Create new file

app.py

@@ -0,0 +1,55 @@
+import streamlit as st
+from datasets import load_dataset
+from spacy_streamlit import visualize_textcat, visualize_ner
+import spacy_streamlit
+
+
+import pandas as pd
+from io import StringIO
+from transformers import pipeline
+import spacy
+from PIL import Image
+
+# we write text
+st.title('Skills Extraction Project')
+
+# we write markdown
+st.markdown('This NLP project helps you extract skills from job description. You just need to paste a job description and directly access the required skills for a specific vacancy. Save time!', unsafe_allow_html=False)
+
+@st.cache(allow_output_mutation=True)
+def get_model():
+    return spacy.load("en_core_web_sm")
+
+nlp = get_model()
+
+raw_text = st.text_area(label="Insert your job description")
+
+#if raw_text != "":
+docx = nlp(raw_text)
+spacy_streamlit.visualize_ner(docx, labels = nlp.get_pipe('ner').labels)
+#spacy_streamlit.visualize_ner(docx,labels=nlp.get_pipe('ner').labels)
+    
+
+#download the skills & job description in a csv from a df
+#@st.cache
+#def convert_df(df):
+  # IMPORTANT: Cache the conversion to prevent computation on every rerun
+  #return df.to_csv().encode('utf-8')
+
+#csv = convert_df(my_large_df)
+
+#st.download_button(
+     #label="Download as as CSV",
+     #data=csv,
+     #file_name='skills.csv',
+     #mime='text/csv',
+ #)
+
+
+
+
+
+@st.cache  # 👈 This function will be cached
+def load_large_dataset():
+    # Do something really slow in here!
+    return load_dataset("glue", "sst2", split="validation")