Delete utils

utils/__init__.py

@@ -1 +0,0 @@
-# adding for package implementation

utils/config.py

@@ -1,31 +0,0 @@
-import configparser
-import logging
-
-def getconfig(configfile_path:str):
-    """
-    configfile_path: file path of .cfg file
-    """
-
-    config = configparser.ConfigParser()
-
-    try:
-        config.read_file(open(configfile_path))
-        return config
-    except:
-        logging.warning("config file not found")
-
-
-# Declare all the necessary variables
-def get_classifier_params(model_name):
-    config = getconfig('paramconfig.cfg')
-    params = {}
-    params['model_name'] = config.get(model_name,'MODEL')
-    params['split_by'] = config.get(model_name,'SPLIT_BY')
-    params['split_length'] = int(config.get(model_name,'SPLIT_LENGTH'))
-    params['split_overlap'] = int(config.get(model_name,'SPLIT_OVERLAP'))
-    params['remove_punc'] = bool(int(config.get(model_name,'REMOVE_PUNC')))
-    params['split_respect_sentence_boundary'] = bool(int(config.get(model_name,'RESPECT_SENTENCE_BOUNDARY')))
-    params['threshold'] = float(config.get(model_name,'THRESHOLD'))
-    params['top_n'] = int(config.get(model_name,'TOP_KEY'))
-
-    return params

utils/groups_classifier.py

@@ -1,93 +0,0 @@
-from typing import List, Tuple
-from typing_extensions import Literal
-import logging
-import pandas as pd
-from pandas import DataFrame, Series
-from utils.config import getconfig
-from utils.preprocessing import processingpipeline
-import streamlit as st
-from transformers import pipeline
-
-## Labels dictionary ###
-_lab_dict = {
-    0: 'Children and Youth',
-    1: 'Informal sector workers',
-    2: 'Other',
-    3: 'Rural populations',
-    4: 'Sexual minorities (LGBTQI+)',
-    5: 'Urban populations',
-    6: 'Women'}
-
-@st.cache_resource
-def load_groupsClassifier(config_file:str = None, classifier_name:str = None):
-    """
-    loads the document classifier using haystack, where the name/path of model
-    in HF-hub as string is used to fetch the model object.Either configfile or 
-    model should be passed.
-    1. https://docs.haystack.deepset.ai/reference/document-classifier-api
-    2. https://docs.haystack.deepset.ai/docs/document_classifier
-    Params
-    --------
-    config_file: config file path from which to read the model name
-    classifier_name: if modelname is passed, it takes a priority if not \
-    found then will look for configfile, else raise error.
-    Return: document classifier model
-    """
-    if not classifier_name:
-        if not config_file:
-            logging.warning("Pass either model name or config file")
-            return
-        else:
-            config = getconfig(config_file)
-            classifier_name = config.get('group_classification','MODEL')
-    
-    logging.info("Loading classifier")  
-      
-    doc_classifier = pipeline("text-classification", 
-                            model=classifier_name, 
-                            top_k =1)
-
-    return doc_classifier
-
-
-@st.cache_data
-def groups_classification(haystack_doc:pd.DataFrame,
-                        threshold:float = 0.5, 
-                        classifier_model:pipeline= None
-                        )->Tuple[DataFrame,Series]:
-    """
-    Text-Classification on the list of texts provided. Classifier provides the 
-    most appropriate label for each text. these labels are in terms of if text 
-    belongs to which particular Sustainable Devleopment Goal (SDG).
-    Params
-    ---------
-    haystack_doc: List of haystack Documents. The output of Preprocessing Pipeline 
-    contains the list of paragraphs in different format,here the list of 
-    Haystack Documents is used.
-    threshold: threshold value for the model to keep the results from classifier
-    classifiermodel: you can pass the classifier model directly,which takes priority
-    however if not then looks for model in streamlit session.
-    In case of streamlit avoid passing the model directly.
-    Returns
-    ----------
-    df: Dataframe with two columns['SDG:int', 'text']
-    x: Series object with the unique SDG covered in the document uploaded and 
-    the number of times it is covered/discussed/count_of_paragraphs. 
-    """
-    logging.info("Working on Group Extraction")
-    if not classifier_model:
-        classifier_model = st.session_state['group_classifier']
-    
-    results = classifier_model(list(haystack_doc.text))
-    labels_= [(l[0]['label'],
-               l[0]['score']) for l in results]
-           
-
-    df1 = DataFrame(labels_, columns=["Group Label","Relevancy"])
-    df = pd.concat([haystack_doc,df1],axis=1)
-    
-    df = df.sort_values(by="Relevancy", ascending=False).reset_index(drop=True)  
-    df.index += 1
-    df['Label_def'] = df['Group Label'].apply(lambda i: _lab_dict[i])
-
-    return df

utils/preprocessing.py

@@ -1,283 +0,0 @@
-from haystack.nodes.base import BaseComponent
-from haystack.schema import Document
-from haystack.nodes import PDFToTextOCRConverter, PDFToTextConverter
-from haystack.nodes import TextConverter, DocxToTextConverter, PreProcessor
-from typing import Callable, Dict, List, Optional, Text, Tuple, Union
-from typing_extensions import Literal
-import pandas as pd
-import logging
-import re
-import string
-from haystack.pipelines import Pipeline
-
-def useOCR(file_path: str)-> Text:
-    """
-    Converts image pdfs into text, Using the Farm-haystack[OCR]
-    
-    Params
-    ----------
-    file_path: file_path of uploade file, returned by add_upload function in 
-    uploadAndExample.py
-    
-    Returns the text file as string.
-    """
-
-    
-    converter = PDFToTextOCRConverter(remove_numeric_tables=True, 
-                                      valid_languages=["eng"])
-    docs = converter.convert(file_path=file_path, meta=None)
-    return docs[0].content
-
-
-
-
-class FileConverter(BaseComponent):
-    """
-    Wrapper class to convert uploaded document into text by calling appropriate 
-    Converter class, will use internally haystack PDFToTextOCR in case of image 
-    pdf. Cannot use the FileClassifier from haystack as its doesnt has any 
-    label/output class for image.
-    1. https://haystack.deepset.ai/pipeline_nodes/custom-nodes
-    2. https://docs.haystack.deepset.ai/docs/file_converters
-    3. https://github.com/deepset-ai/haystack/tree/main/haystack/nodes/file_converter
-    4. https://docs.haystack.deepset.ai/reference/file-converters-api
-    """
-
-    outgoing_edges = 1
-
-    def run(self, file_name: str , file_path: str, encoding: Optional[str]=None,
-            id_hash_keys: Optional[List[str]] = None,
-            ) -> Tuple[dict,str]:
-        """ this is required method to invoke the component in 
-            the pipeline implementation. 
-            
-        Params
-        ----------
-        file_name: name of file
-        file_path: file_path of uploade file, returned by add_upload function in 
-                    uploadAndExample.py
-        
-        See the links provided in Class docstring/description to see other params
-        
-        Return
-        ---------
-        output: dictionary, with key as identifier and value could be anything 
-                we need to return. In this case its the List of Hasyatck Document
-        
-        output_1: As there is only one outgoing edge, we pass 'output_1' string
-        """
-        try:
-            if file_name.endswith('.pdf'):
-                converter = PDFToTextConverter(remove_numeric_tables=True)
-            if file_name.endswith('.txt'):
-                converter = TextConverter(remove_numeric_tables=True)
-            if file_name.endswith('.docx'):
-                converter = DocxToTextConverter() 
-        except Exception as e:
-            logging.error(e)
-            return 
-
-
-
-        documents = []
-
-
-# encoding is empty, probably should be utf-8
-        document = converter.convert(
-                      file_path=file_path, meta=None, 
-                      encoding=encoding, id_hash_keys=id_hash_keys
-                      )[0]
-
-        text = document.content
-
-        # in case of scanned/images only PDF the content might contain only
-        # the page separator (\f or \x0c). We check if is so and use
-        # use the OCR to get the text.
-        filtered = re.sub(r'\x0c', '', text)
-
-        if filtered == "":
-            logging.info("Using OCR")
-            text = useOCR(file_path)
-
-        documents.append(Document(content=text, 
-                              meta={"name": file_name}, 
-                              id_hash_keys=id_hash_keys))
-        
-        logging.info('file conversion succesful')
-        output = {'documents': documents}
-        return output, 'output_1'
-
-    def run_batch():
-        """
-        we dont have requirement to process the multiple files in one go
-        therefore nothing here, however to use the custom node we need to have
-        this method for the class.
-        """
-        
-        return
-
-
-def basic(s:str, remove_punc:bool = False):
-
-    """
-    Performs basic cleaning of text.
-    Params
-    ----------
-    s: string to be processed
-    removePunc: to remove all Punctuation including ',' and '.' or not
-    
-    Returns: processed string: see comments in the source code for more info
-    """
-    
-    # Remove URLs
-    s = re.sub(r'^https?:\/\/.*[\r\n]*', ' ', s, flags=re.MULTILINE)
-    s = re.sub(r"http\S+", " ", s)
-
-    # Remove new line characters
-    s = re.sub('\n', ' ', s) 
-
-    # Remove punctuations
-    if remove_punc == True:
-      translator = str.maketrans(' ', ' ', string.punctuation) 
-      s = s.translate(translator)
-    # Remove distracting single quotes and dotted pattern
-    s = re.sub("\'", " ", s)
-    s = s.replace("..","") 
-    
-    return s.strip()
-
-def paraLengthCheck(paraList, max_len = 100):
-    """
-    There are cases where preprocessor cannot respect word limit, when using 
-    respect sentence boundary flag due to missing sentence boundaries.
-    Therefore we run one more round of split here for those paragraphs
-    
-    Params
-    ---------------
-    paraList : list of paragraphs/text
-    max_len : max length to be respected by sentences which bypassed 
-              preprocessor strategy
-              
-    """
-    new_para_list = []
-    for passage in paraList:
-        # check if para exceeds words limit
-        if len(passage.content.split()) > max_len:
-          # we might need few iterations example if para = 512 tokens
-          # we need to iterate 5 times to reduce para to size limit of '100'
-            iterations = int(len(passage.content.split())/max_len)
-            for i in range(iterations):
-                temp  = " ".join(passage.content.split()[max_len*i:max_len*(i+1)])
-                new_para_list.append((temp,passage.meta['page']))
-            temp  = " ".join(passage.content.split()[max_len*(i+1):])
-            new_para_list.append((temp,passage.meta['page']))
-        else:
-            # paragraphs which dont need any splitting
-            new_para_list.append((passage.content, passage.meta['page']))
-    
-    logging.info("New paragraphs length {}".format(len(new_para_list)))
-    return new_para_list
-
-class UdfPreProcessor(BaseComponent):
-    """
-    class to preprocess the document returned by FileConverter. It will check
-    for splitting strategy and splits the document by word or sentences and then
-    synthetically create the paragraphs. 
-    1. https://docs.haystack.deepset.ai/docs/preprocessor
-    2. https://docs.haystack.deepset.ai/reference/preprocessor-api
-    3. https://github.com/deepset-ai/haystack/tree/main/haystack/nodes/preprocessor
-    """
-    outgoing_edges = 1
-
-    def run(self, documents:List[Document], remove_punc:bool=False, 
-            split_by: Literal["sentence", "word"] = 'sentence',
-            split_length:int = 2, split_respect_sentence_boundary:bool = False,
-            split_overlap:int = 0):
-
-        """ this is required method to invoke the component in 
-        the pipeline implementation. 
-            
-        Params
-        ----------
-        documents: documents from the output dictionary returned by Fileconverter
-        remove_punc: to remove all Punctuation including ',' and '.' or not
-        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.
-        
-        Return
-        ---------
-        output: dictionary, with key as identifier and value could be anything 
-                we need to return. In this case the output will contain 4 objects
-                the paragraphs text list as List, Haystack document, Dataframe and 
-                one raw text file.
-        
-        output_1: As there is only one outgoing edge, we pass 'output_1' string
-      
-        """
-        
-        if split_by == 'sentence':
-            split_respect_sentence_boundary = False
-    
-        else:
-            split_respect_sentence_boundary = split_respect_sentence_boundary
-      
-        preprocessor = PreProcessor(
-            clean_empty_lines=True,
-            clean_whitespace=True,
-            clean_header_footer=True,
-            split_by=split_by,
-            split_length=split_length,
-            split_respect_sentence_boundary= split_respect_sentence_boundary,
-            split_overlap=split_overlap,
-
-            # will add page number only in case of PDF not for text/docx file.
-            add_page_number=True
-            )
-        
-        for i in documents:
-            # # basic cleaning before passing it to preprocessor.
-            # i = basic(i)
-            docs_processed = preprocessor.process([i])
-            for item in docs_processed:
-                item.content = basic(item.content, remove_punc= remove_punc)
-
-        df = pd.DataFrame(docs_processed)
-        all_text = " ".join(df.content.to_list())
-        para_list = df.content.to_list()
-        logging.info('document split into {} paragraphs'.format(len(para_list)))
-        output = {'documents': docs_processed,
-                  'dataframe': df,
-                  'text': all_text,
-                  'paraList': para_list
-                 }
-        return output, "output_1"
-    def run_batch():
-        """
-            we dont have requirement to process the multiple files in one go
-            therefore nothing here, however to use the custom node we need to have
-            this method for the class.
-        """
-        return
-
-def processingpipeline():
-    """
-    Returns the preprocessing pipeline. Will use FileConverter and UdfPreProcesor 
-    from utils.preprocessing
-    """
-
-    preprocessing_pipeline = Pipeline()
-    file_converter = FileConverter()
-    custom_preprocessor = UdfPreProcessor()
-
-    preprocessing_pipeline.add_node(component=file_converter, 
-                                    name="FileConverter", inputs=["File"])
-    preprocessing_pipeline.add_node(component = custom_preprocessor, 
-                            name ='UdfPreProcessor', inputs=["FileConverter"])
-
-    return preprocessing_pipeline

utils/uploadAndExample.py

@@ -1,38 +0,0 @@
-import streamlit as st
-import tempfile
-import json
-
-def add_upload(choice):
-    """
-    Provdies the user with choice to either 'Upload Document' or 'Try Example'.
-    Based on user choice runs streamlit processes and save the path and name of
-    the 'file' to streamlit session_state which then can be fetched later.
-    """
-    
-    if choice == 'Upload Document':
-        
-       # if 'filename' in st.session_state:
-          # Delete all the items in Session state
-        #    for key in st.session_state.keys():
-         #       del st.session_state[key]
-
-        uploaded_file = st.sidebar.file_uploader('Upload the File',
-                            type=['pdf', 'docx', 'txt'])
-        if uploaded_file is not None:
-            with tempfile.NamedTemporaryFile(mode="wb", delete = False) as temp:
-                bytes_data = uploaded_file.getvalue()
-                temp.write(bytes_data)
-                st.session_state['filename'] = uploaded_file.name
-                st.session_state['filepath'] = temp.name
-
-                
-    else:
-        # listing the options
-        with open('docStore/sample/files.json','r') as json_file:
-            files = json.load(json_file)
-
-        option = st.sidebar.selectbox('Select the example document',
-                              list(files.keys()))
-        file_name = file_path  = files[option]
-        st.session_state['filename'] = file_name
-        st.session_state['filepath'] = file_path