def get_signature_genes(X, n, lda=10):
W = np.zeros((X.shape[0], X.shape[0]))
# coarse search from the bottom
while (abs(W).sum(1) > 0).sum() < n:
lda /= 10.
model = MultiTaskLasso(alpha=lda,
max_iter=100,
tol=.001,
selection='random',
warm_start=True)
model.fit(X.T, X.T)
W = model.coef_.T
#print len(np.nonzero(abs(W).sum(1))[0]),model.score(X.T,X.T)
# fine search from the top
while (abs(W).sum(1) > 0).sum() > n * 1.2:
lda *= 2.
model.set_params(alpha=lda)
model.fit(X.T, X.T)
W = model.coef_.T
#print len(np.nonzero(abs(W).sum(1))[0]),model.score(X.T,X.T)
# finer search
while (abs(W).sum(1) > 0).sum() > n:
lda *= 1.1
model.set_params(alpha=lda)
model.fit(X.T, X.T)
W = model.coef_.T
#print len(np.nonzero(abs(W).sum(1))[0]),model.score(X.T,X.T)
return np.nonzero(abs(W).sum(1))[0]
path_test = 'data_test.txt'
X, Y = get_data_own(path_train)
print(X.shape)
print(Y.shape)
print("Split data for CV")
X_train, X_test , y_train, y_test = train_test_split(X, Y, test_size=0.2, random_state=1)
lasso = MultiTaskLasso(max_iter = max_iter, normalize = True)
print("Init train with multitasklassocv")
lassocv = MultiTaskLassoCV(alphas=None, cv=10, max_iter=max_iter, verbose=True, normalize=True)
lassocv.fit(X_train, y_train)
print("Fit multitasklasso with alpha from cv lasso")
lasso.set_params(alpha=lassocv.alpha_)
lasso.fit(X_train, y_train)
print("get mean square error")
mae = mean_absolute_error(y_test, lasso.predict(X_test))
print("mae: {}".format(mae))
rmsle = mean_squared_log_error(y_test, lasso.predict(X_test))
print("rmsle: {}".format(rmsle))
mape = mean_absolute_percentage_error(y_test, lasso.predict(X_test))
print("mape: {}".format(mape))
