File size: 6,952 Bytes
f448bd6
 
 
 
5870362
f448bd6
 
5870362
 
 
f448bd6
 
 
5870362
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e989198
0079a24
5870362
 
f448bd6
 
 
 
 
 
 
 
 
 
5870362
 
f448bd6
5870362
 
 
 
 
 
 
 
f448bd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c2463ad
f448bd6
c2463ad
f448bd6
c2463ad
f448bd6
c2463ad
f448bd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6c0dd69
f448bd6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
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 gliner import GLiNER

import os
from comet_ml import Experiment



st.subheader("8-Named Entity Recognition Web App", divider = "red")
st.link_button("DEMO APP by nlpblogs", "https://nlpblogs.com", type = "tertiary")

expander = st.expander("**Important notes on the 8-Named Entity Recognition Web App**")
expander.write('''
    
    **Named Entities:**
    This 8-Named Entity Recognition Web App predicts eight (8) labels (“person”, “country”, “city”, “organization”, “date”, “money”, “percent value”, “position”). 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:**
    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 info@nlpblogs.com
    
''')


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 = GLiNER.from_pretrained("xomad/gliner-model-merge-large-v1.0")
        labels = ["person", "country", "city", "organization", "date", "money", "percent value", "position"]
        entities = model.predict_entities(text, labels)
        df = pd.DataFrame(entities)

        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('''
            '**text**': ['entity extracted from your text data']
            
            '**score**': ['accuracy score; how accurately a tag has been assigned to a given entity']
            
            '**label**': ['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"), 'text', 'label'],
                                 values='score', color='label')
            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['label'].value_counts()
            df1 = pd.DataFrame(value_counts1)
            final_df = df1.reset_index().rename(columns={"index": "label"})
            col1, col2 = st.columns(2)
            with col1:
                fig1 = px.pie(final_df, values='count', names='label', 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="label", color="label", 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={
                'text': ['entity extracted from your text data'], 'score': ['accuracy score; how accurately a tag has been assigned to a given entity'], 'label': ['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()