Adding version and new test ci preprocess location

.gitignore

@@ -26,5 +26,10 @@ python_install/
 # ignoring insitute dependent parameter files
 Preprocessing-parameters-*.yaml
 # ignoring preprocessing integration test folders
-preprocessing_*/
-test_*_model*/
+test_preprocessing_*/
+test_train_*/
+# ignoring any test directory
+test-*/
+jobs/
+install_*/
+*_batch/
\ No newline at end of file

examples/Preprocessing-parameters.yaml

@@ -7,7 +7,7 @@ sample_path: &sample_path <path_palce_holder>/hybrids/
 # Path where the merged and ready-to-train samples are saved
 file_path: &file_path <path_palce_holder>/preprocessed/
 
-# Name of the output file from the preprocessing
+# Name of the output file from the preprocessing (has to be a .h5 file, no folder)
 .outfile_name: &outfile_name <path_palce_holder>/PFlow-hybrid.h5
 
 # List of variables for training (yaml)

pipelines/.integration_test-gitlab-ci.yaml

@@ -32,7 +32,7 @@ test_preprocessing_dips_count:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_dips/
+      - test_preprocessing_dips/
       - coverage_files/
 
 test_preprocessing_dl1r_count:
@@ -45,7 +45,7 @@ test_preprocessing_dl1r_count:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_dl1r/
+      - test_preprocessing_dl1r/
       - coverage_files/
 
 test_preprocessing_umami_count:
@@ -58,7 +58,7 @@ test_preprocessing_umami_count:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_umami/
+      - test_preprocessing_umami/
       - coverage_files/
 
 test_preprocessing_dips_pdf:
@@ -71,7 +71,7 @@ test_preprocessing_dips_pdf:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_dips_pdf/
+      - test_preprocessing_dips_pdf/
       - coverage_files/
 
 test_preprocessing_dl1r_pdf:
@@ -84,7 +84,7 @@ test_preprocessing_dl1r_pdf:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_dl1r_pdf/
+      - test_preprocessing_dl1r_pdf/
       - coverage_files/
 
 test_preprocessing_umami_pdf:
@@ -97,7 +97,7 @@ test_preprocessing_umami_pdf:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_umami_pdf/
+      - test_preprocessing_umami_pdf/
       - coverage_files/
 
 test_preprocessing_dips_weighting:
@@ -110,7 +110,7 @@ test_preprocessing_dips_weighting:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_dips_weighting/
+      - test_preprocessing_dips_weighting/
       - coverage_files/
 
 test_preprocessing_dl1r_weighting:
@@ -123,7 +123,7 @@ test_preprocessing_dl1r_weighting:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_dl1r_weighting/
+      - test_preprocessing_dl1r_weighting/
       - coverage_files/
 
 test_preprocessing_umami_weighting:
@@ -136,7 +136,7 @@ test_preprocessing_umami_weighting:
     <<: *artifact_template
     paths:
       - plots/
-      - preprocessing_umami_weighting/
+      - test_preprocessing_umami_weighting/
       - coverage_files/
 
 test_train_dips:

setup.py

@@ -10,7 +10,7 @@ from setuptools import setup
 
 setup(
     name="umami",
-    version="0.0.0",  # Also change in module
+    version="0.5",  # Also change in module
     packages=[
         "umami",
         "umami.configuration",
@@ -25,16 +25,6 @@ setup(
         "umami.metrics",
         "umami.models",
     ],
-    # install_requires=[
-    #     "h5py",
-    #     "numpy",
-    #     "matplotlib",
-    #     "seaborn",
-    #     "tables",
-    #     "pandas",
-    #     "tensorflow",
-    #     "keras"
-    # ],
     include_package_data=True,
     test_suite="umami.tests",
     scripts=[

umami/__init__.py

+"""Umami framework used in ATLAS FTAG for dataset preparation and tagger training."""
+__version__ = "0.5"

umami/preprocessing_tools/Configuration.py

@@ -104,7 +104,13 @@ class Configuration:
         if option is None and iteration is None:
             return self.outfile_name
         out_file = self.outfile_name
-        idx = out_file.index(".h5")
+        try:
+            idx = out_file.index(".h5")
+        except ValueError as error:
+            raise ValueError(
+                "Your specified `outfile_name` has to be a .h5 file. "
+                f"You defined in the preprocessing config {out_file}"
+            ) from error
 
         if iteration is None:
             if option is None:

umami/tests/integration/test_preprocessing.py

@@ -188,7 +188,7 @@ def runPreprocessing(config: dict, tagger: str, method: str) -> bool:
                 "Test failed: preprocessing.py --to_records."
             ) from Error
 
-    tagger_path = f"./preprocessing_{tagger}/"
+    tagger_path = f"./test_preprocessing_{tagger}/"
     if not os.path.isdir(tagger_path):
         run(["mkdir", tagger_path], check=True)
 

umami/tests/integration/test_train.py

@@ -72,11 +72,11 @@ def prepareConfig(
     config = os.path.join(test_dir, os.path.basename(config_source))
 
     preprocessing_config_source = os.path.join(
-        f"./preprocessing_{preprocess_files}/preprocessing/",
+        f"./test_preprocessing_{preprocess_files}/preprocessing/",
         os.path.basename(data["test_preprocessing"]["config"]),
     )
     preprocessing_config_paths_source = os.path.join(
-        f"./preprocessing_{preprocess_files}/preprocessing/",
+        f"./test_preprocessing_{preprocess_files}/preprocessing/",
         os.path.basename(data["test_preprocessing"]["config_paths"]),
     )
     preprocessing_config = os.path.join(
@@ -87,7 +87,7 @@ def prepareConfig(
     )
 
     var_dict_source = os.path.join(
-        f"./preprocessing_{preprocess_files}/preprocessing/",
+        f"./test_preprocessing_{preprocess_files}/preprocessing/",
         os.path.basename(data["test_preprocessing"][f"var_dict_{preprocess_files}"]),
     )
     var_dict = os.path.join(test_dir, os.path.basename(var_dict_source))
@@ -96,13 +96,14 @@ def prepareConfig(
     logger.info("Retrieving files from preprocessing...")
 
     train_file = os.path.join(
-        f"./preprocessing_{preprocess_files}/preprocessing/",
+        f"./test_preprocessing_{preprocess_files}/preprocessing/",
         "PFlow-hybrid_70-test-resampled_scaled_shuffled.h5",
     )
     test_file_ttbar = os.path.join(test_dir, "ci_ttbar_testing.h5")
     test_file_zprime = os.path.join(test_dir, "ci_zpext_testing.h5")
     scale_dict = os.path.join(
-        f"./preprocessing_{preprocess_files}/preprocessing/", "PFlow-scale_dict.json"
+        f"./test_preprocessing_{preprocess_files}/preprocessing/",
+        "PFlow-scale_dict.json",
     )
 
     # prepare config files by modifying local copies of config files
@@ -183,7 +184,7 @@ def prepareConfig(
 
     if useTFRecords is True:
         config_file["train_file"] = os.path.join(
-            f"./preprocessing_{preprocess_files}/preprocessing/",
+            f"./test_preprocessing_{preprocess_files}/preprocessing/",
             "PFlow-hybrid_70-test-resampled_scaled_shuffled",
         )
         config_file["model_name"] = data["test_dips"]["model_name"] + "_tfrecords"