Spaces:
Running
Running
| import gradio as gr | |
| from datetime import date | |
| import csv | |
| import datetime | |
| import json | |
| import smtplib | |
| import requests | |
| from email.mime.text import MIMEText | |
| from transformers import AutoTokenizer, AutoModelWithLMHead | |
| import gc | |
| import os | |
| import re as r | |
| from urllib.request import urlopen | |
| import huggingface_hub | |
| from huggingface_hub import Repository | |
| import json | |
| import numpy as np | |
| from tqdm import trange | |
| import torch | |
| import torch.nn.functional as F | |
| # from bert_ner_model_loader import biobert_model | |
| from biobert_utils import * | |
| import pandas as pd | |
| import nltk | |
| nltk.download('punkt') | |
| cwd = os.getcwd() | |
| bio_bert_ner_model = os.path.join(cwd) | |
| Entities_Found =[] | |
| Entity_Types = [] | |
| k = 0 | |
| input_value = "This expression of NT-3 in supporting cells in embryos and neonates may even preserve in Brn3c null mutants the numerous spiral sensory neurons in the apex of 8-day old animals." | |
| HF_TOKEN = os.environ.get("HF_TOKEN") | |
| DATASET_NAME = "biobert_based_ner_dataset" | |
| DATASET_REPO_URL = f"https://huggingface.co/datasets/pragnakalp/{DATASET_NAME}" | |
| DATA_FILENAME = "biobert_base_ner_logs.csv" | |
| DATA_FILE = os.path.join("biobert_base_ner_logs", DATA_FILENAME) | |
| DATASET_REPO_ID = "pragnakalp/biobert_based_ner_dataset" | |
| print("is none?", HF_TOKEN is None) | |
| try: | |
| hf_hub_download( | |
| repo_id=DATASET_REPO_ID, | |
| filename=DATA_FILENAME, | |
| cache_dir=DATA_DIRNAME, | |
| force_filename=DATA_FILENAME | |
| ) | |
| except: | |
| print("file not found") | |
| repo = Repository( | |
| local_dir="biobert_base_ner_logs", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN | |
| ) | |
| def getIP(): | |
| ip_address = '' | |
| try: | |
| d = str(urlopen('http://checkip.dyndns.com/') | |
| .read()) | |
| return r.compile(r'Address: (\d+\.\d+\.\d+\.\d+)').search(d).group(1) | |
| except Exception as e: | |
| print("Error while getting IP address -->",e) | |
| return ip_address | |
| def get_location(ip_addr): | |
| location = {} | |
| try: | |
| ip=ip_addr | |
| req_data={ | |
| "ip":ip, | |
| "token":"pkml123" | |
| } | |
| url = "https://demos.pragnakalp.com/get-ip-location" | |
| # req_data=json.dumps(req_data) | |
| # print("req_data",req_data) | |
| headers = {'Content-Type': 'application/json'} | |
| response = requests.request("POST", url, headers=headers, data=json.dumps(req_data)) | |
| response = response.json() | |
| print("response======>>",response) | |
| return response | |
| except Exception as e: | |
| print("Error while getting location -->",e) | |
| return location | |
| def generate_emotion(article): | |
| if article.strip(): | |
| Entities_Found.clear() | |
| Entity_Types.clear() | |
| text = "Input sentence: " | |
| text += article | |
| biobert_model = BIOBERT_Ner(bio_bert_ner_model) | |
| output = biobert_model.predict(text) | |
| print(output) | |
| k = 0 | |
| for i in output: | |
| for j in i: | |
| if k == 0: | |
| Entities_Found.append(j) | |
| k += 1 | |
| else: | |
| Entity_Types.append(j) | |
| k = 0 | |
| result = {'Entities Found':Entities_Found, 'Entity Types':Entity_Types} | |
| save_data_and_sendmail(article,output) | |
| return pd.DataFrame(result) | |
| else: | |
| raise gr.Error("Please enter text in inputbox!!!!") | |
| def save_data_and_sendmail(article,output): | |
| try: | |
| print("welcome") | |
| ip_address = '' | |
| ip_address= getIP() | |
| print(ip_address) | |
| location = get_location(ip_address) | |
| print(location) | |
| add_csv = [article,output,ip_address,location] | |
| with open(DATA_FILE, "a") as f: | |
| writer = csv.writer(f) | |
| # write the data | |
| writer.writerow(add_csv) | |
| commit_url = repo.push_to_hub() | |
| print("commit data :",commit_url) | |
| url = 'https://pragnakalpdev33.pythonanywhere.com/HF_space_biobert_base_ner' | |
| myobj = {'article': article,'gen_text':output,'ip_addr':ip_address,"location":location} | |
| x = requests.post(url, json = myobj) | |
| return "Successfully save data" | |
| except Exception as e: | |
| print("error") | |
| return "Error while sending mail" + str(e) | |
| inputs=gr.Textbox(lines=3, label="Input Text",elem_id="inp_div",value=input_value) | |
| outputs = [gr.Dataframe(row_count = (2, "dynamic"), col_count=(2, "fixed"), label="Entity Recognition For Input Text", headers=["Word","Entities found"],wrap=True)] | |
| demo = gr.Interface( | |
| generate_emotion, | |
| inputs, | |
| outputs, | |
| title="Named Entity Recognition Using BIOBERT", | |
| css=".gradio-container {background-color: lightgray} #inp_div {background-color: [#7](https://www1.example.com/issues/7)FB3D5;", | |
| article = """<p style='text-align: center;'>Feel free to give us your <a href="https://www.pragnakalp.com/contact/" target="_blank">feedback</a> on this NER demo. | |
| For all your Named Entity Recognition related requirements, we are here to help you. Email us your requirement at | |
| <a href="mailto:letstalk@pragnakalp.com" target="_blank">letstalk@pragnakalp.com</a> And don't forget to check out more interesting | |
| <a href="https://www.pragnakalp.com/services/natural-language-processing-services/" target="_blank">NLP services</a> we are offering.</p> | |
| <p style='text-align: center;'>Developed by: <a href="https://www.pragnakalp.com" target="_blank">Pragnakalp Techlabs</a></p>""" | |
| ) | |
| demo.launch() |