cleanup

src/data_processing/selection.py

 import json
 import re
 import random
+
 import numpy as np
 
 # Define the classification thresholds
@@ -13,6 +14,7 @@ classifications = {
     "D": (0, 599),
 }
 
+
 def init_criteria():
     # Load the actions from the JSON file
     with open("../../data/raw/actions/example_actions.json") as f:
@@ -31,7 +33,8 @@ def init_criteria():
                 # Check if the regular expression matched any numeric characters
                 if rating:
                     try:
-                        likelihood = (101 - abs(int(criterion["rating"])))/100 * subcategory_likelihoods[subcategory["name"]]
+                        likelihood = (101 - abs(int(criterion["rating"]))) / 100 * subcategory_likelihoods[
+                            subcategory["name"]]
                     except KeyError:
                         likelihood = 0
                     criteria.append({"name": criterion["name"],
@@ -42,19 +45,21 @@ def init_criteria():
     # Calculate the likelihood of each action
     for criterion in criteria:
         try:
-            criterion["likelihood"] = (101 - abs(criterion["rating"]))/100 * subcategory_likelihoods[criterion["subcategory_name"]]
+            criterion["likelihood"] = (101 - abs(criterion["rating"])) / 100 * subcategory_likelihoods[
+                criterion["subcategory_name"]]
         except KeyError:
             # you can set default value for the likelihood, for example
             criterion["likelihood"] = 0
         break
     return criteria
 
+
 # Define a function that applies a random action to a given citizen
 def apply_random_action(citizen, criteria):
     # Select an action based on the likelihood
     likelihoods = [c["likelihood"] for c in criteria]
     normalizing_factor = sum(likelihoods)
-    normalized_likelihoods = [likelihood/normalizing_factor for likelihood in likelihoods]
+    normalized_likelihoods = [likelihood / normalizing_factor for likelihood in likelihoods]
     action_index = np.random.choice(len(criteria), p=normalized_likelihoods)
     action = criteria[action_index]
 
@@ -69,6 +74,7 @@ def apply_random_action(citizen, criteria):
             citizen["classification"] = classification
             break
 
+
 # Define the main function that generates synthetic data for a sample of citizens
 def generate_synthetic_data(n_citizens, max_actions):
     # Initialize a list of citizens with 100 credit score and classification "A"
@@ -83,9 +89,11 @@ def generate_synthetic_data(n_citizens, max_actions):
     # Return the list of citizens with updated credit scores, applied actions, and classifications
     return citizens
 
+
 # Generate synthetic data for 10 citizens
 citizens = generate_synthetic_data(10, 5)
 
 # Print the list of citizens with their updated credit scores, applied actions, and classifications
 for citizen in citizens:
-    print("SCORE: ", citizen["credit_score"], "| CLASS: ", citizen["classification"], "| ACTIONS: ", citizen["applied_actions"])
\ No newline at end of file
+    print("SCORE: ", citizen["credit_score"], "| CLASS: ", citizen["classification"], "| ACTIONS: ",
+          citizen["applied_actions"])