Spaces:
Runtime error
Runtime error
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,29 +1,46 @@
|
|
| 1 |
-
# Turkish NER Demo for Various Models
|
| 2 |
-
|
| 3 |
-
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer, DebertaV2Tokenizer, DebertaV2Model
|
| 4 |
-
import sentencepiece
|
| 5 |
import streamlit as st
|
| 6 |
import pandas as pd
|
| 7 |
import spacy
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
st.set_page_config(layout="wide")
|
| 10 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 11 |
example_list = [
|
| 12 |
-
"Mustafa Kemal Atatürk 1919 yılında Samsun'a çıktı.",
|
| 13 |
"""Mustafa Kemal Atatürk, Türk asker, devlet adamı ve Türkiye Cumhuriyeti'nin kurucusudur.
|
| 14 |
-
|
|
|
|
| 15 |
]
|
| 16 |
|
| 17 |
st.title("Demo for Turkish NER Models")
|
| 18 |
|
| 19 |
-
model_list = [
|
| 20 |
-
|
| 21 |
-
|
| 22 |
-
|
| 23 |
-
|
| 24 |
-
|
| 25 |
-
|
| 26 |
-
|
|
|
|
| 27 |
|
| 28 |
st.sidebar.header("Select NER Model")
|
| 29 |
model_checkpoint = st.sidebar.radio("", model_list)
|
|
@@ -31,24 +48,31 @@ model_checkpoint = st.sidebar.radio("", model_list)
|
|
| 31 |
st.sidebar.write("For details of models: 'https://huggingface.co/akdeniz27/")
|
| 32 |
st.sidebar.write("")
|
| 33 |
|
| 34 |
-
if model_checkpoint
|
| 35 |
-
aggregation = "simple"
|
| 36 |
-
elif model_checkpoint == "xlm-roberta-large-finetuned-conll03-english" or model_checkpoint == "asahi417/tner-xlm-roberta-base-ontonotes5":
|
| 37 |
aggregation = "simple"
|
| 38 |
-
|
| 39 |
-
|
| 40 |
else:
|
| 41 |
aggregation = "first"
|
| 42 |
-
|
| 43 |
st.subheader("Select Text Input Method")
|
| 44 |
-
input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text'))
|
|
|
|
| 45 |
if input_method == 'Select from Examples':
|
| 46 |
selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
|
| 47 |
-
st.subheader("Text to Run")
|
| 48 |
input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
|
| 49 |
elif input_method == "Write or Paste New Text":
|
| 50 |
-
st.subheader("Text to Run")
|
| 51 |
input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
|
| 53 |
@st.cache_resource
|
| 54 |
def setModel(model_checkpoint, aggregation):
|
|
@@ -61,7 +85,7 @@ def get_html(html: str):
|
|
| 61 |
WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
|
| 62 |
html = html.replace("\n", " ")
|
| 63 |
return WRAPPER.format(html)
|
| 64 |
-
|
| 65 |
@st.cache_resource
|
| 66 |
def entity_comb(output):
|
| 67 |
output_comb = []
|
|
@@ -74,11 +98,11 @@ def entity_comb(output):
|
|
| 74 |
else:
|
| 75 |
output_comb.append(entity)
|
| 76 |
return output_comb
|
| 77 |
-
|
| 78 |
Run_Button = st.button("Run", key=None)
|
| 79 |
|
| 80 |
if Run_Button and input_text != "":
|
| 81 |
-
|
| 82 |
ner_pipeline = setModel(model_checkpoint, aggregation)
|
| 83 |
output = ner_pipeline(input_text)
|
| 84 |
|
|
@@ -109,8 +133,6 @@ if Run_Button and input_text != "":
|
|
| 109 |
else:
|
| 110 |
if ent["label"] == "PER": ent["label"] = "PERSON"
|
| 111 |
|
| 112 |
-
|
| 113 |
-
html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True, options={"ents": spacy_entity_list}) # , "colors": colors})
|
| 114 |
style = "<style>mark.entity { display: inline-block }</style>"
|
| 115 |
-
st.write(f"{style}{get_html(html)}", unsafe_allow_html=True)
|
| 116 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
import streamlit as st
|
| 2 |
import pandas as pd
|
| 3 |
import spacy
|
| 4 |
+
from transformers import pipeline, AutoModelForTokenClassification, AutoTokenizer
|
| 5 |
+
import PyPDF2
|
| 6 |
+
import docx
|
| 7 |
+
import io
|
| 8 |
|
| 9 |
st.set_page_config(layout="wide")
|
| 10 |
|
| 11 |
+
# Function to read text from uploaded file
|
| 12 |
+
def read_file(file):
|
| 13 |
+
if file.type == "text/plain":
|
| 14 |
+
return file.getvalue().decode("utf-8")
|
| 15 |
+
elif file.type == "application/pdf":
|
| 16 |
+
pdf_reader = PyPDF2.PdfReader(io.BytesIO(file.getvalue()))
|
| 17 |
+
return " ".join(page.extract_text() for page in pdf_reader.pages)
|
| 18 |
+
elif file.type == "application/vnd.openxmlformats-officedocument.wordprocessingml.document":
|
| 19 |
+
doc = docx.Document(io.BytesIO(file.getvalue()))
|
| 20 |
+
return " ".join(paragraph.text for paragraph in doc.paragraphs)
|
| 21 |
+
else:
|
| 22 |
+
st.error("Unsupported file type")
|
| 23 |
+
return None
|
| 24 |
+
|
| 25 |
+
# Rest of your code remains the same
|
| 26 |
example_list = [
|
| 27 |
+
"Mustafa Kemal Atatürk 1919 yılında Samsun'a çıktı.",
|
| 28 |
"""Mustafa Kemal Atatürk, Türk asker, devlet adamı ve Türkiye Cumhuriyeti'nin kurucusudur.
|
| 29 |
+
# ... (rest of the example text)
|
| 30 |
+
"""
|
| 31 |
]
|
| 32 |
|
| 33 |
st.title("Demo for Turkish NER Models")
|
| 34 |
|
| 35 |
+
model_list = [
|
| 36 |
+
'akdeniz27/bert-base-turkish-cased-ner',
|
| 37 |
+
'akdeniz27/convbert-base-turkish-cased-ner',
|
| 38 |
+
'girayyagmur/bert-base-turkish-ner-cased',
|
| 39 |
+
'FacebookAI/xlm-roberta-large',
|
| 40 |
+
'savasy/bert-base-turkish-ner-cased',
|
| 41 |
+
'xlm-roberta-large-finetuned-conll03-english',
|
| 42 |
+
'asahi417/tner-xlm-roberta-base-ontonotes5'
|
| 43 |
+
]
|
| 44 |
|
| 45 |
st.sidebar.header("Select NER Model")
|
| 46 |
model_checkpoint = st.sidebar.radio("", model_list)
|
|
|
|
| 48 |
st.sidebar.write("For details of models: 'https://huggingface.co/akdeniz27/")
|
| 49 |
st.sidebar.write("")
|
| 50 |
|
| 51 |
+
if model_checkpoint in ["akdeniz27/xlm-roberta-base-turkish-ner", "xlm-roberta-large-finetuned-conll03-english", "asahi417/tner-xlm-roberta-base-ontonotes5"]:
|
|
|
|
|
|
|
| 52 |
aggregation = "simple"
|
| 53 |
+
if model_checkpoint != "akdeniz27/xlm-roberta-base-turkish-ner":
|
| 54 |
+
st.sidebar.write("The selected NER model is included just to show the zero-shot transfer learning capability of XLM-Roberta pretrained language model.")
|
| 55 |
else:
|
| 56 |
aggregation = "first"
|
| 57 |
+
|
| 58 |
st.subheader("Select Text Input Method")
|
| 59 |
+
input_method = st.radio("", ('Select from Examples', 'Write or Paste New Text', 'Upload File'))
|
| 60 |
+
|
| 61 |
if input_method == 'Select from Examples':
|
| 62 |
selected_text = st.selectbox('Select Text from List', example_list, index=0, key=1)
|
|
|
|
| 63 |
input_text = st.text_area("Selected Text", selected_text, height=128, max_chars=None, key=2)
|
| 64 |
elif input_method == "Write or Paste New Text":
|
|
|
|
| 65 |
input_text = st.text_area('Write or Paste Text Below', value="", height=128, max_chars=None, key=2)
|
| 66 |
+
else:
|
| 67 |
+
uploaded_file = st.file_uploader("Choose a file", type=["txt", "pdf", "docx"])
|
| 68 |
+
if uploaded_file is not None:
|
| 69 |
+
input_text = read_file(uploaded_file)
|
| 70 |
+
if input_text:
|
| 71 |
+
st.text_area("Extracted Text", input_text, height=128, max_chars=None, key=2)
|
| 72 |
+
else:
|
| 73 |
+
input_text = ""
|
| 74 |
+
|
| 75 |
+
# Rest of your functions (setModel, get_html, entity_comb) remain the same
|
| 76 |
|
| 77 |
@st.cache_resource
|
| 78 |
def setModel(model_checkpoint, aggregation):
|
|
|
|
| 85 |
WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
|
| 86 |
html = html.replace("\n", " ")
|
| 87 |
return WRAPPER.format(html)
|
| 88 |
+
|
| 89 |
@st.cache_resource
|
| 90 |
def entity_comb(output):
|
| 91 |
output_comb = []
|
|
|
|
| 98 |
else:
|
| 99 |
output_comb.append(entity)
|
| 100 |
return output_comb
|
| 101 |
+
|
| 102 |
Run_Button = st.button("Run", key=None)
|
| 103 |
|
| 104 |
if Run_Button and input_text != "":
|
| 105 |
+
# Your existing processing code remains the same
|
| 106 |
ner_pipeline = setModel(model_checkpoint, aggregation)
|
| 107 |
output = ner_pipeline(input_text)
|
| 108 |
|
|
|
|
| 133 |
else:
|
| 134 |
if ent["label"] == "PER": ent["label"] = "PERSON"
|
| 135 |
|
| 136 |
+
html = spacy.displacy.render(spacy_display, style="ent", minify=True, manual=True, options={"ents": spacy_entity_list})
|
|
|
|
| 137 |
style = "<style>mark.entity { display: inline-block }</style>"
|
| 138 |
+
st.write(f"{style}{get_html(html)}", unsafe_allow_html=True)
|
|
|