Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,17 +1,21 @@
|
|
| 1 |
"""Demo for NER4OPT."""
|
| 2 |
import os
|
| 3 |
import warnings
|
| 4 |
-
|
| 5 |
-
warnings.filterwarnings("ignore", category=DeprecationWarning)
|
| 6 |
-
|
| 7 |
import streamlit as st
|
| 8 |
import ner4opt
|
| 9 |
from ner4opt.utils import preprocess, spacy_tokenize_sentence
|
| 10 |
-
|
| 11 |
from spacy import displacy
|
| 12 |
|
|
|
|
|
|
|
| 13 |
HTML_WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
|
| 14 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 15 |
|
| 16 |
@st.cache_resource
|
| 17 |
def load_models():
|
|
@@ -22,27 +26,41 @@ def load_models():
|
|
| 22 |
hybrid_ner_model = ner4opt.Ner4Opt("hybrid")
|
| 23 |
return lexical_ner_model, lexical_plus_ner_model, semantic_ner_model, hybrid_ner_model
|
| 24 |
|
|
|
|
|
|
|
|
|
|
| 25 |
|
| 26 |
def main():
|
| 27 |
-
|
| 28 |
st.title("""Ner4Opt: Named Entity Recognition for Optimization""")
|
| 29 |
-
|
| 30 |
st.markdown("""Given an optimization problem in natural language, Ner4Opt extracts optimization related entities from free-form text. The source code for Ner4Opt is available at https://github.com/skadio/ner4opt""")
|
| 31 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32 |
option = st.sidebar.selectbox(
|
| 33 |
'Select a lexical, semantic, or hybrid model for extracting entities',
|
| 34 |
('Lexical', 'Lexical Plus', 'Semantic', 'Hybrid'), index=3)
|
| 35 |
|
| 36 |
text = st.text_area(
|
| 37 |
"Text",
|
| 38 |
-
|
| 39 |
)
|
| 40 |
text = text.strip()
|
| 41 |
if text == "":
|
| 42 |
st.write("Please write a valid sentence.")
|
| 43 |
|
| 44 |
-
lexical_ner_model, lexical_plus_ner_model, semantic_ner_model, hybrid_ner_model = load_models(
|
| 45 |
-
)
|
| 46 |
|
| 47 |
# get entities
|
| 48 |
if option == "Lexical":
|
|
@@ -74,6 +92,5 @@ def main():
|
|
| 74 |
html_ner = html_ner.replace("\n", " ")
|
| 75 |
st.write(HTML_WRAPPER.format(html_ner), unsafe_allow_html=True)
|
| 76 |
|
| 77 |
-
|
| 78 |
if __name__ == '__main__':
|
| 79 |
-
main()
|
|
|
|
| 1 |
"""Demo for NER4OPT."""
|
| 2 |
import os
|
| 3 |
import warnings
|
|
|
|
|
|
|
|
|
|
| 4 |
import streamlit as st
|
| 5 |
import ner4opt
|
| 6 |
from ner4opt.utils import preprocess, spacy_tokenize_sentence
|
|
|
|
| 7 |
from spacy import displacy
|
| 8 |
|
| 9 |
+
warnings.filterwarnings("ignore", category=DeprecationWarning)
|
| 10 |
+
|
| 11 |
HTML_WRAPPER = """<div style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem">{}</div>"""
|
| 12 |
|
| 13 |
+
# Define your example prompts here for easy management
|
| 14 |
+
EXAMPLE_PROMPTS = {
|
| 15 |
+
"Example 1️⃣: Asset Allocation": "Cautious Asset Investment has a total of $150,000 to manage and decides to invest it in money market fund, which yields a 2% return as well as in foreign bonds, which gives and average rate of return of 10.2%. Internal policies require PAI to diversify the asset allocation so that the minimum investment in money market fund is 40% of the total investment. Due to the risk of default of foreign countries, no more than 40% of the total investment should be allocated to foreign bonds. How much should the Cautious Asset Investment allocate in each asset so as to maximize its average return?",
|
| 16 |
+
"Example 2️⃣: Production Optimization": "A factory produces two types of goods, A and B. Producing one unit of good A requires 2 hours of labor and 1 unit of raw material. Producing one unit of good B requires 3 hours of labor and 2 units of raw material. The factory has a total of 100 labor hours and 50 units of raw material available. If the profit from selling one unit of good A is $10 and from good B is $15, how many units of each good should be produced to maximize the total profit?",
|
| 17 |
+
"Example 3️⃣: Transportation Problem": "A company has two warehouses and three retail stores. Warehouse 1 has 500 units of a product and Warehouse 2 has 700 units. Store 1 requires 300 units, Store 2 requires 400 units, and Store 3 requires 500 units. The cost of shipping one unit from Warehouse 1 to Store 1 is $2, to Store 2 is $3, and to Store 3 is $4. The cost of shipping from Warehouse 2 to Store 1 is $5, to Store 2 is $2, and to Store 3 is $3. How should the company ship the products to minimize the total shipping cost?"
|
| 18 |
+
}
|
| 19 |
|
| 20 |
@st.cache_resource
|
| 21 |
def load_models():
|
|
|
|
| 26 |
hybrid_ner_model = ner4opt.Ner4Opt("hybrid")
|
| 27 |
return lexical_ner_model, lexical_plus_ner_model, semantic_ner_model, hybrid_ner_model
|
| 28 |
|
| 29 |
+
def set_example_text(example_key):
|
| 30 |
+
"""Callback to set the text area value based on the selected example."""
|
| 31 |
+
st.session_state.text_input = EXAMPLE_PROMPTS[example_key]
|
| 32 |
|
| 33 |
def main():
|
|
|
|
| 34 |
st.title("""Ner4Opt: Named Entity Recognition for Optimization""")
|
|
|
|
| 35 |
st.markdown("""Given an optimization problem in natural language, Ner4Opt extracts optimization related entities from free-form text. The source code for Ner4Opt is available at https://github.com/skadio/ner4opt""")
|
| 36 |
|
| 37 |
+
# Initialize session state for the text input if it doesn't exist
|
| 38 |
+
if "text_input" not in st.session_state:
|
| 39 |
+
st.session_state.text_input = EXAMPLE_PROMPTS["Example 1️⃣: Asset Allocation"]
|
| 40 |
+
|
| 41 |
+
# --- Add the example prompts section ---
|
| 42 |
+
st.subheader("Try with an example:")
|
| 43 |
+
cols = st.columns(len(EXAMPLE_PROMPTS))
|
| 44 |
+
for i, (key, value) in enumerate(EXAMPLE_PROMPTS.items()):
|
| 45 |
+
with cols[i]:
|
| 46 |
+
if st.button(key):
|
| 47 |
+
set_example_text(key)
|
| 48 |
+
|
| 49 |
+
# ----------------------------------------
|
| 50 |
+
|
| 51 |
option = st.sidebar.selectbox(
|
| 52 |
'Select a lexical, semantic, or hybrid model for extracting entities',
|
| 53 |
('Lexical', 'Lexical Plus', 'Semantic', 'Hybrid'), index=3)
|
| 54 |
|
| 55 |
text = st.text_area(
|
| 56 |
"Text",
|
| 57 |
+
value=st.session_state.text_input, # Use the session state value here
|
| 58 |
)
|
| 59 |
text = text.strip()
|
| 60 |
if text == "":
|
| 61 |
st.write("Please write a valid sentence.")
|
| 62 |
|
| 63 |
+
lexical_ner_model, lexical_plus_ner_model, semantic_ner_model, hybrid_ner_model = load_models()
|
|
|
|
| 64 |
|
| 65 |
# get entities
|
| 66 |
if option == "Lexical":
|
|
|
|
| 92 |
html_ner = html_ner.replace("\n", " ")
|
| 93 |
st.write(HTML_WRAPPER.format(html_ner), unsafe_allow_html=True)
|
| 94 |
|
|
|
|
| 95 |
if __name__ == '__main__':
|
| 96 |
+
main()
|