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)
|
|