Spaces:
Runtime error
Runtime error
File size: 5,386 Bytes
62ab214 3487527 62ab214 3487527 62ab214 539c75a 62ab214 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 |
import gradio as gr
import tensorflow as tf
import numpy as np
import pickle
# Load model, including its weights and the optimizer
model = tf.keras.models.load_model('core4.h5')
# load tokenizer
with open('tokenizer.pickle', 'rb') as handle:
tokenize = pickle.load(handle)
text_labels = ['How to apply', 'how much can I get', 'who can apply']
# model.summary() # model architecture
def greet(string):
tokenizedText = tokenize.texts_to_matrix([string])
prediction = model.predict(np.array([tokenizedText[0]]))
predicted_label = text_labels[np.argmax(prediction)]
print(prediction[0][np.argmax(prediction)])
print("Predicted label: " + predicted_label + "\n")
###################
import requests as rs
import pandas as pd
spreadsheet_id = '1vjWnYsnGc0J6snT67NVbA-NWSGZ5b0eDBVHmg9lbf9s' # Please set the Spreadsheet ID.
csv_url='https://docs.google.com/spreadsheets/d/' + spreadsheet_id + '/export?format=csv&id=' + spreadsheet_id + '&gid=0'
res=rs.get(url=csv_url)
open('google.csv', 'wb').write(res.content)
df = pd.read_csv('google.csv')
import json
import requests
spreadsheet_id = '1vjWnYsnGc0J6snT67NVbA-NWSGZ5b0eDBVHmg9lbf9s' # Please set the Spreadsheet ID.
url = 'https://script.google.com/macros/s/AKfycbwXP5fsDgOXJ9biZQC293o6bTBL3kDOJ07PlmxKjabzdTej6WYdC8Yos6NpDVqAJeVM/exec?spreadsheetId=' + spreadsheet_id
body = {
"arguments": {"range": "Sheet1!A"+str(len(df)+2), "valueInputOption": "USER_ENTERED"},
"body": {"values": [[string]]}
}
res = requests.post(url, json.dumps(body), headers={'Content-Type': 'application/json'})
body = {
"arguments": {"range": "Sheet1!B"+str(len(df)+2), "valueInputOption": "USER_ENTERED"},
"body": {"values": [[predicted_label]]}
}
res = requests.post(url, json.dumps(body), headers={'Content-Type': 'application/json'})
import datetime
current_time = datetime.datetime.now()
body = {
"arguments": {"range": "Sheet1!C"+str(len(df)+2), "valueInputOption": "USER_ENTERED"},
"body": {"values": [[str(current_time)]]}
}
res = requests.post(url, json.dumps(body), headers={'Content-Type': 'application/json'})
#print(res.text)
#######################
return predicted_label
#One testing case
###################################################
import gradio as gr
from transformers import pipeline
from datetime import datetime
import pandas as pd
import requests
from bs4 import BeautifulSoup
import re
benefits = [
{"benefitName": "Universal Credit", "coreName": "what is this benefit", "link": "https://www.gov.uk/universal-credit/"},
{"benefitName": "Universal Credit", "coreName": "who can apply", "link": "https://www.gov.uk/universal-credit/eligibility"},
{"benefitName": "Universal Credit", "coreName": "how much can I get", "link": "https://www.gov.uk/universal-credit/what-youll-get,https://www.gov.uk/universal-credit/how-youre-paid"},
{"benefitName": "Universal Credit", "coreName": "How to apply", "link": "https://www.gov.uk/universal-credit/how-to-claim"}
]
def requestPage(link):
page = requests.get(link)
# print(page.text)
soup = BeautifulSoup(page.content, "html.parser")
return soup
def scrapeTable(table):
columns = [col.text.strip() for col in table.thead.tr.find_all()]
columns
rows = table.tbody.find_all(recursive=False)
clean_rows = ""
for row in rows:
elements = ["{}: {}".format(columns[index], element.text.strip()) for index, element in enumerate(row.find_all(recursive=False))]
elements = " ".join(elements)
# print(elements)
clean_rows += elements + "\n"
return clean_rows
def scrapePage(page):
# Scrape the text
corpus = ""
# starting from the main page
content = page.find('div', {"id":"guide-contents"})
title = content.find('h1', {"class":"part-title"})
title = title.text.strip()
corpus += title +"\n\n"
print(title)
content = content.find('div', {"class":"gem-c-govspeak"})
fragments = content.find_all(recursive=False)
for frag in fragments:
text= frag.text.strip()
if frag.name == 'ul':
clean = re.sub('\n+', "{;}", text)
corpus += "{;}" + clean
elif frag.name == 'table':
corpus += scrapeTable(frag)
else:
corpus += text
corpus += "\n"
# print(corpus)
return corpus
for benefit in benefits:
links = benefit['link'].split(',')
print(benefit['benefitName'], benefit['coreName'], len(links))
context = ""
for link in links:
page = requestPage(link)
context += scrapePage(page)
benefit['context'] = context
benefit['contextLen'] = len(context)
print("--------------------------------")
benefitsClasses = list(set(list(map(lambda x: x['benefitName'], benefits))))
core4Classes = list(set(list(map(lambda x: x['coreName'], benefits))))
# contexts
benefitsClasses, core4Classes
question_answerer = pipeline("question-answering")
def testQA(question):
predictedBenefit = "Universal Credit"
coreName = greet(string)
predictedCore = coreName
time = datetime.now()
context = list(filter(lambda x: x['benefitName']==predictedBenefit and x['coreName']==predictedCore, benefits))[0]
answer = question_answerer(question = question, context = context['context'])['answer']
time3 = (datetime.now() - time).total_seconds()
return coreName + ': ' + answer
iface = gr.Interface(fn=testQA, inputs="text", outputs="text")
iface.launch()
|