Upload 5 files

.streamlit/config.toml

@@ -0,0 +1,3 @@
+[theme]
+base="light"
+primaryColor="#29B4E8"

Demo.py

@@ -0,0 +1,161 @@
+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
+from streamlit_tags import st_tags
+
+# 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(zeroShotLables=['']):
+    document_assembler = DocumentAssembler() \
+        .setInputCol('text') \
+        .setOutputCol('document')
+
+    tokenizer = Tokenizer() \
+        .setInputCols(['document']) \
+        .setOutputCol('token')
+    
+    zeroShotClassifier = XlmRoBertaForZeroShotClassification \
+        .pretrained('xlm_roberta_large_zero_shot_classifier_xnli_anli', 'xx') \
+        .setInputCols(['token', 'document']) \
+        .setOutputCol('class') \
+        .setCaseSensitive(False) \
+        .setMaxSentenceLength(512) \
+        .setCandidateLabels(zeroShotLables)
+
+    pipeline = Pipeline(stages=[document_assembler, tokenizer, zeroShotClassifier])
+    return pipeline
+
+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)
+
+tasks_models_descriptions = {
+    "Zero-Shot Classification": {
+        "models": ["xlm_roberta_large_zero_shot_classifier_xnli_anli"],
+        "description": "The 'xlm_roberta_large_zero_shot_classifier_xnli_anli' model provides flexible text classification without needing training data for specific categories. It is ideal for dynamic scenarios where text needs to be categorized into topics like urgent issues, technology, or sports without prior labeling."
+    }
+}
+
+# Sidebar content
+task = st.sidebar.selectbox("Choose the task", list(tasks_models_descriptions.keys()))
+model = st.sidebar.selectbox("Choose the pretrained model", tasks_models_descriptions[task]["models"], help="For more info about the models visit: https://sparknlp.org/models")
+
+# Reference notebook link in sidebar
+link = """
+<a href="https://github.com/JohnSnowLabs/spark-nlp-workshop/blob/357691d18373d6e8f13b5b1015137a398fd0a45f/Spark_NLP_Udemy_MOOC/Open_Source/17.01.Transformers-based_Embeddings.ipynb#L103">
+    <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)
+
+# Page content
+title, sub_title = (f'DeBERTa for {task}', tasks_models_descriptions[task]["description"])
+st.markdown(f'<div class="main-title">{title}</div>', unsafe_allow_html=True)
+container = st.container(border=True)
+container.write(sub_title)
+
+# Load examples
+examples_mapping = {
+    "Zero-Shot Classification" : [
+        "In today’s world, staying updated with urgent information is crucial as events can unfold rapidly and require immediate attention.",  # Urgent
+        "Mobile technology has become indispensable, allowing us to access news, updates, and connect with others no matter where we are.",  # Mobile
+        "For those who love to travel, the convenience of mobile apps has transformed how we plan and experience trips, providing real-time updates on flights, accommodations, and local attractions.",  # Travel
+        "The entertainment industry continually offers new movies that captivate audiences with their storytelling and visuals, providing a wide range of genres to suit every taste.",  # Movie
+        "Music is an integral part of modern life, with streaming platforms making it easy to discover new artists and enjoy favorite tunes anytime, anywhere.",  # Music
+        "Sports enthusiasts follow games and matches closely, with live updates and detailed statistics available at their fingertips, enhancing the excitement of every game.",  # Sport
+        "Weather forecasts play a vital role in daily planning, offering accurate and timely information to help us prepare for various weather conditions and adjust our plans accordingly.",  # Weather
+        "Technology continues to evolve rapidly, driving innovation across all sectors and improving our everyday lives through smarter devices, advanced software, and enhanced connectivity."  # Technology
+    ]
+}
+   
+examples = examples_mapping[task]
+selected_text = st.selectbox("Select an example", examples)
+custom_input = st.text_input("Try it with your own Sentence!")
+
+if task == 'Zero-Shot Classification':
+    zeroShotLables = ["urgent", "mobile", "travel", "movie", "music", "sport", "weather", "technology"]
+    lables = st_tags(
+        label='Select labels',
+        text='Press enter to add more',
+        value=zeroShotLables,
+        suggestions=[
+          "Positive", "Negative", "Neutral",
+          "Urgent", "Mobile", "Travel", "Movie", "Music", "Sport", "Weather", "Technology",
+          "Happiness", "Sadness", "Anger", "Fear", "Surprise", "Disgust",
+          "Informational", "Navigational", "Transactional", "Commercial Investigation",
+          "Politics", "Business", "Sports", "Entertainment", "Health", "Science",
+          "Product Quality", "Delivery Experience", "Customer Service", "Pricing", "Return Policy",
+          "Education", "Finance", "Lifestyle", "Fashion", "Food", "Art", "History",
+          "Culture", "Environment", "Real Estate", "Automotive", "Travel", "Fitness", "Career"],
+        maxtags = -1)
+
+try:
+  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)
+except:
+  text_to_analyze = selected_text
+
+# Initialize Spark and create pipeline
+spark = init_spark()
+pipeline = create_pipeline(zeroShotLables)
+output = fit_data(pipeline, text_to_analyze)
+
+# Display matched sentence
+st.subheader("Prediction:")
+st.markdown(f"Document Classified as: **{output[0]['class'][0].result}**")

Dockerfile

@@ -0,0 +1,72 @@
+# Download base image ubuntu 18.04
+FROM ubuntu:18.04
+
+# Set environment variables
+ENV NB_USER jovyan
+ENV NB_UID 1000
+ENV HOME /home/${NB_USER}
+ENV JAVA_HOME /usr/lib/jvm/java-8-openjdk-amd64/
+
+# Install required packages
+RUN apt-get update && apt-get install -y \
+    tar \
+    wget \
+    bash \
+    rsync \
+    gcc \
+    libfreetype6-dev \
+    libhdf5-serial-dev \
+    libpng-dev \
+    libzmq3-dev \
+    python3 \
+    python3-dev \
+    python3-pip \
+    unzip \
+    pkg-config \
+    software-properties-common \
+    graphviz \
+    openjdk-8-jdk \
+    ant \
+    ca-certificates-java \
+    && apt-get clean \
+    && update-ca-certificates -f
+
+# Install Python 3.8 and pip
+RUN add-apt-repository ppa:deadsnakes/ppa \
+    && apt-get update \
+    && apt-get install -y python3.8 python3-pip \
+    && apt-get clean
+
+# Set up JAVA_HOME
+RUN echo "export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-amd64/" >> /etc/profile \
+    && echo "export PATH=\$JAVA_HOME/bin:\$PATH" >> /etc/profile
+# Create a new user named "jovyan" with user ID 1000
+RUN useradd -m -u ${NB_UID} ${NB_USER}
+
+# Switch to the "jovyan" user
+USER ${NB_USER}
+
+# Set home and path variables for the user
+ENV HOME=/home/${NB_USER} \
+    PATH=/home/${NB_USER}/.local/bin:$PATH
+
+# Set up PySpark to use Python 3.8 for both driver and workers
+ENV PYSPARK_PYTHON=/usr/bin/python3.8
+ENV PYSPARK_DRIVER_PYTHON=/usr/bin/python3.8
+
+# Set the working directory to the user's home directory
+WORKDIR ${HOME}
+
+# Upgrade pip and install Python dependencies
+RUN python3.8 -m pip install --upgrade pip
+COPY requirements.txt /tmp/requirements.txt
+RUN python3.8 -m pip install -r /tmp/requirements.txt
+
+# Copy the application code into the container at /home/jovyan
+COPY --chown=${NB_USER}:${NB_USER} . ${HOME}
+
+# Expose port for Streamlit
+EXPOSE 7860
+
+# Define the entry point for the container
+ENTRYPOINT ["streamlit", "run", "Demo.py", "--server.port=7860", "--server.address=0.0.0.0"]

pages/Workflow & Model Overview.py

@@ -0,0 +1,189 @@
+import streamlit as st
+
+# Page configuration
+st.set_page_config(
+    layout="wide", 
+    initial_sidebar_state="auto"
+)
+
+# 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)
+
+# Title
+st.markdown('<div class="main-title">Introduction to XLM-RoBERTa Annotators in Spark NLP</div>', unsafe_allow_html=True)
+
+# Subtitle
+st.markdown("""
+<div class="section">
+    <p>XLM-RoBERTa (Cross-lingual Robustly Optimized BERT Approach) is an advanced multilingual model that extends the capabilities of RoBERTa to over 100 languages. Pre-trained on a massive, diverse corpus, XLM-RoBERTa is designed to handle various NLP tasks in a multilingual context, making it ideal for applications that require cross-lingual understanding. Below, we provide an overview of the XLM-RoBERTa annotators for these tasks:</p>
+</div>
+""", unsafe_allow_html=True)
+
+st.markdown("""<div class="sub-title">Zero-Shot Classification with XLM-RoBERTa</div>""", unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <p>Zero-shot classification is a powerful technique that allows models to classify text into categories that the model has never seen before during training. This is particularly useful in scenarios where labeled training data is scarce or when new categories emerge frequently.</p>
+    <p><strong>XLM-RoBERTa</strong> is a multilingual model, making it highly effective for zero-shot classification tasks across various languages. It leverages large-scale cross-lingual pretraining to understand and classify text in multiple languages without requiring language-specific annotated data.</p>
+<p>Using XLM-RoBERTa for Zero-Shot Classification enables:</p>
+    <ul>
+        <li><strong>Multilingual Understanding:</strong> Classify text across multiple languages without needing language-specific training data.</li>
+        <li><strong>Dynamic Classification:</strong> Adapt to new or emerging categories without retraining the model.</li>
+        <li><strong>Resource Efficiency:</strong> Bypass the need for extensive labeled datasets for each language or category.</li>
+    </ul>
+<p>Advantages of using XLM-RoBERTa for Zero-Shot Classification in Spark NLP include:</p>
+    <ul>
+        <li><strong>Scalability:</strong> Built on Apache Spark, the solution scales efficiently for processing large datasets.</li>
+        <li><strong>Flexibility:</strong> Easily adapt and integrate with existing Spark pipelines.</li>
+        <li><strong>Cross-Lingual Transfer:</strong> Benefit from XLM-RoBERTa’s cross-lingual transfer capabilities to classify text in various languages without additional fine-tuning.</li>
+        <li><strong>Pretrained Models:</strong> Leverage state-of-the-art pretrained models available in Spark NLP, reducing the need for custom training.</li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)
+
+st.markdown("""<div class="sub-title">How to Use XLM-RoBERTa for Token Classification in Spark NLP</div>""", unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+<p>To leverage XLM-RoBERTa for zero-shot classification, Spark NLP offers a seamless pipeline configuration. The following example demonstrates how to utilize XLM-RoBERTa for zero-shot text classification, enabling the classification of text into categories that the model has never encountered during training. Thanks to its multilingual training, XLM-RoBERTa can perform zero-shot classification across various languages, making it a versatile tool for global NLP applications.</p>
+</div>""", unsafe_allow_html=True)
+st.code('''
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+document_assembler = DocumentAssembler() \\
+    .setInputCol('text') \\
+    .setOutputCol('document')
+
+tokenizer = Tokenizer() \\
+    .setInputCols(['document']) \\
+    .setOutputCol('token')
+
+zeroShotClassifier = XlmRoBertaForZeroShotClassification \\
+    .pretrained('xlm_roberta_large_zero_shot_classifier_xnli_anli', 'xx') \\
+    .setInputCols(['token', 'document']) \\
+    .setOutputCol('class') \\
+    .setCaseSensitive(False) \\
+    .setMaxSentenceLength(512) \\
+    .setCandidateLabels(["urgent", "mobile", "travel", "movie", "music", "sport", "weather", "technology"])
+
+pipeline = Pipeline(stages=[
+    document_assembler,
+    tokenizer,
+    zeroShotClassifier
+])
+
+example = spark.createDataFrame([['I have a problem with my iphone that needs to be resolved asap!!']]).toDF("text")
+result = pipeline.fit(example).transform(example)
+result.select("class.result").show(truncate=False)
+''', language='python')
+
+st.text("""
++------------------+
+|result            |
++------------------+
+|["urgent"]        |
++------------------+
+""")
+
+# Example Output
+st.markdown("""
+<div class="section">
+    <p>This pipeline processes the input text and classifies it into one of the candidate labels provided. In the example given, the text is classified into categories such as "urgent", "mobile", "travel", etc.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Model Info Section
+st.markdown('<div class="sub-title">Choosing the Right Model</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <p>The XLM-RoBERTa model used here is pretrained on large multilingual datasets and fine-tuned for zero-shot classification tasks. It is available in Spark NLP, providing robust performance across different languages without needing task-specific annotated data.</p>
+    <p>For more information about the model, visit the <a class="link" href="https://huggingface.co/xlm-roberta-large-zero-shot-classifier-xnli-anli" target="_blank">XLM-RoBERTa Model Hub</a>.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# References Section
+st.markdown('<div class="sub-title">References</div>', unsafe_allow_html=True)
+st.markdown("""
+<div class="section">
+    <ul>
+        <li><a class="link" href="https://arxiv.org/abs/1911.02116" target="_blank">XLM-R: Cross-lingual Pre-training</a></li>
+        <li><a class="link" href="https://arxiv.org/abs/2008.03415" target="_blank">Zero-Shot Learning with XLM-RoBERTa</a></li>
+        <li><a class="link" href="https://huggingface.co/xlm-roberta-large-zero-shot-classifier-xnli-anli" target="_blank">XLM-RoBERTa Zero-Shot Classifier</a></li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)
+
+
+# Footer
+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)
+
+st.markdown('<div class="sub-title">Quick Links</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <ul>
+        <li><a class="link" href="https://sparknlp.org/docs/en/quickstart" target="_blank">Getting Started</a></li>
+        <li><a class="link" href="https://nlp.johnsnowlabs.com/models" target="_blank">Pretrained Models</a></li>
+        <li><a class="link" href="https://github.com/JohnSnowLabs/spark-nlp/tree/master/examples/python/annotation/text/english" target="_blank">Example Notebooks</a></li>
+        <li><a class="link" href="https://sparknlp.org/docs/en/install" target="_blank">Installation Guide</a></li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)

requirements.txt

@@ -0,0 +1,7 @@
+streamlit
+st-annotated-text
+streamlit-tags
+pandas
+numpy
+spark-nlp
+pyspark