appStore/vulnerability_analysis.py

# set path
import glob, os, sys; 
sys.path.append('../utils')

#import needed libraries
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
import streamlit as st
from utils.vulnerability_classifier import load_vulnerabilityClassifier, vulnerability_classification
import logging
logger = logging.getLogger(__name__)
from utils.config import get_classifier_params
from utils.preprocessing import paraLengthCheck
from io import BytesIO
import xlsxwriter
import plotly.express as px


# Declare all the necessary variables
classifier_identifier = 'vulnerability'
params  = get_classifier_params(classifier_identifier)

@st.cache_data
def to_excel(df,sectorlist):
    len_df = len(df)
    output = BytesIO()
    writer = pd.ExcelWriter(output, engine='xlsxwriter')
    df.to_excel(writer, index=False, sheet_name='Sheet1')
    workbook = writer.book
    worksheet = writer.sheets['Sheet1']
    worksheet.data_validation('S2:S{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': ['No', 'Yes', 'Discard']})
    worksheet.data_validation('X2:X{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': sectorlist + ['Blank']})
    worksheet.data_validation('T2:T{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': sectorlist + ['Blank']})
    worksheet.data_validation('U2:U{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': sectorlist + ['Blank']})                               
    worksheet.data_validation('V2:V{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': sectorlist + ['Blank']})
    worksheet.data_validation('W2:U{}'.format(len_df), 
                              {'validate': 'list', 
                               'source': sectorlist + ['Blank']})                            
    writer.save()
    processed_data = output.getvalue()
    return processed_data

def app():

    ### Main app code ###
    with st.container():
                   
            if 'key0' in st.session_state:
                df = st.session_state.key1
                classifier = load_vulnerabilityClassifier(classifier_name=params['model_name'])
                st.session_state['{}_classifier'.format(classifier_identifier)] = classifier

                if sum(df['Target Label'] == 'TARGET') > 100:
                    warning_msg = ": This might take sometime, please sit back and relax."
                else:
                    warning_msg = ""
                    
                df = vulnerability_classification(haystack_doc=df,
                                            threshold= params['threshold'])

                st.session_state.key0 = df


                # # st.write(df)
                # threshold= params['threshold']
                # truth_df = df.drop(['text'],axis=1)
                # truth_df = truth_df.astype(float) >= threshold
                # truth_df = truth_df.astype(str)
                # categories = list(truth_df.columns)

                # placeholder = {}
                # for val in categories:
                #     placeholder[val] = dict(truth_df[val].value_counts())
                # count_df = pd.DataFrame.from_dict(placeholder)
                # count_df = count_df.T
                # count_df = count_df.reset_index()
                # # st.write(count_df)
                # placeholder  = []
                # for i in range(len(count_df)):
                #     placeholder.append([count_df.iloc[i]['index'],count_df['True'][i],'Yes'])
                #     placeholder.append([count_df.iloc[i]['index'],count_df['False'][i],'No'])
                # count_df = pd.DataFrame(placeholder, columns = ['category','count','truth_value'])
                # # st.write("Total Paragraphs: {}".format(len(df)))
                # fig = px.bar(count_df, x='category', y='count',
                #             color='truth_value')
                # # c1, c2 = st.columns([1,1])
                # # with c1:
                # st.plotly_chart(fig,use_container_width= True)

                # truth_df['labels'] = truth_df.apply(lambda x: {i if x[i]=='True' else None for i in categories}, axis=1)
                # truth_df['labels'] = truth_df.apply(lambda x: list(x['labels'] -{None}),axis=1)
                # # st.write(truth_df)
                # df = pd.concat([df,truth_df['labels']],axis=1)
                # df['Validation'] =  'No'
                # df['Sector1'] = 'Blank'
                # df['Sector2'] = 'Blank'
                # df['Sector3'] = 'Blank'
                # df['Sector4'] = 'Blank'
                # df['Sector5'] = 'Blank'
                # df_xlsx = to_excel(df,categories)
                # st.download_button(label='📥 Download Current Result',
                #                 data=df_xlsx ,
            #     #               file_name= 'file_sector.xlsx')
            # else:
            #     st.info("🤔 No document found, please try to upload it at the sidebar!")
            #     logging.warning("Terminated as no document provided")
        
        # # Creating truth value dataframe
        # if 'key' in st.session_state:
        #     if st.session_state.key is not None:
        #         df = st.session_state.key
        #         st.markdown("###### Select the threshold for classifier ######")
        #         c4, c5 = st.columns([1,1])

        #         with c4:                    
        #             threshold = st.slider("Threshold", min_value=0.00, max_value=1.0,
        #                                   step=0.01, value=0.5,
        #                 help = "Keep High Value if want refined result, low if dont want to miss anything" )
        #         sectors =set(df.columns)
        #         removecols = {'Validation','Sector1','Sector2','Sector3','Sector4',
        #                       'Sector5','text'}
        #         sectors  = list(sectors - removecols)

        #         placeholder = {}
        #         for val in sectors:
        #             temp = df[val].astype(float) > threshold
        #             temp = temp.astype(str)
        #             placeholder[val] = dict(temp.value_counts())
                    
        #         count_df = pd.DataFrame.from_dict(placeholder)
        #         count_df = count_df.T
        #         count_df = count_df.reset_index()
        #         placeholder  = []
        #         for i in range(len(count_df)):
        #             placeholder.append([count_df.iloc[i]['index'],count_df['False'][i],'False'])
        #             placeholder.append([count_df.iloc[i]['index'],count_df['True'][i],'True'])

        #         count_df = pd.DataFrame(placeholder, columns = ['sector','count','truth_value'])
        #         fig = px.bar(count_df, x='sector', y='count',
        #                     color='truth_value',
        #                     height=400)
        #         st.write("")
        #         st.plotly_chart(fig)

                # df['Validation'] =  'No'
                # df['Sector1'] = 'Blank'
                # df['Sector2'] = 'Blank'
                # df['Sector3'] = 'Blank'
                # df['Sector4'] = 'Blank'
                # df['Sector5'] = 'Blank'
                # df_xlsx = to_excel(df,sectors)
                # st.download_button(label='📥 Download Current Result',
                #                 data=df_xlsx ,
                #               file_name= 'file_sector.xlsx')