def fit_predict_only(config, x_test=None, y_test=None):
estimator = joblib.load('filename.pkl')
learning_cfg = config.get("learning", None)
scorers = set_scorer_functions(learning_cfg.get("scorer", ['mae', 'rmse']))
log.debug(x_test)
if (x_test is not None):
while x_test != 'null':
log.debug("Predicting unseen data using the trained model...(from previously learned model)")
y_hat = estimator.predict(x_test)
#log.info(y_hat)
#print y_hat
sys.stdout.write(str(y_hat) + '\n')
sys.stdout.flush()
log.debug("Evaluating prediction on the test set...")
#for scorer_name, scorer_func in scorers:
#v = scorer_func(y_test, y_hat)
#log.info("%s = %s" % (scorer_name, v))
n_input = raw_input()
x_test = read_features_test(n_input, '\t')
def run(config):
'''
Runs the main code of the program. Checks for mandatory parameters, opens
input files and performs the learning steps.
'''
# check if the mandatory parameters are set in the config file
x_train_path = config.get("x_train", None)
if not x_train_path:
msg = "'x_train' option not found in the configuration file. \
The training dataset is mandatory."
raise Exception(msg)
y_train_path = config.get("y_train", None)
if not y_train_path:
msg = "'y_train' option not found in the configuration file. \
The training dataset is mandatory."
raise Exception(msg)
learning = config.get("learning", None)
if not learning:
msg = "'learning' option not found. At least one \
learning method must be set."
raise Exception(msg)
# checks for the optional parameters
x_test_path = config.get("x_test", None)
y_test_path = config.get("y_test", None)
# output file
output_file_path = config.get("output", None)
separator = config.get("separator", DEFAULT_SEP)
labels_path = config.get("labels", None)
scale = config.get("scale", True)
log.debug("Opening input files ...")
log.debug("X_train: %s" % x_train_path)
log.debug("y_train: %s" % y_train_path)
log.debug("X_test: %s" % x_test_path)
log.debug("y_test_path: %s" % y_test_path)
# open feature and response files
X_train, y_train, X_test, y_test, labels = \
open_datasets(x_train_path, y_train_path, x_test_path,
y_test_path, separator, labels_path)
if scale:
# preprocess and execute mean removal
X_train, X_test = scale_datasets(X_train, X_test)
predict_only = config.get("predict_only", False)
if predict_only:
feats_lines = []
line = raw_input()
X_test = read_features_test(line, '\t')
y_test = 2
log.debug(X_test)
y_hat = fit_predict_only(config, X_test, y_test)
else:
# fits training data and predicts the test set using the trained model
y_hat = fit_predict(config, X_train, y_train, X_test, y_test)
