File size: 6,149 Bytes
4a20529 49a314a 4a20529 cc5c327 49a314a 4a20529 78f3ebc 49a314a cc5c327 4a20529 49a314a cc5c327 4a20529 49a314a cc5c327 4a20529 49a314a 4a20529 49a314a cc5c327 4a20529 49a314a 4a20529 cc5c327 4a20529 3b97e90 4a20529 cc5c327 4a20529 cc5c327 4a20529 49a314a cc5c327 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 |
from haystack.nodes import TfidfRetriever
from haystack.document_stores import InMemoryDocumentStore
import configparser
import spacy
import re
from spacy.matcher import Matcher
import streamlit as st
from markdown import markdown
from annotated_text import annotation
from haystack.schema import Document
from typing import List, Tuple, Text
from utils.preprocessing import processingpipeline
config = configparser.ConfigParser()
config.read_file(open('paramconfig.cfg'))
def tokenize_lexical_query(query:str)-> List[str]:
"""
Removes the stop words from query and returns the list of important keywords
in query. For the lexical search the relevent paragraphs in document are
retreived using TfIDFretreiver from Haystack. However to highlight these
keywords we need the tokenized form of query.
Params
--------
query: string which represents either list of keywords user is looking for
or a query in form of Question.
Return
-----------
token_list: list of important keywords in the query.
"""
nlp = spacy.load("en_core_web_sm")
token_list = [token.text.lower() for token in nlp(query) if not token.is_stop]
return token_list
def runSpacyMatcher(token_list:List[str], document:Text):
"""
Using the spacy in backend finds the keywords in the document using the
Matcher class from spacy. We can alternatively use the regex, but spacy
finds all keywords in serialized manner which helps in annotation of answers.
Params
-------
token_list: this is token list which tokenize_lexical_query function returns
document: text in which we need to find the tokens
Return
--------
matches: List of [start_index, end_index] in the spacydoc(at word level not
character) for the keywords in token list.
spacydoc: the keyword index in the spacydoc are at word level and not character,
therefore to allow the annotator to work seamlessly we return the spacydoc.
"""
nlp = spacy.load("en_core_web_sm")
spacydoc = nlp(document)
matcher = Matcher(nlp.vocab)
token_pattern = [[{"LOWER":token}] for token in token_list]
matcher.add(",".join(token_list), token_pattern)
spacymatches = matcher(spacydoc)
# getting start and end index in spacydoc so that annotator can work seamlessly
matches = []
for match_id, start, end in spacymatches:
matches = matches + [[start, end]]
return matches, spacydoc
def runRegexMatcher(token_list:List[str], document:Text):
"""
Using the regex in backend finds the keywords in the document.
Params
-------
token_list: this is token list which tokenize_lexical_query function returns
document: text in which we need to find the tokens
Return
--------
matches: List of [start_index, end_index] in the document for the keywords
in token list at character level.
document: the keyword index returned by regex are at character level,
therefore to allow the annotator to work seamlessly we return the text back.
"""
matches = []
for token in token_list:
matches = matches + [[val.start(), val.start()+ len(token)] for val in re.finditer(token, document)]
return matches, document
def searchAnnotator(matches: List[List[int]], document):
"""
Annotates the text in the document defined by list of [start index, end index]
Example: "How are you today", if document type is text, matches = [[0,3]]
will give answer = "How", however in case we used the spacy matcher then the
matches = [[0,3]] will give answer = "How are you". However if spacy is used
to find "How" then the matches = [[0,1]] for the string defined above.
"""
start = 0
annotated_text = ""
for match in matches:
start_idx = match[0]
end_idx = match[1]
annotated_text = annotated_text + document[start:start_idx].text + str(annotation(body=document[start_idx:end_idx].text, label="ANSWER", background="#964448", color='#ffffff'))
start = end_idx
st.write(
markdown(annotated_text),
unsafe_allow_html=True,
)
def lexical_search(query:Text,documents:List[Document]):
"""
Performs the Lexical search on the List of haystack documents which is
returned by preprocessing Pipeline.
"""
document_store = InMemoryDocumentStore()
document_store.write_documents(documents)
# Haystack Retriever works with document stores only.
retriever = TfidfRetriever(document_store)
results = retriever.retrieve(query=query,
top_k= int(config.get('lexical_search','TOP_K')))
query_tokens = tokenize_lexical_query(query)
for result in results:
matches, doc = runSpacyMatcher(query_tokens,result.content)
searchAnnotator(matches, doc)
def runLexicalPreprocessingPipeline()->List[Document]:
"""
creates the pipeline and runs the preprocessing pipeline,
the params for pipeline are fetched from paramconfig
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.
"""
file_path = st.session_state['filepath']
file_name = st.session_state['filename']
sdg_processing_pipeline = processingpipeline()
split_by = config.get('lexical_search','SPLIT_BY')
split_length = int(config.get('lexical_search','SPLIT_LENGTH'))
output_lexical_pre = sdg_processing_pipeline.run(file_paths = file_path,
params= {"FileConverter": {"file_path": file_path, \
"file_name": file_name},
"UdfPreProcessor": {"removePunc": False, \
"split_by": split_by, \
"split_length":split_length}})
return output_lexical_pre['documents']
|