Bug fixes for input parameter limiting

ecnet/data_utils.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #
 # ecnet/data_utils.py
-# v.1.5
+# v.1.5.1
 # Developed in 2018 by Travis Kessler <[email protected]>
 #
 # Contains the "DataFrame" class, and functions for processing/importing/
@@ -190,7 +190,7 @@ def shuffle(self, *args, split):
         '''
 
         if 'l' and 'v' and 't' in args:
-            self.create_sets(split=split)
+            self.create_sets(random=True, split=split)
 
         elif 'l' and 'v' in args:
             lv_set = []

ecnet/limit_parameters.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #
 # ecnet/limit_parameters.py
-# v.1.5
+# v.1.5.1
 # Developed in 2018 by Travis Kessler <[email protected]>
 #
 # Contains the functions necessary for reducing the input dimensionality of a
@@ -20,7 +20,7 @@
 import ecnet.error_utils
 
 
-def limit_iterative_include(DataFrame, limit_num):
+def limit_iterative_include(DataFrame, limit_num, print_feedback=True):
     '''
     Limits the dimensionality of input data found in supplied *DataFrame*
     object to a dimensionality of *limit_num* using iterative inclusion
@@ -114,24 +114,27 @@ def limit_iterative_include(DataFrame, limit_num):
                 test_input_retained[idx].append(param[0])
 
         retained_input_list.append(DataFrame.input_names[rmse_idx])
-        print(retained_input_list)
-        print(rmse_val)
-        print()
+        if print_feedback:
+            print(retained_input_list)
+            print(rmse_val)
+            print()
 
     return retained_input_list
 
 
 def limit_genetic(DataFrame, limit_num, population_size, num_survivors,
-                  num_generations, shuffle=False, print_feedback=True):
+                  num_generations, shuffle=False, data_split=[0.65, 0.25, 0.1],
+                  print_feedback=True):
     '''
     Limits the dimensionality of input data found in supplied *DataFrame*
     object to a dimensionality of *limit_num* using a genetic algorithm.
     Optional arguments for *population_size* of genetic algorithm's population,
     *num_survivors* for selecting the best performers from each population
     generation to reproduce, *num_generations* for the number of times the
     population will reproduce, *shuffle* for shuffling the data sets for each
-    population member, and *print_feedback* for printing the average fitness
-    score of the population after each generation.
+    population member, *data_split* to determine l/v/t splits if shuffling,
+    and *print_feedback* for printing the average fitness score of the
+    population after each generation.
     '''
 
     def ecnet_limit_inputs(feed_dict):
@@ -147,7 +150,7 @@ def ecnet_limit_inputs(feed_dict):
         test_input = []
 
         if shuffle:
-            DataFrame.shuffle('l', 'v', 't')
+            DataFrame.shuffle('l', 'v', 't', split=data_split)
             packaged_data_cf = DataFrame.package_sets()
         else:
             packaged_data_cf = packaged_data

ecnet/server.py

@@ -2,7 +2,7 @@
 # -*- coding: utf-8 -*-
 #
 # ecnet/server.py
-# v.1.5
+# v.1.5.1
 # Developed in 2018 by Travis Kessler <[email protected]>
 #
 # Contains the "Server" class, which handles ECNet project creation, neural
@@ -128,7 +128,7 @@ def import_data(self, data_filename, sort_type='random',
     def limit_input_parameters(self, limit_num, output_filename,
                                use_genetic=False, population_size=500,
                                num_survivors=200, num_generations=25,
-                               shuffle=False):
+                               shuffle=False, data_split=[0.65, 0.25, 0.1]):
         '''
         Limits the input dimensionality of currently loaded DataFrame; default
         method is an iterative inclusion algorithm, options for using a genetic
@@ -144,20 +144,36 @@ def limit_input_parameters(self, limit_num, output_filename,
         *num_generations*   - number of generations the algorithm will run for
         *shuffle*           - whether to shuffle learning, validation and
                               testing sets for each population member
+        *data_split*        - if shuffling, learning/validation/testing data
+                              is split using this argument
 
         See https://github.com/tjkessler/pygenetics for genetic algorithm
         source code.
         '''
 
         if use_genetic:
-            params = ecnet.limit_parameters.limit_genetic(
-                self.DataFrame, limit_num, population_size, num_survivors,
-                shuffle=shuffle, print_feedback=self.__print_feedback
-            )
+            try:
+                params = ecnet.limit_parameters.limit_genetic(
+                    self.DataFrame, limit_num, population_size,
+                    num_survivors, num_generations, shuffle=shuffle,
+                    print_feedback=self.__print_feedback
+                )
+            except:
+                params = ecnet.limit_parameters.limit_genetic(
+                    self.DataFrame, limit_num, population_size, num_survivors,
+                    num_generations, shuffle=shuffle, data_split=data_split,
+                    print_feedback=True
+                )
         else:
-            params = ecnet.limit_parameters.limit_iterative_include(
-                self.DataFrame, limit_num
-            )
+            try:
+                params = ecnet.limit_parameters.limit_iterative_include(
+                    self.DataFrame, limit_num,
+                    print_feedback=self.__print_feedback
+                )
+            except:
+                params = ecnet.limit_parameters.limit_iterative_include(
+                    self.DataFrame, limit_num, print_feedback=True
+                )
         ecnet.limit_parameters.output(self.DataFrame, params, output_filename)
 
     def tune_hyperparameters(self, target_score=None, iteration_amt=50,

examples/limit_input_parameters.py

@@ -8,9 +8,9 @@
 sv.import_data('my_data.csv')
 
 # Limit the input dimensionality to 15, save to 'my_data_limited.csv'
-sv.limit_parameters(15, 'my_data_limited.csv')
+sv.limit_input_parameters(15, 'my_data_limited.csv')
 
 
 # Use this line instead for limiting the input dimensionality using a genetic
 # algorithm
-sv.limit_parameters(15, 'my_data_limited_genetic.csv', use_genetic=True)
+sv.limit_input_parameters(15, 'my_data_limited_genetic.csv', use_genetic=True)