wip added multivariate

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/Time-Series-Transformers-Comparison.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="jdk" jdkName="hf2" jdkType="Python SDK" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

.idea/inspectionProfiles/profiles_settings.xml

@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>

.idea/misc.xml

@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="hf2" project-jdk-type="Python SDK" />
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/Time-Series-Transformers-Comparison.iml" filepath="$PROJECT_DIR$/.idea/Time-Series-Transformers-Comparison.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="" vcs="Git" />
+  </component>
+</project>

multivariate/train.py

@@ -0,0 +1,91 @@
+from gluonts.dataset.multivariate_grouper import MultivariateGrouper
+from gluonts.time_feature import time_features_from_frequency_str
+
+from datasets import load_dataset
+from functools import lru_cache
+
+import pandas as pd
+import numpy as np
+
+from functools import partial
+from transformers import InformerConfig, InformerForPrediction
+
+freq = "1H"
+prediction_length = 48
+
+
+def get_train_test_datasets():
+
+    @lru_cache(10_000)
+    def convert_to_pandas_period(date, freq):
+        return pd.Period(date, freq)
+
+    def transform_start_field(batch, freq):
+        batch["start"] = [convert_to_pandas_period(date, freq) for date in batch["start"]]
+        return batch
+
+    dataset = load_dataset("monash_tsf", "traffic_hourly")
+    train_dataset = dataset["train"]
+    test_dataset = dataset["test"]
+
+    train_dataset.set_transform(partial(transform_start_field, freq=freq))
+    test_dataset.set_transform(partial(transform_start_field, freq=freq))
+
+    return train_dataset, test_dataset
+
+
+def get_train_test_multivariate_grouper(train_dataset, test_dataset):
+    num_of_variates = len(train_dataset)
+
+    train_grouper = MultivariateGrouper(max_target_dim=num_of_variates)
+    test_grouper = MultivariateGrouper(
+        max_target_dim=num_of_variates,
+        num_test_dates=len(test_dataset) // num_of_variates,  # number of rolling test windows
+    )
+    return train_grouper, test_grouper
+
+
+def get_informer_model(num_of_variates, time_features):
+    config = InformerConfig(
+        # in the multivariate setting, input_size is the number of variates in the time series per time step
+        input_size=num_of_variates,
+        # prediction length:
+        prediction_length=prediction_length,
+        # context length:
+        context_length=prediction_length * 2,
+        # lags value copied from 1 week before:
+        lags_sequence=[1, 24 * 7],
+        # we'll add 5 time features ("hour_of_day", ..., and "age"):
+        num_time_features=len(time_features) + 1,
+
+        # informer params:
+        dropout=0.1,
+        encoder_layers=6,
+        decoder_layers=4,
+        # project input from num_of_variates*len(lags_sequence)+num_time_features to:
+        d_model=64,
+    )
+
+    model = InformerForPrediction(config)
+    return model
+
+
+def main():
+    train_dataset, test_dataset = get_train_test_datasets()
+    train_grouper, test_grouper = get_train_test_multivariate_grouper(train_dataset, test_dataset)
+    multi_variate_train_dataset = train_grouper(train_dataset)
+    multi_variate_test_dataset = test_grouper(test_dataset)
+
+    multi_variate_train_example = multi_variate_train_dataset[0]
+    train_example = train_dataset[0]
+    print('train_example["target"].shape =', len(train_example["target"]))
+    print('multi_variate_train_example["target"].shape =', multi_variate_train_example["target"].shape)
+
+    time_features = time_features_from_frequency_str(freq)
+    print(time_features)
+
+    informer = get_informer_model(num_of_variates=62, time_features=time_features)
+
+
+if __name__ == '__main__':
+    main()