def lme_regression(output_dir: str,
table: pd.DataFrame, tree: skbio.TreeNode,
metadata: Metadata, formula: str,
groups: str) -> None:
res = mixedlm(table=table, metadata=metadata._dataframe,
formula=formula, groups=groups)
res.fit()
lme_summary(output_dir, res, tree)
def lme_regression(output_dir: str,
table: pd.DataFrame, tree: skbio.TreeNode,
metadata: Metadata, formula: str,
groups: str) -> None:
if np.any(table.var(axis=0) == 0):
message = ('Detected zero variance balances - '
'double check your table for unobserved features.')
raise UserWarning(message)
res = mixedlm(table=table, metadata=metadata.to_dataframe(),
formula=formula, groups=groups)
res.fit()
lme_summary(output_dir, res, tree)
def test_visualization(self):
model = mixedlm("x1 + x2", self.table, self.metadata,
groups="groups")
model.fit()
lme_summary(self.results, model, self.tree)
pvals = pd.read_csv(os.path.join(self.results, 'pvalues.csv'),
index_col=0)
coefs = pd.read_csv(os.path.join(self.results, 'coefficients.csv'),
index_col=0)
pred = pd.read_csv(os.path.join(self.results, 'predicted.csv'),
index_col=0)
resid = pd.read_csv(os.path.join(self.results, 'residuals.csv'),
index_col=0)
exp_pvals = pd.DataFrame({
'Intercept': {'Y1': 4.8268860492262526e-236,
'Y2': 0.099411090631406948},
'Group Var': {'Y1': 4.4193804668281966e-05,
'Y2': 4.4193804668280984e-05},
'x1': {'Y1': 3.9704936434633392e-35,
'Y2': 3.9704936434628853e-35},
'x2': {'Y1': 3.56912071867573e-30,
'Y2': 3.56912071867573e-30}}).sort_index(axis=1)
pvals = pvals.sort_index(axis=0).sort_index(axis=1)
exp_pvals = exp_pvals.sort_index(axis=0).sort_index(axis=1)
npt.assert_allclose(pvals, exp_pvals, rtol=1e-5)
exp_coefs = pd.DataFrame({
'Intercept': {'Y1': 4.2115280233151946,
'Y2': 0.211528023315187},
'Group Var': {'Y1': 0.093578639287859755,
'Y2': 0.093578639287860019},
'x1': {'Y1': 1.0220072967452645,
'Y2': 1.0220072967452651},
'x2': {'Y1': 0.92487193877761575,
'Y2': 0.92487193877761564}}
).sort_index(axis=1)
npt.assert_allclose(coefs.sort_index(axis=0),
exp_coefs.sort_index(axis=0),
rtol=1e-2, atol=1e-2)
exp_resid = pd.read_csv(get_data_path('exp_resid.csv'), index_col=0)
npt.assert_allclose(resid, exp_resid.T, rtol=1e-2, atol=1e-2)
exp_pred = pd.read_csv(get_data_path('exp_pred.csv'), index_col=0)
npt.assert_allclose(pred, exp_pred.T, rtol=1e-2, atol=1e-2)
def test_visualization(self):
model = mixedlm("x1 + x2", self.table, self.metadata,
groups="groups")
model.fit()
lme_summary(self.results, model, self.tree)
pvals = pd.read_csv(os.path.join(self.results, 'pvalues.csv'),
index_col=0)
coefs = pd.read_csv(os.path.join(self.results, 'coefficients.csv'),
index_col=0)
pred = pd.read_csv(os.path.join(self.results, 'predicted.csv'),
index_col=0)
resid = pd.read_csv(os.path.join(self.results, 'residuals.csv'),
index_col=0)
exp_pvals = pd.DataFrame({
'Intercept': {'Y1': 4.8268860492262526e-236,
'Y2': 0.099411090631406948},
'groups RE': {'Y1': 4.4193804668281966e-05,
'Y2': 4.4193804668280984e-05},
'x1': {'Y1': 3.9704936434633392e-35,
'Y2': 3.9704936434628853e-35},
'x2': {'Y1': 3.56912071867573e-30,
'Y2': 3.56912071867573e-30}})
npt.assert_allclose(pvals, exp_pvals, rtol=1e-5)
exp_coefs = pd.DataFrame({
'Intercept': {'Y1': 4.2115280233151946,
'Y2': 0.211528023315187},
'groups RE': {'Y1': 0.093578639287859755,
'Y2': 0.093578639287860019},
'x1': {'Y1': 1.0220072967452645,
'Y2': 1.0220072967452651},
'x2': {'Y1': 0.92487193877761575,
'Y2': 0.92487193877761564}}
)
npt.assert_allclose(coefs, exp_coefs, rtol=1e-2, atol=1e-2)
exp_resid = pd.read_csv(get_data_path('exp_resid.csv'), index_col=0)
npt.assert_allclose(resid, exp_resid.T, rtol=1e-2, atol=1e-2)
exp_pred = pd.read_csv(get_data_path('exp_pred.csv'), index_col=0)
npt.assert_allclose(pred, exp_pred.T, rtol=1e-2, atol=1e-2)