Moves internal utils to package

gedi/augmentation.py

@@ -3,8 +3,8 @@ from collections import Counter
 from datetime import datetime as dt
 from imblearn.over_sampling import SMOTE
 from gedi.utils.matrix_tools import insert_missing_data
-from utils.param_keys import INPUT_PATH, OUTPUT_PATH
-from utils.param_keys.augmentation import AUGMENTATION_PARAMS, NO_SAMPLES, FEATURE_SELECTION, METHOD
+from gedi.utils.param_keys import INPUT_PATH, OUTPUT_PATH
+from gedi.utils.param_keys.augmentation import AUGMENTATION_PARAMS, NO_SAMPLES, FEATURE_SELECTION, METHOD
 
 class InstanceAugmentator:
     def __init__(self, aug_params=None, samples=None):

gedi/benchmark.py

@@ -14,9 +14,9 @@ from pm4py import precision_alignments
 from pm4py.objects.bpmn.obj import BPMN
 from pm4py.objects.log.importer.xes import importer as xes_importer
 from gedi.utils.io_helpers import dump_features_json
+from gedi.utils.param_keys import INPUT_PATH, OUTPUT_PATH
+from gedi.utils.param_keys.benchmark import MINERS
 from tqdm import tqdm
-from utils.param_keys import INPUT_PATH, OUTPUT_PATH
-from utils.param_keys.benchmark import MINERS
 
 class BenchmarkTest:
     def __init__(self, params=None, event_logs=None):

gedi/config.py

@@ -1,8 +1,8 @@
 import json
 import warnings
 
-from utils.param_keys import PIPELINE_STEP, INPUT_PATH, OUTPUT_PATH
-from utils.param_keys.features import FEATURE_SET, FEATURE_PARAMS
+from gedi.utils.param_keys import PIPELINE_STEP, INPUT_PATH, OUTPUT_PATH
+from gedi.utils.param_keys.features import FEATURE_SET, FEATURE_PARAMS
 
 def get_model_params_list(alg_json_file: str) :#-> list[dict]:
     """

gedi/features.py

@@ -7,10 +7,11 @@ from datetime import datetime as dt
 from functools import partial
 from feeed.feature_extractor import extract_features
 from pathlib import Path
-from utils.param_keys import INPUT_PATH
-from utils.param_keys.features import FEATURE_PARAMS, FEATURE_SET
+from gedi.utils.column_mappings import column_mappings
 from gedi.utils.io_helpers import dump_features_json
-from utils.column_mappings import column_mappings
+from gedi.utils.param_keys import INPUT_PATH
+from gedi.utils.param_keys.features import FEATURE_PARAMS, FEATURE_SET
+
 def get_sortby_parameter(elem):
     number = int(elem.rsplit(".")[0].rsplit("_", 1)[1])
     return number

gedi/generator.py

@@ -17,11 +17,11 @@ from pm4py import generate_process_tree
 from pm4py import write_xes
 from pm4py.sim import play_out
 from smac import HyperparameterOptimizationFacade, Scenario
-from utils.param_keys import OUTPUT_PATH, INPUT_PATH
-from utils.param_keys.generator import GENERATOR_PARAMS, EXPERIMENT, CONFIG_SPACE, N_TRIALS
+from gedi.utils.column_mappings import column_mappings
 from gedi.utils.io_helpers import get_output_key_value_location, dump_features_json, compute_similarity
 from gedi.utils.io_helpers import read_csvs
-from utils.column_mappings import column_mappings
+from gedi.utils.param_keys import OUTPUT_PATH, INPUT_PATH
+from gedi.utils.param_keys.generator import GENERATOR_PARAMS, EXPERIMENT, CONFIG_SPACE, N_TRIALS
 import xml.etree.ElementTree as ET
 import re
 from xml.dom import minidom

gedi/plotter.py

@@ -8,20 +8,20 @@ import seaborn as sns
 import os
 import glob
 
+from collections import defaultdict
+from gedi.generator import get_tasks
+from gedi.utils.io_helpers import get_keys_abbreviation
+from gedi.utils.io_helpers import read_csvs, select_instance
+from gedi.utils.param_keys import PLOT_TYPE, PROJECTION, EXPLAINED_VAR, PLOT_3D_MAP
+from gedi.utils.param_keys import OUTPUT_PATH, PIPELINE_STEP
+from gedi.utils.param_keys.generator import GENERATOR_PARAMS, EXPERIMENT, PLOT_REFERENCE_FEATURE
+from gedi.utils.param_keys.plotter import REAL_EVENTLOG_PATH, FONT_SIZE, BOXPLOT_WIDTH
 from matplotlib.axes import Axes
 from matplotlib.figure import Figure
 from matplotlib.lines import Line2D
-from utils.param_keys import PLOT_TYPE, PROJECTION, EXPLAINED_VAR, PLOT_3D_MAP
-from utils.param_keys import OUTPUT_PATH, PIPELINE_STEP
-from utils.param_keys.generator import GENERATOR_PARAMS, EXPERIMENT, PLOT_REFERENCE_FEATURE
-from utils.param_keys.plotter import REAL_EVENTLOG_PATH, FONT_SIZE, BOXPLOT_WIDTH
-from collections import defaultdict
-
 from sklearn.preprocessing import Normalizer, StandardScaler
 from sklearn.decomposition import PCA
-from gedi.generator import get_tasks
-from gedi.utils.io_helpers import get_keys_abbreviation
-from gedi.utils.io_helpers import read_csvs, select_instance
+
 
 def insert_newlines(string, every=140):
     return '\n'.join(string[i:i+every] for i in range(0, len(string), every))

gedi/run.py

@@ -1,13 +1,14 @@
-import gedi.config as 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.config import get_model_params_list
+from gedi.features import EventLogFeatures
+from gedi.generator import GenerateEventLogs
 from gedi.plotter import BenchmarkPlotter, FeaturesPlotter, AugmentationPlotter, GenerationPlotter
-from utils.default_argparse import ArgParser
-from utils.param_keys import PARAMS, PIPELINE_STEP
+from gedi.utils.default_argparse import ArgParser
+from gedi.utils.param_keys import PARAMS, PIPELINE_STEP
 
 def run(kwargs:dict, model_params_list: list, filename_list:list):
     """
@@ -49,5 +50,5 @@ def gedi(config_path):
         contains the path to the config file
     @return:
     """
-    model_params_list = config.get_model_params_list(config_path)
+    model_params_list = get_model_params_list(config_path)
     run({'params':""}, model_params_list, [])

gedi/utils/__init__.py

@@ -0,0 +1,8 @@
+from .param_keys import PIPELINE_STEP, INPUT_PATH, OUTPUT_PATH
+from .io_helpers import sort_files
+from .column_mappings import column_mappings
+
+__all__ = [
+           "column_mappings","sort_files",
+           "PIPELINE_STEP", "INPUT_PATH", "OUTPUT_PATH"
+           ]

{utils → gedi/utils}/column_mappings.py

@@ -1,5 +1,5 @@
 def column_mappings():
-    
+
     column_names_short = {
     'rutpt': 'ratio_unique_traces_per_trace',
     'rmcv': 'ratio_most_common_variant',
@@ -12,5 +12,5 @@ def column_mappings():
     'eseef': 'epa_sequence_entropy_exponential_forgetting',
     'enseef': 'epa_normalized_sequence_entropy_exponential_forgetting'
     }
-    
+
     return column_names_short

{utils → gedi/utils}/param_keys/__init__.py

@@ -1,3 +1,5 @@
+from .features import FEATURE_PARAMS, FEATURE_SET
+
 # Model params
 ALGORITHM_NAME = 'algorithm_name'
 PIPELINE_STEP = 'pipeline_step'

setup.py

@@ -1,4 +1,4 @@
-from setuptools import setup
+from setuptools import setup, find_packages
 import os
 
 with open("README.md", "r") as fh:
@@ -11,6 +11,7 @@ version = version_string
 setup(
         name = 'gedi',
         version = str(version),
+        packages=find_packages(),
         description = 'Generating Event Data with Intentional Features for Benchmarking Process Mining',
         author = 'Andrea Maldonado',
         author_email = '[email protected]',
@@ -80,7 +81,6 @@ setup(
             'urllib3==2.2.1',
             'zict==3.0.0'
             ],
-        packages = ['gedi'],
         classifiers=[
             'Development Status :: 3 - Alpha',      # Chose either "3 - Alpha", "4 - Beta" or "5 - Production/Stable" as the current state of your package
             'Intended Audience :: Science/Research',      # Define that your audience are developers

utils/param_keys/analyser.py

@@ -1,4 +0,0 @@
-# Analyser params
-MODEL = 'model'
-INPUT_PARAMS = 'input_params'
-PERPLEXITY = 'perplexity'