def test_formula(): for j in 0, 1: np.random.seed(34234) n = 200 y = np.random.randint(0, 2, size=n) x1 = np.random.normal(size=n) x2 = np.random.normal(size=n) g = np.random.randint(0, 25, size=n) x = np.hstack((x1[:, None], x2[:, None])) if j == 0: model1 = ConditionalLogit(y, x, groups=g) else: model1 = ConditionalPoisson(y, x, groups=g) result1 = model1.fit() df = pd.DataFrame({"y": y, "x1": x1, "x2": x2, "g": g}) if j == 0: model2 = ConditionalLogit.from_formula( "y ~ 0 + x1 + x2", groups="g", data=df) else: model2 = ConditionalPoisson.from_formula( "y ~ 0 + x1 + x2", groups="g", data=df) result2 = model2.fit() assert_allclose(result1.params, result2.params, rtol=1e-5) assert_allclose(result1.bse, result2.bse, rtol=1e-5) assert_allclose(result1.cov_params(), result2.cov_params(), rtol=1e-5) assert_allclose(result1.tvalues, result2.tvalues, rtol=1e-5)
def test_poisson_2d(): y = np.r_[3, 1, 4, 8, 2, 5, 4, 7, 2, 6] g = np.r_[0, 0, 0, 1, 1, 1, 2, 2, 2, 2] x1 = np.r_[0, 1, 0, 0, 1, 1, 0, 0, 1, 0] x2 = np.r_[2, 1, 0, 0, 1, 2, 3, 2, 0, 1] x = np.empty((10, 2)) x[:, 0] = x1 x[:, 1] = x2 model = ConditionalPoisson(y, x, groups=g) # Check the gradient for the loglikelihood for x in -1, 0, 1, 2: params = np.r_[-0.5*x, 0.5*x] grad = approx_fprime(params, model.loglike) score = model.score(params) assert_allclose(grad, score, rtol=1e-4) result = model.fit() # From Stata assert_allclose(result.params, np.r_[-.9478957, -.0134279], rtol=1e-3) assert_allclose(result.bse, np.r_[.3874942, .1686712], rtol=1e-5) result.summary()
def test_lasso_poisson(): np.random.seed(342394) n = 200 groups = np.arange(10) groups = np.kron(groups, np.ones(n // 10)) group_effects = np.random.normal(size=10) group_effects = np.kron(group_effects, np.ones(n // 10)) x = np.random.normal(size=(n, 4)) params = np.r_[0, 0, 1, 0] lin_pred = np.dot(x, params) + group_effects mean = np.exp(lin_pred) y = np.random.poisson(mean) model0 = ConditionalPoisson(y, x, groups=groups) result0 = model0.fit() # Should be the same as model0 model1 = ConditionalPoisson(y, x, groups=groups) result1 = model1.fit_regularized(L1_wt=0, alpha=0) assert_allclose(result0.params, result1.params, rtol=1e-3) model2 = ConditionalPoisson(y, x, groups=groups) result2 = model2.fit_regularized(L1_wt=1, alpha=0.2) # Regression test assert_allclose(result2.params, np.r_[0, 0, 0.91697508, 0], rtol=1e-4) # Test with formula df = pd.DataFrame({ "y": y, "x1": x[:, 0], "x2": x[:, 1], "x3": x[:, 2], "x4": x[:, 3], "groups": groups }) fml = "y ~ 0 + x1 + x2 + x3 + x4" model3 = ConditionalPoisson.from_formula(fml, groups="groups", data=df) result3 = model3.fit_regularized(L1_wt=1, alpha=0.2) assert_allclose(result2.params, result3.params)
def test_poisson_1d(): y = np.r_[3, 1, 1, 4, 5, 2, 0, 1, 6, 2] g = np.r_[0, 0, 0, 0, 1, 1, 1, 1, 1, 1] x = np.r_[0, 1, 0, 0, 1, 1, 0, 0, 1, 0] x = x[:, None] model = ConditionalPoisson(y, x, groups=g) # Check the gradient for the loglikelihood for x in -1, 0, 1, 2: grad = approx_fprime(np.r_[x, ], model.loglike) score = model.score(np.r_[x, ]) assert_allclose(grad, score, rtol=1e-4) result = model.fit() # From Stata assert_allclose(result.params, np.r_[0.6466272], rtol=1e-4) assert_allclose(result.bse, np.r_[0.4170918], rtol=1e-5)
def test_lasso_poisson(): np.random.seed(342394) n = 200 groups = np.arange(10) groups = np.kron(groups, np.ones(n // 10)) group_effects = np.random.normal(size=10) group_effects = np.kron(group_effects, np.ones(n // 10)) x = np.random.normal(size=(n, 4)) params = np.r_[0, 0, 1, 0] lin_pred = np.dot(x, params) + group_effects mean = np.exp(lin_pred) y = np.random.poisson(mean) model0 = ConditionalPoisson(y, x, groups=groups) result0 = model0.fit() # Should be the same as model0 model1 = ConditionalPoisson(y, x, groups=groups) result1 = model1.fit_regularized(L1_wt=0, alpha=0) assert_allclose(result0.params, result1.params, rtol=1e-3) model2 = ConditionalPoisson(y, x, groups=groups) result2 = model2.fit_regularized(L1_wt=1, alpha=0.2) # Regression test assert_allclose(result2.params, np.r_[0, 0, 0.91697508, 0], rtol=1e-4) # Test with formula df = pd.DataFrame({"y": y, "x1": x[:, 0], "x2": x[:, 1], "x3": x[:, 2], "x4": x[:, 3], "groups": groups}) fml = "y ~ 0 + x1 + x2 + x3 + x4" model3 = ConditionalPoisson.from_formula(fml, groups="groups", data=df) result3 = model3.fit_regularized(L1_wt=1, alpha=0.2) assert_allclose(result2.params, result3.params)