import requests import random import time import pandas as pd import gradio as gr import numpy as np from transformers import AutoTokenizer, AutoModelForSequenceClassification from transformers import pipeline def read3(num_selected_former): fname = 'data3_convai2_inferred.txt' with open(fname, encoding='utf-8') as f: content = f.readlines() index_selected = random.randint(0,len(content)/2-1) while index_selected == num_selected_former: index_selected = random.randint(0,len(content)/2-1) text = eval(content[index_selected*2]) interpretation = eval(content[int(index_selected*2+1)]) min_len = 5 tokens = [i[0] for i in interpretation] tokens = tokens[1:-1] while len(tokens) <= min_len or '\\' in text['text'] or '//' in text['text']: index_selected = random.randint(0,len(content)/2-1) text = eval(content[int(index_selected*2)]) res_tmp = [(i, 0) for i in text['text'].split(' ')] res = {"original": text['text'], "interpretation": res_tmp} return res, index_selected def func3(num_selected, human_predict, num1, num2, user_important): chatbot = [] # num1: Human score; num2: AI score fname = 'data3_convai2_inferred.txt' with open(fname) as f: content = f.readlines() text = eval(content[int(num_selected*2)]) interpretation = eval(content[int(num_selected*2+1)]) golden_label = (text['binary_label']^1) * 100 if golden_label == 0: golden_label = int(50 * (1 - text['binary_score'])) else: golden_label = int(50 * (1 + text['binary_score'])) # (START) off-the-shelf version -- slow at the beginning # Load model directly # Use a pipeline as a high-level helper classifier = pipeline("text-classification", model="padmajabfrl/Gender-Classification") output = classifier([text['text']]) print(output) out = output[0] # (END) off-the-shelf version if out['label'] == 'Female': ai_predict = int(out['score']) else: ai_predict = 1 - int(out['score']) user_select = "You focused on " flag_select = False if user_important == "": user_select += "nothing. Interesting! " else: user_select += user_important user_select += ". " # for i in range(len(user_marks)): # if user_marks[i][1] != None and h1[i][0] not in ["P", "N"]: # flag_select = True # user_select += "'" + h1[i][0] + "'" # if i == len(h1) - 1: # user_select += ". " # else: # user_select += ", " # if not flag_select: # user_select += "nothing. Interesting! " user_select += "Wanna see how the AI made the guess? Click here. ⬅️" if abs(golden_label - human_predict) <= 20 and abs(golden_label - ai_predict) <= 20: chatbot.append(("The correct answer is " + str(golden_label) + ". Congratulations! 🎉 Both of you get the correct answer!", user_select)) num1 += 1 num2 += 1 elif abs(golden_label - human_predict) > 20 and abs(golden_label - ai_predict) > 20: chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry.. No one gets the correct answer. But nice try! 😉", user_select)) elif abs(golden_label - human_predict) <= 20 and abs(golden_label - ai_predict) > 20: chatbot.append(("The correct answer is " + str(golden_label) + ". Great! 🎉 You are closer to the answer and better than AI!", user_select)) num1 += 1 else: chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry.. AI wins in this round.", user_select)) num2 += 1 tot_scores = ''' ###

Machine   ''' + str(int(num2)) + '''   VS   ''' + str(int(num1)) + '''   Human

''' num_tmp = max(num1, num2) y_lim_upper = (int((num_tmp + 3)/10)+1) * 10 return ai_predict, chatbot, num1, num2, tot_scores def interpre3(lang_selected, num_selected): fname = 'data3_convai2_inferred.txt' with open(fname) as f: content = f.readlines() text = eval(content[int(num_selected*2)]) interpretation = eval(content[int(num_selected*2+1)]) print(interpretation) res = {"original": text['text'], "interpretation": interpretation} # pos = [] # neg = [] # res = [] # for i in interpretation: # if i[1] > 0: # pos.append(i[1]) # elif i[1] < 0: # neg.append(i[1]) # else: # continue # median_pos = np.median(pos) # median_neg = np.median(neg) # res.append(("P", "+")) # res.append(("/", None)) # res.append(("N", "-")) # res.append(("Review:", None)) # for i in interpretation: # if i[1] > median_pos: # res.append((i[0], "+")) # elif i[1] < median_neg: # res.append((i[0], "-")) # else: # res.append((i[0], None)) return res def func3_written(text_written, human_predict, lang_written): chatbot = [] # num1: Human score; num2: AI score # (START) off-the-shelf version # tokenizer = AutoTokenizer.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment") # model = AutoModelForSequenceClassification.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment") classifier = pipeline("text-classification", model="padmajabfrl/Gender-Classification") output = classifier([text_written]) # star2num = { # "5 stars": 100, # "4 stars": 75, # "3 stars": 50, # "2 stars": 25, # "1 star": 0, # } print(output) out = output[0] # (END) off-the-shelf version if out['label'] == 'Female': ai_predict = int(out['score']) else: ai_predict = 1 - int(out['score']) if abs(ai_predict - human_predict) <= 20: chatbot.append(("AI gives it a close score! 🎉", "⬅️ Feel free to try another one! ⬅️")) else: chatbot.append(("AI thinks in a different way from human. 😉", "⬅️ Feel free to try another one! ⬅️")) import shap gender_classifier = pipeline("text-classification", model="padmajabfrl/Gender-Classification", return_all_scores=True) explainer = shap.Explainer(gender_classifier) shap_values = explainer([text_written]) interpretation = list(zip(shap_values.data[0], shap_values.values[0, :, 1])) res = {"original": text_written, "interpretation": interpretation} print(res) return res, ai_predict, chatbot