def main():
X_train, y_train, X_test, y_test = get_initial_split(
df_full_factorial_feat, y)
for train_size in TRAIN_SIZES:
for i in range(REPEAT):
X_train, _, y_train, _ = train_test_split(X_train,
y_train,
train_size=train_size)
# Train coregionalized model
wandb.init(project='dispersant_screener',
tags=['coregionalized', 'matern32'],
save_code=True)
m = build_coregionalized_model(X_train, y_train)
y0, var0 = predict_coregionalized(m, X_test, 0)
y1, var1 = predict_coregionalized(m, X_test, 1)
metrics_0 = get_metrics(y0, y_test[:, 0])
metrics_0 = add_postfix_to_keys(metrics_0, 0)
metrics_1 = get_metrics(y1, y_test[:, 1])
metrics_1 = add_postfix_to_keys(metrics_0, 1)
variance_0 = get_variance_descriptors(var0)
variance_1 = get_variance_descriptors(var1)
variance_0 = add_postfix_to_keys(variance_0, 0)
variance_1 = add_postfix_to_keys(variance_1, 1)
overall_metrics = metrics_0
overall_metrics.update(metrics_1)
overall_metrics.update(variance_0)
overall_metrics.update(variance_1)
overall_metrics['train_size'] = len(X_train)
overall_metrics['coregionalized'] = True
plot_parity(y0, y_test[:, 0], var0, y1, y_test[:, 1], var1,
'coregionalized_{}_{}.pdf'.format(len(X_train), i))
wandb.log(overall_metrics)
# Train "simple models"
wandb.init(project='dispersant_screener',
tags=['matern32'],
save_code=True)
m0 = build_model(X_train, y_train[:, 0])
m1 = build_model(X_train, y_train[:, 1])
y0, var0 = predict(m0, X_test)
y1, var1 = predict(m1, X_test)
metrics_0 = get_metrics(y0, y_test[:, 0])
metrics_0 = add_postfix_to_keys(metrics_0, 0)
metrics_1 = get_metrics(y1, y_test[:, 1])
metrics_1 = add_postfix_to_keys(metrics_0, 1)
variance_0 = get_variance_descriptors(var0)
variance_1 = get_variance_descriptors(var1)
variance_0 = add_postfix_to_keys(variance_0, 0)
variance_1 = add_postfix_to_keys(variance_1, 1)
overall_metrics = metrics_0
overall_metrics.update(metrics_1)
overall_metrics.update(variance_0)
overall_metrics.update(variance_1)
overall_metrics['train_size'] = len(X_train)
overall_metrics['coregionalized'] = False
plot_parity(y0, y_test[:, 0], var0, y1, y_test[:, 1], var1,
'coregionalized_{}_{}.pdf'.format(len(X_train), i))
wandb.log(overall_metrics)
def main(): # pylint:disable=too-many-locals, too-many-statements
"""Runs everything"""
X_train_, y_train_, X_test, y_test = get_initial_split(df_full_factorial_feat, y)
for train_size in TRAIN_SIZES:
for i in range(REPEAT):
X_train, _, y_train, _ = train_test_split(X_train_, y_train_, train_size=train_size)
# Train coregionalized model
wandb.init(project='dispersant_screener', tags=['coregionalized', 'matern32'], reinit=True)
m = build_coregionalized_model(X_train, y_train)
m.optimize_restarts(20)
y0, var0 = predict_coregionalized(m, X_test, 0)
y1, var1 = predict_coregionalized(m, X_test, 1)
metrics_0 = get_metrics(y0, y_test[:, 0])
metrics_0 = add_postfix_to_keys(metrics_0, 0)
metrics_1 = get_metrics(y1, y_test[:, 1])
metrics_1 = add_postfix_to_keys(metrics_0, 1)
variance_0 = get_variance_descriptors(var0)
variance_1 = get_variance_descriptors(var1)
variance_0 = add_postfix_to_keys(variance_0, 0)
variance_1 = add_postfix_to_keys(variance_1, 1)
overall_metrics = metrics_0
overall_metrics.update(metrics_1)
overall_metrics.update(variance_0)
overall_metrics.update(variance_1)
overall_metrics['train_size'] = len(X_train)
overall_metrics['coregionalized'] = True
METRICS.append(overall_metrics)
plot_parity([(y0, y_test[:, 0], var0), (y1, y_test[:, 1], var1)],
'coregionalized_{}_{}.pdf'.format(len(X_train), i))
wandb.log(overall_metrics)
wandb.join()
# Train "simple models"
wandb.init(project='dispersant_screener', tags=['matern32'], reinit=True)
m0 = build_model(X_train, y_train, 0)
m0.optimize_restarts(20)
m1 = build_model(X_train, y_train, 1)
m1.optimize_restarts(20)
y0, var0 = predict(m0, X_test)
y1, var1 = predict(m1, X_test)
metrics_0 = get_metrics(y0, y_test[:, 0])
metrics_0 = add_postfix_to_keys(metrics_0, 0)
metrics_1 = get_metrics(y1, y_test[:, 1])
metrics_1 = add_postfix_to_keys(metrics_0, 1)
variance_0 = get_variance_descriptors(var0)
variance_1 = get_variance_descriptors(var1)
variance_0 = add_postfix_to_keys(variance_0, 0)
variance_1 = add_postfix_to_keys(variance_1, 1)
overall_metrics = metrics_0
overall_metrics.update(metrics_1)
overall_metrics.update(variance_0)
overall_metrics.update(variance_1)
overall_metrics['train_size'] = len(X_train)
overall_metrics['coregionalized'] = False
METRICS.append(overall_metrics)
plot_parity([(y0, y_test[:, 0], var0), (y1, y_test[:, 1], var1)],
'simple_{}_{}.pdf'.format(len(X_train), i))
wandb.log(overall_metrics)
wandb.join()
df = pd.DataFrame(METRICS)
df.to_csv('metrics.csv')
