pages/Workflow & Model Overview.py

import streamlit as st
import pandas as pd

# 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;
        }
    </style>
""", unsafe_allow_html=True)

# Main Title
st.markdown('<div class="main-title">Persian Named Entity Recognition - Word Embeddings-based Model</div>', unsafe_allow_html=True)

# Introduction
st.markdown("""
<div class="section">
    <p>Named Entity Recognition (NER) models identify and categorize important entities in a text. This page details a word embeddings-based NER model for Persian texts, using the <code>persian_w2v_cc_300d</code> word embeddings. The model is pretrained and available for use with Spark NLP.</p>
</div>
""", unsafe_allow_html=True)

# Model Description
st.markdown('<div class="sub-title">Description</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>The <code>personer_cc_300d</code> model uses Persian word embeddings to find 6 different types of entities in Persian text. It is trained using <code>persian_w2v_cc_300d</code> word embeddings, so please use the same embeddings in the pipeline. It can identify the following types of entities:</p>
    <ul>
        <li>PER (Persons)</li>
        <li>FAC (Facilities)</li>
        <li>PRO (Products)</li>
        <li>LOC (Locations)</li>
        <li>ORG (Organizations)</li>
        <li>EVENT (Events)</li>
    </ul>
</div>
""", unsafe_allow_html=True)

# Setup Instructions
st.markdown('<div class="sub-title">Setup</div>', unsafe_allow_html=True)
st.markdown('<p>To use the model, you need Spark NLP installed. You can install it using pip:</p>', unsafe_allow_html=True)
st.code("""
pip install spark-nlp
pip install pyspark
""", language="bash")

st.markdown("<p>Then, import Spark NLP and start a Spark session:</p>", unsafe_allow_html=True)
st.code("""
import sparknlp

# Start Spark Session
spark = sparknlp.start()
""", language='python')

# Example Usage
st.markdown('<div class="sub-title">Example Usage with Persian NER Model</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>Below is an example of how to set up and use the <code>personer_cc_300d</code> model for named entity recognition in Persian:</p>
</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, round, concat, lit, explode

# Define the components of the pipeline
documentAssembler = DocumentAssembler() \\
    .setInputCol("text") \\
    .setOutputCol("document")

sentenceDetector = SentenceDetectorDLModel.pretrained("sentence_detector_dl", "xx") \\
    .setInputCols(["document"]) \\
    .setOutputCol("sentence")

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

word_embeddings = WordEmbeddingsModel.pretrained("persian_w2v_cc_300d", "fa") \\
    .setInputCols(["document", "token"]) \\
    .setOutputCol("embeddings")

ner = NerDLModel.pretrained("personer_cc_300d", "fa") \\
    .setInputCols(["sentence", "token", "embeddings"]) \\
    .setOutputCol("ner")

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

# Create the pipeline
pipeline = Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, word_embeddings, ner, ner_converter])

# Create sample data
example = """
به گزارش خبرنگار ایرنا ، بر اساس تصمیم این مجمع ، محمد قمی نماینده مردم پاکدشت به عنوان رئیس و علی‌اکبر موسوی خوئینی و شمس‌الدین وهابی نمایندگان مردم تهران به عنوان نواب رئیس انتخاب شدند
"""
data = spark.createDataFrame([[example]]).toDF("text")

# Fit and transform data with the pipeline
result = pipeline.fit(data).transform(data)

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

import pandas as pd

# Create the data for the DataFrame
data = {
    "chunk": [
        "خبرنگار ایرنا", 
        "محمد قمی", 
        "پاکدشت", 
        "علی‌اکبر موسوی خوئینی", 
        "شمس‌الدین وهابی", 
        "تهران"
    ],
    "ner_label": [
        "ORG", 
        "PER", 
        "LOC", 
        "PER", 
        "PER", 
        "LOC"
    ]
}

# Creating the DataFrame
df = pd.DataFrame(data)
df.index += 1
st.dataframe(df)

# Model Information
st.markdown('<div class="sub-title">Model Information</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>The <code>personer_cc_300d</code> model details are as follows:</p>
    <ul>
        <li><strong>Model Name:</strong> personer_cc_300d</li>
        <li><strong>Type:</strong> ner</li>
        <li><strong>Compatibility:</strong> Spark NLP 2.7.0+</li>
        <li><strong>License:</strong> Open Source</li>
        <li><strong>Edition:</strong> Official</li>
        <li><strong>Input Labels:</strong> [document, token, word_embeddings]</li>
        <li><strong>Output Labels:</strong> [ner]</li>
        <li><strong>Language:</strong> fa</li>
        <li><strong>Dependencies:</strong> persian_w2v_cc_300d</li>
    </ul>
</div>
""", unsafe_allow_html=True)

# Summary
st.markdown('<div class="sub-title">Summary</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>This page provided an overview of the <code>personer_cc_300d</code> model for Persian NER. We discussed how to set up and use the model with Spark NLP, including example code and results. We also provided details on the model's specifications and links to relevant resources for further exploration.</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/2020/12/07/personer_cc_300d_fa.html" rel="noopener">personer_cc_300d_fa</a></li>
        <li><a class="link" href="https://www.aclweb.org/anthology/C16-1319/" target="_blank" rel="noopener">Data Source</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://github.com/JohnSnowLabs/spark-nlp" target="_blank">GitHub Repository</a>: Report issues or contribute</li>
        <li><a class="link" href="https://forum.johnsnowlabs.com/" target="_blank">Community Forum</a>: Ask questions, share ideas, and get support</li>
    </ul>
</div>
""", unsafe_allow_html=True)