity\t(Std)\"\n"
)
f.write(
f"{ae_model_path.name}\t{bisec_km_nmi}\t{bisec_km_acc}\t{bisec_km_purity}\t{leaf_purity_value}\n"
)
f.close()
def run_experiment(ae_model_path):
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(f"Working now on {ae_model_path.name}")
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
logger.info(
f"++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++"
)
new_seed = random.randint(0, 1000)
logger.info(f"Seed value for this is: {new_seed}")
set_random_seed(new_seed)
ae_module = stacked_ae(pt_data.shape[1], [500, 500, 2000, 10],
weight_initalizer=torch.nn.init.xavier_normal_,
activation_fn=lambda x: F.relu(x),
loss_fn=None,
optimizer_fn=None)
model_data = torch.load(ae_model_path, map_location='cpu')
ae_module.load_state_dict(model_data)
ae_module = ae_module.cuda()
# Get embedded data
embedded_data = None
for batch_data in torch.utils.data.DataLoader(pt_data,
batch_size=256,
shuffle=False):
embedded_batch_np = ae_module.forward(
batch_data.cuda())[0].detach().cpu().numpy()
if embedded_data is None:
embedded_data = embedded_batch_np
else:
embedded_data = np.concatenate([embedded_data, embedded_batch_np],
0)
del ae_module
sl_cl = AgglomerativeClustering(compute_full_tree=True,
n_clusters=n_clusters,
linkage="single").fit(embedded_data)
sl_labels = sl_cl.labels_
sl_purity_tree = prune_dendrogram_purity_tree(
to_dendrogram_purity_tree(sl_cl.children_), n_leaf_nodes_final)
sl_nmi = nmi(gold_labels, sl_labels, average_method='arithmetic')
sl_acc = cluster_acc(sl_labels, gold_labels)[0]
sl_purity = dendrogram_purity(sl_purity_tree, gold_labels)
sl_lp = leaf_purity(sl_purity_tree, gold_labels)
sl_leaf_purity_value = f"{sl_lp[0]:1.3}\t({sl_lp[1]:1.3})"
result_file_sl = Path(
f"{result_dir}/results_ae_agglo_single_{dataset_name}.txt")
result_file_sl_exists = result_file_sl.exists()
f = open(result_file_sl, "a+")
if not result_file_sl_exists:
f.write(
"#\"ae_model_name\"\t\"NMI\"\t\"ACC\"\t\"Dendrogram_Purity\"\t\"Leaf_Purity\t(Std)\"\n"
)
f.write(
f"{ae_model_path.name}\t{sl_nmi}\t{sl_acc}\t{sl_purity}\t{sl_leaf_purity_value}\n"
)
f.close()
del sl_cl, sl_labels, sl_purity_tree
cl_cl = AgglomerativeClustering(compute_full_tree=True,
n_clusters=n_clusters,
linkage="complete").fit(embedded_data)
cl_labels = cl_cl.labels_
cl_purity_tree = prune_dendrogram_purity_tree(
to_dendrogram_purity_tree(cl_cl.children_), n_leaf_nodes_final)
cl_nmi = nmi(gold_labels, cl_labels, average_method='arithmetic')
cl_acc = cluster_acc(cl_labels, gold_labels)[0]
cl_purity = dendrogram_purity(cl_purity_tree, gold_labels)
cl_lp = leaf_purity(cl_purity_tree, gold_labels)
cl_leaf_purity_value = f"{cl_lp[0]:1.3}\t({cl_lp[1]:1.3})"
result_file_cl = Path(
f"{result_dir}/results_ae_agglo_complete_{dataset_name}.txt", )
result_file_cl_exists = result_file_cl.exists()
f = open(result_file_cl, "a+")
if not result_file_cl_exists:
f.write(
"#\"ae_model_name\"\t\"NMI\"\t\"ACC\"\t\"Dendrogram_Purity\"\t\"Leaf_Purity\t(Std)\"\n"
)
f.write(
f"{ae_model_path.name}\t{cl_nmi}\t{cl_acc}\t{cl_purity}\t{cl_leaf_purity_value}\n"
)
f.close()
del cl_cl, cl_labels, cl_purity_tree