| import streamlit as st | |
| import time | |
| import pandas as pd | |
| import io | |
| from transformers import pipeline | |
| from streamlit_extras.stylable_container import stylable_container | |
| import plotly.express as px | |
| import zipfile | |
| from PyPDF2 import PdfReader | |
| import docx | |
| import os | |
| from comet_ml import Experiment | |
| import re | |
| import numpy as np | |
| st.subheader("4-Named Entity Recognition Web App", divider = "rainbow") | |
| st.link_button("by nlpblogs", "https://nlpblogs.com", type = "tertiary") | |
| expander = st.expander("**Important notes on the 4-Named Entity Recognition Web App**") | |
| expander.write(''' | |
| **Named Entities:** | |
| This 4-Named Entity Recognition Web App predicts four (4) labels (“person”, “location”, “organization”, “miscellaneous”). Results are presented in an easy-to-read table, visualized in an interactive tree map, pie chart, and bar chart, and are available for download along with a Glossary of tags. | |
| **How to Use:** | |
| Upload your .pdf or .docx file. Then, click the 'Results' button to extract and tag entities in your text data. | |
| **Usage Limits:** | |
| You can request results up to 10 times. | |
| **Customization:** | |
| To change the app's background color to white or black, click the three-dot menu on the right-hand side of your app, go to Settings and then Choose app theme, colors and fonts. | |
| **Technical issues:** | |
| If your connection times out, please refresh the page or reopen the app's URL. | |
| For any errors or inquiries, please contact us at [email protected] | |
| ''') | |
| with st.sidebar: | |
| container = st.container(border=True) | |
| container.write("**Named Entity Recognition (NER)** is the task of extracting and tagging entities in text data. Entities can be persons, organizations, locations, countries, products, events etc.") | |
| st.subheader("Related NLP Web Apps", divider = "rainbow") | |
| st.link_button("8-Named Entity Recognition Web App", "https://nlpblogs.com/shop/named-entity-recognition-ner/8-named-entity-recognition-web-app/", type = "primary") | |
| COMET_API_KEY = os.environ.get("COMET_API_KEY") | |
| COMET_WORKSPACE = os.environ.get("COMET_WORKSPACE") | |
| COMET_PROJECT_NAME = os.environ.get("COMET_PROJECT_NAME") | |
| if COMET_API_KEY and COMET_WORKSPACE and COMET_PROJECT_NAME: | |
| comet_initialized = True | |
| else: | |
| comet_initialized = False | |
| st.warning("Comet ML not initialized. Check environment variables.") | |
| if 'file_upload_attempts' not in st.session_state: | |
| st.session_state['file_upload_attempts'] = 0 | |
| max_attempts = 10 | |
| upload_file = st.file_uploader("Upload your file. Accepted file formats include: .pdf, .docx", type=['pdf', 'docx']) | |
| text = None | |
| df = None | |
| if upload_file is not None: | |
| file_extension = upload_file.name.split('.')[-1].lower() | |
| if file_extension == 'pdf': | |
| try: | |
| pdf_reader = PdfReader(upload_file) | |
| text = "" | |
| for page in pdf_reader.pages: | |
| text += page.extract_text() | |
| st.write("Due to security protocols, the file content is hidden.") | |
| except Exception as e: | |
| st.error(f"An error occurred while reading PDF: {e}") | |
| elif file_extension == 'docx': | |
| try: | |
| doc = docx.Document(upload_file) | |
| text = "\n".join([para.text for para in doc.paragraphs]) | |
| st.write("Due to security protocols, the file content is hidden.") | |
| except Exception as e: | |
| st.error(f"An error occurred while reading docx: {e}") | |
| else: | |
| st.warning("Unsupported file type.") | |
| st.stop() | |
| st.divider() | |
| if st.button("Results"): | |
| if st.session_state['file_upload_attempts'] >= max_attempts: | |
| st.error(f"You have requested results {max_attempts} times. You have reached your daily request limit.") | |
| st.stop() | |
| st.session_state['file_upload_attempts'] += 1 | |
| with st.spinner("Wait for it...", show_time=True): | |
| time.sleep(5) | |
| model = pipeline("token-classification", model="dslim/distilbert-NER", aggregation_strategy = "max") | |
| text1 = model(text) | |
| df1 = pd.DataFrame(text1) | |
| pattern = r'[^\w\s]' | |
| df1['word'] = df1['word'].replace(pattern, '', regex=True) | |
| df2 = df1.replace('', 'Unknown') | |
| df = df2.dropna() | |
| if comet_initialized: | |
| experiment = Experiment( | |
| api_key=COMET_API_KEY, | |
| workspace=COMET_WORKSPACE, | |
| project_name=COMET_PROJECT_NAME, | |
| ) | |
| experiment.log_parameter("input_text", text) | |
| experiment.log_table("predicted_entities", df) | |
| properties = {"border": "2px solid gray", "color": "blue", "font-size": "16px"} | |
| df_styled = df.style.set_properties(**properties) | |
| st.dataframe(df_styled) | |
| with st.expander("See Glossary of tags"): | |
| st.write(''' | |
| '**word**': ['entity extracted from your text data'] | |
| '**score**': ['accuracy score; how accurately a tag has been assigned to a given entity'] | |
| '**entity_group**': ['label (tag) assigned to a given extracted entity'] | |
| '**start**': ['index of the start of the corresponding entity'] | |
| '**end**': ['index of the end of the corresponding entity'] | |
| ''') | |
| if df is not None: | |
| fig = px.treemap(df, path=[px.Constant("all"), 'word', 'entity_group'], | |
| values='score', color='entity_group') | |
| fig.update_layout(margin = dict(t=50, l=25, r=25, b=25)) | |
| st.subheader("Tree map", divider = "rainbow") | |
| st.plotly_chart(fig) | |
| if comet_initialized: | |
| experiment.log_figure(figure=fig, figure_name="entity_treemap") | |
| if df is not None: | |
| value_counts1 = df['entity_group'].value_counts() | |
| df1 = pd.DataFrame(value_counts1) | |
| final_df = df1.reset_index().rename(columns={"index": "entity_group"}) | |
| col1, col2 = st.columns(2) | |
| with col1: | |
| fig1 = px.pie(final_df, values='count', names='entity_group', hover_data=['count'], labels={'count': 'count'}, title='Percentage of predicted labels') | |
| fig1.update_traces(textposition='inside', textinfo='percent+label') | |
| st.subheader("Pie Chart", divider = "rainbow") | |
| st.plotly_chart(fig1) | |
| if comet_initialized: | |
| experiment.log_figure(figure=fig1, figure_name="label_pie_chart") | |
| with col2: | |
| fig2 = px.bar(final_df, x="count", y="entity_group", color="entity_group", text_auto=True, title='Occurrences of predicted labels') | |
| st.subheader("Bar Chart", divider = "rainbow") | |
| st.plotly_chart(fig2) | |
| if comet_initialized: | |
| experiment.log_figure(figure=fig2, figure_name="label_bar_chart") | |
| dfa = pd.DataFrame( | |
| data={ | |
| 'word': ['entity extracted from your text data'], 'score': ['accuracy score; how accurately a tag has been assigned to a given entity'], 'entity_group': ['label (tag) assigned to a given extracted entity'], | |
| 'start': ['index of the start of the corresponding entity'], | |
| 'end': ['index of the end of the corresponding entity'], | |
| }) | |
| buf = io.BytesIO() | |
| with zipfile.ZipFile(buf, "w") as myzip: | |
| myzip.writestr("Summary of the results.csv", df.to_csv(index=False)) | |
| myzip.writestr("Glossary of tags.csv", dfa.to_csv(index=False)) | |
| with stylable_container( | |
| key="download_button", | |
| css_styles="""button { background-color: yellow; border: 1px solid black; padding: 5px; color: black; }""", | |
| ): | |
| st.download_button( | |
| label="Download zip file", | |
| data=buf.getvalue(), | |
| file_name="zip file.zip", | |
| mime="application/zip", | |
| ) | |
| if comet_initialized: | |
| experiment.log_asset(buf.getvalue(), file_name="downloadable_results.zip") | |
| st.divider() | |
| if comet_initialized: | |
| experiment.end() | |
| st.write(f"Number of times you requested results: {st.session_state['file_upload_attempts']}/{max_attempts}") | |