Update examples

Co-authored-by: Gustavo Viera López <[email protected]>

examples/example_02.py

@@ -14,6 +14,7 @@
     num_heads=4,
     num_transformer_blocks=4,
     optimizer=keras.optimizers.Adam(learning_rate=1e-4),
+    random_state=SEED,
 )
 
 # Split into train and test sets

examples/example_03.py

@@ -7,13 +7,14 @@
     LSTMModel,
     RandomForestModel,
     SVMModel,
-    TransformerModel, # TODO: Falta XGBoost
+    TransformerModel,
+    XGBoostModel,
 )
 
-SEED = 0 # TODO: Use this for reproducibility
+SEED = 0  # Random seed for reproducibility
 
-dataset = Dataset.mnist_stroke()
-train, test = dataset.cut(60_000)
+dataset = Dataset.uci_characters()
+train, test = dataset.split(.8, random_state=SEED)
 
 featurizer = featurizers.UniversalFeaturizer()
 vectorized_models = [
@@ -24,6 +25,7 @@
         bootstrap=False,
         warm_start=True,
         n_jobs=6,
+        random_state=SEED,
     ),
     KNeighborsModel(
         featurizer=featurizer,
@@ -32,9 +34,15 @@
     DecisionTreeModel(
         featurizer=featurizer,
         max_depth=7,
+        random_state=SEED,
     ),
     SVMModel(
         featurizer=featurizer,
+        random_state=SEED,
+    ),
+    XGBoostModel(
+        featurizer=featurizer,
+        random_state=SEED,
     ),
 ]
 
@@ -44,12 +52,14 @@
     num_heads=4,
     num_transformer_blocks=4,
     optimizer=keras.optimizers.Adam(learning_rate=1e-4),
+    random_state=SEED,
 )
 
 lstm = LSTMModel(
     loss="sparse_categorical_crossentropy",
     optimizer="rmsprop",
     metrics=["accuracy"],
+    random_state=SEED,
 )
 
 # Train and evaluate vectorized models
@@ -61,7 +71,7 @@
 
 # Train and evaluate LSTM model
 checkpoint = keras.callbacks.ModelCheckpoint(
-    "partially_trained_model_lstm_mnist_stroke.h5",
+    f"partially_trained_model_lstm_{dataset.name}.h5",
     monitor="loss",
     verbose=1,
     save_best_only=True,
@@ -73,7 +83,7 @@
 
 # Train and evaluate Transformer model
 checkpoint = keras.callbacks.ModelCheckpoint(
-    "partially_trained_model_transformer_mnist_stroke.h5",
+    f"partially_trained_model_transformer_{dataset.name}.h5",
     monitor="loss",
     verbose=1,
     save_best_only=True,

examples/example_04.py

@@ -23,7 +23,10 @@
     # Split the dataset into train and test
     train, test = dataset.filter(
         lambda traj, _: len(traj) >= 5 and traj.r.delta.norm.sum() > 0
-    ).split(train_size=0.7, random_state=SEED)
+    ).split(
+        train_size=0.7,
+        random_state=SEED,
+    )
 
     # Select the desired features to be extracted from the trajectories
     featurizer = featurizers.UniversalFeaturizer()

pactus/models/lstm_model.py

@@ -1,8 +1,11 @@
+import datetime
 import logging
+import time
 from pathlib import Path
 from typing import Any, List, Tuple, Union
 
 import numpy as np
+import tensorflow as tf
 from sklearn.preprocessing import LabelEncoder
 from tensorflow import keras
 from yupi import Trajectory
@@ -30,6 +33,7 @@ def __init__(
         loss="sparse_categorical_crossentropy",
         optimizer="rmsprop",
         metrics=None,
+        random_state: Union[int, None] = None,
         **kwargs,
     ):
         super().__init__(NAME)
@@ -38,6 +42,7 @@ def __init__(
         self.dataset: Union[Dataset, None] = None
         self.model: keras.Secuential
         self.max_len = 0
+        self.random_state = random_state
         metrics = ["accuracy"] if metrics is None else metrics
         self.units = [128, 64] if units is None else units
         kwargs.update(dict(loss=loss, optimizer=optimizer, metrics=metrics))
@@ -111,6 +116,13 @@ def train(
         callbacks: Union[list, None] = None,
         checkpoint: Union[keras.callbacks.ModelCheckpoint, None] = None,
     ):
+        if self.random_state is not None:
+            tf.keras.utils.set_random_seed(self.random_state)
+            logging.warning(
+                f"Custom seed provided for {self.name} model. This "
+                "calls 'tf.keras.utils.set_random_seed' which sets a global "
+                "random state on python, numpy and tensorflow."
+            )
         if cross_validation != 0:
             logging.warning("Cross validation is not supported yet for lstm")
         self.set_summary(epochs=epochs, validation_split=validation_split)

pactus/models/transformer_model.py

@@ -3,6 +3,7 @@
 from typing import Any, List, Tuple, Union
 
 import numpy as np
+import tensorflow as tf
 from sklearn.model_selection import KFold
 from sklearn.preprocessing import LabelEncoder
 from tensorflow import keras
@@ -39,9 +40,9 @@ def __init__(
         max_traj_len: int = -1,
         skip_long_trajs: bool = False,
         mask_value=cfg.MASK_VALUE,
-        name=NAME,
+        random_state: Union[int, None] = None,
     ):
-        super().__init__(name)
+        super().__init__(NAME)
         self.head_size = head_size
         self.num_heads = num_heads
         self.ff_dim = ff_dim
@@ -59,6 +60,7 @@ def __init__(
         self.encoder: Union[LabelEncoder, None] = None
         self.labels: Union[List[Any], None] = None
         self.original_data: Union[Data, None] = None
+        self.random_state: Union[int, None] = random_state
         self.set_summary(
             head_size=self.head_size,
             num_heads=self.num_heads,
@@ -85,6 +87,13 @@ def train(
         callbacks: Union[list, None] = None,
         checkpoint: Union[keras.callbacks.ModelCheckpoint, None] = None,
     ):
+        if self.random_state is not None:
+            tf.keras.utils.set_random_seed(self.random_state)
+            logging.warning(
+                f"Custom seed provided for {self.name} model. This "
+                "calls 'tf.keras.utils.set_random_seed' which sets a global "
+                "random state on python, numpy and tensorflow."
+            )
         self.set_summary(
             cross_validation=cross_validation,
             epochs=epochs,