Demo.py

import streamlit as st
import sparknlp
import os
import pandas as pd

from sparknlp.base import *
from sparknlp.annotator import *
from pyspark.ml import Pipeline
from sparknlp.pretrained import PretrainedPipeline
from annotated_text import annotated_text

# Page configuration
st.set_page_config(
    layout="wide", 
    page_title="Spark NLP Demos App", 
    initial_sidebar_state="auto"
)

# CSS for styling
st.markdown("""
    <style>
        .main-title {
            font-size: 36px;
            color: #4A90E2;
            font-weight: bold;
            text-align: center;
        }
        .section p, .section ul {
            color: #666666;
        }
        .stTable {
            margin-left: auto;
            margin-right: auto;
        }
    </style>
""", unsafe_allow_html=True)

@st.cache_resource
def init_spark():
    return sparknlp.start()

@st.cache_resource
def create_pipeline(model):
    document_assembler = DocumentAssembler() \
    .setInputCol('text') \
    .setOutputCol('document')

    sentence_detector = SentenceDetector() \
        .setInputCols(['document']) \
        .setOutputCol('sentences')

    tokenizer = Tokenizer() \
        .setInputCols(['sentences']) \
        .setOutputCol('tokens') \
        .setContextChars(['(', ')', '?', '!', '.', ','])

    keywords = YakeKeywordExtraction() \
        .setInputCols('tokens') \
        .setOutputCol('keywords') \
        .setMinNGrams(2) \
        .setMaxNGrams(5) \
        .setNKeywords(100) \
        .setStopWords(StopWordsCleaner().getStopWords())

    pipeline = Pipeline(stages=[
        document_assembler, 
        sentence_detector,
        tokenizer,
        keywords
    ])

    return pipeline

def fit_data(pipeline, data):
    empty_df = spark.createDataFrame([['']]).toDF('text')
    pipeline_model = pipeline.fit(empty_df)
    model = LightPipeline(pipeline_model)
    results = model.fullAnnotate(data)[0]

    return results
    
def highlight_keywords(data):
    document_text = data["document"][0].result
    keywords = data["keywords"]
    annotations = []
    last_index = 0

    for keyword in keywords:
        keyword_text = keyword.result
        start_index = document_text.find(keyword_text, last_index)
        if start_index != -1:
            if start_index > last_index:
                annotations.append(document_text[last_index:start_index])
            annotations.append((keyword_text, 'Key Word'))
            last_index = start_index + len(keyword_text)
    
    if last_index < len(document_text):
        annotations.append(document_text[last_index:])

    annotated_text(*annotations)

# Set up the page layout
st.markdown('<div class="main-title">Detect Key Phrases With Spark NLP</div>', unsafe_allow_html=True)

# Sidebar content
model = st.sidebar.selectbox(
    "Choose the pretrained model",
    ["yake_model"],
    help="For more info about the models visit: https://sparknlp.org/models"
)

# Reference notebook link in sidebar
link = """
<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/KEYPHRASE_EXTRACTION.ipynb">
    <img src="https://colab.research.google.com/assets/colab-badge.svg" style="zoom: 1.3" alt="Open In Colab"/>
</a>
"""
st.sidebar.markdown('Reference notebook:')
st.sidebar.markdown(link, unsafe_allow_html=True)

# Load examples
folder_path = f"inputs/{model}"
examples = [
    lines[1].strip() 
    for filename in os.listdir(folder_path) 
    if filename.endswith('.txt') 
    for lines in [open(os.path.join(folder_path, filename), 'r', encoding='utf-8').readlines()] 
    if len(lines) >= 2
]

selected_text = st.selectbox("Select a sample text", examples)
custom_input = st.text_input("Try it for yourself!")

if custom_input:
    selected_text = custom_input
elif selected_text:
    selected_text = selected_text

st.subheader('Selected Text')
st.write(selected_text)

# Initialize Spark and create pipeline
spark = init_spark()
pipeline = create_pipeline(model)
output = fit_data(pipeline, selected_text)

# Display output
st.subheader("Annotated Document:")
highlight_keywords(output)

keys_df = pd.DataFrame([(k.result, k.begin, k.end, k.metadata['score'], k.metadata['sentence']) for k in output['keywords']],
                       columns=['keywords', 'begin', 'end', 'score', 'sentence'])
keys_df['score'] = keys_df['score'].astype(float)
# ordered by relevance
with st.expander("View Data Table"):
    st.table(keys_df.sort_values(['sentence', 'score']))