pages/Workflow & Model Overview.py

import streamlit as st

# Custom CSS for better styling
st.markdown("""
    <style>
        .main-title {
            font-size: 36px;
            color: #4A90E2;
            font-weight: bold;
            text-align: center;
        }
        .sub-title {
            font-size: 24px;
            color: #4A90E2;
            margin-top: 20px;
        }
        .section {
            background-color: #f9f9f9;
            padding: 15px;
            border-radius: 10px;
            margin-top: 20px;
        }
        .section h2 {
            font-size: 22px;
            color: #4A90E2;
        }
        .section p, .section ul {
            color: #666666;
        }
        .link {
            color: #4A90E2;
            text-decoration: none;
        }
        .benchmark-table {
            width: 100%;
            border-collapse: collapse;
            margin-top: 20px;
        }
        .benchmark-table th, .benchmark-table td {
            border: 1px solid #ddd;
            padding: 8px;
            text-align: left;
        }
        .benchmark-table th {
            background-color: #4A90E2;
            color: white;
        }
        .benchmark-table td {
            background-color: #f2f2f2;
        }
    </style>
""", unsafe_allow_html=True)

# Main Title
st.markdown('<div class="main-title">Detect Entities (66-labeled) in General Scope</div>', unsafe_allow_html=True)

# Description
st.markdown("""
<div class="section">
    <p>This app utilizes the <strong>nerdl_fewnerd_subentity_100d</strong> model, which is trained on the Few-NERD/inter public dataset to detect 66 entities with high accuracy. The model is based on 100d GloVe embeddings, ensuring robust entity detection.</p>
</div>
""", unsafe_allow_html=True)

# What is Entity Recognition
st.markdown('<div class="sub-title">What is Entity Recognition?</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p><strong>Entity Recognition</strong> is a task in Natural Language Processing (NLP) that involves identifying and classifying named entities in text into predefined categories. For general texts, this model focuses on detecting a wide range of entities, which are crucial for understanding and analyzing diverse content.</p>
</div>
""", unsafe_allow_html=True)

# Model Importance and Applications
st.markdown('<div class="sub-title">Model Importance and Applications</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>The <strong>nerdl_fewnerd_subentity_100d</strong> model is highly effective for extracting named entities from general texts. Its applications include:</p>
    <ul>
        <li><strong>Text Analysis:</strong> The model can be used to identify and categorize mentions of a wide variety of entities in text documents, which is valuable for text mining and information retrieval.</li>
        <li><strong>Content Classification:</strong> By recognizing key entities, the model helps in categorizing content based on entity types, which is useful for organizing and filtering large volumes of data.</li>
        <li><strong>Knowledge Graph Construction:</strong> Companies can use the model to extract entities and build comprehensive knowledge graphs from textual data.</li>
        <li><strong>Research and Development:</strong> The model aids in identifying specific entities in scientific and technical documents, facilitating better research and analysis.</li>
    </ul>
    <p>Why use the <strong>nerdl_fewnerd_subentity_100d</strong> model?</p>
    <ul>
        <li><strong>Pre-trained on Few-NERD Dataset:</strong> The model is specifically trained on diverse general data, making it well-suited for handling a wide range of text types.</li>
        <li><strong>High Accuracy:</strong> The model achieves impressive precision and recall, ensuring reliable entity detection.</li>
        <li><strong>Ease of Use:</strong> Simplifies the process of entity recognition with minimal setup required.</li>
    </ul>
</div>
""", unsafe_allow_html=True)

# Predicted Entities
st.markdown('<div class="sub-title">Predicted Entities</div>', unsafe_allow_html=True)
# st.markdown("""
# <div class="section">
#     <ul>
#         <li><strong>building-theater</strong></li>
#         <li><strong>art-other</strong></li>
#         <li><strong>location-bodiesofwater</strong></li>
#         <li><strong>other-god</strong></li>
#         <li><strong>organization-politicalparty</strong></li>
#         <li><strong>product-other</strong></li>
#         <li><strong>building-sportsfacility</strong></li>
#         <li><strong>building-restaurant</strong></li>
#         <li><strong>organization-sportsleague</strong></li>
#         <li><strong>event-election</strong></li>
#         <li><strong>organization-media/newspaper</strong></li>
#         <li><strong>product-software</strong></li>
#         <li><strong>other-educationaldegree</strong></li>
#         <li><strong>person-politician</strong></li>
#         <li><strong>person-soldier</strong></li>
#         <li><strong>other-disease</strong></li>
#         <li><strong>product-airplane</strong></li>
#         <li><strong>person-athlete</strong></li>
#         <li><strong>location-mountain</strong></li>
#         <li><strong>organization-company</strong></li>
#         <li><strong>other-biologything</strong></li>
#         <li><strong>location-other</strong></li>
#         <li><strong>other-livingthing</strong></li>
#         <li><strong>person-actor</strong></li>
#         <li><strong>organization-other</strong></li>
#         <li><strong>event-protest</strong></li>
#         <li><strong>art-film</strong></li>
#         <li><strong>other-award</strong></li>
#         <li><strong>other-astronomything</strong></li>
#         <li><strong>building-airport</strong></li>
#         <li><strong>product-food</strong></li>
#         <li><strong>person-other</strong></li>
#         <li><strong>event-disaster</strong></li>
#         <li><strong>product-weapon</strong></li>
#         <li><strong>event-sportsevent</strong></li>
#         <li><strong>location-park</strong></li>
#         <li><strong>product-ship</strong></li>
#         <li><strong>building-library</strong></li>
#         <li><strong>art-painting</strong></li>
#         <li><strong>building-other</strong></li>
#         <li><strong>other-currency</strong></li>
#         <li><strong>organization-education</strong></li>
#         <li><strong>person-scholar</strong></li>
#         <li><strong>organization-showorganization</strong></li>
#         <li><strong>person-artist/author</strong></li>
#         <li><strong>product-train</strong></li>
#         <li><strong>location-GPE</strong></li>
#         <li><strong>product-car</strong></li>
#         <li><strong>art-writtenart</strong></li>
#         <li><strong>event-attack/battle/war/militaryconflict</strong></li>
#         <li><strong>other-law</strong></li>
#         <li><strong>other-medical</strong></li>
#         <li><strong>organization-sportsteam</strong></li>
#         <li><strong>art-broadcastprogram</strong></li>
#         <li><strong>art-music</strong></li>
#         <li><strong>organization-government/governmentagency</strong></li>
#         <li><strong>other-language</strong></li>
#         <li><strong>event-other</strong></li>
#         <li><strong>person-director</strong></li>
#         <li><strong>other-chemicalthing</strong></li>
#         <li><strong>product-game</strong></li>
#         <li><strong>organization-religion</strong></li>
#         <li><strong>location-road/railway/highway/transit</strong></li>
#         <li><strong>location-island</strong></li>
#         <li><strong>building-hotel</strong></li>
#         <li><strong>building-hospital</strong></li>
#     </ul>
# </div>
# """, unsafe_allow_html=True)

st.markdown("""<div class="section"><p><code class="language-plaintext highlighter-rouge">building-theater</code>, <code class="language-plaintext highlighter-rouge">art-other</code>, <code class="language-plaintext highlighter-rouge">location-bodiesofwater</code>, <code class="language-plaintext highlighter-rouge">other-god</code>, <code class="language-plaintext highlighter-rouge">organization-politicalparty</code>, <code class="language-plaintext highlighter-rouge">product-other</code>, <code class="language-plaintext highlighter-rouge">building-sportsfacility</code>, <code class="language-plaintext highlighter-rouge">building-restaurant</code>, <code class="language-plaintext highlighter-rouge">organization-sportsleague</code>, <code class="language-plaintext highlighter-rouge">event-election</code>, <code class="language-plaintext highlighter-rouge">organization-media/newspaper</code>, <code class="language-plaintext highlighter-rouge">product-software</code>, <code class="language-plaintext highlighter-rouge">other-educationaldegree</code>, <code class="language-plaintext highlighter-rouge">person-politician</code>, <code class="language-plaintext highlighter-rouge">person-soldier</code>, <code class="language-plaintext highlighter-rouge">other-disease</code>, <code class="language-plaintext highlighter-rouge">product-airplane</code>, <code class="language-plaintext highlighter-rouge">person-athlete</code>, <code class="language-plaintext highlighter-rouge">location-mountain</code>, <code class="language-plaintext highlighter-rouge">organization-company</code>, <code class="language-plaintext highlighter-rouge">other-biologything</code>, <code class="language-plaintext highlighter-rouge">location-other</code>, <code class="language-plaintext highlighter-rouge">other-livingthing</code>, <code class="language-plaintext highlighter-rouge">person-actor</code>, <code class="language-plaintext highlighter-rouge">organization-other</code>, <code class="language-plaintext highlighter-rouge">event-protest</code>, <code class="language-plaintext highlighter-rouge">art-film</code>, <code class="language-plaintext highlighter-rouge">other-award</code>, <code class="language-plaintext highlighter-rouge">other-astronomything</code>, <code class="language-plaintext highlighter-rouge">building-airport</code>, <code class="language-plaintext highlighter-rouge">product-food</code>, <code class="language-plaintext highlighter-rouge">person-other</code>, <code class="language-plaintext highlighter-rouge">event-disaster</code>, <code class="language-plaintext highlighter-rouge">product-weapon</code>, <code class="language-plaintext highlighter-rouge">event-sportsevent</code>, <code class="language-plaintext highlighter-rouge">location-park</code>, <code class="language-plaintext highlighter-rouge">product-ship</code>, <code class="language-plaintext highlighter-rouge">building-library</code>, <code class="language-plaintext highlighter-rouge">art-painting</code>, <code class="language-plaintext highlighter-rouge">building-other</code>, <code class="language-plaintext highlighter-rouge">other-currency</code>, <code class="language-plaintext highlighter-rouge">organization-education</code>, <code class="language-plaintext highlighter-rouge">person-scholar</code>, <code class="language-plaintext highlighter-rouge">organization-showorganization</code>, <code class="language-plaintext highlighter-rouge">person-artist/author</code>, <code class="language-plaintext highlighter-rouge">product-train</code>, <code class="language-plaintext highlighter-rouge">location-GPE</code>, <code class="language-plaintext highlighter-rouge">product-car</code>, <code class="language-plaintext highlighter-rouge">art-writtenart</code>, <code class="language-plaintext highlighter-rouge">event-attack/battle/war/militaryconflict</code>, <code class="language-plaintext highlighter-rouge">other-law</code>, <code class="language-plaintext highlighter-rouge">other-medical</code>, <code class="language-plaintext highlighter-rouge">organization-sportsteam</code>, <code class="language-plaintext highlighter-rouge">art-broadcastprogram</code>, <code class="language-plaintext highlighter-rouge">art-music</code>, <code class="language-plaintext highlighter-rouge">organization-government/governmentagency</code>, <code class="language-plaintext highlighter-rouge">other-language</code>, <code class="language-plaintext highlighter-rouge">event-other</code>, <code class="language-plaintext highlighter-rouge">person-director</code>, <code class="language-plaintext highlighter-rouge">other-chemicalthing</code>, <code class="language-plaintext highlighter-rouge">product-game</code>, <code class="language-plaintext highlighter-rouge">organization-religion</code>, <code class="language-plaintext highlighter-rouge">location-road/railway/highway/transit</code>, <code class="language-plaintext highlighter-rouge">location-island</code>, <code class="language-plaintext highlighter-rouge">building-hotel</code>, <code class="language-plaintext highlighter-rouge">building-hospital</code></p></div>""", unsafe_allow_html=True)

# How to Use the Model
st.markdown('<div class="sub-title">How to Use the Model</div>', unsafe_allow_html=True)
st.code('''
from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
from pyspark.sql.functions import col, expr

# Load the pre-trained model
document_assembler = DocumentAssembler() \\
    .setInputCol("text") \\
    .setOutputCol("document")

sentence_detector = SentenceDetector() \\
    .setInputCols(["document"]) \\
    .setOutputCol("sentence")

tokenizer = Tokenizer() \\
    .setInputCols(["sentence"]) \\
    .setOutputCol("token")

embeddings = WordEmbeddingsModel.pretrained("glove_100d", "en")\\
    .setInputCols("sentence", "token") \\
    .setOutputCol("embeddings")

ner_tagger = NerDLModel.pretrained("nerdl_fewnerd_subentity_100d", "en") \\
    .setInputCols(['sentence', 'token', 'embeddings']) \\
    .setOutputCol("ner")

ner_converter = NerConverter() \\
    .setInputCols(["document", "token", "ner"]) \\
    .setOutputCol("ner_chunk")

pipeline = Pipeline(stages=[
    document_assembler,
    sentence_detector,
    tokenizer,
    embeddings,
    ner_tagger,
    ner_converter
])

# Sample text
text = """
  In 2023, Apple Inc. announced the release of their new iPhone 15 at a major event held in San Francisco. 
  The announcement was made by Tim Cook, the CEO of Apple, who highlighted the innovative features of the device, 
  including its advanced camera system and improved battery life. The event took place on September 12, 2023, 
  and was streamed live on the company's official website. 
  During the event, several prominent tech bloggers, such as John Doe from TechCrunch and Jane Smith from The Verge, 
  were present to cover the announcement. Additionally, the event featured a surprise appearance by popular musician 
  Taylor Swift, who performed her hit single "Anti-Hero." The new iPhone 15 will be available for pre-order starting 
  on September 15, 2023, and is expected to hit the stores on September 22, 2023.
"""

# Create a DataFrame with the text
data = spark.createDataFrame([[text]]).toDF("text")

# Apply the pipeline to the data
model = pipeline.fit(data)
result = model.transform(data)

# Display results
result.select(
    expr("explode(ner_chunk) as ner_chunk")
).select(
    col("ner_chunk.result").alias("chunk"),
    col("ner_chunk.metadata.entity").alias("ner_label")
).show(truncate=False)
''', language='python')

st.text("""
+-------------+----------------------------+
|chunk        |ner_label                   |
+-------------+----------------------------+
|Apple Inc.   |organization-company        |
|iPhone 15    |product-other               |
|San Francisco|location-GPE                |
|Apple        |organization-company        |
|company's    |location-GPE                |
|TechCrunch   |organization-media/newspaper|
|Taylor Swift |person-artist/author        |
|iPhone 15    |product-other               |
+-------------+----------------------------+
""")

# Model Information
st.markdown('<div class="sub-title">Model Information</div>', unsafe_allow_html=True)
st.markdown("""
    <table class="benchmark-table">
        <tr>
            <th>Attribute</th>
            <th>Description</th>
        </tr>
        <tr>
            <td><strong>Model Name</strong></td>
            <td>nerdl_fewnerd_subentity_100d</td>
        </tr>
        <tr>
            <td><strong>Type</strong></td>
            <td>ner</td>
        </tr>
        <tr>
            <td><strong>Compatibility</strong></td>
            <td>Spark NLP 3.1.1+</td>
        </tr>
        <tr>
            <td><strong>License</strong></td>
            <td>Open Source</td>
        </tr>
        <tr>
            <td><strong>Edition</strong></td>
            <td>Official</td>
        </tr>
        <tr>
            <td><strong>Input Labels</strong></td>
            <td>[sentence, token, embeddings]</td>
        </tr>
        <tr>
            <td><strong>Output Labels</strong></td>
            <td>[ner]</td>
        </tr>
        <tr>
            <td><strong>Language</strong></td>
            <td>en</td>
        </tr>
    </table>
""", unsafe_allow_html=True)

# Data Source Information
st.markdown('<div class="sub-title">Data Source Information</div>', unsafe_allow_html=True)
st.markdown("""
    <table class="benchmark-table">
        <tr>
            <th>Attribute</th>
            <th>Description</th>
        </tr>
        <tr>
            <td><strong>Dataset</strong></td>
            <td>Few-NERD: A Few-shot Named Entity Recognition Dataset</td>
        </tr>
        <tr>
            <td><strong>Authors</strong></td>
            <td>Ding, Ning; Xu, Guangwei; Chen, Yulin; Wang, Xiaobin; Han, Xu; Xie, Pengjun; Zheng, Hai-Tao; Liu, Zhiyuan</td>
        </tr>
        <tr>
            <td><strong>Conference</strong></td>
            <td>ACL-IJCNL 2021</td>
        </tr>
    </table>
""", unsafe_allow_html=True)

# Benchmarking Results Description
st.markdown('<div class="sub-title">Benchmarking Results</div>', unsafe_allow_html=True)

st.markdown("""
<div class="section">
    <table class="benchmark-table">
        <thead>
            <tr>
                <th>Metric</th>
                <th>Score</th>
            </tr>
        </thead>
        <tbody>
            <tr>
                <td>Precision</td>
                <td>89.45%</td>
            </tr>
            <tr>
                <td>Recall</td>
                <td>91.67%</td>
            </tr>
            <tr>
                <td>F1-Score</td>
                <td>90.55%</td>
            </tr>
        </tbody>
    </table>
</div>
""", unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>The benchmarking results highlight the performance of the <strong>nerdl_fewnerd_subentity_100d</strong> model. The metrics used are:</p>
    <ul>
        <li><strong>Precision:</strong> The percentage of correctly identified entities out of all entities identified by the model.</li>
        <li><strong>Recall:</strong> The percentage of correctly identified entities out of all entities that should have been identified.</li>
        <li><strong>F1-Score:</strong> The harmonic mean of precision and recall, providing a balanced measure of the model's performance.</li>
    </ul>
    <p>The scores indicate that the model achieves high accuracy and reliability in detecting entities within general scope texts.</p>
</div>
""", unsafe_allow_html=True)

# Conclusion
st.markdown('<div class="sub-title">Conclusion</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>The <strong>nerdl_fewnerd_subentity_100d</strong> model is a powerful tool for entity recognition in general texts, offering high accuracy across a diverse set of entities. Its robust performance, as demonstrated by the benchmark results, makes it suitable for various applications such as text analysis, content classification, and knowledge graph construction. By utilizing this model, users can effectively extract and categorize entities, enhancing their ability to analyze and understand textual data.</p>
    <p>For more information and to access the model, visit the <a href="https://nlp.johnsnowlabs.com/2023/01/30/nerdl_fewnerd_subentity_100d_en.html" class="link">John Snow Labs Model Page</a> or the <a href="https://github.com/JohnSnowLabs/spark-nlp" class="link">Spark NLP GitHub Repository</a>.</p>
</div>
""", unsafe_allow_html=True)

# References
st.markdown('<div class="sub-title">References</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <ul>
        <li><a class="link" href="https://sparknlp.org/api/python/reference/autosummary/sparknlp/annotator/ner/ner_dl/index.html" target="_blank" rel="noopener">NerDLModel</a> annotator documentation</li>
        <li>Model Used: <a class="link" href="https://sparknlp.org/2021/07/22/nerdl_fewnerd_subentity_100d_en.html" rel="noopener">nerdl_fewnerd_subentity_100d_en</a></li>
        <li><a class="link" href="https://nlp.johnsnowlabs.com/recognize_entitie" target="_blank" rel="noopener">Visualization demos for NER in Spark NLP</a></li>
        <li><a class="link" href="https://www.johnsnowlabs.com/named-entity-recognition-ner-with-bert-in-spark-nlp/">Named Entity Recognition (NER) with BERT in Spark NLP</a></li>
    </ul>
</div>
""", unsafe_allow_html=True)

# Community & Support
st.markdown('<div class="sub-title">Community & Support</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <ul>
        <li><a class="link" href="https://sparknlp.org/" target="_blank">Official Website</a>: Documentation and examples</li>
        <li><a class="link" href="https://join.slack.com/t/spark-nlp/shared_invite/zt-198dipu77-L3UWNe_AJ8xqDk0ivmih5Q" target="_blank">Slack</a>: Live discussion with the community and team</li>
        <li><a class="link" href="https://github.com/JohnSnowLabs/spark-nlp" target="_blank">GitHub</a>: Bug reports, feature requests, and contributions</li>
        <li><a class="link" href="https://medium.com/spark-nlp" target="_blank">Medium</a>: Spark NLP articles</li>
        <li><a class="link" href="https://www.youtube.com/channel/UCmFOjlpYEhxf_wJUDuz6xxQ/videos" target="_blank">YouTube</a>: Video tutorials</li>
    </ul>
</div>
""", unsafe_allow_html=True)