Andrii Demydenko commited on
Commit 路
6e4b95f
1
Parent(s): 5b15289
add requirements, multi-pages struct, basic functionality
Browse files- app.py +21 -0
- pages/data_analysis.py +25 -0
- pages/introduction.py +11 -0
- pages/run_models.py +9 -0
- requirements.txt +5 -0
app.py
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
from st_pages import Page, show_pages, add_page_title
|
| 3 |
+
|
| 4 |
+
|
| 5 |
+
def main():
|
| 6 |
+
st.session_state["shared"] = True
|
| 7 |
+
st.set_page_config(
|
| 8 |
+
page_title="NLP - Project",
|
| 9 |
+
page_icon="馃",
|
| 10 |
+
)
|
| 11 |
+
add_page_title()
|
| 12 |
+
show_pages(
|
| 13 |
+
[
|
| 14 |
+
Page("pages/introduction.py", "Intro", "馃槉"),
|
| 15 |
+
Page("pages/data_analysis.py", "Data and data", "馃搳"),
|
| 16 |
+
Page("pages/run_models.py", "Run models", "馃"),
|
| 17 |
+
]
|
| 18 |
+
)
|
| 19 |
+
|
| 20 |
+
if __name__ == "__main__":
|
| 21 |
+
main()
|
pages/data_analysis.py
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
|
| 3 |
+
from matplotlib import pyplot as plt
|
| 4 |
+
from wordcloud import WordCloud, STOPWORDS
|
| 5 |
+
from datasets import load_dataset
|
| 6 |
+
import numpy as np
|
| 7 |
+
|
| 8 |
+
|
| 9 |
+
ds = load_dataset("rajteer/Natural_disaster_tweets", revision="main", split='train')
|
| 10 |
+
|
| 11 |
+
text_data = ' '.join([row['tweet_text'] for row in ds])
|
| 12 |
+
|
| 13 |
+
|
| 14 |
+
wordcloud = WordCloud(width=800, height=400).generate(text_data)
|
| 15 |
+
|
| 16 |
+
fig, ax = plt.subplots(figsize=(10, 5))
|
| 17 |
+
ax.imshow(wordcloud, interpolation='bilinear')
|
| 18 |
+
ax.axis('off')
|
| 19 |
+
|
| 20 |
+
st.pyplot(fig)
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
# DataSet links
|
| 24 |
+
st.subheader("DataSet links")
|
| 25 |
+
st.markdown("- [Humaid Dataset](https://crisisnlp.qcri.org/humaid_dataset?fbclid=IwAR2rpSdcVhcXvQagxAG5VA2dvwAUOJOCVwTKxqtDiz7soIhVMUtp_N0BfSo)")
|
pages/introduction.py
ADDED
|
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
|
| 3 |
+
st.title("NLP - Project")
|
| 4 |
+
|
| 5 |
+
st.write("**_Wprowadzenie do przetwarzania j臋zyka naturalnego_**")
|
| 6 |
+
|
| 7 |
+
st.subheader("Contributors:")
|
| 8 |
+
st.markdown("```\nAndrii Demydenko - 317084\nMieszko Niewiarowski - xxxxxx\nPawe艂 Rajter - xxxxxx```")
|
| 9 |
+
|
| 10 |
+
st.header("Topic of the project")
|
| 11 |
+
st.write("**Topic**: Wykrywanie wypadk贸w (miejsce, rodzaj, czas) na podstawie wpis贸w w mediach spo艂eczno艣ciowych")
|
pages/run_models.py
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import streamlit as st
|
| 2 |
+
from transformers import pipeline
|
| 3 |
+
|
| 4 |
+
pipe = pipeline( model="nlp-pw/test-model-2")
|
| 5 |
+
text = st.text_area("Enter your text here 馃槂")
|
| 6 |
+
|
| 7 |
+
if text:
|
| 8 |
+
out = pipe(text)
|
| 9 |
+
st.json(out)
|
requirements.txt
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
torch
|
| 2 |
+
transformers
|
| 3 |
+
|
| 4 |
+
wordcloud
|
| 5 |
+
st_pages
|