DL: Add input preprocessor for validation data

doc/mainpage.dox.in

@@ -291,7 +291,7 @@ Interface and implementation are subject to change.
     @details A collection of modules for deep learning.
     @{
         @defgroup grp_keras_model_arch Load Model Architecture
-        @defgroup grp_minibatch_preprocessing_dl Mini-Batch Preprocessor for Images
+        @defgroup grp_input_preprocessor_dl Preprocessor for Images
     @}
     @defgroup grp_bayes Naive Bayes Classification
     @defgroup grp_sample Random Sampling

src/ports/postgres/modules/deep_learning/madlib_keras_helper.py_in

@@ -27,12 +27,48 @@ def expand_input_dims(input_data, target_type=None):
         input_data = input_data.astype(target_type)
     return input_data
 
+def strip_trailing_nulls_from_class_values(class_values):
+    """
+        class_values is a list of unique class levels in training data. This
+        could have multiple Nones in it, and this function strips out all the
+        Nones that occur after the first element in the list.
+        Examples:
+            1) input class_values = ['cat', 'dog']
+               output class_values = ['cat', 'dog']
+
+            2) input class_values = [None, 'cat', 'dog']
+               output class_values = [None, 'cat', 'dog']
+
+            3) input class_values = [None, 'cat', 'dog', None, None]
+               output class_values = [None, 'cat', 'dog']
+
+            4) input class_values = ['cat', 'dog', None, None]
+               output class_values = ['cat', 'dog']
+
+            5) input class_values = [None, None]
+               output class_values = [None]
+        @args:
+            @param: class_values, list
+        @returns:
+            updated class_values list
+    """
+    num_of_valid_class_values = 0
+    if class_values is not None:
+        for ele in class_values:
+            if ele is None and num_of_valid_class_values > 0:
+                break
+            num_of_valid_class_values += 1
+        # Pass only the valid class_values for creating columns
+        class_values = class_values[:num_of_valid_class_values]
+    return class_values
+
 # Name of columns in model summary table.
 CLASS_VALUES_COLNAME = "class_values"
 NORMALIZING_CONST_COLNAME = "normalizing_const"
 COMPILE_PARAMS_COLNAME = "compile_params"
 DEPENDENT_VARNAME_COLNAME = "dependent_varname"
 DEPENDENT_VARTYPE_COLNAME = "dependent_vartype"
+INDEPENDENT_VARNAME_COLNAME = "independent_varname"
 MODEL_ARCH_TABLE_COLNAME = "model_arch_table"
 MODEL_ARCH_ID_COLNAME = "model_arch_id"
 MODEL_DATA_COLNAME = "model_data"

src/ports/postgres/modules/deep_learning/madlib_keras_predict.py_in

@@ -29,6 +29,7 @@ import numpy as np
 
 from madlib_keras_helper import expand_input_dims
 from madlib_keras_helper import MODEL_DATA_COLNAME
+from madlib_keras_helper import strip_trailing_nulls_from_class_values
 from madlib_keras_validator import PredictInputValidator
 from madlib_keras_wrapper import get_device_name_and_set_cuda_env
 from madlib_keras_wrapper import set_model_weights
@@ -45,41 +46,6 @@ import madlib_keras_serializer
 
 MODULE_NAME = 'madlib_keras_predict'
 
-def _strip_trailing_nulls_from_class_values(class_values):
-    """
-        class_values is a list of unique class levels in training data. This
-        could have multiple Nones in it, and this function strips out all the
-        Nones that occur after the first element in the list.
-        Examples:
-            1) input class_values = ['cat', 'dog']
-               output class_values = ['cat', 'dog']
-
-            2) input class_values = [None, 'cat', 'dog']
-               output class_values = [None, 'cat', 'dog']
-
-            3) input class_values = [None, 'cat', 'dog', None, None]
-               output class_values = [None, 'cat', 'dog']
-
-            4) input class_values = ['cat', 'dog', None, None]
-               output class_values = ['cat', 'dog']
-
-            5) input class_values = [None, None]
-               output class_values = [None]
-        @args:
-            @param: class_values, list
-        @returns:
-            updated class_values list
-    """
-    num_of_valid_class_values = 0
-    if class_values is not None:
-        for ele in class_values:
-            if ele is None and num_of_valid_class_values > 0:
-                break
-            num_of_valid_class_values += 1
-        # Pass only the valid class_values for creating columns
-        class_values = class_values[:num_of_valid_class_values]
-    return class_values
-
 def predict(schema_madlib, model_table, test_table, id_col,
             independent_varname, output_table, pred_type, use_gpu, **kwargs):
     if not pred_type:
@@ -108,7 +74,7 @@ def predict(schema_madlib, model_table, test_table, id_col,
         pred_col_name = "prob"
         pred_col_type = 'double precision'
 
-    class_values = _strip_trailing_nulls_from_class_values(class_values)
+    class_values = strip_trailing_nulls_from_class_values(class_values)
 
     prediction_select_clause = create_cols_from_array_sql_string(
         class_values, intermediate_col, pred_col_name,