def main(input_filepath, model_filepath, output_filepath, config_file):
"""Runs data loading and cleaning and pre-processing scripts and
saves data in ../processed."""
logger = logging.getLogger(__name__)
logger.info('Loading training set, test set and model and predicting.')
# Parse config file
config = parse_config(config_file)
# Load data
X_train = pd.read_csv(input_filepath + '/X_train.csv')
y_train = pd.read_csv(input_filepath + '/y_train.csv').values.ravel()
X_test = pd.read_csv(input_filepath + '/X_test.csv')
y_test = pd.read_csv(input_filepath + '/y_test.csv').values.ravel()
# Load model
model = Model.load(model_filepath + config['predicting']['model_name'])
# Make predictions
train_pred = model.predict(X_train)
test_pred = model.predict(X_test)
# Evaluate model
train_score = np.sqrt(mean_squared_error(y_train, train_pred))
test_score = np.sqrt(mean_squared_error(y_test, test_pred))
# Plot predictions
scores = (
(r'$RMSE={:,.0f}$' + ' EUR').format(train_score),
(r'$RMSE={:,.0f}$' + ' EUR').format(test_score),
)
pred_plots = plot_predictions(scores, train_pred, test_pred, y_train,
y_test)
pred_plots.savefig(output_filepath + '/pred_plots.png')
def predict(model_filepath, config, input_data):
"""Return prediction from user input."""
# Load model
model = Model.load(model_filepath + config['predicting']['model_name'])
# Predict
prediction = int(np.round(model.predict(input_data), -3)[0])
return prediction
def main(input_train, input_test, input_model, output_prediction):
""" Runs modeling scripts using model pickle (../models) to predict
outcomes. Outcomes file is saved as .csv (saved in ../models).
"""
logger = logging.getLogger(__name__)
logger.info('predicting outcomes')
data = DataSet(train_dir=input_train, test_dir=input_test)
test = data.get_test_set()
X_test = data.get_features(test)
model = Model.load(input_model + 'XGBClassifier')
y_pred = model.predict(X_test)
output = pd.DataFrame({
'PassengerId': test['PassengerId'],
'Survived': y_pred
})
output.to_csv(output_prediction + 'submission_{}.csv'.format(model.name),
index=False)
num_workers=8,
drop_last=True,
shuffle=True)
val_dataset = InpaintingDataset(config,
val_list,
fix_mask_path=val_fix_mask,
training=False)
val_loader = DataLoader(dataset=val_dataset,
batch_size=config.batch_size,
num_workers=2,
drop_last=False,
shuffle=False)
sample_iterator = val_dataset.create_iterator(config.sample_size)
model = Model(config, logger=logger)
model.load(is_test=False)
steps_per_epoch = len(train_dataset) // config.batch_size
iteration = model.iteration
epoch = model.iteration // steps_per_epoch
logger.info('Start from epoch:{}, iteration:{}'.format(epoch, iteration))
model.train()
keep_training = True
best_score = {}
while (keep_training):
epoch += 1
stateful_metrics = ['epoch', 'iter', 'g_lr']
progbar = Progbar(len(train_dataset),
max_iters=steps_per_epoch,
width=20,