pep8

gneiss/_formula.py

@@ -8,7 +8,7 @@
 import pandas as pd
 import statsmodels.formula.api as smf
 from skbio.stats.composition import ilr
-from gneiss.util import match, match_tips
+from gneiss.util import match, match_tips, rename_internal_nodes
 from gneiss._summary import RegressionResults
 from gneiss.balances import balance_basis
 
@@ -28,6 +28,17 @@ def _process(table, metadata, tree):
     return _table, _metadata, _tree
 
 
+def _transform(table, tree):
+    non_tips = [n.name for n in tree.levelorder() if not n.is_tip()]
+    basis, _ = balance_basis(tree)
+
+    mat = ilr(table.values, basis=basis)
+    ilr_table = pd.DataFrame(mat,
+                             columns=non_tips,
+                             index=table.index)
+    return ilr_table, basis
+
+
 def ols(formula, table, metadata, tree, **kwargs):
     """ Ordinary Least Squares applied to balances.
 
@@ -64,14 +75,7 @@ def ols(formula, table, metadata, tree, **kwargs):
     statsmodels.regression.linear_model.OLS
     """
     _table, _metadata, _tree = _process(table, metadata, tree)
-    basis, _ = balance_basis(_tree)
-    non_tips = [n.name for n in _tree.levelorder() if not n.is_tip()]
-
-    mat = ilr(_table.values, basis=basis)
-    ilr_table = pd.DataFrame(mat,
-                             columns=non_tips,
-                             index=table.index)
-
+    ilr_table, basis = _transform(_table, _tree)
     data = pd.merge(ilr_table, _metadata, left_index=True, right_index=True)
 
     fits = []

gneiss/_summary.py

@@ -163,11 +163,10 @@ def residuals(self, project=False):
             # https://github.com/biocore/scikit-bio/pull/1396
             proj_resid = ilr_inv(resid.values.T, basis=self.basis,
                                  check=False).T
-            proj_resid = pd.DataFrame(proj_resid, index=self.feature_names,
-                                      columns=resid.columns)
-            return proj_resid
+            return pd.DataFrame(proj_resid, index=self.feature_names,
+                                columns=resid.columns).T
         else:
-            return resid
+            return resid.T
 
     def predict(self, X=None, project=False, **kwargs):
         """ Performs a prediction based on model.
@@ -210,9 +209,8 @@ def predict(self, X=None, project=False, **kwargs):
             # https://github.com/biocore/scikit-bio/pull/1396
             proj_prediction = ilr_inv(prediction.values.T, basis=self.basis,
                                       check=False)
-            proj_prediction = pd.DataFrame(proj_prediction,
-                                           columns=self.feature_names,
-                                           index=prediction.columns)
-            return proj_prediction
+            return pd.DataFrame(proj_prediction,
+                                columns=self.feature_names,
+                                index=prediction.columns).T
 
         return prediction.T

gneiss/tests/test_formula.py

@@ -10,10 +10,8 @@
 import numpy as np
 import pandas as pd
 import pandas.util.testing as pdt
-import statsmodels.formula.api as smf
 import unittest
-from gneiss._summary import RegressionResults
-from skbio.stats.composition import _gram_schmidt_basis, ilr_inv
+from skbio.stats.composition import ilr_inv
 from skbio import TreeNode
 from gneiss._formula import ols
 

gneiss/tests/test_summary.py

@@ -117,7 +117,7 @@ def test_regression_results_residuals_projection(self):
                                   's5': ilr_inv(A([-1.065789, 1.184211])),
                                   's6': ilr_inv(A([-1.144737, -0.394737])),
                                   's7': ilr_inv(A([0.394737, 1.894737]))},
-                                 index=['Z1', 'Z2', 'Z3'])
+                                 index=['Z1', 'Z2', 'Z3']).T
         feature_names = ['Z1', 'Z2', 'Z3']
         basis = _gram_schmidt_basis(3)
         res = RegressionResults(self.results, basis=basis,
@@ -134,7 +134,7 @@ def test_regression_results_residuals(self):
                                   's5': [-1.065789, 1.184211],
                                   's6': [-1.144737, -0.394737],
                                   's7': [0.394737, 1.894737]},
-                                 index=['Y1', 'Y2'])
+                                 index=['Y1', 'Y2']).T
         res = RegressionResults(self.results)
         pdt.assert_frame_equal(res.residuals(), exp_resid,
                                check_exact=False,
@@ -183,7 +183,7 @@ def test_regression_results_predict_projection(self):
                                     's5': ilr_inv(A([3.065789, 3.815789])),
                                     's6': ilr_inv(A([4.144737, 6.394737])),
                                     's7': ilr_inv(A([3.605263, 5.105263]))},
-                                   index=feature_names).T
+                                   index=feature_names)
 
         pdt.assert_frame_equal(res_predict, exp_predict)