app.py

# import all packages
import requests
import streamlit as st
from sklearn.model_selection import StratifiedKFold
from sklearn.model_selection import train_test_split
from sklearn.model_selection import KFold
# tokenizer
from transformers import AutoTokenizer, DistilBertTokenizerFast
# sequence tagging model + training-related 
from transformers import DistilBertForTokenClassification, Trainer, TrainingArguments
import numpy as np
import pandas as pd
import torch
import json
import sys
import os
from sklearn.metrics import classification_report
from pandas import read_csv
from sklearn.linear_model import LogisticRegression
import sklearn.model_selection
from sklearn.feature_extraction.text import TfidfTransformer
from sklearn.feature_extraction.text import CountVectorizer
from sklearn.pipeline import Pipeline, FeatureUnion
import math
from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_recall_fscore_support
from sklearn.model_selection import train_test_split
import json
import re
import numpy as np 
import pandas as pd
import re
import nltk
nltk.download("punkt")
import string
from sklearn.model_selection import train_test_split
from transformers import AutoTokenizer, Trainer, TrainingArguments, AutoModelForSequenceClassification, AutoConfig
import torch
from torch.utils.data import TensorDataset, DataLoader, RandomSampler, SequentialSampler
import itertools
import json
import glob
from transformers import TextClassificationPipeline, TFAutoModelForSequenceClassification, AutoTokenizer
from transformers import pipeline
import pickle
import urllib.request  
import csv
import pdfplumber
import pathlib 
import shutil
import webbrowser
from streamlit.components.v1 import html
import streamlit.components.v1 as components
from PyPDF2 import PdfReader
from huggingface_hub import HfApi
import io
from datasets import load_dataset

import huggingface_hub
from huggingface_hub import Repository
from datetime import datetime
import pathlib as Path


DATASET_REPO_URL = "https://huggingface.co/datasets/Seetha/visual_files/raw/main"
DATA_FILENAME = "level2.json"
DATA_FILE = os.path.join(DATASET_REPO_URL, DATA_FILENAME)

feedback_file = Path("https://huggingface.co/datasets/Seetha/visual_files/") / f"level2.json"
st.write(feedback_file)

HF_TOKEN = os.environ.get("HF_TOKEN")

# repo = Repository(
#     local_dir="huggingface-hub", clone_from=DATASET_REPO_URL, use_auth_token=HF_TOKEN
# )
#dataset = load_dataset('Seetha/visual_files')

# print("is none?", HF_TOKEN is None)

# print("hfh", huggingface_hub.__version__)


def main():

  st.title("Text to Causal Knowledge Graph")
  st.sidebar.title("Please upload your text documents in one file here:")
  k=2
  seed = 1
  k1= 5
  text_list = []
  causal_sents = []

  uploaded_file = None
  try:
      uploaded_file = st.sidebar.file_uploader("Choose a file", type = "pdf")
  except:
      uploaded_file = PdfReader('sample_anno.pdf')
      st.error("Please upload your own PDF to be analyzed")

  if uploaded_file is not None:
    reader = PdfReader(uploaded_file)
    for page in reader.pages:
      text = page.extract_text()
      text_list.append(text)
  else:
     st.error("Please upload your own PDF to be analyzed")
     st.stop()
      
  text_list_final = [x.replace('\n', '') for x in text_list]
  text_list_final = re.sub('"', '', str(text_list_final))
  
  sentences = nltk.sent_tokenize(text_list_final)
  
  result =[]
  for i in sentences:
    result1 = i.lower()
    result2 = re.sub(r'[^\w\s]','',result1)
    result.append(result2)
    
  tokenizer = AutoTokenizer.from_pretrained("bert-base-uncased") #bert-base-uncased
  
  model_path = "checkpoint-2850"
  
  model = AutoModelForSequenceClassification.from_pretrained(model_path,id2label={0:'non-causal',1:'causal'})

  pipe1 = pipeline("text-classification", model=model,tokenizer=tokenizer)
  for sent in result:
    pred = pipe1(sent)
    for lab in pred:
        if lab['label'] == 'causal': #causal
            causal_sents.append(sent)

  model_name = "distilbert-base-cased"
  tokenizer = DistilBertTokenizerFast.from_pretrained(model_name)
  
  
  
  model_path1 = "DistilBertforTokenclassification"
  
  model = DistilBertForTokenClassification.from_pretrained(model_path1) #len(unique_tags),, num_labels= 7, , id2label={0:'CT',1:'E',2:'C',3:'O'}
  pipe = pipeline('ner', model=model, tokenizer=tokenizer,aggregation_strategy='simple') #grouped_entities=True

  sentence_pred = []
  class_list = []
  entity_list = []
  for k in causal_sents:
    pred= pipe(k)
    #st.write(pred)
    for i in pred:
      
      sentence_pred.append(k)
      class_list.append(i['word'])
      entity_list.append(i['entity_group'])
  
  filename = 'Checkpoint-classification.sav'
  loaded_model = pickle.load(open(filename, 'rb'))
  loaded_vectorizer = pickle.load(open('vectorizefile_classification.pickle', 'rb'))

  pipeline_test_output = loaded_vectorizer.transform(class_list)
  predicted = loaded_model.predict(pipeline_test_output)
  pred1 = predicted
  level0 = []
  count =0
  for i in predicted:
    if i == 3:
      level0.append('Non-Performance')
      count +=1
    else:
      level0.append('Performance')
      count +=1

  list_pred = {0: 'Customers',1:'Employees',2:'Investors',3:'Non-performance',4:'Society',5:'Unclassified'}
  pred_val = [list_pred[i] for i in pred1]

  #print('count',count)
  for ind,(sent,preds) in enumerate(zip(class_list,pred_val)):
      if 'customers' in sent or 'client' in sent or 'consumer' in sent or 'user' in sent:
          pred_val[ind] = 'Customers'
      elif 'investor' in sent or 'finance' in sent or 'shareholder' in sent or 'stockholder' in sent or 'owners' in sent:
          pred_val[ind] = 'Investors'
      elif 'employee' in sent or 'worker' in sent or 'staff' in sent:
          pred_val[ind] = 'Employees'
      elif 'society' in sent or 'societal' in sent or 'social responsib*' in sent or 'social performance' in sent or 'community' in sent:
          pred_val[ind] = 'Society'

  sent_id, unique = pd.factorize(sentence_pred)

  final_list = pd.DataFrame(
      {'Id': sent_id,
       'Fullsentence': sentence_pred,
       'Component': class_list,
       'causeOrEffect': entity_list,
       'Labellevel1': level0,
       'Labellevel2': pred_val
      })
  s = final_list['Component'].shift(-1)
  m = s.str.startswith('##', na=False)
  final_list.loc[m, 'Component'] += (' ' + s[m])


  final_list1 = final_list[~final_list['Component'].astype(str).str.startswith('##')]
  
  li = []
  uni = final_list1['Id'].unique()
  for i in uni:
    df_new = final_list1[final_list1['Id'] == i]
    uni1 = df_new['Id'].unique()
    if 'E' not in df_new.values:
      li.append(uni1)
  out = np.concatenate(li).ravel()
  li_pan = pd.DataFrame(out,columns=['Id'])
  df3 = pd.merge(final_list1, li_pan[['Id']], on='Id', how='left', indicator=True) \
              .query("_merge == 'left_only'") \
              .drop("_merge",axis=1) 
  
  #df = df3.groupby(['Id','Fullsentence','causeOrEffect', 'Labellevel1', 'Labellevel2'])['Component'].apply(', '.join).reset_index()
  #st.write(df)

  #df = df3
  df3["causeOrEffect"].replace({"C": "cause", "E": "effect"}, inplace=True)
  df_final = df3[df3['causeOrEffect'] != 'CT'] 
  df3['New string'] = df_final['Component'].replace(r'[##]+', ' ', regex=True)

  df_final = df_final.drop("Component",axis=1)
  df_final.insert(2, "Component", df3['New string'], True)

  df_final1 = df_final[df_final['Component'].str.split().str.len().gt(1)]
    #st.write(df_final[df_final['Component'].str.len() != 1])
  #df_final1.to_csv('predictions.csv')
  
#   buffer = io.BytesIO()
#   with pd.ExcelWriter(buffer, engine="xlsxwriter") as writer:
#     df_final.to_excel(writer, sheet_name="Sheet1", index=False)
#     writer.close()
  
  count_NP_NP = 0
  count_NP_investor = 0
  count_NP_customer = 0
  count_NP_employees = 0
  count_NP_society = 0

  count_inv_np = 0
  count_inv_investor = 0
  count_inv_customer = 0
  count_inv_employee = 0
  count_inv_society = 0

  count_cus_np = 0
  count_cus_investor = 0
  count_cus_customer = 0
  count_cus_employee = 0
  count_cus_society = 0

  count_emp_np = 0
  count_emp_investor = 0
  count_emp_customer = 0
  count_emp_employee = 0
  count_emp_society = 0

  count_soc_np = 0
  count_soc_investor = 0
  count_soc_customer = 0
  count_soc_employee = 0
  count_soc_society = 0
  for i in range(0,df_final['Id'].max()):
    j = df_final.loc[df_final['Id'] == i]
    cause_tab = j.loc[j['causeOrEffect'] == 'cause']
    effect_tab = j.loc[j['causeOrEffect'] == 'effect']
    cause_coun_NP = (cause_tab.Labellevel2 == 'Non-performance').sum()
    effect_coun_NP = (effect_tab.Labellevel2 == 'Non-performance').sum()

    if (cause_coun_NP > 0) and (effect_coun_NP > 0):
        count_NP = cause_coun_NP if cause_coun_NP >= effect_coun_NP else effect_coun_NP
    else:
        count_NP = 0
    effect_NP_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_NP > 0) and (effect_NP_inv > 0):
        count_NP_inv = cause_coun_NP if cause_coun_NP >= effect_NP_inv else effect_NP_inv
    else:
        count_NP_inv = 0
    effect_NP_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_NP > 0) and (effect_NP_cus > 0):
        count_NP_cus = cause_coun_NP if cause_coun_NP >= effect_NP_cus else effect_NP_cus
    else:
        count_NP_cus = 0
    effect_NP_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_NP > 0) and (effect_NP_emp > 0):
        count_NP_emp = cause_coun_NP if cause_coun_NP >= effect_NP_emp else effect_NP_emp
    else:
        count_NP_emp = 0
    effect_NP_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_NP > 0) and (effect_NP_soc > 0):
        count_NP_soc = cause_coun_NP if cause_coun_NP >= effect_NP_soc else effect_NP_soc
    else:
        count_NP_soc = 0

    cause_coun_inv = (cause_tab.Labellevel2 == 'Investors').sum()
    effect_coun_inv = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_inv > 0) and (effect_coun_inv > 0):
        count_NP_inv = cause_coun_inv if cause_coun_inv >= effect_coun_inv else effect_coun_inv
    else:
        count_NP_inv = 0

    effect_inv_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_inv > 0) and (effect_inv_inv > 0):
        count_inv_inv = cause_coun_inv if cause_coun_inv >= effect_inv_inv else effect_inv_inv
    else:
        count_inv_inv = 0
    effect_inv_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_inv > 0) and (effect_inv_cus > 0):
        count_inv_cus = cause_coun_inv if cause_coun_inv >= effect_inv_cus else effect_inv_cus
    else:
        count_inv_cus = 0
    effect_inv_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_inv > 0) and (effect_inv_emp > 0):
        count_inv_emp = cause_coun_inv if cause_coun_inv >= effect_inv_emp else effect_inv_emp
    else:
        count_inv_emp = 0

    effect_inv_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_inv > 0) and (effect_inv_soc > 0):
        count_inv_soc = cause_coun_inv if cause_coun_inv >= effect_inv_soc else effect_inv_soc
    else:
        count_inv_soc = 0

    cause_coun_cus = (cause_tab.Labellevel2 == 'Customers').sum()
    effect_coun_cus = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_cus > 0) and (effect_coun_cus > 0):
        count_NP_cus = cause_coun_cus if cause_coun_cus >= effect_coun_cus else effect_coun_cus
    else:
        count_NP_cus = 0

    effect_cus_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_cus > 0) and (effect_cus_inv > 0):
        count_cus_inv = cause_coun_cus if cause_coun_cus >= effect_cus_inv else effect_cus_inv
    else:
        count_cus_inv = 0

    effect_cus_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_cus > 0) and (effect_cus_cus > 0):
        count_cus_cus = cause_coun_cus if cause_coun_cus >= effect_cus_cus else effect_cus_cus
    else:
        count_cus_cus = 0

    effect_cus_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_cus > 0) and (effect_cus_emp > 0):
        count_cus_emp = cause_coun_cus if cause_coun_cus >= effect_cus_emp else effect_cus_emp
    else:
        count_cus_emp = 0

    effect_cus_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_cus > 0) and (effect_cus_soc > 0):
        count_cus_soc = cause_coun_cus if cause_coun_cus >= effect_cus_soc else effect_cus_soc
    else:
        count_cus_soc = 0

    cause_coun_emp = (cause_tab.Labellevel2 == 'Employees').sum()
    effect_coun_emp = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_emp > 0) and (effect_coun_emp > 0):
        count_NP_emp = cause_coun_emp if cause_coun_emp >= effect_coun_emp else effect_coun_emp
    else:
        count_NP_emp = 0

    effect_emp_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_emp > 0) and (effect_emp_inv > 0):
        count_emp_inv = cause_coun_emp if cause_coun_emp >= effect_emp_inv else effect_emp_inv
    else:
        count_emp_inv = 0

    effect_emp_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_emp > 0) and (effect_emp_cus > 0):
        count_emp_cus = cause_coun_emp if cause_coun_emp >= effect_emp_cus else effect_emp_cus
    else:
        count_emp_cus = 0

    effect_emp_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_emp > 0) and (effect_emp_emp > 0):
        count_emp_emp = cause_coun_emp if cause_coun_emp >= effect_emp_emp else effect_emp_emp
    else:
        count_emp_emp = 0

    effect_emp_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_emp > 0) and (effect_emp_soc > 0):
        count_emp_soc = cause_coun_emp if cause_coun_emp >= effect_emp_soc else effect_emp_soc
    else:
        count_emp_soc = 0

    cause_coun_soc = (cause_tab.Labellevel2 == 'Society').sum()
    effect_coun_soc = (effect_tab.Labellevel2 == 'Non-performance').sum()
    if (cause_coun_soc > 0) and (effect_coun_soc > 0):
        count_NP_soc = cause_coun_soc if cause_coun_soc >= effect_coun_soc else effect_coun_soc
    else:
        count_NP_soc = 0

    effect_soc_inv = (effect_tab.Labellevel2 == 'Investors').sum()
    if (cause_coun_soc > 0) and (effect_soc_inv > 0):
        count_soc_inv = cause_coun_soc if cause_coun_soc >= effect_soc_inv else effect_soc_inv
    else:
        count_soc_inv = 0

    effect_soc_cus = (effect_tab.Labellevel2 == 'Customers').sum()
    if (cause_coun_soc > 0) and (effect_soc_cus > 0):
        count_soc_cus = cause_coun_soc if cause_coun_soc >= effect_soc_cus else effect_soc_cus
    else:
        count_soc_cus = 0

    effect_soc_emp = (effect_tab.Labellevel2 == 'Employees').sum()
    if (cause_coun_soc > 0) and (effect_soc_emp > 0):
        count_soc_emp = cause_coun_soc if cause_coun_soc >= effect_soc_emp else effect_soc_emp
    else:
        count_soc_emp = 0

    effect_soc_soc = (effect_tab.Labellevel2 == 'Society').sum()
    if (cause_coun_soc > 0) and (effect_soc_soc > 0):
        count_soc_soc = cause_coun_soc if cause_coun_soc >= effect_soc_soc else effect_soc_soc
    else:
        count_soc_soc = 0

    count_NP_NP = count_NP_NP + count_NP
    count_NP_investor = count_NP_investor + count_NP_inv
    count_NP_customer = count_NP_customer + count_NP_cus
    count_NP_employees = count_NP_employees + count_NP_emp
    count_NP_society = count_NP_society + count_NP_soc

    count_inv_np = count_inv_np + count_NP_inv
    count_inv_investor = count_inv_investor + count_inv_inv
    count_inv_customer = count_inv_customer + count_inv_cus
    count_inv_employee = count_inv_employee + count_inv_emp
    count_inv_society = count_inv_society + count_inv_soc

    count_cus_np = count_cus_np + count_NP_cus
    count_cus_investor = count_cus_investor + count_cus_inv
    count_cus_customer = count_cus_customer + count_cus_cus
    count_cus_employee = count_cus_employee + count_cus_emp
    count_cus_society = count_cus_society + count_cus_soc

    count_emp_np = count_emp_np + count_NP_emp
    count_emp_investor = count_emp_investor + count_emp_inv
    count_emp_customer = count_emp_customer + count_emp_cus
    count_emp_employee = count_emp_employee + count_emp_emp
    count_emp_society = count_emp_society + count_emp_soc

    count_soc_np = count_soc_np + count_NP_soc
    count_soc_investor = count_soc_investor + count_soc_inv
    count_soc_customer = count_soc_customer + count_soc_cus
    count_soc_employee = count_soc_employee + count_soc_emp
    count_soc_society = count_soc_society + count_soc_soc
    
    df_tab = pd.DataFrame(columns = ['Non-performance', 'Investors', 'Customers', 'Employees', 'Society'],index=['Non-performance', 'Investors', 'Customers', 'Employees', 'Society'], dtype=object)
    
    df_tab.loc['Non-performance'] = [count_NP_NP, count_NP_investor, count_NP_customer, count_NP_employees, count_NP_society]
    df_tab.loc['Investors'] = [count_inv_np, count_inv_investor, count_inv_customer, count_inv_employee, count_inv_society]
    df_tab.loc['Customers'] = [count_cus_np, count_cus_investor, count_cus_customer, count_cus_employee, count_cus_society]
    df_tab.loc['Employees'] = [count_emp_np, count_emp_investor, count_emp_customer, count_emp_employee, count_emp_society]
    df_tab.loc['Society'] = [count_soc_np, count_soc_investor, count_soc_customer, count_soc_employee, count_soc_society]


#  df_tab = pd.DataFrame({
#      'Non-performance': [count_NP_NP, count_NP_investor, count_NP_customer, count_NP_employees, count_NP_society],
#      'Investors': [count_inv_np, count_inv_investor, count_inv_customer, count_inv_employee, count_inv_society],
#      'Customers': [count_cus_np, count_cus_investor, count_cus_customer, count_cus_employee, count_cus_society],
#      'Employees': [count_emp_np, count_emp_investor, count_emp_customer, count_emp_employee, count_emp_society],
#      'Society': [count_soc_np, count_soc_investor, count_soc_customer, count_soc_employee, count_soc_society]},
#       index=['Non-performance', 'Investors', 'Customers', 'Employees', 'Society'])

  #df_tab.to_csv('final_data.csv')
  
  buffer = io.BytesIO()
  with pd.ExcelWriter(buffer, engine="xlsxwriter") as writer:
    df_tab.to_excel(writer,sheet_name="count_result",index=False)
    df_final1.to_excel(writer,sheet_name="Detailed_results",index=False)
    writer.close()
  #df = pd.read_csv('final_data.csv', index_col=0)
#474-515
  # # Convert to JSON format
  json_data = []
  for row in df_tab.index:
    for col in df_tab.columns:
      json_data.append({
            'source': row,
            'target': col,
            'value': int(df_tab.loc[row, col])
        })
  # base_url = "https://huggingface.co/datasets/Seetha/visual_files/tree/main"
  # dataset = load_dataset(base_url, data_files='https://huggingface.co/datasets/Seetha/visual_files/blob/main/level2.json')

  #st.write(dataset)
  
  # Write JSON to file
  #with open(DATA_FILE, 'w') as f: #w+
  with open('https://huggingface.co/datasets/Seetha/visual_files/raw/main/level2.json','w') as f:
    st.write(f)
    f.write(json.dump(json_data))
    #json.dump(json_data, f)
    #repo.push_to_hub()
  # commit_url = repo.push_to_hub()
  # st.write(commit_url)
  #dataset = load_dataset("seetha/visual_files")
  #repo.push_to_hub("level2.json")
  #   # repo.git_pull()
  #   # repo.git_add("ch.json")
  #   # repo.git_commit(commit_message="add ch.json :)")
  #   # repo.push()

  df_final1.to_csv('predictions.csv')
  csv_file = "predictions.csv"
  json_file = "detailedResults.json"

  # Open the CSV file and read the data
  with open(csv_file, "r") as f:
    csv_data = csv.DictReader(f)

    #   # Convert the CSV data to a list of dictionaries
    data_list = []
    for row in csv_data:
        data_list.append(dict(row))

  # # Convert the list of dictionaries to JSON
  json_data = json.dumps(data_list)

  # # Write the JSON data to a file
  # #with open("smalljson.json", "r+") as fi:
  #   #data = fi.read()
  #   #fi.seek(0)
  with open('detailedResults.json','w') as fi:
    #data = json.load(fi)
    fi.write(json_data)
  
  def convert_df(df):

  #IMPORTANT: Cache the conversion to prevent computation on every rerun

    return df.to_csv().encode('utf-8')

               

  csv1 = convert_df(df_final1.astype(str))
  csv2 = convert_df(df_tab.astype(str))

  with st.container():
    
    st.download_button(label="Download the result table",data=buffer,file_name="t2cg_outputs.xlsx",mime="application/vnd.ms-excel")
    

if __name__ == '__main__':
    main()