Update utils.py

utils.py

@@ -1,3 +1,4 @@
+import os
 import pandas as pd
 import numpy as np
 import warnings
@@ -6,11 +7,50 @@ from sklearn.feature_extraction.text import TfidfVectorizer, CountVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 from joblib import dump, load
 from sklearn.preprocessing import normalize
+import re
+
+def get_next_version(file_prefix, folder='RecommendationFiles/'):
+    """Find the latest version of a file and return the next version's filename."""
+    # Regular expression to match files like 'file_0001.joblib'
+    pattern = re.compile(rf"{file_prefix}_(\d+)\.joblib")
+    files = [f for f in os.listdir(folder) if pattern.match(f)]
+    
+    # Extract version numbers from matching files
+    versions = [int(pattern.match(f).group(1)) for f in files]
+    
+    # Determine the next version number
+    if versions:
+        next_version = max(versions) + 1
+    else:
+        next_version = 1  # If no versions exist, start with 1
+    
+    # Return the next version filename
+    return f"{file_prefix}_{next_version:04d}.joblib"
+
+def get_latest_version(file_prefix, folder='RecommendationFiles/'):
+    """Find the latest version of a file to load."""
+    # Regular expression to match files like 'file_0001.joblib'
+    pattern = re.compile(rf"{file_prefix}_(\d+)\.joblib")
+    files = [f for f in os.listdir(folder) if pattern.match(f)]
+    
+    # Extract version numbers from matching files
+    versions = [int(pattern.match(f).group(1)) for f in files]
+    
+    if versions:
+        latest_version = max(versions)
+        return f"{file_prefix}_{latest_version:04d}.joblib"
+    else:
+        raise FileNotFoundError(f"No versions found for {file_prefix}")
+
 
 def recomienda_tf(new_basket, cestas, productos): 
+
+    tf_matrix_file = get_latest_version('count_matrix')
+    count_vectorizer_file = get_latest_version('count_vectorizer')
+    
     # Cargar la matriz TF y el modelo
-    tf_matrix = load('count_matrix_2.joblib')
-    count = load('count_vectorizer_2.joblib')
+    tf_matrix = load(tf_matrix_file)
+    count = load(count_vectorizer_file)
                     
     # Convertir la nueva cesta en formato TF (Term Frequency)
     new_basket_str = ' '.join(new_basket)
@@ -86,5 +126,4 @@ def retroalimentacion(cestas, cesta_nueva):
     dump(tf_matrix, tf_matrix_file)
     
 
-    return None
-
+    return None