modules/module_connection.py

import numpy as np
import pandas as pd
import gradio as gr
from abc import ABC, abstractmethod

from modules.module_WordExplorer import WordExplorer
from modules.module_BiasExplorer import WordBiasExplorer

class Connector(ABC):
    def parse_word(self, word : str):
        return word.lower().strip()

    def parse_words(self, array_in_string : str):
        words = array_in_string.strip()
        if not words:
            return []
        words = [self.parse_word(word) for word in words.split(',') if word.strip() != '']
        return words

    def process_error(self, err: str):
        if err is None:
            return
        return "<center><h3>" + err + "</h3></center>"
    

class WordExplorerConnector(Connector):

    def __init__(self, **kwargs):
        if 'embedding' in kwargs:
            embedding = kwargs.get('embedding')
        else:
            raise KeyError
        self.word_explorer = WordExplorer(embedding)

    def plot_proyection_2d( self,
                            wordlist_0,
                            wordlist_1,
                            wordlist_2,
                            wordlist_3,
                            wordlist_4,
                            color_wordlist_0,
                            color_wordlist_1,
                            color_wordlist_2,
                            color_wordlist_3,
                            color_wordlist_4,
                            n_alpha,
                            fontsize,
                            n_neighbors
                            ):
        err = ""
        neighbors_method = 'sklearn'
        wordlist_0 = self.parse_words(wordlist_0)
        wordlist_1 = self.parse_words(wordlist_1)
        wordlist_2 = self.parse_words(wordlist_2)
        wordlist_3 = self.parse_words(wordlist_3)
        wordlist_4 = self.parse_words(wordlist_4)

        if not (wordlist_0 or wordlist_1 or wordlist_2 or wordlist_1 or wordlist_4):
            err = self.process_error("Ingresa al menos 1 palabras para continuar")
            return None, err
        
        err = self.word_explorer.check_oov([wordlist_0, wordlist_1, wordlist_2, wordlist_3, wordlist_4])
        if err:
            return None, self.process_error(err)

        fig = self.word_explorer.plot_projections_2d(wordlist_0,
                                                     wordlist_1,
                                                     wordlist_2,
                                                     wordlist_3,
                                                     wordlist_4,
                                                     color_wordlist_0=color_wordlist_0,
                                                     color_wordlist_1=color_wordlist_1,
                                                     color_wordlist_2=color_wordlist_2,
                                                     color_wordlist_3=color_wordlist_3,
                                                     color_wordlist_4=color_wordlist_4,
                                                     n_alpha=n_alpha,
                                                     fontsize=fontsize,
                                                     n_neighbors=n_neighbors,
                                                     nn_method = neighbors_method
                                                     )
        return fig, self.process_error(err)

class BiasWordExplorerConnector(Connector):

    def __init__(self, **kwargs):
        if 'embedding' in kwargs:
            embedding = kwargs.get('embedding')
        else:
            raise KeyError
        self.bias_word_explorer = WordBiasExplorer(embedding)

    def calculate_bias_2d(self,
                         wordlist_1,
                         wordlist_2,
                         to_diagnose_list
                         ):
        err = ""
        wordlist_1 = self.parse_words(wordlist_1)
        wordlist_2 = self.parse_words(wordlist_2)
        to_diagnose_list = self.parse_words(to_diagnose_list)

        word_lists = [wordlist_1, wordlist_2, to_diagnose_list]
        for list in word_lists:
            if not list:
                err = "Debe ingresar al menos 1 palabra en las lista de palabras a diagnosticar, sesgo 1 y sesgo 2"
        if err:
            return None, self.process_error(err)

        err = self.bias_word_explorer.check_oov(word_lists)
        if err:
            return None, self.process_error(err)

        fig = self.bias_word_explorer.plot_biased_words(to_diagnose_list, wordlist_2, wordlist_1)

        return fig, self.process_error(err)

    def calculate_bias_4d(self,
                         wordlist_1,
                         wordlist_2,
                         wordlist_3,
                         wordlist_4,
                         to_diagnose_list
                         ):
        err = ""
        wordlist_1 = self.parse_words(wordlist_1)
        wordlist_2 = self.parse_words(wordlist_2)
        wordlist_3 = self.parse_words(wordlist_3)
        wordlist_4 = self.parse_words(wordlist_4)
        to_diagnose_list = self.parse_words(to_diagnose_list)

        wordlists = [wordlist_1, wordlist_2, wordlist_3, wordlist_4, to_diagnose_list]
        for list in wordlists:
            if not list:
                err = "¡Para graficar con 4 espacios, debe ingresar al menos 1 palabra en todas las listas!"
        if err:
            return None, self.process_error(err)

        err = self.bias_word_explorer.check_oov(wordlists)
        if err:
            return None, self.process_error(err)

        fig = self.bias_word_explorer.plot_biased_words(to_diagnose_list, wordlist_1, wordlist_2, wordlist_3, wordlist_4)
        return fig, self.process_error(err)