app.py

import os

import pandas as pd
import plotly.io as pio
import clustering
from dotenv import load_dotenv
from flask import Flask, render_template, request
import logging

logging.basicConfig(
    level=logging.INFO,
    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()

api_key = os.getenv("youtube_api_key")

app = Flask(__name__)
app.logger.setLevel(logging.ERROR)
app.config["PROPAGATE_EXCEPTIONS"] = False

RANDOM_STATE = 333


def convert_graph_to_html(graph, full_html=False):
    return pio.to_html(graph, full_html=full_html) if graph else None


@app.route("/", methods=["GET", "POST"])
def index():
    video_details = None
    sankey_graph = None
    scores_graph = None
    image_path = None
    sentiment_daily_graph = None
    sentiment_count = None
    error_message = None

    current_directory = os.getcwd()
    log_message("Iniciando procesamiento...")

    if request.method == "POST":
        url = request.form.get("url")  # Utiliza get para evitar KeyError
        if not url:
            error_message = "La URL es requerida."
            return render_template("index.html", error_message=error_message)

        log_message("Obteniendo datos de Youtube")
        video_details = clustering.get_youtube_video_details(url, api_key)
        if "error" in video_details:  # Manejo de error al obtener detalles del video
            error_message = video_details["error"]
            return render_template("index.html", error_message=error_message)

        comments_df = clustering.get_youtube_comments(api_key, url)
        if comments_df is None:  # Verifica si no hay comentarios
            error_message = "No se pudieron obtener comentarios."
            return render_template("index.html", error_message=error_message)

        log_message("Generando embeddings")
        comments_df = clustering.add_normalized_embeddings_to_dataframe(comments_df, "comment")
        
        log_message("Procesamiento de los datos")
        comments_df["published_at"] = pd.to_datetime(comments_df["published_at"]).dt.date
        
        log_message("Clasificación de los sentimientos")
        comments_df = clustering.classify_sentiment_df(comments_df)
        comments_df.to_pickle("./data/Comentarios-Youtube/comments_df.pkl")
        
        sentiment_count = comments_df["sentimiento"].value_counts().to_dict()
        sentiment_daily_graph = clustering.plot_sentiment_daily(comments_df)
        sentiment_daily_graph = convert_graph_to_html(sentiment_daily_graph)

        umap_df, min_eps, max_eps = clustering.transform_embeddings(comments_df, embeddings_col="embeddings")

        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]
        min_items_by_cluster = clustering.determine_min_items_by_cluster(total)

        log_message("Modelado y generación de métricas")
        (cluster_assignments, cluster_counts, calinski_harabasz_scores, silhouette_scores, most_similar_comments, umap_df) = clustering.perform_clustering(
            umap_df, min_eps, max_eps, n=10, embeddings_col="embeddings"
        )

        log_message(f"Clusters assignments {cluster_assignments}")
        log_message("Creación de gráfico de Sankey")
        labels, source, target, values, comments = clustering.build_sankey_data(
            cluster_assignments, cluster_counts, most_similar_comments, min_items_by_cluster=min_items_by_cluster
        )

        sankey_graph = clustering.plot_sankey(labels, source, target, values, comments, height=1000, width=1200)
        sankey_graph = convert_graph_to_html(sankey_graph)

        scores_graph, _ = clustering.plot_clustering_metric(silhouette_scores, calinski_harabasz_scores)
        scores_graph = convert_graph_to_html(scores_graph)

    return render_template(
        "index.html",
        video_details=video_details,
        sankey_graph=sankey_graph,
        scores_graph=scores_graph,
        wordcloud_path=image_path,
        sentiment_daily_graph=sentiment_daily_graph,
        sentiment_count=sentiment_count,
        error_message=error_message,  # Incluye el mensaje de error si existe
    )

#  gunicorn -b 0.0.0.0:5000 app_clustering.app:app
# http://172.20.0.2:5000/
# http://0.0.0.0:5000/
if __name__ == "__main__":
    app.run(host='0.0.0.0', port=7860)