File size: 10,820 Bytes
7c257bf f61c42f 7c257bf |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 |
import re
import spacy_streamlit
from spacy_streamlit import visualize_parser
from collections import Counter
import spacy
import streamlit as st
# try:
# from .scripts.custom_functions import build_mean_max_reducer1, build_mean_max_reducer2, build_mean_max_reducer3
# except ImportError:
# from pipeline.custom_functions import build_mean_max_reducer1, build_mean_max_reducer2, build_mean_max_reducer3
from spacy.tokens import Doc
from spacy.cli._util import import_code
from utils.visualize import visualize_spans
from utils.utility import preprocess, delete_overlapping_span, cleanup_justify
from resources.text_list import TEXT_LIST
from resources.text_list_BAWE import TEXT_LIST_BAWE
from resources.template_list import TPL_SPAN, TPL_SPAN_SLICE, TPL_SPAN_START
from resources.colors import COLORS_1
import_code("pipeline/custom_functions.py")
st.set_page_config(page_title='Engagement model comparaer', layout="wide")
# spacy.prefer_gpu()
MODEL_LIST =['en_engagement_LSTM', 'en_engagement_LSTM']
# MODEL_LIST = [
# 'en_engagement_three_RoBERTa_base_LSTM384-0.9.2/en_engagement_three_RoBERTa_base_LSTM384/en_engagement_three_RoBERTa_base_LSTM384-0.9.2',
# 'en_engagement_three_RoBERTa_acad3_db-0.9.2/en_engagement_three_RoBERTa_acad3_db/en_engagement_three_RoBERTa_acad3_db-0.9.2',
# 'silver-sweep-34/model-best',
# 'expert-sweep-4/model-best',
# 'confused-sweep-6/model-best',
# 'warm-sweep-20/model-best',
# "en_engagement_three_RoBERTa_base-1.10.0/en_engagement_three_RoBERTa_base/en_engagement_three_RoBERTa_base-1.10.0",
# "en_engagement_three_RoBERTa_acad_db-1.10.0/en_engagement_three_RoBERTa_acad_db/en_engagement_three_RoBERTa_acad_db-1.10.0",
# "en_engagement_para_RoBERTa_acad_db3-0.9.0/en_engagement_para_RoBERTa_acad_db3/en_engagement_para_RoBERTa_acad_db3-0.9.0",
# "en_engagement_para_RoBERTa_acad_LSTM2-0.9.0/en_engagement_para_RoBERTa_acad_LSTM2/en_engagement_para_RoBERTa_acad_LSTM2-0.9.0",
# "en_engagement_three_RoBERTa_acad_db3-0.9.1/en_engagement_three_RoBERTa_acad_db3/en_engagement_three_RoBERTa_acad_db3-0.9.1",
# "en_engagement_three_RoBERTa_acad_LSTM2-0.9.1/en_engagement_three_RoBERTa_acad_LSTM2/en_engagement_three_RoBERTa_acad_LSTM2-0.9.1",
# "en_engagement_three_RoBERTa_acad_db3-0.9.2/en_engagement_three_RoBERTa_acad_db3/en_engagement_three_RoBERTa_acad_db3-0.9.2",
# 'en_engagement_spl_RoBERTa_acad_db-0.7.4/en_engagement_spl_RoBERTa_acad_db/en_engagement_spl_RoBERTa_acad_db-0.7.4',
# 'en_engagement_spl_RoBERTa_acad_db3-0.9.0/en_engagement_spl_RoBERTa_acad_db3/en_engagement_spl_RoBERTa_acad_db3-0.9.0',
# 'en_engagement_spl_RoBERTa_acad_LSTM-0.7.2/en_engagement_spl_RoBERTa_acad_LSTM/en_engagement_spl_RoBERTa_acad_LSTM-0.7.2',
# 'en_engagement_spl_RoBERTa_acad_512',
# 'en_engagement_spl_RoBERTa_acad',
# 'en_engagement_spl_RoBERTa_exp-0.6.5/en_engagement_spl_RoBERTa_exp/en_engagement_spl_RoBERTa_exp-0.6.5',
# # 'en_engagement_spl_RoBERTa_acad-0.3.4.1221/en_engagement_spl_RoBERTa_acad/en_engagement_spl_RoBERTa_acad-0.3.4.1221',
# # 'en_engagement_spl_RoBERTa_acad-0.2.2.1228/en_engagement_spl_RoBERTa_acad/en_engagement_spl_RoBERTa_acad-0.2.2.1228',
# # 'en_engagement_spl_RoBERTa_acad-0.2.1.1228/en_engagement_spl_RoBERTa_acad/en_engagement_spl_RoBERTa_acad-0.2.1.1228',
# # 'en_engagement_spl_RoBERTa_acad-0.2.2.1220/en_engagement_spl_RoBERTa_acad/en_engagement_spl_RoBERTa_acad-0.2.2.1220',
# # 'en_engagement_spl_RoBERTa2-0.2.2.1210/en_engagement_spl_RoBERTa2/en_engagement_spl_RoBERTa2-0.2.2.1210',
# # 'en_engagement_spl_RoBERTa-0.2.2.1210/en_engagement_spl_RoBERTa/en_engagement_spl_RoBERTa-0.2.2.1210',
# # 'en_engagement_spl_RoBERTa_acad_max1_do02',
# # 'en_engagement_spl_RoBERTa2-0.2.2.1210/en_engagement_spl_RoBERTa2/en_engagement_spl_RoBERTa2-0.2.2.1210',
# # 'en_engagement_spl_RoBERTa_acad-0.2.3.1210/en_engagement_spl_RoBERTa_acad/en_engagement_spl_RoBERTa_acad-0.2.3.1210',
# # 'en_engagement_spl_RoBERTa_acad_max1_do02',
# # 'en_engagement_spl_RoBERTa_sqbatch_RAdam-20221202_0.1.5/en_engagement_spl_RoBERTa_sqbatch_RAdam/en_engagement_spl_RoBERTa_sqbatch_RAdam-20221202_0.1.5',
# # 'en_engagement_spl_RoBERTa_context_flz-20221130_0.1.4/en_engagement_spl_RoBERTa_context_flz/en_engagement_spl_RoBERTa_context_flz-20221130_0.1.4',
# # 'en_engagement_spl_RoBERTa_cx_max1_do2-20221202_0.1.5/en_engagement_spl_RoBERTa_cx_max1_do2/en_engagement_spl_RoBERTa_cx_max1_do2-20221202_0.1.5',
# # 'en_engagement_spl_RoBERTa_context_flz-20221125_0.1.4/en_engagement_spl_RoBERTa_context_flz/en_engagement_spl_RoBERTa_context_flz-20221125_0.1.4',
# # 'en_engagement_RoBERTa_context_flz-20221125_0.1.4/en_engagement_RoBERTa_context_flz/en_engagement_RoBERTa_context_flz-20221125_0.1.4',
# # 'en_engagement_RoBERTa_context_flz-20221117_0.1.3/en_engagement_RoBERTa_context_flz/en_engagement_RoBERTa_context_flz-20221117_0.1.3',
# # 'en_engagement_spl_RoBERTa_acad_context_flz-20221117_0.1.3/en_engagement_spl_RoBERTa_acad_context_flz/en_engagement_spl_RoBERTa_acad_context_flz-20221117_0.1.3',
# # 'en_engagement_RoBERTa_context_flz-Batch2_0.1.1/en_engagement_RoBERTa_context_flz/en_engagement_RoBERTa_context_flz-Batch2_0.1.1',
# # 'en_engagement_RoBERTa_context_flz-20221113_0.1.3/en_engagement_RoBERTa_context_flz/en_engagement_RoBERTa_context_flz-20221113_0.1.3',
# # 'en_engagement_RoBERTa_context_flz-20221113_0.1.1/en_engagement_RoBERTa_context_flz/en_engagement_RoBERTa_context_flz-20221113_0.1.1',
# # 'en_engagement_RoBERTa-0.0.2/en_engagement_RoBERTa/en_engagement_RoBERTa-0.0.2',
# # 'en_engagement_RoBERTa_combined-Batch2Eng_0.2/en_engagement_RoBERTa_combined/en_engagement_RoBERTa_combined-Batch2Eng_0.2',
# # 'en_engagement_RoBERTa_acad-0.2.1/en_engagement_RoBERTa_acad/en_engagement_RoBERTa_acad-0.2.1',
# # # 'en_engagement_BERT-0.0.2/en_engagement_BERT/en_engagement_BERT-0.0.2',
# # # 'en_engagement_BERT_acad-0.0.2/en_engagement_BERT_acad/en_engagement_BERT_acad-0.0.2',
# # # 'en_engagement_RoBERTa_acad-0.0.2/en_engagement_RoBERTa_acad/en_engagement_RoBERTa_acad-0.0.2',
# # 'en_engagement_RoBERTa-0.0.1/en_engagement_RoBERTa/en_engagement_RoBERTa-0.0.1',
# # # ' en_engagement_RoBERTa_sent-0.0.1_null/en_engagement_RoBERTa_sent/en_engagement_RoBERTa_sent-0.0.1_null',
# # # 'en_engagement_RoBERTa_combined-0.0.1/en_engagement_RoBERTa_combined/en_engagement_RoBERTa_combined-0.0.1',
# # 'en_engagement_RoBERTa-ME_AtoE/en_engagement_RoBERTa/en_engagement_RoBERTa-ME_AtoE',
# # 'en_engagement_RoBERTa-AtoI_0.0.3/en_engagement_RoBERTa/en_engagement_RoBERTa-AtoI_0.0.3',
# # 'en_engagement_RoBERTa-AtoI_0.0.3/en_engagement_RoBERTa/en_engagement_RoBERTa-AtoI_0.0.2'
# ]
multicol = st.checkbox("Compare two models", value=False, key=None, help=None)
model1 = st.selectbox('Select model option 1', MODEL_LIST, index=0)
model2 = st.selectbox('Select model option 2', MODEL_LIST, index=1)
if '/' in model1:
model1 = "packages/" + model1
if '/' in model2:
model2 = "packages/" + model2
@st.cache(allow_output_mutation=True)
def load_model(spacy_model):
# source = spacy.blank("en")
nlp = spacy.load(spacy_model) #, vocab=nlp_to_copy.vocab
nlp.add_pipe('sentencizer')
return (nlp)
# source = spacy.blank("en")
nlp = load_model(model1)
if multicol:
nlp2 = load_model(model2)
text = st.selectbox('select sent to debug', TEXT_LIST_BAWE)
input_text = st.text_area("", height=200)
# Dependency parsing
st.header("Text", "text")
if len(input_text.split(" ")) > 1:
doc = nlp(preprocess(input_text))
if multicol:
doc2 = nlp2(preprocess(input_text))
# st.markdown("> " + input_text)
else:
doc = nlp(preprocess(text))
if multicol:
doc2 = nlp2(preprocess(text))
# st.markdown("> " + text)
clearjustify = st.checkbox(
"Clear problematic JUSTIFYING spans", value=True, key=None, help=None)
delete_overlaps = st.checkbox(
"Delete overlaps", value=True, key=None, help=None)
# combine = st.checkbox(
# "Combine", value=False, key=None, help=None)
# import copy
# def combine_spangroups(doc1, doc2):
# # new_doc = Doc.from_docs([doc1, doc2], ensure_whitespace=True)
# new_doc = copy.deepcopy(doc1)
# # type()
# new_doc.spans['sc'].extend(doc2.spans['sc'])
# return new_doc
# if combine:
# new_doc = combine_spangroups(doc, doc2)
# visualize_spans(new_doc,
# spans_key="sc",
# title='Combined spans:',
# displacy_options={
# 'template': {
# "span": TPL_SPAN,
# 'slice': TPL_SPAN_SLICE,
# 'start': TPL_SPAN_START,
# },
# "colors": COLORS_1,
# },
# simple=False)
if clearjustify:
cleanup_justify(doc, doc.spans['sc'])
if delete_overlaps:
delete_overlapping_span(doc.spans['sc'])
if multicol:
delete_overlapping_span(doc2.spans['sc'])
if not multicol:
visualize_spans(doc,
spans_key="sc",
title='Engagement Span Anotations 1',
displacy_options={
'template': {
"span": TPL_SPAN,
'slice': TPL_SPAN_SLICE,
'start': TPL_SPAN_START,
},
"colors": COLORS_1,
},
simple=False)
else:
col1, col2 = st.columns(2)
with col1:
visualize_spans(doc,
spans_key="sc",
title='Engagement Span Anotations 1',
displacy_options={
'template': {
"span": TPL_SPAN,
'slice': TPL_SPAN_SLICE,
'start': TPL_SPAN_START,
},
"colors": COLORS_1,
},
simple=False)
with col2:
visualize_spans(doc2,
spans_key="sc",
title='Engagement Span Anotations 2',
displacy_options={
'template': {
"span": TPL_SPAN,
'slice': TPL_SPAN_SLICE,
'start': TPL_SPAN_START,
},
"colors": COLORS_1,
},
simple=False)
dep_options = {"fine_grained": True, "distance": 120}
visualize_parser(doc, displacy_options=dep_options) |