Update app.py

app.py

@@ -7,6 +7,16 @@ from dotenv import load_dotenv
 from flask import Flask, render_template, request
 import logging
 
+logging.basicConfig(
+    level=logging.DEBUG,
+    format='%(asctime)s - %(levelname)s - %(message)s',
+    datefmt='%Y-%m-%d %H:%M:%S'
+)
+
+def log_message(message):
+    """"""
+    logging.info(message)
+
 if os.getenv("HUGGINGFACE_HUB_CACHE") is None:
     load_dotenv()
 
@@ -34,23 +44,23 @@ def index():
     sentiment_count = None
 
     current_directory = os.getcwd()
-    print("Iniciando procesamiento...")
+    log_message("Iniciando procesamiento...")
 
     if request.method == "POST":
         url = request.form["url"]
         if url:
-            print("Obteniendo datos")
+            log_message("Obteniendo datos de Youtube")
             video_details = clustering.get_youtube_video_details(url, api_key)
             comments_df = clustering.get_youtube_comments(api_key, url)
-            print("Generando embeddings")
+            log_message("Generando embeddings")
             comments_df = clustering.add_normalized_embeddings_to_dataframe(
                 comments_df, "comment"
             )
-            print("Procesamiento de los datos")
+            log_message("Procesamiento de los datos")
             comments_df["published_at"] = pd.to_datetime(
                 comments_df["published_at"]
             ).dt.date
-            print("Clasificación de los sentimientos")
+            log_message("Clasificación de los sentimientos")
             comments_df = clustering.classify_sentiment_df(comments_df)
             comments_df.to_pickle(
                 "./data/Comentarios-Youtube/comments_df.pkl"
@@ -66,14 +76,14 @@ def index():
             umap_df, min_eps, max_eps = clustering.transform_embeddings(
                 comments_df, embeddings_col="embeddings"
             )
-            print("Generación de wordcloud")
+            log_message("Generación de wordcloud")
             image_path = os.path.join("static", "wordcloud.png")
             clustering.plot_wordcloud(comments_df, text_column="comment", output_filename=image_path)
 
             total = comments_df.shape[0]
-            print("Evaluación de métricas")
+            
             min_items_by_cluster = clustering.determine_min_items_by_cluster(total)
-            print("Modelado")
+            log_message("Modelado y generación de métricas")
             (
                 cluster_assignments,
                 cluster_counts,
@@ -86,7 +96,7 @@ def index():
                 threshold_values=[0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9],
                 embeddings_col="embeddings"
             )
-            print("Creación de gráfico de Sankey")
+            log_message("Creación de gráfico de Sankey")
             labels, source, target, values, comments = clustering.build_sankey_data(
                 cluster_assignments,
                 cluster_counts,