Merge pull request #118 from theislab/fix_simulators

fixed missing methods and imports

Author: picciama

batchglm/api/models/tf2/glm_beta.py

@@ -1,2 +1,2 @@
-#from batchglm.models.glm_beta import InputDataGLM, Model, Simulator
-#from batchglm.train.tf2.glm_beta import Estimator
+from batchglm.models.glm_beta import InputDataGLM, Model, Simulator
+# from batchglm.train.tf2.glm_beta import Estimator

batchglm/api/models/tf2/glm_nb.py

@@ -1,2 +1,2 @@
 from batchglm.models.glm_nb import InputDataGLM, Model, Simulator
-from batchglm.train.tf2.glm_nb import Estimator
+# from batchglm.train.tf2.glm_nb import Estimator

batchglm/api/models/tf2/glm_norm.py

@@ -1,2 +1,2 @@
-#from batchglm.models.glm_norm import InputDataGLM, Model, Simulator
-#from batchglm.train.tf2.glm_norm import Estimator
+from batchglm.models.glm_norm import InputDataGLM, Model, Simulator
+# from batchglm.train.tf2.glm_norm import Estimator

batchglm/models/glm_beta/external.py

@@ -5,4 +5,6 @@
 from batchglm.models.base_glm import closedform_glm_mean, closedform_glm_scale
 
 import batchglm.data as data_utils
-from batchglm.utils.linalg import groupwise_solve_lm
+from batchglm.utils.linalg import groupwise_solve_lm
+
+from batchglm import pkg_constants

batchglm/models/glm_beta/model.py

@@ -32,6 +32,16 @@ def eta_loc(self) -> np.ndarray:
             assert False, "size factors not allowed"
         return eta
 
+    def eta_loc_j(self, j) -> np.ndarray:
+        # Make sure that dimensionality of sliced array is kept:
+        if isinstance(j, int) or isinstance(j, np.int32) or isinstance(j, np.int64):
+            j = [j]
+        eta = np.matmul(self.design_loc, self.a[:, j])
+        if self.size_factors is not None:
+            assert False, "size factors not allowed"
+        eta = self.np_clip_param(eta, "eta_loc")
+        return eta
+
     # Re-parameterizations:
 
     @property

batchglm/models/glm_beta/simulator.py

@@ -2,6 +2,7 @@
 
 from .model import Model
 from .external import InputDataGLM, _SimulatorGLM
+from .external import pkg_constants
 
 
 class Simulator(_SimulatorGLM, Model):
@@ -22,6 +23,42 @@ def __init__(
             num_features=num_features
         )
 
+    def param_bounds(
+            self,
+            dtype
+    ):
+
+        dtype = np.dtype(dtype)
+        dmin = np.finfo(dtype).min
+        dmax = np.finfo(dtype).max
+        dtype = dtype.type
+
+        zero = np.nextafter(0, np.inf, dtype=dtype)
+        one = np.nextafter(1, -np.inf, dtype=dtype)
+
+        sf = dtype(pkg_constants.ACCURACY_MARGIN_RELATIVE_TO_LIMIT)
+        bounds_min = {
+            "a_var": np.log(zero/(1-zero)) / sf,
+            "b_var": np.log(zero) / sf,
+            "eta_loc": np.log(zero/(1-zero)) / sf,
+            "eta_scale": np.log(zero) / sf,
+            "mean": np.nextafter(0, np.inf, dtype=dtype),
+            "samplesize": np.nextafter(0, np.inf, dtype=dtype),
+            "probs": dtype(0),
+            "log_probs": np.log(zero),
+        }
+        bounds_max = {
+            "a_var": np.log(one/(1-one)) / sf,
+            "b_var": np.nextafter(np.log(dmax), -np.inf, dtype=dtype) / sf,
+            "eta_loc": np.log(one/(1-one)) / sf,
+            "eta_scale": np.nextafter(np.log(dmax), -np.inf, dtype=dtype) / sf,
+            "mean": one,
+            "samplesize": np.nextafter(dmax, -np.inf, dtype=dtype) / sf,
+            "probs": dtype(1),
+            "log_probs": dtype(0),
+        }
+        return bounds_min, bounds_max
+
     def generate_params(
             self,
             rand_fn_ave=lambda shape: np.random.uniform(0.2, 0.8, shape),

batchglm/models/glm_norm/external.py

@@ -5,4 +5,6 @@
 from batchglm.models.base_glm import closedform_glm_mean, closedform_glm_scale
 
 import batchglm.data as data_utils
-from batchglm.utils.linalg import groupwise_solve_lm
+from batchglm.utils.linalg import groupwise_solve_lm
+
+from batchglm import pkg_constants

batchglm/models/glm_norm/model.py

@@ -32,8 +32,18 @@ def eta_loc(self) -> np.ndarray:
             eta *= np.expand_dims(self.size_factors, axis=1)
         return eta
 
+    def eta_loc_j(self, j) -> np.ndarray:
+        # Make sure that dimensionality of sliced array is kept:
+        if isinstance(j, int) or isinstance(j, np.int32) or isinstance(j, np.int64):
+            j = [j]
+        eta = np.matmul(self.design_loc, self.a[:, j])
+        if self.size_factors is not None:
+            eta *= np.expand_dims(self.size_factors, axis=1)
+        eta = self.np_clip_param(eta, "eta_loc")
+        return eta
+
     # Re-parameterizations:
-    
+
     @property
     def mean(self) -> np.ndarray:
         return self.location

batchglm/models/glm_norm/simulator.py

@@ -2,6 +2,7 @@
 
 from .model import Model
 from .external import InputDataGLM, _SimulatorGLM
+from .external import pkg_constants
 
 
 class Simulator(_SimulatorGLM, Model):
@@ -22,6 +23,38 @@ def __init__(
             num_features=num_features
         )
 
+    def param_bounds(
+            self,
+            dtype
+    ):
+        dtype = np.dtype(dtype)
+        dmin = np.finfo(dtype).min
+        dmax = np.finfo(dtype).max
+        dtype = dtype.type
+
+        sf = dtype(pkg_constants.ACCURACY_MARGIN_RELATIVE_TO_LIMIT)
+        bounds_min = {
+            "a_var": np.nextafter(-dmax, np.inf, dtype=dtype) / sf,
+            "b_var": np.log(np.nextafter(0, np.inf, dtype=dtype)) / sf,
+            "eta_loc": np.nextafter(-dmax, np.inf, dtype=dtype) / sf,
+            "eta_scale": np.log(np.nextafter(0, np.inf, dtype=dtype)) / sf,
+            "mean": np.nextafter(-dmax, np.inf, dtype=dtype) / sf,
+            "sd": np.nextafter(0, np.inf, dtype=dtype),
+            "probs": dtype(0),
+            "log_probs": np.log(np.nextafter(0, np.inf, dtype=dtype)),
+        }
+        bounds_max = {
+            "a_var": np.nextafter(dmax, -np.inf, dtype=dtype) / sf,
+            "b_var": np.nextafter(np.log(dmax), -np.inf, dtype=dtype) / sf,
+            "eta_loc": np.nextafter(dmax, -np.inf, dtype=dtype) / sf,
+            "eta_scale": np.nextafter(np.log(dmax), -np.inf, dtype=dtype) / sf,
+            "mean": np.nextafter(dmax, -np.inf, dtype=dtype) / sf,
+            "sd": np.nextafter(dmax, -np.inf, dtype=dtype) / sf,
+            "probs": dtype(1),
+            "log_probs": dtype(0),
+        }
+        return bounds_min, bounds_max
+
     def generate_params(
             self,
             rand_fn_ave=lambda shape: np.random.uniform(10, 1000, shape),