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

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

# Initialize Spark NLP
@st.cache_resource
def init_spark():
    return sparknlp.start()

# Create Spark NLP pipeline
@st.cache_resource
def create_pipeline(year, month, day):
    document_assembler = DocumentAssembler()\
        .setInputCol("text")\
        .setOutputCol("document")

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

    date_matcher = DateMatcher() \
        .setInputCols(['sentence'])\
        .setOutputCol("date")\
        .setAnchorDateYear(year)\
        .setAnchorDateMonth(month)\
        .setAnchorDateDay(day)

    pipeline = Pipeline(
        stages=[ 
            document_assembler, 
            sentence_detector,
            date_matcher,
        ])

    return pipeline

# Fit data and get results
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)

    return results

# Set up the page layout
st.markdown('<div class="main-title">State-of-the-Art Date Detecting and normalization with Spark NLP</div>', unsafe_allow_html=True)
st.write("")

# Sidebar content
date = st.sidebar.date_input('Select reference date')

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

# Load examples from files
folder_path = f"inputs/date_matcher"
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
]

st.subheader("Automatically detect phrases expressing dates and normalize them with respect to a reference date.")
selected_text = st.selectbox("Select an example", examples)
custom_input = st.text_input("Try it with your own Sentence!")

text_to_analyze = custom_input if custom_input else selected_text

st.subheader('Full example text')
st.write(text_to_analyze)

# Initialize Spark and create pipeline
spark = init_spark()
pipeline = create_pipeline(date.year, date.month, date.day)
output = fit_data(pipeline, text_to_analyze)

# Display matched sentence
st.subheader("Dates matched:")

# Extracting the results into a list
data = []
for result in output:
    sentences = result['sentence']
    dates = result['date']
    for date in dates:
        sent = sentences[int(date.metadata['sentence'])]
        data.append({
            'text/chunk': sent.result[date.begin:date.end+1],
            'mapped_date': date.result
        })

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