Create app.py

app.py

@@ -0,0 +1,179 @@
+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
+
+
+import os
+from comet_ml import Experiment
+
+
+
+st.subheader("7-Persian Named Entity Recognition Web App", divider = "red")
+st.link_button("by nlpblogs", "https://nlpblogs.com", type = "tertiary")
+
+expander = st.expander("**Important notes on the 7-Persian Named Entity Recognition Web App**")
+expander.write('''
+    
+    **Named Entities:**
+    This 7-Persian Named Entity Recognition Web App predicts seven (7) labels (“person”, “location”, “money”, “organization”, “date”, “percent value”, “time”). 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.
+    Please check and adjust the language settings in your computer, so the Persian characters are handled properly in your downloaded file.
+    
+    **How to Use:**
+    Type or paste your text and press Ctrl + Enter. Then, click the 'Results' button to extract and tag entities in your text data.
+    
+    **Usage Limits:**
+    Unlimited number of Result requests.
+ 
+    **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 = "red")
+    st.link_button("14-Named Entity Recognition Web App", "https://nlpblogs.com/shop/named-entity-recognition-ner/14-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.")
+
+    
+
+text = st.text_area("Type or paste your text below, and then press Ctrl + Enter", key='my_text_area')
+st.write("**Input text**: ", text)
+
+def clear_text():
+    st.session_state['my_text_area'] = ""
+
+st.button("Clear text", on_click=clear_text)
+
+st.divider()
+
+if st.button("Results"):
+    with st.spinner("Wait for it...", show_time=True):
+        time.sleep(5)
+        model = pipeline("token-classification", model="HooshvareLab/bert-fa-base-uncased-ner-peyma", 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']
+            
+            **What does B and I mean in front of each entity_group?**
+            
+            Supposing that there are two words (word A, word B).
+            
+            **B** indicates that word A is the beginning of an entity_group and **I** indicates that word B is inside that entity_group. 
+            
+            For example, **Los** is the beginning of the entity_group **Location** and **Angeles** is inside the entity_group **Location**.
+            
+            Los (B-LOC) - Beginning of the entity_group **Location**
+            
+            Angeles (I-LOC) - Inside the entity_group **Location**
+            
+            ''')
+
+        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 = "red")
+            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 = "red")
+                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 = "red")
+                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()