def main(readcsv=read_csv, method='defaultDense'):
infile = "./data/batch/linear_regression_train.csv"
testfile = "./data/batch/linear_regression_test.csv"
# Configure a Lasso regression training object
train_algo = d4p.lasso_regression_training(interceptFlag=True)
# Read data. Let's have 10 independent, and 1 dependent variable (for each observation)
indep_data = readcsv(infile, range(10))
dep_data = readcsv(infile, range(10, 11))
# Now train/compute, the result provides the model for prediction
train_result = train_algo.compute(indep_data, dep_data)
# Now let's do some prediction
predict_algo = d4p.lasso_regression_prediction()
# read test data (with same #features)
pdata = readcsv(testfile, range(10))
ptdata = readcsv(testfile, range(10, 11))
# now predict using the model from the training above
predict_result = predict_algo.compute(pdata, train_result.model)
# The prediction result provides prediction
assert predict_result.prediction.shape == (pdata.shape[0],
dep_data.shape[1])
assert np.square(predict_result.prediction - ptdata).mean() < 2.4
return (predict_result, ptdata)
def main(readcsv=read_csv, method='defaultDense'):
infile = "./data/batch/linear_regression_train.csv"
testfile = "./data/batch/linear_regression_test.csv"
# Configure a Lasso regression training object
train_algo = d4p.lasso_regression_training(interceptFlag=True)
# Read data. Let's have 10 independent, and 2 dependent variables (for each observation)
indep_data = readcsv(infile, range(10))
dep_data = readcsv(infile, range(10, 12))
# Now train/compute, the result provides the model for prediction
train_result = train_algo.compute(indep_data, dep_data)
# Now let's do some prediction
predict_algo = d4p.lasso_regression_prediction()
# read test data (with same #features)
pdata = readcsv(testfile, range(10))
ptdata = readcsv(testfile, range(10, 12))
# now predict using the model from the training above
predict_result = predict_algo.compute(pdata, train_result.model)
# The prediction result provides prediction
assert predict_result.prediction.shape == (pdata.shape[0],
dep_data.shape[1])
# the example is used in tests with the scipy.sparse matrix
# we use this trick until subtracting a sparse matrix is not supported
if hasattr(ptdata, 'toarray'):
ptdata = ptdata.toarray()
# this assertion is outdated, will be fixed in next release
# assert np.square(predict_result.prediction - np.asarray(ptdata)).mean() < 2.2
return (predict_result, ptdata)
def _daal4py_predict_lasso(self, X):
X = make2d(X)
_fptype = getFPType(self.coef_)
lasso_palg = daal4py.lasso_regression_prediction(fptype=_fptype,
method='defaultDense')
lasso_res = lasso_palg.compute(X, self.daal_model_)
res = lasso_res.prediction
if res.shape[1] == 1 and self.coef_.ndim == 1:
res = np.ravel(res)
return res
def _daal4py_predict_lasso(self, X):
X = make2d(X)
_fptype = getFPType(self.coef_)
lasso_palg = daal4py.lasso_regression_prediction(fptype=_fptype,
method='defaultDense')
if self.n_features_in_ != X.shape[1]:
raise ValueError((f'X has {X.shape[1]} features, '
f'but Lasso is expecting '
f'{self.n_features_in_} features as input'))
lasso_res = lasso_palg.compute(X, self.daal_model_)
res = lasso_res.prediction
if res.shape[1] == 1 and self.coef_.ndim == 1:
res = np.ravel(res)
return res
