def train_pca_svm(learning_data, pca_dims, probability=True, cache_size=3000, **svm_kwargs):
(X_train, y_train, train_ids), (X_test, y_test, test_ids) = learning_data
pca = TruncatedSVD(n_components=pca_dims)
n_symbols = max(
np.max(X_train) + 1, np.max(X_test) + 1
)
logger.info("Forming CSR Matrices")
x_train, x_test = create_csr_matrix(X_train, n_symbols), create_csr_matrix(X_test, n_symbols)
logger.info("Starting PCA")
# pseudo-supervised PCA: fit on positive class only
pca = pca.fit(x_train[y_train > 0])
x_train_pca = pca.transform(x_train)
x_test_pca = pca.transform(x_test)
logger.info("Starting SVM")
svc = SVC(probability=probability, cache_size=cache_size, **svm_kwargs)
svc.fit(x_train_pca, y_train)
logger.info("Scoring SVM")
score = svc.score(x_test_pca, y_test)
logger.info(score)
svc.test_score = score
pca.n_symbols = n_symbols
return svc, pca, x_train_pca, x_test_pca
