y_hline = np.recarray(X_hline.shape[0], dtype=y_dtype)
results = np.recarray(0,
dtype=[("train_id", "S16"), ("test_id", "S16"),
("min_diff", "f"), ("max_diff", "f"),
("samples", "i"), ("score", "f")])
# fit regressor on training data
for train_id, rgr in regressors.items():
rgr.fit(X_train[train_id], y_train[train_id])
# compute and report initial score on test data
for test_id, train_id in test_id2train_id.items():
rgr = regressors[train_id]
sys_scores = rgr.predict(X_test[test_id])
postprocess(sys_input[test_id], sys_scores)
r = correlation(sys_scores, y_test[test_id])
n = X_train[train_id].shape[0]
results.resize(results.size + 1)
if isinstance(train_id, tuple):
train_id = "+".join(train_id)
results[-1] = (train_id, test_id, 0, 0, n, r)
print "{:32s} {:32s} {:>8d} {:8.4f}".format(train_id, test_id, n, r)
# score headlines
for train_id in hline_regressors:
# TODO: full postprocessing
scores = regressors[train_id].predict(X_hline)
scores[scores < 0] = 0.0
scores[scores > 5] = 5.0
y_hline[train_id] = scores
("min_diff", "f"),
("max_diff", "f"),
("samples", "i"),
("iteration", "i"),
("score", "f")])
# fit regressor on training data
for train_id, rgr in regressors.items():
rgr.fit(X_train[train_id], y_train[train_id])
# compute and report initial score on test data
for test_id, train_id in test_id2train_id.items():
rgr = regressors[train_id]
sys_scores = rgr.predict(X_test[test_id])
postprocess(sys_input[test_id], sys_scores)
r = correlation(sys_scores, y_test[test_id])
n = X_train[train_id].shape[0]
results.resize(results.size + 1)
if isinstance(train_id, tuple):
train_id = "+".join(train_id)
results[-1] = (train_id, test_id, 0, 0, n, 0, r)
print "{:32s} {:32s} {:>8d} {:8.4f}".format(train_id, test_id, n, r)
# score headlines
for train_id in hline_regressors:
# TODO: full postprocessing
scores = regressors[train_id].predict(X_hline)
scores[scores < 0] = 0.0
scores[scores > 5] = 5.0
y_hline[train_id] = scores