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", 
    initial_sidebar_state="auto"
)

# CSS for styling
st.markdown("""
    <style>
        .main-title {
            font-size: 36px;
            color: #4A90E2;
            font-weight: bold;
            text-align: center;
        }
        .section {
            background-color: #f9f9f9;
            padding: 10px;
            border-radius: 10px;
            margin-top: 10px;
        }
        .section p, .section ul {
            color: #666666;
        }
    </style>
""", unsafe_allow_html=True)

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

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

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

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

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


    if model == 'xlm_roberta_large_token_classifier_masakhaner':
      tokenClassifier = XlmRoBertaForTokenClassification.pretrained("xlm_roberta_large_token_classifier_masakhaner", "xx")\
          .setInputCols(["sentence",'token'])\
          .setOutputCol("ner")

    else:
      tokenClassifier = DistilBertForTokenClassification.pretrained("distilbert_base_token_classifier_masakhaner", "xx")\
          .setInputCols(["sentence",'token'])\
          .setOutputCol("ner")

    nlpPipeline = Pipeline(stages=[documentAssembler, sentenceDetector, tokenizer, tokenClassifier, ner_converter])
    return nlpPipeline

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

def annotate(data):
    document, chunks, labels = data["Document"], data["NER Chunk"], data["NER Label"]
    annotated_words = []
    for chunk, label in zip(chunks, labels):
        parts = document.split(chunk, 1)
        if parts[0]:
            annotated_words.append(parts[0])
        annotated_words.append((chunk, label))
        document = parts[1]
    if document:
        annotated_words.append(document)
    annotated_text(*annotated_words)

# Set up the page layout
st.markdown('<div class="main-title">Recognize entities in 10 African languages</div>', unsafe_allow_html=True)
st.markdown("""
<div class="section">
    <p>This model carries out Name Entity Recognition on 10 African languages (Amharic, Hausa, Igbo, Kinyarwanda, Luganda, Nigerian, Pidgin, Swahilu, Wolof, and Yorùbá).</p>
</div>
""", unsafe_allow_html=True)

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

language = st.sidebar.selectbox(
    "Choose the pretrained model",
    ["Amharic", "Hausa", "Igbo", "Kinyarwanda", "Luganda", "Nigerian", "Pidgin", "Swahilu", "Wolof", "Yorùbá"],
    help="For more info about the models visit: https://sparknlp.org/models"
)

try:
    labels_set = set()
    for i in results['NER Chunk'].values:
        labels_set.add(results["NER Label"][i])
        labels_set = list(labels_set)

    labels = st.sidebar.multiselect("Entity labels", options=labels_set, default=list(labels_set))
        
    NER_labs = ['PER', 'ORG', 'LOC', 'DATE']
    NER_exp = ['People, including fictional.', 'Companies, agencies, institutions, etc.', 'Countries, cities, states.', 'Date, Year']

    NER_dict = dict(zip(NER_labs, NER_exp))

    show_exp = st.sidebar.checkbox("Explain NER Labels", value=True)
    if show_exp:
        t_ner_k = []
        t_ner_v = []
    for t_lab in labels_set:
        if t_lab in NER_dict:
            t_ner_k.append(t_lab)
            t_ner_v.append(NER_dict[t_lab])
    tdf = pd.DataFrame({"NER": t_ner_k, "Meaning": t_ner_v})
    tdf.index=['']*len(t_ner_k)
    st.sidebar.table(tdf)
except:
    pass

# Reference notebook link in sidebar
link = """
<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/Ner_masakhaner.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/{language}"
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 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')
HTML_WRAPPER = """<div class="scroll entities" style="overflow-x: auto; border: 1px solid #e6e9ef; border-radius: 0.25rem; padding: 1rem; margin-bottom: 2.5rem; white-space:pre-wrap">{}</div>"""
st.markdown(HTML_WRAPPER.format(text_to_analyze), unsafe_allow_html=True)

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

# Display matched sentence
st.subheader("Processed output:")

results = {
    'Document': output[0]['document'][0].result,
    'NER Chunk': [n.result for n in output[0]['ner_chunk']],
    "NER Label": [n.metadata['entity'] for n in output[0]['ner_chunk']]
}

annotate(results)

with st.expander("View DataFrame"):
    df = pd.DataFrame({'NER Chunk': results['NER Chunk'], 'NER Label': results['NER Label']})
    df.index += 1
    st.dataframe(df)