def fit(self, X, Y):
"""Fits linear model on data points. Warning: serializing the classifier object won't save the model; specifying a model file is necessary.
Parameters
----------
X: numpy array, shape = [n_samples, n_features]
Training vectors, where n_samples is the number of samples and n_features is the number of features.
Y: numpy array
Target Values.
"""
self._dim = X.shape[1]
data = make_svmlight(X, Y).name
argv = map(str, self.fit_argv)
argv += ["--training_file", data]
self._default(argv)
def predict(self, X, Y=None):
"""Returns model prediction of data points.
Parameters
----------
X: numpy array, shape = [n_samples, n_features]
Testing vectors, where n_samples is the number of samples and n_features is the number of features.
Y: Not used for computation, optional
"""
assert self._dim == X.shape[1]
data = make_svmlight(X, Y).name
results_file = tempfile().name
argv = map(str, self.pred_argv)
argv += ["--test_file", data]
argv += ["--results_file", results_file]
self._default(argv)
Y = read_csv(results_file, sep='\t', header=None, index_col=False)
return Y.as_matrix()[:, 0]
def _preprocess(self, X):
X = make_matrix(X)
temporary_file = make_svmlight(X).name
self._dim = str(X.shape[1])
self._data = temporary_file
