def test_logistic_lmm():
df = pd.read_csv(os.path.join(get_resource_path(), "sample_data.csv"))
model = Lmer("DV_l ~ IV1+ (IV1|Group)", data=df, family="binomial")
model.fit(summarize=False)
assert model.coefs.shape == (2, 13)
estimates = np.array([-0.16098421, 0.00296261])
assert np.allclose(model.coefs["Estimate"], estimates, atol=0.001)
assert isinstance(model.fixef, pd.core.frame.DataFrame)
assert model.fixef.shape == (47, 2)
assert isinstance(model.ranef, pd.core.frame.DataFrame)
assert model.ranef.shape == (47, 2)
assert np.allclose(model.coefs.loc[:, "Estimate"], model.fixef.mean(), atol=0.01)
# Test prediction
assert np.allclose(model.predict(model.data, use_rfx=True), model.data.fits)
assert np.allclose(
model.predict(model.data, use_rfx=True, pred_type="link"),
logit(model.data.fits),
)
# Test RFX only
model = Lmer("DV_l ~ 0 + (IV1|Group)", data=df, family="binomial")
model.fit(summarize=False)
assert model.fixef.shape == (47, 2)
model = Lmer("DV_l ~ 0 + (IV1|Group) + (1|IV3)", data=df, family="binomial")
model.fit(summarize=False)
assert isinstance(model.fixef, list)
assert model.fixef[0].shape == (47, 2)
assert model.fixef[1].shape == (3, 2)
def test_logistic_lmm():
df = pd.read_csv(os.path.join(get_resource_path(), 'sample_data.csv'))
model = Lmer('DV_l ~ IV1+ (IV1|Group)', data=df, family='binomial')
model.fit(summarize=False)
assert model.coefs.shape == (2, 13)
estimates = np.array([-0.16098421, 0.00296261])
assert np.allclose(model.coefs['Estimate'], estimates, atol=.001)
assert isinstance(model.fixef, pd.core.frame.DataFrame)
assert model.fixef.shape == (47, 2)
assert isinstance(model.ranef, pd.core.frame.DataFrame)
assert model.ranef.shape == (47, 2)
assert np.allclose(model.coefs.loc[:, 'Estimate'],
model.fixef.mean(),
atol=.01)
# Test prediction
assert np.allclose(model.predict(model.data, use_rfx=True),
model.data.fits)
assert np.allclose(
model.predict(model.data, use_rfx=True, pred_type='link'),
logit(model.data.fits))
def test_gaussian_lmm():
df = pd.read_csv(os.path.join(get_resource_path(), "sample_data.csv"))
model = Lmer("DV ~ IV3 + IV2 + (IV2|Group) + (1|IV3)", data=df)
opt_opts = "optimizer='Nelder_Mead', optCtrl = list(FtolAbs=1e-8, XtolRel=1e-8)"
model.fit(summarize=False, control=opt_opts)
assert model.coefs.shape == (3, 8)
estimates = np.array([12.04334602, -1.52947016, 0.67768509])
assert np.allclose(model.coefs["Estimate"], estimates, atol=0.001)
assert isinstance(model.fixef, list)
assert model.fixef[0].shape == (47, 3)
assert model.fixef[1].shape == (3, 3)
assert isinstance(model.ranef, list)
assert model.ranef[0].shape == (47, 2)
assert model.ranef[1].shape == (3, 1)
assert model.ranef_corr.shape == (1, 3)
assert model.ranef_var.shape == (4, 3)
assert np.allclose(model.coefs.loc[:, "Estimate"], model.fixef[0].mean(), atol=0.01)
# Test prediction
assert np.allclose(model.predict(model.data, use_rfx=True), model.data.fits)
# Smoketest for simulate
model.simulate(2)
model.simulate(2, use_rfx=True)
# Smoketest for old_optimizer
model.fit(summarize=False, old_optimizer=True)
def test_gaussian_lmm():
df = pd.read_csv(os.path.join(get_resource_path(), 'sample_data.csv'))
model = Lmer('DV ~ IV3 + IV2 + (IV2|Group) + (1|IV3)', data=df)
model.fit(summarize=False)
assert model.coefs.shape == (3, 8)
estimates = np.array([12.04334602, -1.52947016, 0.67768509])
assert np.allclose(model.coefs['Estimate'], estimates, atol=.001)
assert isinstance(model.fixef, list)
assert model.fixef[0].shape == (47, 3)
assert model.fixef[1].shape == (3, 3)
assert isinstance(model.ranef, list)
assert model.ranef[0].shape == (47, 2)
assert model.ranef[1].shape == (3, 1)
assert model.ranef_corr.shape == (1, 3)
assert model.ranef_var.shape == (4, 3)
assert np.allclose(model.coefs.loc[:, 'Estimate'],
model.fixef[0].mean(),
atol=.01)
# Test prediction
assert np.allclose(model.predict(model.data, use_rfx=True),
model.data.fits)
def test_gaussian_lmm():
df = pd.read_csv(os.path.join(get_resource_path(), "sample_data.csv"))
model = Lmer("DV ~ IV3 + IV2 + (IV2|Group) + (1|IV3)", data=df)
opt_opts = "optimizer='Nelder_Mead', optCtrl = list(FtolAbs=1e-8, XtolRel=1e-8)"
model.fit(summarize=False, control=opt_opts)
assert model.coefs.shape == (3, 8)
estimates = np.array([12.04334602, -1.52947016, 0.67768509])
assert np.allclose(model.coefs["Estimate"], estimates, atol=0.001)
assert isinstance(model.fixef, list)
assert (model.fixef[0].index.astype(int) == df.Group.unique()).all()
assert (model.fixef[1].index.astype(float) == df.IV3.unique()).all()
assert model.fixef[0].shape == (47, 3)
assert model.fixef[1].shape == (3, 3)
assert isinstance(model.ranef, list)
assert model.ranef[0].shape == (47, 2)
assert model.ranef[1].shape == (3, 1)
assert (model.ranef[1].index == ["0.5", "1", "1.5"]).all()
assert model.ranef_corr.shape == (1, 3)
assert model.ranef_var.shape == (4, 3)
assert np.allclose(model.coefs.loc[:, "Estimate"],
model.fixef[0].mean(),
atol=0.01)
# Test prediction
assert np.allclose(model.predict(model.data, use_rfx=True),
model.data.fits)
# Test simulate
out = model.simulate(2)
assert isinstance(out, pd.DataFrame)
assert out.shape == (model.data.shape[0], 2)
out = model.simulate(2, use_rfx=True)
assert isinstance(out, pd.DataFrame)
assert out.shape == (model.data.shape[0], 2)
# Smoketest for old_optimizer
model.fit(summarize=False, old_optimizer=True)
# test fixef code for 1 fixed effect
model = Lmer("DV ~ IV3 + IV2 + (IV2|Group)", data=df)
model.fit(summarize=False, control=opt_opts)
assert (model.fixef.index.astype(int) == df.Group.unique()).all()
assert model.fixef.shape == (47, 3)
assert np.allclose(model.coefs.loc[:, "Estimate"],
model.fixef.mean(),
atol=0.01)
# test fixef code for 0 fixed effects
model = Lmer("DV ~ (IV2|Group) + (1|IV3)", data=df)
model.fit(summarize=False, control=opt_opts)
assert isinstance(model.fixef, list)
assert (model.fixef[0].index.astype(int) == df.Group.unique()).all()
assert (model.fixef[1].index.astype(float) == df.IV3.unique()).all()
assert model.fixef[0].shape == (47, 2)
assert model.fixef[1].shape == (3, 2)
"base_atom_order ~ 1.0 + uid_b_a_logit + rig_b_a_logit + (1.0|language_family) + (1.0|Subfamily)",
data=df_uid,
family="binomial")
#model = Lmer("base_atom_order ~ rig_b_a_prob + (rig_b_a_prob|language_family) + (rig_b_a_prob|Subfamily)", data=df)
model_uid_fit = model_uid.fit()
model_rig_fit = model_rig.fit()
model_total_fit = model_total.fit()
print(model_total_fit)
model_total_fit.plot_summary()
assert False
#table = anova_lm(model_uid.model_obj, model_rig.model_obj)
#print(table)
#assert False
model_preds_uid = model_uid.predict(df_uid)
model_preds_rig = model_rig.predict(df_rig)
error_rig = model_preds_rig - df_rig["base_atom_order"]
error_uid = model_preds_uid - df_uid["base_atom_order"]
SE = np.square(error_rig) # squared errors
SE_uid = np.square(error_uid)
MSE = np.mean(SE) # mean squared errors
MSE_uid = np.mean(SE_uid) # mean squared errors
RMSE = np.sqrt(MSE) # Root Mean Squared Error, RMSE
RMSE_uid = np.sqrt(MSE_uid) # Root Mean Squared Error, RMSE
F = np.var(error_uid) / np.var(error_rig)
Rsquared = 1.0 - (np.var(error_rig) / np.var(df_rig["base_atom_order"]))
Rsquared_uid = 1.0 - (np.var(error_uid) /
