Upload 3 files

appStore/adapmit.py

@@ -0,0 +1,174 @@
+# 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.adapmit_classifier import load_adapmitClassifier,adapmit_classification
+# from utils.keyword_extraction import textrank
+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 = 'adapmit'
+params  = get_classifier_params(classifier_identifier)
+
+@st.cache_data
+def to_excel(df):
+    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('E2:E{}'.format(len_df), 
+                              {'validate': 'list', 
+                               'source': ['No', 'Yes', 'Discard']})
+    worksheet.data_validation('F2:F{}'.format(len_df), 
+                              {'validate': 'list', 
+                               'source': ['No', 'Yes', 'Discard']})
+    worksheet.data_validation('G2:G{}'.format(len_df), 
+                              {'validate': 'list', 
+                               'source': ['No', 'Yes', 'Discard']})                               
+    writer.save()
+    processed_data = output.getvalue()
+    return processed_data
+
+def app():
+
+    ### Main app code ###
+    with st.container():
+                   
+        if 'key1' in st.session_state:
+            df = st.session_state.key1
+
+            classifier = load_adapmitClassifier(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 = adapmit_classification(haystack_doc=df,
+                                        threshold= params['threshold'])
+
+            st.session_state.key1 = 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, y='category', x='count',
+            #                 color='truth_value',orientation='h', height =200)
+            #     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)
+            #     st.markdown("###### Top few 'Mitigation' related paragraph/text ######")
+            #     df = df.sort_values(by = ['Mitigation'], ascending=False)
+            #     for i in range(3):
+            #         if df.iloc[i]['Mitigation'] >= 0.50:
+            #             st.write('**Result {}** (Relevancy Score: {:.2f})'.format(i+1,df.iloc[i]['Mitigation']))
+            #             st.write("\t Text: \t{}".format(df.iloc[i]['text'].replace("\n", " ")))
+                
+            #     st.markdown("###### Top few 'Adaptation' related paragraph/text ######")
+            #     df = df.sort_values(by = ['Adaptation'], ascending=False)
+            #     for i in range(3):
+            #         if df.iloc[i]['Adaptation'] > 0.5:
+            #             st.write('**Result {}** (Relevancy Score: {:.2f})'.format(i+1,df.iloc[i]['Adaptation']))
+            #             st.write("\t Text: \t{}".format(df.iloc[i]['text'].replace("\n", " ")))
+            #     # st.write(df[['text','labels']])
+            #     df['Validation'] =  'No'
+            #     df['Val-Mitigation'] = 'No'
+            #     df['Val-Adaptation'] = 'No'
+            #     df_xlsx = to_excel(df)
+            #     st.download_button(label='📥 Download Current Result',
+            #                     data=df_xlsx ,
+            #                   file_name= 'file_adaptation-mitigation.xlsx')
+            #     # st.session_state.key4 = 
+
+            #     # category =set(df.columns)
+            #     # removecols = {'Validation','Val-Adaptation','Val-Mitigation','text'}
+            #     # category  = list(category - removecols)
+
+            # 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 'key4' in st.session_state:
+        #     if st.session_state.key4 is not None:
+        #         df = st.session_state.key4
+        #         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" )
+        #         category =set(df.columns)
+        #         removecols = {'Validation','Val-Adaptation','Val-Mitigation','text'}
+        #         category  = list(category - removecols)
+
+        #         placeholder = {}
+        #         for val in category:
+        #             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 = ['category','count','truth_value'])
+        #         fig = px.bar(count_df, x='category', y='count',
+        #                     color='truth_value',
+        #                     height=400)
+        #         st.write("")
+        #         st.plotly_chart(fig)
+
+        #         df['Validation'] =  'No'
+        #         df['Val-Mitigation'] = 'No'
+        #         df['Val-Adaptation'] = 'No'
+        #         df_xlsx = to_excel(df)
+        #         st.download_button(label='📥 Download Current Result',
+        #                         data=df_xlsx ,
+        #                       file_name= 'file_adaptation-mitigation.xlsx')
+
+

appStore/doc_processing (1).py

@@ -0,0 +1,77 @@
+# set path
+import glob, os, sys; 
+sys.path.append('../utils')
+from typing import List, Tuple
+from typing_extensions import Literal
+from haystack.schema import Document
+from utils.config import get_classifier_params
+from utils.preprocessing import processingpipeline,paraLengthCheck
+import streamlit as st
+import logging
+import pandas as pd
+params  = get_classifier_params("preprocessing")
+
+@st.cache_data
+def runPreprocessingPipeline(file_name:str, file_path:str, 
+            split_by: Literal["sentence", "word"] = 'sentence',
+            split_length:int = 2, split_respect_sentence_boundary:bool = False,
+            split_overlap:int = 0,remove_punc:bool = False)->List[Document]:
+    """
+    creates the pipeline and runs the preprocessing pipeline, 
+    the params for pipeline are fetched from paramconfig
+    Params
+    ------------
+    file_name: filename, in case of streamlit application use 
+    st.session_state['filename']
+    file_path: filepath, in case of streamlit application use st.session_state['filepath']
+    split_by: document splitting strategy either as word or sentence
+    split_length: when synthetically creating the paragrpahs from document,
+                    it defines the length of paragraph.
+    split_respect_sentence_boundary: Used when using 'word' strategy for 
+    splititng of text.
+    split_overlap: Number of words or sentences that overlap when creating
+        the paragraphs. This is done as one sentence or 'some words' make sense
+        when  read in together with others. Therefore the overlap is used.
+    remove_punc: to remove all Punctuation including ',' and '.' or not
+    Return
+    --------------
+    List[Document]: When preprocessing pipeline is run, the output dictionary 
+    has four objects. For the Haysatck implementation of SDG classification we, 
+    need to use the List of Haystack Document, which can be fetched by 
+    key = 'documents' on output.
+    """
+
+    processing_pipeline = processingpipeline()
+
+    output_pre = processing_pipeline.run(file_paths = file_path, 
+                            params= {"FileConverter": {"file_path": file_path, \
+                                        "file_name": file_name}, 
+                                     "UdfPreProcessor": {"remove_punc": remove_punc, \
+                                            "split_by": split_by, \
+                                            "split_length":split_length,\
+                                            "split_overlap": split_overlap, \
+        "split_respect_sentence_boundary":split_respect_sentence_boundary}})
+    
+    return output_pre
+
+
+def app():
+    with st.container():           
+          if 'filepath' in st.session_state:
+              file_name = st.session_state['filename']
+              file_path = st.session_state['filepath']
+
+              
+              all_documents = runPreprocessingPipeline(file_name= file_name,
+                              file_path= file_path, split_by= params['split_by'],
+                              split_length= params['split_length'],
+              split_respect_sentence_boundary= params['split_respect_sentence_boundary'],
+              split_overlap= params['split_overlap'], remove_punc= params['remove_punc'])
+              paralist = paraLengthCheck(all_documents['documents'], 100)
+              df = pd.DataFrame(paralist,columns = ['text','page'])
+              # saving the dataframe to session state
+              st.session_state['key0'] = df
+              
+          else:
+                st.info("🤔 No document found, please try to upload it at the sidebar!")
+                logging.warning("Terminated as no document provided")

appStore/indicator.py

@@ -0,0 +1,166 @@
+# 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.indicator_classifier import load_indicatorClassifier, indicator_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 = 'indicator'
+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 'key1' in st.session_state:
+                df = st.session_state.key1
+                classifier = load_indicatorClassifier(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 = indicator_classification(haystack_doc=df,
+                                            threshold= params['threshold'])
+
+                st.session_state.key1 = 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')