Prepares pip working pip release

.conda.yml

@@ -3,78 +3,155 @@ channels:
   - defaults
   - conda-forge
 dependencies:
+  - asttokens=2.4.1=pyhd8ed1ab_0
+  - backcall=0.2.0=pyh9f0ad1d_0
+  - bzip2=1.0.8=hfdf4475_7
+  - ca-certificates=2024.7.4=h8857fd0_0
   - certifi=2024.2.2=pyhd8ed1ab_0
+  - colorama=0.4.6=pyhd8ed1ab_0
+  - comm=0.2.2=pyhd8ed1ab_0
   - cycler=0.12.1=pyhd8ed1ab_0
-  - font-ttf-dejavu-sans-mono=2.37=hab24e00_0
-  - font-ttf-inconsolata=3.000=h77eed37_0
-  - font-ttf-source-code-pro=2.038=h77eed37_0
-  - font-ttf-ubuntu=0.83=h77eed37_1
-  - fonts-conda-ecosystem=1=0
-  - fonts-conda-forge=1=0
-  - importlib-resources=6.1.2=pyhd8ed1ab_0
-  - importlib_resources=6.1.2=pyhd8ed1ab_0
-  - joblib=1.3.2=pyhd8ed1ab_0
+  - decorator=5.1.1=pyhd8ed1ab_0
+  - executing=2.0.1=pyhd8ed1ab_0
+  - importlib-metadata=7.1.0=pyha770c72_0
+  - importlib-resources=6.4.0=pyhd8ed1ab_0
+  - importlib_metadata=7.1.0=hd8ed1ab_0
+  - importlib_resources=6.4.0=pyhd8ed1ab_0
+  - jedi=0.19.1=pyhd8ed1ab_0
+  - joblib=1.4.0=pyhd8ed1ab_0
+  - jupyter_client=8.6.1=pyhd8ed1ab_0
+  - krb5=1.21.3=h37d8d59_0
+  - libcxx=18.1.8=hd876a4e_6
+  - libedit=3.1.20191231=h0678c8f_2
+  - libffi=3.4.2=h0d85af4_5
+  - libsodium=1.0.18=hbcb3906_1
+  - libsqlite=3.46.0=h1b8f9f3_0
+  - libzlib=1.3.1=h87427d6_1
+  - matplotlib-inline=0.1.7=pyhd8ed1ab_0
   - munkres=1.1.4=pyh9f0ad1d_0
-  - packaging=23.2=pyhd8ed1ab_0
+  - ncurses=6.5=hf036a51_1
+  - nest-asyncio=1.6.0=pyhd8ed1ab_0
+  - openssl=3.3.1=hd23fc13_3
+  - packaging=24.0=pyhd8ed1ab_0
+  - parso=0.8.4=pyhd8ed1ab_0
+  - pickleshare=0.7.5=py_1003
   - pip=24.0=pyhd8ed1ab_0
-  - ply=3.11=py_1
-  - pyparsing=3.1.1=pyhd8ed1ab_0
+  - platformdirs=4.2.0=pyhd8ed1ab_0
+  - ply=3.11=pyhd8ed1ab_2
+  - prompt-toolkit=3.0.42=pyha770c72_0
+  - prompt_toolkit=3.0.42=hd8ed1ab_0
+  - pure_eval=0.2.2=pyhd8ed1ab_0
+  - pygments=2.17.2=pyhd8ed1ab_0
+  - pyparsing=3.1.2=pyhd8ed1ab_0
+  - python=3.9.19=h7a9c478_0_cpython
   - python-dateutil=2.9.0=pyhd8ed1ab_0
   - python-tzdata=2024.1=pyhd8ed1ab_0
   - python_abi=3.9=4_cp39
   - pytz=2024.1=pyhd8ed1ab_0
-  - setuptools=69.1.1=pyhd8ed1ab_0
+  - pyzmq=26.2.0=py39ha6bd863_0
+  - readline=8.2=h9e318b2_1
+  - setuptools=69.5.1=pyhd8ed1ab_0
   - six=1.16.0=pyh6c4a22f_0
-  - threadpoolctl=3.3.0=pyhc1e730c_0
+  - stack_data=0.6.2=pyhd8ed1ab_0
+  - threadpoolctl=3.4.0=pyhc1e730c_0
+  - tk=8.6.13=h1abcd95_1
   - toml=0.10.2=pyhd8ed1ab_0
   - tomli=2.0.1=pyhd8ed1ab_0
+  - traitlets=5.14.3=pyhd8ed1ab_0
+  - typing_extensions=4.11.0=pyha770c72_0
   - tzdata=2024a=h0c530f3_0
-  - wheel=0.42.0=pyhd8ed1ab_0
+  - wcwidth=0.2.13=pyhd8ed1ab_0
+  - wheel=0.43.0=pyhd8ed1ab_1
+  - xz=5.2.6=h775f41a_0
+  - zeromq=4.3.5=hde137ed_4
   - zipp=3.17.0=pyhd8ed1ab_0
   - pip:
-      - click==8.1.7
-      - cloudpickle==3.0.0
-      - configspace==0.7.1
-      - cvxopt==1.3.2
-      - dask==2024.2.1
-      - dask-jobqueue==0.8.5
-      - deprecation==2.1.0
-      - distributed==2024.2.1
-      - emcee==3.1.4
-      - feeed == 1.2.0
-      - fsspec==2024.2.0
-      - imbalanced-learn==0.12.0
-      - imblearn==0.0
-      - importlib-metadata==7.0.1
-      - intervaltree==3.1.0
-      - jinja2==3.1.3
-      - levenshtein==0.23.0
-      - locket==1.0.0
-      - lxml==5.1.0
-      - markupsafe==2.1.5
-      - more-itertools==10.2.0
-      - msgpack==1.0.8
-      - networkx==3.2.1
-      - numpy==1.26.4
-      - pandas==2.0.0
-      - partd==1.4.1
-      - pm4py==2.7.2
-      - psutil==5.9.8
-      - pydotplus==2.0.2
-      - pynisher==1.0.10
-      - pyrfr==0.9.0
-      - pyyaml==6.0.1
-      - rapidfuzz==3.6.1
-      - regex==2023.12.25
-      - scikit-learn==1.2.2
-      - scipy==1.10.1
-      - seaborn==0.13.2
-      - smac==2.0.2
-      - sortedcontainers==2.4.0
-      - stringdist==1.0.9
-      - tblib==3.0.0
-      - toolz==0.12.1
-      - tqdm==4.65.0
-      - typing-extensions==4.10.0
-      - urllib3==2.2.1
-      - zict==3.0.0
+    - altair==5.3.0
+    - appnope==0.1.4
+    - attrs==23.2.0
+    - blinker==1.8.2
+    - brotli==1.1.0
+    - cachetools==5.4.0
+    - charset-normalizer==3.3.2
+    - click==8.1.7
+    - cloudpickle==3.0.0
+    - configspace==0.7.1
+    - contourpy==1.2.1
+    - cvxopt==1.3.2
+    - dask==2024.4.1
+    - dask-jobqueue==0.8.5
+    - debugpy==1.8.1
+    - deprecation==2.1.0
+    - distributed==2024.4.1
+    - emcee==3.1.4
+    - feeed==1.2.0
+    - fonttools==4.51.0
+    - fsspec==2024.3.1
+    - gitdb==4.0.11
+    - gitpython==3.1.43
+    - idna==3.7
+    - imbalanced-learn==0.12.2
+    - imblearn==0.0
+    - intervaltree==3.1.0
+    - ipykernel==6.29.3
+    - ipython==8.12.0
+    - jinja2==3.1.3
+    - jsonschema==4.23.0
+    - jsonschema-specifications==2023.12.1
+    - jupyter-core==5.7.2
+    - kiwisolver==1.4.5
+    - levenshtein==0.23.0
+    - llvmlite==0.42.0
+    - locket==1.0.0
+    - lxml==5.2.1
+    - markdown-it-py==3.0.0
+    - markupsafe==2.1.5
+    - matplotlib==3.8.4
+    - mdurl==0.1.2
+    - more-itertools==10.2.0
+    - msgpack==1.0.8
+    - networkx==3.2.1
+    - numba==0.59.1
+    - numpy==1.26.4
+    - opyenxes==0.3.0
+    - pandas==2.2.2
+    - partd==1.4.1
+    - pexpect==4.9.0
+    - pillow==10.4.0
+    - pm4py==2.7.2
+    - protobuf==5.27.2
+    - psutil==6.0.0
+    - ptyprocess==0.7.0
+    - pyarrow==17.0.0
+    - pydeck==0.9.1
+    - pydotplus==2.0.2
+    - pynisher==1.0.10
+    - pyrfr==0.9.0
+    - python-graphviz==0.20.3
+    - pyyaml==6.0.1
+    - rapidfuzz==3.8.1
+    - referencing==0.35.1
+    - regex==2023.12.25
+    - requests==2.32.3
+    - rich==13.7.1
+    - rpds-py==0.19.0
+    - scikit-learn==1.2.2
+    - scipy==1.13.0
+    - seaborn==0.13.2
+    - slicer==0.0.8
+    - smac==2.0.2
+    - smmap==5.0.1
+    - sortedcontainers==2.4.0
+    - streamlit==1.36.0
+    - stringdist==1.0.9
+    - tabulate==0.9.0
+    - tblib==3.0.0
+    - tenacity==8.5.0
+    - toolz==0.12.1
+    - tornado==6.4
+    - tqdm==4.65.0
+    - urllib3==2.2.1
+    - watchdog==4.0.1
+    - xgboost==2.1.0
+    - zict==3.0.0
+    - zstd==1.5.5.1

gedi/__init__.py

@@ -1,7 +1,3 @@
-from .generator import GenerateEventLogs
-from .features import EventLogFeatures
-from .augmentation import InstanceAugmentator
-from .benchmark import BenchmarkTest
-from .plotter import BenchmarkPlotter, FeaturesPlotter, AugmentationPlotter, GenerationPlotter
+from .run import gedi
 
-__all__=[ 'GenerateEventLogs', 'EventLogFeatures', 'FeatureAnalyser', 'InstanceAugmentator', 'BenchmarkTest', 'BenchmarkPlotter', 'FeaturesPlotter', 'AugmentationPlotter', 'GenerationPlotter']
+__all__=['gedi']

gedi/run.py

@@ -0,0 +1,54 @@
+import config
+import pandas as pd
+from datetime import datetime as dt
+from gedi.generator import GenerateEventLogs
+from gedi.features import EventLogFeatures
+from gedi.augmentation import InstanceAugmentator
+from gedi.benchmark import BenchmarkTest
+from gedi.plotter import BenchmarkPlotter, FeaturesPlotter, AugmentationPlotter, GenerationPlotter
+from utils.default_argparse import ArgParser
+from utils.param_keys import *
+
+def run(kwargs:dict, model_params_list: list, filename_list:list):
+    """
+    This function chooses the running option for the program.
+    @param kwargs: dict
+        contains the running parameters and the event-log file information
+    @param model_params_list: list
+        contains a list of model parameters, which are used to analyse this different models.
+    @param filename_list: list
+        contains the list of the filenames to load multiple event-logs
+    @return:
+    """
+    params = kwargs[PARAMS]
+    ft = EventLogFeatures(None)
+    augmented_ft = InstanceAugmentator()
+    gen = pd.DataFrame(columns=['log'])
+
+    for model_params in model_params_list:
+        if model_params.get(PIPELINE_STEP) == 'instance_augmentation':
+            augmented_ft = InstanceAugmentator(aug_params=model_params, samples=ft.feat)
+            AugmentationPlotter(augmented_ft, model_params)
+        elif model_params.get(PIPELINE_STEP) == 'event_logs_generation':
+            gen = pd.DataFrame(GenerateEventLogs(model_params).log_config)
+            #gen = pd.read_csv("output/features/generated/grid_2objectives_enseef_enve/2_enseef_enve_feat.csv")
+            #GenerationPlotter(gen, model_params, output_path="output/plots")
+            return gen
+        elif model_params.get(PIPELINE_STEP) == 'benchmark_test':
+            benchmark = BenchmarkTest(model_params, event_logs=gen['log'])
+            # BenchmarkPlotter(benchmark.features, output_path="output/plots")
+        elif model_params.get(PIPELINE_STEP) == 'feature_extraction':
+            ft = EventLogFeatures(**kwargs, logs=gen['log'], ft_params=model_params)
+            FeaturesPlotter(ft.feat, model_params)
+        elif model_params.get(PIPELINE_STEP) == "evaluation_plotter":
+            GenerationPlotter(gen, model_params, output_path=model_params['output_path'], input_path=model_params['input_path'])
+
+def gedi(config_path):
+    """
+    This function runs the GEDI pipeline.
+    @param config_path: str
+        contains the path to the config file
+    @return:
+    """
+    model_params_list = config.get_model_params_list(config_path)
+    run({'params':""}, model_params_list, [])

main.py

@@ -1,54 +1,12 @@
 import config
-import pandas as pd
 from datetime import datetime as dt
-from gedi.generator import GenerateEventLogs
-from gedi.features import EventLogFeatures
-from gedi.augmentation import InstanceAugmentator
-from gedi.benchmark import BenchmarkTest
-from gedi.plotter import BenchmarkPlotter, FeaturesPlotter, AugmentationPlotter, GenerationPlotter
+from gedi.run import gedi, run
 from utils.default_argparse import ArgParser
 from utils.param_keys import *
 
-def run(kwargs:dict, model_paramas_list: list, filename_list:list):
-    """
-    This function chooses the running option for the program.
-    @param kwargs: dict
-        contains the running parameters and the event-log file information
-    @param model_params_list: list
-        contains a list of model parameters, which are used to analyse this different models.
-    @param filename_list: list
-        contains the list of the filenames to load multiple event-logs
-    @return:
-    """
-    params = kwargs[PARAMS]
-    ft = EventLogFeatures(None)
-    augmented_ft = InstanceAugmentator()
-    gen = pd.DataFrame(columns=['log'])
-
-    for model_params in model_params_list:
-        if model_params.get(PIPELINE_STEP) == 'instance_augmentation':
-            augmented_ft = InstanceAugmentator(aug_params=model_params, samples=ft.feat)
-            AugmentationPlotter(augmented_ft, model_params)
-        elif model_params.get(PIPELINE_STEP) == 'event_logs_generation':
-            gen = pd.DataFrame(GenerateEventLogs(model_params).log_config)
-            #gen = pd.read_csv("output/features/generated/grid_2objectives_enseef_enve/2_enseef_enve_feat.csv")
-            #GenerationPlotter(gen, model_params, output_path="output/plots")
-        elif model_params.get(PIPELINE_STEP) == 'benchmark_test':
-            benchmark = BenchmarkTest(model_params, event_logs=gen['log'])
-            # BenchmarkPlotter(benchmark.features, output_path="output/plots")
-        elif model_params.get(PIPELINE_STEP) == 'feature_extraction':
-            ft = EventLogFeatures(**kwargs, logs=gen['log'], ft_params=model_params)
-            FeaturesPlotter(ft.feat, model_params)
-        elif model_params.get(PIPELINE_STEP) == "evaluation_plotter":
-            GenerationPlotter(gen, model_params, output_path=model_params['output_path'], input_path=model_params['input_path'])
-
-
 if __name__=='__main__':
     start_gedi = dt.now()
     print(f'INFO: GEDI starting {start_gedi}')
-
     args = ArgParser().parse('GEDI main')
-    model_params_list = config.get_model_params_list(args.alg_params_json)
-    run({'params':""}, model_params_list, [])
-
+    gedi(args.alg_params_json)
     print(f'SUCCESS: GEDI took {dt.now()-start_gedi} sec.')

setup.py

@@ -4,7 +4,7 @@ import os
 with open("README.md", "r") as fh:
     long_description = fh.read()
 
-version_string = os.environ.get("VERSION_PLACEHOLDER", "0.0.1")
+version_string = os.environ.get("VERSION_PLACEHOLDER", "0.0.2")
 print(version_string)
 version = version_string
 
@@ -25,14 +25,59 @@ setup(
             'Levenshtein==0.23.0',
             'matplotlib==3.8.4',
             'numpy==1.26.4',
-            'pandas==2.2.2',
             'pm4py==2.7.2',
             'scikit-learn==1.2.2',
-            'scipy==1.13.0',
+            'scipy==1.10.1',
             'seaborn==0.13.2',
             'smac==2.0.2',
             'tqdm==4.65.0',
-            'streamlit-toggle-switch>=1.0.2'
+            'streamlit-toggle-switch>=1.0.2',
+            'click==8.1.7',
+            'cloudpickle==3.0.0',
+            'configspace==0.7.1',
+            'cvxopt==1.3.2',
+            'dask==2024.2.1',
+            'dask-jobqueue==0.8.5',
+            'deprecation==2.1.0',
+            'distributed==2024.2.1',
+            'emcee==3.1.4',
+            'feeed == 1.2.0',
+            'fsspec==2024.2.0',
+            'imbalanced-learn==0.12.0',
+            'imblearn==0.0',
+            'importlib-metadata==7.0.1',
+            'intervaltree==3.1.0',
+            'jinja2==3.1.3',
+            'levenshtein==0.23.0',
+            'locket==1.0.0',
+            'lxml==5.1.0',
+            'markupsafe==2.1.5',
+            'more-itertools==10.2.0',
+            'msgpack==1.0.8',
+            'networkx==3.2.1',
+            'numpy==1.26.4',
+            'pandas>=2.0.0',
+            'partd==1.4.1',
+            'pm4py==2.7.2',
+            'psutil==5.9.8',
+            'pydotplus==2.0.2',
+            'pynisher==1.0.10',
+            'pyrfr==0.9.0',
+            'pyyaml==6.0.1',
+            'rapidfuzz==3.6.1',
+            'regex==2023.12.25',
+            'scikit-learn==1.2.2',
+            'scipy==1.10.1',
+            'seaborn==0.13.2',
+            'smac==2.0.2',
+            'sortedcontainers==2.4.0',
+            'stringdist==1.0.9',
+            'tblib==3.0.0',
+            'toolz==0.12.1',
+            'tqdm==4.65.0',
+            'typing-extensions==4.10.0',
+            'urllib3==2.2.1',
+            'zict==3.0.0'
             ],
         packages = ['gedi'],
         classifiers=[