JRQi's picture
Update game1.py
706d8ee
raw
history blame
14.7 kB
import requests
import random
import time
import pandas as pd
import gradio as gr
import numpy as np
def read1(lang, num_selected_former):
if lang in ['en']:
fname = 'data1_en.txt'
else:
fname = 'data1_nl_10.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)])
if lang == 'en':
min_len = 4
else:
min_len = 2
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}
# res_empty = {"original": "", "interpretation": []}
# res = []
# res.append(("P", "+"))
# res.append(("/", None))
# res.append(("N", "-"))
# res.append(("Review:", None))
# for i in text['text'].split(' '):
# res.append((i, None))
# res_empty = None
# checkbox_update = gr.CheckboxGroup.update(choices=tokens, value=None)
return res, lang, index_selected
def read1_written(lang):
if lang in ['en']:
fname = 'data1_en.txt'
else:
fname = 'data1_nl_10.txt'
with open(fname, encoding='utf-8') as f:
content = f.readlines()
index_selected = random.randint(0,len(content)/2-1)
text = eval(content[index_selected*2])
if lang == 'en':
min_len = 4
else:
min_len = 2
while (len(text['text'].split(' '))) <= min_len or '\\' in text['text'] or '//' in text['text']:
# while (len(text['text'].split(' '))) <= min_len:
index_selected = random.randint(0,len(content)/2-1)
text = eval(content[int(index_selected*2)])
# interpretation = [(i, 0) for i in text['text'].split(' ')]
# res = {"original": text['text'], "interpretation": interpretation}
# print(res)
return text['text']
def func1(lang_selected, num_selected, human_predict, num1, num2, user_important):
chatbot = []
# num1: Human score; num2: AI score
if lang_selected in ['en']:
fname = 'data1_en.txt'
else:
fname = 'data1_nl_10.txt'
with open(fname) as f:
content = f.readlines()
text = eval(content[int(num_selected*2)])
interpretation = eval(content[int(num_selected*2+1)])
if lang_selected in ['en']:
golden_label = text['label'] * 25
else:
golden_label = text['label'] * 100
'''
# (START) API version -- quick
API_URL = "https://api-inference.huggingface.co/models/nlptown/bert-base-multilingual-uncased-sentiment"
# API_URL = "https://api-inference.huggingface.co/models/cmarkea/distilcamembert-base-sentiment"
headers = {"Authorization": "Bearer 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"}
response = requests.post(API_URL, headers=headers, json=text['text'])
output = response.json()
# result = dict()
star2num = {
"5 stars": 100,
"4 stars": 75,
"3 stars": 50,
"2 stars": 25,
"1 star": 0,
}
print(output)
out = output[0][0]
# (END) API version
'''
# (START) off-the-shelf version -- slow at the beginning
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification
tokenizer = AutoTokenizer.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
model = AutoModelForSequenceClassification.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
# Use a pipeline as a high-level helper
from transformers import pipeline
classifier = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
output = classifier([text['text']])
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
ai_predict = star2num[out['label']]
# result[label] = 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 lang_selected in ['en']:
if ai_predict == golden_label:
if abs(human_predict - golden_label) < 12.5: # Both correct
golden_label = int((human_predict + ai_predict) / 2)
chatbot.append(("The correct answer is " + str(golden_label) + ". Congratulations! 🎉 Both of you get the correct answer!", user_select))
num1 += 1
num2 += 1
else:
golden_label += random.randint(-2, 2)
while golden_label > 100 or golden_label < 0 or golden_label % 25 == 0:
golden_label += random.randint(-2, 2)
chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry.. AI wins in this round.", user_select))
num2 += 1
else:
if abs(human_predict - golden_label) < abs(ai_predict - golden_label):
if abs(human_predict - golden_label) < 12.5:
golden_label = int((golden_label + human_predict) / 2)
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) + ". Both wrong... Maybe next time you'll win!", user_select))
else:
chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry.. No one gets the correct answer. But nice try! 😉", user_select))
else:
if golden_label == 100:
if ai_predict > 50 and human_predict > 50:
golden_label = int((human_predict + ai_predict)/2) + random.randint(-10, 10)
while golden_label > 100:
golden_label = int((human_predict + ai_predict)/2) + random.randint(-10, 10)
ai_predict = int((golden_label + ai_predict) / 2)
chatbot.append(("The correct answer is " + str(golden_label) + ". Congratulations! 🎉 Both of you get the correct answer!", user_select))
num1 += 1
num2 += 1
elif ai_predict > 50 and human_predict <= 50:
golden_label -= random.randint(0, 10)
ai_predict = 90 + random.randint(-5, 5)
chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry.. AI wins in this round.", user_select))
num2 += 1
elif ai_predict <= 50 and human_predict > 50:
golden_label = human_predict + random.randint(-4, 4)
while golden_label > 100:
golden_label = human_predict + random.randint(-4, 4)
chatbot.append(("The correct answer is " + str(golden_label) + ". Great! 🎉 You are close to the answer and better than AI!", user_select))
num1 += 1
else:
chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry... No one gets the correct answer. But nice try! 😉", user_select))
else:
if ai_predict < 50 and human_predict < 50:
golden_label = int((human_predict + ai_predict)/2) + random.randint(-10, 10)
while golden_label < 0:
golden_label = int((human_predict + ai_predict)/2) + random.randint(-10, 10)
ai_predict = int((golden_label + ai_predict) / 2)
chatbot.append(("The correct answer is " + str(golden_label) + ". Congratulations! 🎉 Both of you get the correct answer!", user_select))
num1 += 1
num2 += 1
elif ai_predict < 50 and human_predict >= 50:
golden_label += random.randint(0, 10)
ai_predict = 10 + random.randint(-5, 5)
chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry.. AI wins in this round.", user_select))
num2 += 1
elif ai_predict >= 50 and human_predict < 50:
golden_label = human_predict + random.randint(-4, 4)
while golden_label < 0:
golden_label = human_predict + random.randint(-4, 4)
chatbot.append(("The correct answer is " + str(golden_label) + ". Great! 🎉 You are close to the answer and better than AI!", user_select))
num1 += 1
else:
chatbot.append(("The correct answer is " + str(golden_label) + ". Sorry... No one gets the correct answer. But nice try! 😉", user_select))
# data = pd.DataFrame(
# {
# "Role": ["AI 🤖", "HUMAN 👨👩"],
# "Scores": [num2, num1],
# }
# )
# scroe_human = ''' # Human: ''' + str(int(num1))
# scroe_robot = ''' # Robot: ''' + str(int(num2))
tot_scores = ''' ### <p style="text-align: center;"> Machine &ensp; ''' + str(int(num2)) + ''' &ensp; VS &ensp; ''' + str(int(num1)) + ''' &ensp; Human </p>'''
num_tmp = max(num1, num2)
y_lim_upper = (int((num_tmp + 3)/10)+1) * 10
# figure = gr.BarPlot.update(
# data,
# x="Role",
# y="Scores",
# color="Role",
# vertical=False,
# y_lim=[0,y_lim_upper],
# color_legend_position='none',
# height=250,
# width=500,
# show_label=False,
# container=False,
# )
# tooltip=["Role", "Scores"],
return ai_predict, chatbot, num1, num2, tot_scores
def interpre1(lang_selected, num_selected):
if lang_selected in ['en']:
fname = 'data1_en.txt'
else:
fname = 'data1_nl_10.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 func1_written(text_written, human_predict, lang_written):
chatbot = []
# num1: Human score; num2: AI score
'''
# (START) API version
API_URL = "https://api-inference.huggingface.co/models/nlptown/bert-base-multilingual-uncased-sentiment"
# API_URL = "https://api-inference.huggingface.co/models/cmarkea/distilcamembert-base-sentiment"
headers = {"Authorization": "Bearer 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"}
response = requests.post(API_URL, headers=headers, json=text_written)
output = response.json()
# result = dict()
star2num = {
"5 stars": 100,
"4 stars": 75,
"3 stars": 50,
"2 stars": 25,
"1 star": 0,
}
out = output[0][0]
# (END) API version
'''
# (START) off-the-shelf version
from transformers import AutoTokenizer, AutoModelForSequenceClassification
from transformers import pipeline
# tokenizer = AutoTokenizer.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
# model = AutoModelForSequenceClassification.from_pretrained("nlptown/bert-base-multilingual-uncased-sentiment")
classifier = pipeline("sentiment-analysis", model="nlptown/bert-base-multilingual-uncased-sentiment")
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
ai_predict = star2num[out['label']]
# result[label] = out['score']
if abs(ai_predict - human_predict) <= 12.5:
chatbot.append(("AI gives it a close score! 🎉", "⬅️ Feel free to try another one! ⬅️"))
else:
ai_predict += random.randint(-2, 2)
while ai_predict > 100 or ai_predict < 0 or ai_predict % 25 == 0:
ai_predict += random.randint(-2, 2)
chatbot.append(("AI thinks in a different way from human. 😉", "⬅️ Feel free to try another one! ⬅️"))
import shap
# sentiment_classifier = pipeline("text-classification", return_all_scores=True)
if lang_written == "Dutch":
sentiment_classifier = pipeline("text-classification", model='DTAI-KULeuven/robbert-v2-dutch-sentiment', return_all_scores=True)
else:
sentiment_classifier = pipeline("text-classification", model='distilbert-base-uncased-finetuned-sst-2-english', return_all_scores=True)
explainer = shap.Explainer(sentiment_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