def single_run_single_gate(params):
start_time = time.time()
#evauntually uncomment this leaving asis in order ot keep the same results as before to compare.
#set_random_seeds(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
data_input.split_data(split_seed=params['random_seed'])
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer']
)
data_input.save_transformer(params['save_dir'])
data_input.normalize_data()
unused_cluster_gate_inits = init_plot_and_save_gates(data_input, params)
#everything below differs from the other main_UMAP
data_input.convert_all_data_to_tensors()
init_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(
unused_cluster_gate_inits, data_input, params, model=None)
model = initialize_model(params['model_params'], [init_gate_tree])
performance_tracker = run_train_model(model, params['train_params'],
data_input)
model_save_path = os.path.join(params['save_dir'], 'model.pkl')
torch.save(model.state_dict(), model_save_path)
trackers_save_path = os.path.join(params['save_dir'],
'last_CV_rounds_tracker.pkl')
with open(trackers_save_path, 'wb') as f:
pickle.dump(performance_tracker, f)
results_plotter = DataAndGatesPlotterDepthOne(
model, np.concatenate(data_input.x_tr))
#fig, axes = plt.subplots(params['gate_init_params']['n_clusters'], figsize=(1 * params['gate_init_params']['n_clusters'], 3 * params['gate_init_params']['n_clusters']))
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'final_gates.png'))
with open(os.path.join(params['save_dir'], 'configs.pkl'), 'wb') as f:
pickle.dump(params, f)
print('Complete main loop took %.4f seconds' % (time.time() - start_time))
return performance_tracker, model
def main(path_to_params):
start_time = time.time()
params = TransformParameterParser(path_to_params).parse_params()
print(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
data_input.split_data()
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
params['transform_params']['cells_to_subsample'],
params['transform_params']['num_cells_for_transformer'])
data_input.save_transformer(params['save_dir'])
data_input.normalize_data()
init_gate_tree = init_plot_and_save_gates(data_input, params)
model = initialize_model(params['model_params'], init_gate_tree)
data_input.prepare_data_for_training()
performance_tracker = run_train_model(model, params['train_params'],
data_input)
model_save_path = os.path.join(params['save_dir'], 'model.pkl')
torch.save(model.state_dict(), model_save_path)
tracker_save_path = os.path.join(params['save_dir'], 'tracker.pkl')
with open(tracker_save_path, 'wb') as f:
pickle.dump(performance_tracker, f)
results_plotter = DataAndGatesPlotterDepthOne(
model, np.concatenate(data_input.x_tr))
#fig, axes = plt.subplots(params['gate_init_params']['n_clusters'], figsize=(1 * params['gate_init_params']['n_clusters'], 3 * params['gate_init_params']['n_clusters']))
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'final_gates.png'))
print('Complete main loop took %.4f seconds' % (time.time() - start_time))
def cross_validate(path_to_params, n_runs, start_seed=0):
start_time = time.time()
params = TransformParameterParser(path_to_params).parse_params()
print(params)
check_consistency_of_params(params)
#evauntually uncomment this leaving asis in order ot keep the same results as before to compare.
set_random_seeds(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
te_accs = []
tr_accs = []
# to get to the correct new split at start
for i in range(start_seed):
data_input.split_data()
for run in range(start_seed, n_runs):
if not os.path.exists(os.path.join(params['save_dir'], 'run%d' % run)):
os.makedirs(os.path.join(params['save_dir'], 'run%d' % run))
savepath = os.path.join(params['save_dir'], 'run%d' % run)
data_input.split_data()
print(data_input.idxs_tr)
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer'],
use_labels_to_transform_data=params['transform_params']['use_labels_to_transform_data']
)
data_input.save_transformer(savepath)
data_input.normalize_data()
unused_cluster_gate_inits = init_plot_and_save_gates(
data_input, params)
#everything below differs from the other main_UMAP
data_input.convert_all_data_to_tensors()
init_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(
unused_cluster_gate_inits, data_input, params, model=None)
model = initialize_model(params['model_params'], [init_gate_tree])
performance_tracker = run_train_model(model, params['train_params'],
data_input)
model_save_path = os.path.join(savepath, 'model.pkl')
torch.save(model.state_dict(), model_save_path)
tracker_save_path = os.path.join(savepath, 'tracker.pkl')
with open(tracker_save_path, 'wb') as f:
pickle.dump(performance_tracker, f)
results_plotter = DataAndGatesPlotterDepthOne(
model, np.concatenate(data_input.x_tr))
#fig, axes = plt.subplots(params['gate_init_params']['n_clusters'], figsize=(1 * params['gate_init_params']['n_clusters'], 3 * params['gate_init_params']['n_clusters']))
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(savepath, 'final_gates.png'))
with open(os.path.join(savepath, 'configs.pkl'), 'wb') as f:
pickle.dump(params, f)
print('Complete main loop for run %d took %.4f seconds' %
(run, time.time() - start_time))
start_time = time.time()
print('Accuracy tr %.3f, te %.3f' %
(performance_tracker.metrics['tr_acc'][-1],
performance_tracker.metrics['te_acc'][-1]))
te_accs.append(performance_tracker.metrics['te_acc'][-1])
tr_accs.append(performance_tracker.metrics['tr_acc'][-1])
tr_accs = np.array(tr_accs)
te_accs = np.array(te_accs)
print('Average tr acc: %.3f, te acc %.3f' %
(np.mean(tr_accs), np.mean(te_accs)))
print('Std dev tr acc: %.3f, te_acc %.3f' %
(np.std(tr_accs), np.std(te_accs)))
def main(path_to_params):
start_time = time.time()
params = TransformParameterParser(path_to_params).parse_params()
print(params)
check_consistency_of_params(params)
#evauntually uncomment this leaving asis in order ot keep the same results as before to compare.
set_random_seeds(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
data_input.split_data()
print('%d samples in the training data' % len(data_input.x_tr))
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer'],
use_labels_to_transform_data=params['transform_params']['use_labels_to_transform_data']
)
# can't pickle opentsne objects
if not params['transform_params'] == 'tsne':
data_input.save_transformer(params['save_dir'])
data_input.normalize_data()
potential_gates = get_all_potential_gates(data_input, params)
data_input.convert_all_data_to_tensors()
model = initialize_model(params['model_params'], potential_gates)
if params['train_params']['fix_gates']:
model.freeze_gate_params()
tracker = run_train_model(\
model, params['train_params'], data_input
)
# if params['transform_params']['embed_dim'] == 3:
# unused_cluster_gate_inits = init_gates(data_input, params)
# else:
# unused_cluster_gate_inits = init_plot_and_save_gates(data_input, params)
# #everything below differs from the other main_UMAP
# data_input.convert_all_data_to_tensors()
# init_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(unused_cluster_gate_inits, data_input, params, model=None)
# model = initialize_model(params['model_params'], [init_gate_tree])
# trackers_per_round = []
# num_gates_left = len(unused_cluster_gate_inits)
# #print(num_gates_left, 'asdfasdfasdfasdfasdfasdfas')
# for i in range(num_gates_left + 1):
# performance_tracker = run_train_model(model, params['train_params'], data_input)
# trackers_per_round.append(performance_tracker.get_named_tuple_rep())
# if i == params['train_params']['num_gates_to_learn'] - 1:
# break
# if not i == num_gates_left:
# next_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(unused_cluster_gate_inits, data_input, params, model=model)
# model.add_node(next_gate_tree)
model_save_path = os.path.join(params['save_dir'], 'model.pkl')
torch.save(model.state_dict(), model_save_path)
tracker_save_path = os.path.join(params['save_dir'], 'tracker.pkl')
# trackers_per_round = [tracker.get_named_tuple_rep() for tracker in trackers_per_round]
with open(tracker_save_path, 'wb') as f:
pickle.dump(tracker, f)
if params['plot_umap_reflection']:
# reflection is about x=.5 since the data is already in umap space here
reflected_data = []
for data in data_input.x_tr:
data[:, 0] = 1 - data[:, 0]
reflected_data.append(data)
data_input.x_tr = reflected_data
gate_tree = model.get_gate_tree()
reflected_gates = []
for gate in gate_tree:
print(gate)
#order switches since reflected over x=.5
low_reflected = 1 - gate[0][2]
high_reflected = 1 - gate[0][1]
gate[0][1] = low_reflected
gate[0][2] = high_reflected
print(gate)
reflected_gates.append(gate)
model.init_nodes(reflected_gates)
print(model.init_nodes)
print(model.get_gates())
results_plotter = DataAndGatesPlotterDepthOne(
model, np.concatenate(data_input.x_tr))
#fig, axes = plt.subplots(params['gate_init_params']['n_clusters'], figsize=(1 * params['gate_init_params']['n_clusters'], 3 * params['gate_init_params']['n_clusters']))
if params['transform_params']['embed_dim'] == 2:
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'final_gates.png'))
else:
fig_pos, ax_pos, fig_neg, ax_neg = results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
with open(os.path.join(params['save_dir'], 'final_gates_pos_3d.pkl'),
'wb') as f:
pickle.dump(fig_pos, f)
with open(os.path.join(params['save_dir'], 'final_gates_neg_3d.pkl'),
'wb') as f:
pickle.dump(fig_neg, f)
with open(os.path.join(params['save_dir'], 'configs.pkl'), 'wb') as f:
pickle.dump(params, f)
print('Learned weights:', model.linear.weight)
print('Complete main loop took %.4f seconds' % (time.time() - start_time))
def main(params):
start_time = time.time()
#evauntually uncomment this leaving asis in order ot keep the same results as before to compare.
set_random_seeds(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
data_input.split_data()
print('%d samples in the training data' % len(data_input.x_tr))
# force identity for the first transform
data_transformer = DataTransformerFactory({
'transform_type': 'identity'
}, params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer'],
use_labels_to_transform_data=params['transform_params']['use_labels_to_transform_data']
)
# can't pickle opentsne objects
if not params['transform_params'] == 'tsne':
data_input.save_transformer(params['save_dir'])
data_input.normalize_data()
# gates aren't plotted because we're in n dimensions
unused_cluster_gate_inits = init_gates(data_input, params)
data_input.convert_all_data_to_tensors()
init_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(
unused_cluster_gate_inits, data_input, params, model=None)
model = initialize_model(params['model_params'], [init_gate_tree])
trackers_per_round = []
num_gates_left = len(unused_cluster_gate_inits)
for i in range(num_gates_left + 1):
performance_tracker = run_train_model(model, params['train_params'],
data_input)
trackers_per_round.append(performance_tracker.get_named_tuple_rep())
if i == params['train_params']['num_gates_to_learn'] - 1:
break
if not i == num_gates_left:
next_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(
unused_cluster_gate_inits, data_input, params, model=model)
model.add_node(next_gate_tree)
model_save_path = os.path.join(params['save_dir'], 'model.pkl')
torch.save(model.state_dict(), model_save_path)
trackers_save_path = os.path.join(params['save_dir'], 'trackers.pkl')
# trackers_per_round = [tracker.get_named_tuple_rep() for tracker in trackers_per_round]
with open(trackers_save_path, 'wb') as f:
pickle.dump(trackers_per_round, f)
if params['plot_umap_reflection']:
# reflection is about x=.5 since the data is already in umap space here
reflected_data = []
for data in data_input.x_tr:
data[:, 0] = 1 - data[:, 0]
reflected_data.append(data)
data_input.x_tr = reflected_data
gate_tree = model.get_gate_tree()
reflected_gates = []
for gate in gate_tree:
print(gate)
#order switches since reflected over x=.5
low_reflected = 1 - gate[0][2]
high_reflected = 1 - gate[0][1]
gate[0][1] = low_reflected
gate[0][2] = high_reflected
print(gate)
reflected_gates.append(gate)
model.init_nodes(reflected_gates)
print(model.init_nodes)
print(model.get_gates())
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.convert_all_data_to_numpy()
data_input.x_tr = data_input.x_tr_raw
data_input.x_te = data_input.x_te_raw
old_scale = data_input.scale
old_offset = data_input.offset
print("fitting projection")
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer'],
use_labels_to_transform_data=params['transform_params']['use_labels_to_transform_data']
)
results_plotter = MultidimDataAndGatesPlotter(
model, np.concatenate(data_input.x_tr),
np.concatenate(data_input.untransformed_matched_x_tr), old_scale,
old_offset, data_input.transformer)
results_plotter.plot_in_feature_space(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'feature_results.png'))
if params['transform_params']['embed_dim'] == 2:
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'final_gates.png'))
else:
fig_pos, ax_pos, fig_neg, ax_neg = results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
with open(os.path.join(params['save_dir'], 'final_gates_pos_3d.pkl'),
'wb') as f:
pickle.dump(fig_pos, f)
with open(os.path.join(params['save_dir'], 'final_gates_neg_3d.pkl'),
'wb') as f:
pickle.dump(fig_neg, f)
with open(os.path.join(params['save_dir'], 'configs.pkl'), 'wb') as f:
pickle.dump(params, f)
print('Complete main loop took %.4f seconds' % (time.time() - start_time))
return trackers_per_round[-1]
def main(path_to_params):
start_time = time.time()
params = TransformParameterParser(path_to_params).parse_params()
print(params)
check_consistency_of_params(params)
#evauntually uncomment this leaving asis in order ot keep the same results as before to compare.
set_random_seeds(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
data_input.split_data()
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer'],
use_labels_to_transform_data=params['transform_params']['use_labels_to_transform_data']
)
data_input.save_transformer(params['save_dir'])
data_input.normalize_data()
unused_cluster_gate_inits = init_plot_and_save_gates(data_input, params)
data_input.convert_all_data_to_tensors()
init_gate_tree, unused_cluster_gate_inits = get_next_gate_tree(
unused_cluster_gate_inits, data_input, params, model=None)
model1 = initialize_model(params['model_params'], [init_gate_tree])
performance_tracker1 = run_train_model(model1, params['train_params'],
data_input)
model1_save_path = os.path.join(params['save_dir'], 'model1.pkl')
torch.save(model1.state_dict(), model1_save_path)
tracker1_save_path = os.path.join(params['save_dir'], 'tracker1.pkl')
with open(tracker1_save_path, 'wb') as f:
pickle.dump(performance_tracker1, f)
# now select the data inside the learned model1 gate and re-run umap
data_input.filter_data_inside_first_model_gate(model1)
unused_cluster_gate_inits = init_plot_and_save_gates(data_input, params)
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
cells_to_subsample=params['transform_params']['cells_to_subsample'],
num_cells_for_transformer=params['transform_params']['num_cells_for_transformer'],
use_labels_to_transform_data=params['transform_params']['use_labels_to_transform_data']
)
data_input.save_transformer(params['save_dir'])
data_input.convert_all_data_to_tensors()
init_gate_tree, _ = get_next_gate_tree(unused_cluster_gate_inits,
data_input,
params,
model=None)
model2 = initialize_model(params['model_params'], [init_gate_tree])
performance_tracker2 = run_train_model(model2, params['train_params'],
data_input)
model2_save_path = os.path.join(params['save_dir'], 'model2.pkl')
torch.save(model2.state_dict(), model2_save_path)
tracker2_save_path = os.path.join(params['save_dir'], 'tracker2.pkl')
with open(tracker2_save_path, 'wb') as f:
pickle.dump(performance_tracker2, f)
results_plotter = DataAndGatesPlotterDepthOne(
model2, np.concatenate(data_input.x_tr))
#fig, axes = plt.subplots(params['gate_init_params']['n_clusters'], figsize=(1 * params['gate_init_params']['n_clusters'], 3 * params['gate_init_params']['n_clusters']))
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'final_gates.png'))
with open(os.path.join(params['save_dir'], 'configs.pkl'), 'wb') as f:
pickle.dump(params, f)
print('Complete main loop took %.4f seconds' % (time.time() - start_time))
def main(path_to_params):
start_time = time.time()
params = TransformParameterParser(path_to_params).parse_params()
print(params)
check_consistency_of_params(params)
set_random_seeds(params)
if not os.path.exists(params['save_dir']):
os.makedirs(params['save_dir'])
with open(os.path.join(params['save_dir'], 'params.pkl'), 'wb') as f:
pickle.dump(params, f)
data_input = DataInput(params['data_params'])
data_input.split_data()
data_transformer = DataTransformerFactory(
params['transform_params'],
params['random_seed']).manufacture_transformer()
data_input.embed_data_and_fit_transformer(\
data_transformer,
params['transform_params']['cells_to_subsample'],
params['transform_params']['num_cells_for_transformer']
)
data_input.save_transformer(params['save_dir'])
data_input.normalize_data()
#everything below differs from the other main_UMAP
multi_gate_initializer = MultipleGateInitializerHeuristic(
data_input, params['model_params']['node_type'],
params['gate_init_multi_heuristic_params'])
init_gate_tree = [multi_gate_initializer.init_next_gate()]
model = initialize_model(params['model_params'], init_gate_tree)
data_input.prepare_data_for_training()
trackers_per_step = []
num_gates = params['gate_init_multi_heuristic_params']['num_gates']
for i in range(num_gates):
performance_tracker = run_train_model(model, params['train_params'],
data_input)
multi_gate_initializer.gates = model.get_gates()
if not (i == num_gates - 1):
print(model.get_gates())
next_gate = multi_gate_initializer.init_next_gate()
if next_gate is None:
print(
'There are no non-overlapping initializations left to try!'
)
break
model.add_node(next_gate)
model_save_path = os.path.join(params['save_dir'], 'model.pkl')
torch.save(model.state_dict(), model_save_path)
tracker_save_path = os.path.join(params['save_dir'], 'tracker.pkl')
with open(tracker_save_path, 'wb') as f:
pickle.dump(performance_tracker, f)
results_plotter = DataAndGatesPlotterDepthOne(
model, np.concatenate(data_input.x_tr))
#fig, axes = plt.subplots(params['gate_init_params']['n_clusters'], figsize=(1 * params['gate_init_params']['n_clusters'], 3 * params['gate_init_params']['n_clusters']))
results_plotter.plot_data_with_gates(
np.array(
np.concatenate([
data_input.y_tr[i] *
torch.ones([data_input.x_tr[i].shape[0], 1])
for i in range(len(data_input.x_tr))
])))
plt.savefig(os.path.join(params['save_dir'], 'final_gates.png'))
print('Complete main loop took %.4f seconds' % (time.time() - start_time))