Merge pull request #192 from theislab/correct_constraint_doc

davidsebfischer · web-flow · commit 974b482f92c4 · 2021-03-09T14:53:23.000+01:00
Correct constraint doc
diff --git a/diffxpy/fit/fit.py b/diffxpy/fit/fit.py
@@ -80,9 +80,10 @@ def model(
     :param constraints_loc: Constraints for location model. Can be one of the following:
 
             - np.ndarray:
-                Array with constraints in rows and model parameters in columns.
-                Each constraint contains non-zero entries for the a of parameters that
-                has to sum to zero. This constraint is enforced by binding one parameter
+                Array with constraints in columns and model parameters in rows.
+                Each constraint contains non-zero entries for the constrained parameters that
+                have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                contains 1 in the parameter row. This constraint is enforced by binding one parameter
                 to the negative sum of the other parameters, effectively representing that
                 parameter as a function of the other parameters. This dependent
                 parameter is indicated by a -1 in this array, the independent parameters
@@ -113,9 +114,10 @@ def model(
     :param constraints_scale: Constraints for scale model. Can be one of the following:
 
             - np.ndarray:
-                Array with constraints in rows and model parameters in columns.
-                Each constraint contains non-zero entries for the a of parameters that
-                has to sum to zero. This constraint is enforced by binding one parameter
+                Array with constraints in columns and model parameters in rows.
+                Each constraint contains non-zero entries for the constrained parameters that
+                have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                contains 1 in the parameter row. This constraint is enforced by binding one parameter
                 to the negative sum of the other parameters, effectively representing that
                 parameter as a function of the other parameters. This dependent
                 parameter is indicated by a -1 in this array, the independent parameters
@@ -291,9 +293,10 @@ def residuals(
     :param constraints_loc: Constraints for location model. Can be one of the following:
 
             - np.ndarray:
-                Array with constraints in rows and model parameters in columns.
-                Each constraint contains non-zero entries for the a of parameters that
-                has to sum to zero. This constraint is enforced by binding one parameter
+                Array with constraints in columns and model parameters in rows.
+                Each constraint contains non-zero entries for the constrained parameters that
+                have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                contains 1 in the parameter row. This constraint is enforced by binding one parameter
                 to the negative sum of the other parameters, effectively representing that
                 parameter as a function of the other parameters. This dependent
                 parameter is indicated by a -1 in this array, the independent parameters
@@ -324,9 +327,10 @@ def residuals(
     :param constraints_scale: Constraints for scale model. Can be one of the following:
 
             - np.ndarray:
-                Array with constraints in rows and model parameters in columns.
-                Each constraint contains non-zero entries for the a of parameters that
-                has to sum to zero. This constraint is enforced by binding one parameter
+                Array with constraints in columns and model parameters in rows.
+                Each constraint contains non-zero entries for the constrained parameters that
+                have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                contains 1 in the parameter row. This constraint is enforced by binding one parameter
                 to the negative sum of the other parameters, effectively representing that
                 parameter as a function of the other parameters. This dependent
                 parameter is indicated by a -1 in this array, the independent parameters
@@ -550,9 +554,10 @@ def model(
         :param constraints_loc: Constraints for location model. Can be one of the following:
 
                 - np.ndarray:
-                    Array with constraints in rows and model parameters in columns.
-                    Each constraint contains non-zero entries for the a of parameters that
-                    has to sum to zero. This constraint is enforced by binding one parameter
+                    Array with constraints in columns and model parameters in rows.
+                    Each constraint contains non-zero entries for the constrained parameters that
+                    have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                    contains 1 in the parameter row. This constraint is enforced by binding one parameter
                     to the negative sum of the other parameters, effectively representing that
                     parameter as a function of the other parameters. This dependent
                     parameter is indicated by a -1 in this array, the independent parameters
@@ -583,9 +588,10 @@ def model(
         :param constraints_scale: Constraints for scale model. Can be one of the following:
 
                 - np.ndarray:
-                    Array with constraints in rows and model parameters in columns.
-                    Each constraint contains non-zero entries for the a of parameters that
-                    has to sum to zero. This constraint is enforced by binding one parameter
+                    Array with constraints in columns and model parameters in rows.
+                    Each constraint contains non-zero entries for the constrained parameters that
+                    have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                    contains 1 in the parameter row. This constraint is enforced by binding one parameter
                     to the negative sum of the other parameters, effectively representing that
                     parameter as a function of the other parameters. This dependent
                     parameter is indicated by a -1 in this array, the independent parameters
@@ -707,9 +713,10 @@ def residuals(
         :param constraints_loc: Constraints for location model. Can be one of the following:
 
                 - np.ndarray:
-                    Array with constraints in rows and model parameters in columns.
-                    Each constraint contains non-zero entries for the a of parameters that
-                    has to sum to zero. This constraint is enforced by binding one parameter
+                    Array with constraints in columns and model parameters in rows.
+                    Each constraint contains non-zero entries for the constrained parameters that
+                    have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                    contains 1 in the parameter row. This constraint is enforced by binding one parameter
                     to the negative sum of the other parameters, effectively representing that
                     parameter as a function of the other parameters. This dependent
                     parameter is indicated by a -1 in this array, the independent parameters
@@ -740,9 +747,10 @@ def residuals(
         :param constraints_scale: Constraints for scale model. Can be one of the following:
 
                 - np.ndarray:
-                    Array with constraints in rows and model parameters in columns.
-                    Each constraint contains non-zero entries for the a of parameters that
-                    has to sum to zero. This constraint is enforced by binding one parameter
+                    Array with constraints in columns and model parameters in rows.
+                    Each constraint contains non-zero entries for the constrained parameters that
+                    have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                    contains 1 in the parameter row. This constraint is enforced by binding one parameter
                     to the negative sum of the other parameters, effectively representing that
                     parameter as a function of the other parameters. This dependent
                     parameter is indicated by a -1 in this array, the independent parameters
diff --git a/diffxpy/testing/tests.py b/diffxpy/testing/tests.py
@@ -52,18 +52,20 @@ def _fit(
     :param design_loc: Design matrix of location model.
     :param design_loc: Design matrix of scale model.
     :param constraints_loc: : Constraints for location model.
-        Array with constraints in rows and model parameters in columns.
-        Each constraint contains non-zero entries for the a of parameters that
-        has to sum to zero. This constraint is enforced by binding one parameter
+        Array with constraints in columns and model parameters in rows.
+        Each constraint contains non-zero entries for the constrained parameters that
+        have to sum to zero. For a non-constrained parameter the revelant constraint column 
+        contains 1 in the parameter row. This constraint is enforced by binding one parameter
         to the negative sum of the other parameters, effectively representing that
         parameter as a function of the other parameters. This dependent
         parameter is indicated by a -1 in this array, the independent parameters
         of that constraint (which may be dependent at an earlier constraint)
         are indicated by a 1.
     :param constraints_scale: : Constraints for scale model.
-        Array with constraints in rows and model parameters in columns.
-        Each constraint contains non-zero entries for the a of parameters that
-        has to sum to zero. This constraint is enforced by binding one parameter
+        Array with constraints in columns and model parameters in rows.
+        Each constraint contains non-zero entries for the constrained parameters that
+        have to sum to zero. For a non-constrained parameter the revelant constraint column 
+        contains 1 in the parameter row. This constraint is enforced by binding one parameter
         to the negative sum of the other parameters, effectively representing that
         parameter as a function of the other parameters. This dependent
         parameter is indicated by a -1 in this array, the independent parameters
@@ -519,9 +521,10 @@ def wald(
     :param constraints_loc: Constraints for location model. Can be one of the following:
 
             - np.ndarray:
-                Array with constraints in rows and model parameters in columns.
-                Each constraint contains non-zero entries for the a of parameters that
-                has to sum to zero. This constraint is enforced by binding one parameter
+                Array with constraints in columns and model parameters in rows.
+                Each constraint contains non-zero entries for the constrained parameters that
+                have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                contains 1 in the parameter row. This constraint is enforced by binding one parameter
                 to the negative sum of the other parameters, effectively representing that
                 parameter as a function of the other parameters. This dependent
                 parameter is indicated by a -1 in this array, the independent parameters
@@ -552,9 +555,10 @@ def wald(
     :param constraints_scale: Constraints for scale model. Can be one of the following:
 
             - np.ndarray:
-                Array with constraints in rows and model parameters in columns.
-                Each constraint contains non-zero entries for the a of parameters that
-                has to sum to zero. This constraint is enforced by binding one parameter
+                Array with constraints in columns and model parameters in rows.
+                Each constraint contains non-zero entries for the constrained parameters that
+                have to sum to zero. For a non-constrained parameter the revelant constraint column 
+                contains 1 in the parameter row. This constraint is enforced by binding one parameter
                 to the negative sum of the other parameters, effectively representing that
                 parameter as a function of the other parameters. This dependent
                 parameter is indicated by a -1 in this array, the independent parameters
@@ -1896,19 +1900,21 @@ def wald(
             This makes sense for number of genes, time, pseudotime or space
             for example.
         :param constraints_loc: : Constraints for location model.
-            Array with constraints in rows and model parameters in columns.
-            Each constraint contains non-zero entries for the a of parameters that
-            has to sum to zero. This constraint is enforced by binding one parameter
+            Array with constraints in columns and model parameters in rows.
+            Each constraint contains non-zero entries for the constrained parameters that
+            have to sum to zero. For a non-constrained parameter the revelant constraint column 
+            contains 1 in the parameter row. This constraint is enforced by binding one parameter
             to the negative sum of the other parameters, effectively representing that
             parameter as a function of the other parameters. This dependent
             parameter is indicated by a -1 in this array, the independent parameters
             of that constraint (which may be dependent at an earlier constraint)
             are indicated by a 1. It is highly recommended to only use this option
             together with prebuilt design matrix for the location model, dmat_loc.
         :param constraints_scale: : Constraints for scale model.
-            Array with constraints in rows and model parameters in columns.
-            Each constraint contains non-zero entries for the a of parameters that
-            has to sum to zero. This constraint is enforced by binding one parameter
+            Array with constraints in columns and model parameters in rows.
+            Each constraint contains non-zero entries for the constrained parameters that
+            have to sum to zero. For a non-constrained parameter the revelant constraint column 
+            contains 1 in the parameter row. This constraint is enforced by binding one parameter
             to the negative sum of the other parameters, effectively representing that
             parameter as a function of the other parameters. This dependent
             parameter is indicated by a -1 in this array, the independent parameters
diff --git a/docs/tutorials.rst b/docs/tutorials.rst
@@ -36,9 +36,7 @@ Diffxpy allows you to define a data set partition and to conduct test on each ge
 Multiple tests per gene
 ~~~~~~~~~~~~~~~~~~~~~~~
 
-How to perform `pairwise <https://nbviewer.jupyter.org/github/theislab/diffxpy_tutorials/tree/master/diffxpy_tutorials/test/multiple_tests_per_gene.ipynb>`__ tests.
-
-How to perform group tests versus all other groups (versus `rest <https://nbviewer.jupyter.org/github/theislab/diffxpy_tutorials/tree/master/diffxpy_tutorials/test/multiversus_rest.ipynb>`__).
+How to perform `pairwise tests, group versus rest tests and tests within each parition  <https://nbviewer.jupyter.org/github/theislab/diffxpy_tutorials/tree/master/diffxpy_tutorials/test/multiple_tests_per_gene.ipynb>`__ tests.
 
 
 Gene set enrichment: enrich
