import dask.array as da
import dask.dataframe as dd
import numpy as np
import pandas as pd
import pytest
from dask.dataframe.utils import assert_eq
from dask_glm.regularizers import Regularizer
from sklearn.pipeline import make_pipeline
from dask_ml.datasets import make_classification, make_counts, make_regression
from dask_ml.linear_model import LinearRegression, LogisticRegression, PoissonRegression
from dask_ml.linear_model.utils import add_intercept
from dask_ml.model_selection import GridSearchCV
@pytest.fixture(params=[r() for r in Regularizer.__subclasses__()])
def solver(request):
"""Parametrized fixture for all the solver names"""
return request.param
@pytest.fixture(params=[r() for r in Regularizer.__subclasses__()])
def regularizer(request):
"""Parametrized fixture for all the regularizer names"""
return request.param
class DoNothingTransformer:
def fit(self, X, y=None):
return self
opt = family.pointwise_loss(result, X, y).compute()
test_val = family.pointwise_loss(test_vec, X, y).compute()
assert opt < test_val
@pytest.mark.parametrize('func,kwargs', [
(admm, {'abstol': 1e-4}),
(proximal_grad, {'tol': 1e-7}),
])
@pytest.mark.parametrize('N', [1000])
@pytest.mark.parametrize('nchunks', [1, 10])
@pytest.mark.parametrize('family', [Logistic, Normal, Poisson])
@pytest.mark.parametrize('lam', [0.01, 1.2, 4.05])
@pytest.mark.parametrize('reg', [r() for r in Regularizer.__subclasses__()])
def test_basic_reg_descent(func, kwargs, N, nchunks, family, lam, reg):
beta = np.random.normal(size=2)
M = len(beta)
X = da.random.random((N, M), chunks=(N // nchunks, M))
y = make_y(X, beta=np.array(beta), chunks=(N // nchunks,))
X, y = persist(X, y)
result = func(X, y, family=family, lamduh=lam, regularizer=reg, **kwargs)
test_vec = np.random.normal(size=2)
f = reg.add_reg_f(family.pointwise_loss, lam)
opt = f(result, X, y).compute()
test_val = f(test_vec, X, y).compute()
