adding num_cores parameter to all the estimators

Author: ilblackdragon

skflow/estimators/dnn.py

@@ -47,6 +47,7 @@ def exp_decay(global_step):
             Setting this value, allows consistency between reruns.
         continue_training: when continue_training is True, once initialized
             model will be continuely trained on every call of fit.
+        num_cores: Number of cores to be used. (default: 4)
         early_stopping_rounds: Activates early stopping if this is not None.
             Loss needs to decrease at least every every <early_stopping_rounds>
             round(s) to continue training. (default: None)
@@ -61,7 +62,7 @@ def exp_decay(global_step):
     def __init__(self, hidden_units, n_classes, tf_master="", batch_size=32,
                  steps=200, optimizer="SGD", learning_rate=0.1,
                  class_weight=None,
-                 tf_random_seed=42, continue_training=False,
+                 tf_random_seed=42, continue_training=False, num_cores=4,
                  verbose=1, early_stopping_rounds=None,
                  max_to_keep=5, keep_checkpoint_every_n_hours=10000):
         self.hidden_units = hidden_units
@@ -71,7 +72,7 @@ def __init__(self, hidden_units, n_classes, tf_master="", batch_size=32,
             batch_size=batch_size, steps=steps, optimizer=optimizer,
             learning_rate=learning_rate, class_weight=class_weight,
             tf_random_seed=tf_random_seed,
-            continue_training=continue_training, verbose=verbose,
+            continue_training=continue_training, num_cores=4, verbose=verbose,
             early_stopping_rounds=early_stopping_rounds,
             max_to_keep=max_to_keep,
             keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
@@ -121,14 +122,28 @@ def exp_decay(global_step):
             Setting this value, allows consistency between reruns.
         continue_training: when continue_training is True, once initialized
             model will be continuely trained on every call of fit.
+        num_cores: Number of cores to be used. (default: 4)
         early_stopping_rounds: Activates early stopping if this is not None.
             Loss needs to decrease at least every every <early_stopping_rounds>
             round(s) to continue training. (default: None)
-    """
+        verbose: Controls the verbosity, possible values:
+                 0: the algorithm and debug information is muted.
+                 1: trainer prints the progress.
+                 2: log device placement is printed.
+        early_stopping_rounds: Activates early stopping if this is not None.
+            Loss needs to decrease at least every every <early_stopping_rounds>
+            round(s) to continue training. (default: None)
+        max_to_keep: The maximum number of recent checkpoint files to keep.
+            As new files are created, older files are deleted.
+            If None or 0, all checkpoint files are kept.
+            Defaults to 5 (that is, the 5 most recent checkpoint files are kept.)
+        keep_checkpoint_every_n_hours: Number of hours between each checkpoint
+            to be saved. The default value of 10,000 hours effectively disables the feature.
+   """
 
     def __init__(self, hidden_units, n_classes=0, tf_master="", batch_size=32,
                  steps=200, optimizer="SGD", learning_rate=0.1,
-                 tf_random_seed=42, continue_training=False,
+                 tf_random_seed=42, continue_training=False, num_cores=4,
                  verbose=1, early_stopping_rounds=None,
                  max_to_keep=5, keep_checkpoint_every_n_hours=10000):
         self.hidden_units = hidden_units
@@ -137,7 +152,7 @@ def __init__(self, hidden_units, n_classes=0, tf_master="", batch_size=32,
             n_classes=n_classes, tf_master=tf_master,
             batch_size=batch_size, steps=steps, optimizer=optimizer,
             learning_rate=learning_rate, tf_random_seed=tf_random_seed,
-            continue_training=continue_training, verbose=verbose,
+            continue_training=continue_training, num_cores=num_cores, verbose=verbose,
             early_stopping_rounds=early_stopping_rounds,
             max_to_keep=max_to_keep,
             keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)

skflow/estimators/linear.py

@@ -26,14 +26,14 @@ class TensorFlowLinearRegressor(TensorFlowEstimator, RegressorMixin):
 
     def __init__(self, n_classes=0, tf_master="", batch_size=32, steps=200, optimizer="SGD",
                  learning_rate=0.1, tf_random_seed=42, continue_training=False,
-                 verbose=1, early_stopping_rounds=None,
+                 num_cores=4, verbose=1, early_stopping_rounds=None,
                  max_to_keep=5, keep_checkpoint_every_n_hours=10000):
         super(TensorFlowLinearRegressor, self).__init__(
             model_fn=models.linear_regression, n_classes=n_classes,
             tf_master=tf_master,
             batch_size=batch_size, steps=steps, optimizer=optimizer,
             learning_rate=learning_rate, tf_random_seed=tf_random_seed,
-            continue_training=continue_training,
+            continue_training=continue_training, num_cores=num_cores,
             verbose=verbose, early_stopping_rounds=early_stopping_rounds,
             max_to_keep=max_to_keep,
             keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
@@ -54,7 +54,7 @@ class TensorFlowLinearClassifier(TensorFlowEstimator, ClassifierMixin):
 
     def __init__(self, n_classes, tf_master="", batch_size=32, steps=200, optimizer="SGD",
                  learning_rate=0.1, class_weight=None,
-                 tf_random_seed=42, continue_training=False,
+                 tf_random_seed=42, continue_training=False, num_cores=4,
                  verbose=1, early_stopping_rounds=None,
                  max_to_keep=5, keep_checkpoint_every_n_hours=10000):
         super(TensorFlowLinearClassifier, self).__init__(
@@ -63,7 +63,7 @@ def __init__(self, n_classes, tf_master="", batch_size=32, steps=200, optimizer=
             batch_size=batch_size, steps=steps, optimizer=optimizer,
             learning_rate=learning_rate, class_weight=class_weight,
             tf_random_seed=tf_random_seed,
-            continue_training=continue_training,
+            continue_training=continue_training, num_cores=num_cores,
             verbose=verbose, early_stopping_rounds=early_stopping_rounds,
             max_to_keep=max_to_keep,
             keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)

skflow/estimators/rnn.py

@@ -61,6 +61,7 @@ def exp_decay(global_step):
             Setting this value, allows consistency between reruns.
         continue_training: when continue_training is True, once initialized
             model will be continuely trained on every call of fit.
+        num_cores: Number of cores to be used. (default: 4)
         early_stopping_rounds: Activates early stopping if this is not None.
             Loss needs to decrease at least every every <early_stopping_rounds>
             round(s) to continue training. (default: None)
@@ -79,7 +80,7 @@ def __init__(self, rnn_size, n_classes, cell_type='gru', num_layers=1,
                  steps=50, optimizer="SGD", learning_rate=0.1,
                  class_weight=None,
                  tf_random_seed=42, continue_training=False,
-                 verbose=1, early_stopping_rounds=None,
+                 num_cores=4, verbose=1, early_stopping_rounds=None,
                  max_to_keep=5, keep_checkpoint_every_n_hours=10000):
         self.rnn_size = rnn_size
         self.cell_type = cell_type
@@ -94,7 +95,8 @@ def __init__(self, rnn_size, n_classes, cell_type='gru', num_layers=1,
             batch_size=batch_size, steps=steps, optimizer=optimizer,
             learning_rate=learning_rate, class_weight=class_weight,
             tf_random_seed=tf_random_seed,
-            continue_training=continue_training, verbose=verbose,
+            continue_training=continue_training, num_cores=num_cores,
+            verbose=verbose,
             early_stopping_rounds=early_stopping_rounds,
             max_to_keep=max_to_keep,
             keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)
@@ -150,18 +152,32 @@ def exp_decay(global_step):
             Setting this value, allows consistency between reruns.
         continue_training: when continue_training is True, once initialized
             model will be continuely trained on every call of fit.
+        num_cores: Number of cores to be used. (default: 4)
         early_stopping_rounds: Activates early stopping if this is not None.
             Loss needs to decrease at least every every <early_stopping_rounds>
             round(s) to continue training. (default: None)
-    """
+        verbose: Controls the verbosity, possible values:
+                 0: the algorithm and debug information is muted.
+                 1: trainer prints the progress.
+                 2: log device placement is printed.
+        early_stopping_rounds: Activates early stopping if this is not None.
+            Loss needs to decrease at least every every <early_stopping_rounds>
+            round(s) to continue training. (default: None)
+        max_to_keep: The maximum number of recent checkpoint files to keep.
+            As new files are created, older files are deleted.
+            If None or 0, all checkpoint files are kept.
+            Defaults to 5 (that is, the 5 most recent checkpoint files are kept.)
+        keep_checkpoint_every_n_hours: Number of hours between each checkpoint
+            to be saved. The default value of 10,000 hours effectively disables the feature.
+   """
 
     def __init__(self, rnn_size, cell_type='gru', num_layers=1,
                  input_op_fn=null_input_op_fn, initial_state=None,
                  bidirectional=False, sequence_length=None,
                  n_classes=0, tf_master="", batch_size=32,
                  steps=50, optimizer="SGD", learning_rate=0.1,
                  tf_random_seed=42, continue_training=False,
-                 verbose=1, early_stopping_rounds=None,
+                 num_cores=4, verbose=1, early_stopping_rounds=None,
                  max_to_keep=5, keep_checkpoint_every_n_hours=10000):
         self.rnn_size = rnn_size
         self.cell_type = cell_type
@@ -175,7 +191,7 @@ def __init__(self, rnn_size, cell_type='gru', num_layers=1,
             n_classes=n_classes, tf_master=tf_master,
             batch_size=batch_size, steps=steps, optimizer=optimizer,
             learning_rate=learning_rate, tf_random_seed=tf_random_seed,
-            continue_training=continue_training, verbose=verbose,
+            continue_training=continue_training, num_cores=num_cores, verbose=verbose,
             early_stopping_rounds=early_stopping_rounds,
             max_to_keep=max_to_keep,
             keep_checkpoint_every_n_hours=keep_checkpoint_every_n_hours)