further experimental scripts

code/deep_features_random_forest_runner.py

+#!/usr/bin/env python3
+"""
+Random Forest DAP Runner on Deep Features (OS-32 Layer)
+as resulting from CDRP-N+A Multi-task Network for SEQC-NB
+Dataset
+"""
+
+import os
+from dap.runners import RandomForestRunnerDAP
+from dataset import load_nb_camda, OS_LAB
+
+
+class RandomForestDeepFeaturesDAP(RandomForestRunnerDAP):
+    """
+    RandomForest DAP Runner
+    """
+
+    def __init__(self, experiment):
+        """"""
+        self._target_prediction_name = OS_LAB
+        super(RandomForestDeepFeaturesDAP, self).__init__(experiment=experiment)
+        self.experiment_data.nb_classes = experiment.nb_classes_targets[self._target_prediction_name]
+
+    @property
+    def results_folder(self):
+        """
+        Compose path to the folder where reports and metrics will be saved.
+        """
+        base_foldername = self._target_prediction_name.lower()
+        folder_name = '_'.join([self.ml_model_name, str(self._hyper_params['n_estimators']),
+                                self._hyper_params['criterion'], self._hyper_params['max_features'],
+                                self.feature_scaling_name, self.feature_ranking_name,
+                                str(self.cv_n), str(self.cv_k)])
+
+        ds_name = self.experiment_data.dataset_name \
+            if 'dataset_name' in self.experiment_data.keys() else self.experiment_data.DESCR
+        output_folder_path = os.path.join(os.path.abspath(os.path.dirname(__file__)),
+                                          'results', ds_name, base_foldername, folder_name)
+
+        os.makedirs(output_folder_path, exist_ok=True)
+        return output_folder_path
+
+    @property
+    def ml_model_name(self):
+        return "RandomForest"
+
+    # Override DAP Methods
+    # --------------------
+
+    def _set_training_data(self):
+        """Default implementation for classic and quite standard DAP implementation.
+         More complex implementation require overriding this method.
+        """
+        self.X = self.experiment_data.training_data
+        self.y = self.experiment_data.targets[self._target_prediction_name]
+
+    def _set_test_data(self):
+        self.X_test = self.experiment_data.test_data
+        self.y_test = self.experiment_data.test_targets[self._target_prediction_name]
+
+
+def main():
+    # Load Dataset
+    # ============
+    training_data_fpath = os.path.join(os.path.abspath(os.path.dirname(__file__)),
+                                       'data', '..', 'OS32_SEQC', 'SEQC2_OS_32_training.csv')
+    test_data_fpath = os.path.join(os.path.abspath(os.path.dirname(__file__)),
+                                   'data', '..', 'OS32_SEQC', 'SEQC2_OS_32_test.csv')
+
+    dataset = load_nb_camda(dataset_name='SEQC2_OS32_HRONLY',
+                            training_data_fpath=training_data_fpath,
+                            test_data_fpath=test_data_fpath, hr_only=True)
+    print('RUNNING ON DATASET {}'.format(dataset.dataset_name.upper()))
+
+    # ============
+    # DAP Settings
+    # ============
+    from dap import settings as dap_settings
+    dap_settings.to_categorical = False
+    dap_settings.feature_ranges = [75, 90, 100]
+
+    from dap.scaling import MinMaxScaler
+    dap_settings.feature_scaler = MinMaxScaler(feature_range=(-1, 1), copy=False)
+
+    # ============================
+    # Model Settings (hyperparams)
+    # ============================
+    dap = RandomForestDeepFeaturesDAP(dataset)
+    dap.hyper_params.criterion = 'entropy'
+    dap.hyper_params.n_estimators = 500
+    dap.hyper_params.max_features = 'log2'
+
+    trained_model = dap.run(verbose=True)
+    dap.predict_on_test(trained_model)
+    print("Computation completed!")
+
+
+if __name__ == '__main__':
+    main()

code/targetnb_svm_runner_multiple_splits.py

+"""
+Script to generate Random train/test split for the TARGET-NB Dataset
+"""
+
+import os
+from dap.runners import SupportVectorRunnerDAP
+from dataset import generate_dataset_partitions
+import argparse
+
+
+class SupportVectorMachineRunner(SupportVectorRunnerDAP):
+    """
+    SVM DAP Runner
+    """
+
+    def __init__(self, experiment, target_prediction):
+        """"""
+        # One of: 'HR', 'EFS', 'OS'
+        self._target_prediction_name = target_prediction
+        super(SupportVectorMachineRunner, self).__init__(experiment=experiment)
+        self.experiment_data.nb_classes = experiment.nb_classes_targets[self._target_prediction_name]
+
+    @property
+    def results_folder(self):
+        """
+        Compose path to the folder where reports and metrics will be saved.
+        """
+        base_foldername = self._target_prediction_name.lower()
+        folder_name = '_'.join([self.ml_model_name,
+                                self._hyper_params['kernel'], str(self._hyper_params['C']),
+                                self.feature_scaling_name, self.feature_ranking_name,
+                                str(self.cv_n), str(self.cv_k)])
+
+        ds_name = self.experiment_data.dataset_name \
+            if 'dataset_name' in self.experiment_data.keys() else self.experiment_data.DESCR
+        output_folder_path = os.path.join(os.path.abspath(os.path.dirname(__file__)),
+                                          'out_multi_split_25', ds_name, base_foldername, folder_name)
+        os.makedirs(output_folder_path, exist_ok=True)
+        return output_folder_path
+
+    @property
+    def ml_model_name(self):
+        return "LSVM"
+
+    # Override DAP Methods
+    # --------------------
+
+    def _set_training_data(self):
+        """Default implementation for classic and quite standard DAP implementation.
+         More complex implementation require overriding this method.
+        """
+        self.X = self.experiment_data.training_data
+        self.y = self.experiment_data.targets[self._target_prediction_name]
+
+    def _set_test_data(self):
+        self.X_test = self.experiment_data.test_data
+        self.y_test = self.experiment_data.test_targets[self._target_prediction_name]
+
+
+def main():
+
+    for targetNB_partition in generate_dataset_partitions(n_partitions=100, test_size=.25):
+        print('RUNNING ON DATASET {}'.format(targetNB_partition.dataset_name.upper()))
+
+        parser = argparse.ArgumentParser()
+        parser.add_argument("-t", "--target", help="Target Endpoint prediction",
+                            type=str, choices=targetNB_partition.targets_names)
+        args = parser.parse_args()
+
+        # ============
+        # DAP Settings
+        # ============
+        from dap import settings as dap_settings
+        dap_settings.to_categorical = False
+
+        dap_settings.feature_ranges = [2, 5, 10, 15, 20, 25, 50, 75, 100]
+
+        from dap.scaling import MinMaxScaler, StandardScaler
+        dap_settings.feature_scaler = MinMaxScaler(feature_range=(-1, 1), copy=False)
+        # dap_settings.feature_scaler = StandardScaler(copy=False)
+
+        # ============================
+        # Model Settings (hyperparams)
+        # ============================
+        dap = SupportVectorMachineRunner(targetNB_partition, target_prediction=args.target)
+        dap.hyper_params.C = 1.0
+        dap.hyper_params.kernel = 'linear'
+
+        trained_model = dap.run(verbose=True)
+        dap.predict_on_test(trained_model)
+        print("Computation completed!")
+
+
+if __name__ == '__main__':
+    main()