Upload 5 files

.streamlit/config.toml

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

Demo.py

@@ -0,0 +1,109 @@
+import streamlit as st
+import sparknlp
+
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+# 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():
+    documentAssembler = DocumentAssembler() \
+        .setInputCol("text") \
+        .setOutputCol("documents")
+        
+    t5 = T5Transformer.pretrained("t5_grammar_error_corrector") \
+        .setTask("gec:") \
+        .setInputCols(["documents"])\
+        .setMaxOutputLength(200)\
+        .setOutputCol("corrections")
+
+    pipeline = Pipeline().setStages([documentAssembler, t5])
+    return pipeline
+
+def fit_data(pipeline, data):
+    df = spark.createDataFrame([[data]]).toDF("text")
+    result = pipeline.fit(df).transform(df)
+    return result.select('corrections.result').collect()
+
+# Sidebar content
+model = st.sidebar.selectbox(
+    "Choose the pretrained model",
+    ['t5_grammar_error_corrector'],
+    help="For more info about the models visit: https://sparknlp.org/models"
+)
+
+# Set up the page layout
+title = "Correct Sentences Grammar"
+sub_title = "This demo uses a text-to-text model fine-tuned to correct grammatical errors when the task is set to “gec:”. It is based on Prithiviraj Damodaran’s Gramformer model."
+
+st.markdown(f'<div class="main-title">{title}</div>', unsafe_allow_html=True)
+st.markdown(f'<div style="text-align: center; color: #666666;">{sub_title}</div>', unsafe_allow_html=True)
+
+# Reference notebook link in sidebar
+link = """
+<a href="https://colab.research.google.com/github/JohnSnowLabs/spark-nlp-workshop/blob/master/tutorials/streamlit_notebooks/T5_LINGUISTIC.ipynb#scrollTo=QAZ3vOX_SW7B">
+    <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)
+
+# Define the exampless
+examples = [
+    "She don't knows nothing about what's happening in the office.",
+    "They was playing soccer yesterday when it start raining heavily.",
+    "This car are more faster than that one, but it costed less money.",
+    "I seen him go to the store, but he don't buy nothing from there.",
+    "We was going to the park but it start raining before we could leave."
+]
+
+# Text selection and analysis
+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.write('Text to be converted to SQL query:')
+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()
+output = fit_data(pipeline, text_to_analyze)
+
+# Display transformed sentence
+st.write("Predicted Sentence:")
+output_text = "".join(output[0][0])
+st.markdown(f'<div class="scroll">{output_text}</div>', unsafe_allow_html=True)

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 +1,168 @@
+import streamlit as st
+
+# 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)
+
+# Title
+st.markdown('<div class="main-title">Correct Sentences Grammar</div>', unsafe_allow_html=True)
+
+# Introduction Section
+st.markdown("""
+<div class="section">
+    <p>Ensuring correct grammar in sentences is essential for clear and effective communication. Whether writing an email, an academic paper, or a casual message, proper grammar ensures that your message is understood as intended.</p>
+    <p>This page demonstrates how to implement a grammar correction pipeline using advanced NLP models. We utilize the T5 Transformer model, fine-tuned for grammar error correction, to automatically correct sentences and enhance their grammatical accuracy.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# T5 Transformer Overview
+st.markdown('<div class="sub-title">Understanding the T5 Transformer for Grammar Correction</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>The T5 (Text-To-Text Transfer Transformer) model, developed by Google, is a versatile tool for various NLP tasks, including grammar correction. By processing input sentences and applying the appropriate grammar corrections, T5 generates outputs that maintain the original meaning while correcting errors.</p>
+    <p>This is particularly useful for applications in writing assistance, automated editing, and educational tools, where grammatical accuracy is crucial.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Performance Section
+st.markdown('<div class="sub-title">Performance and Use Cases</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>The T5 model has shown strong performance in grammar correction tasks. It consistently produces accurate and contextually appropriate corrections, making it a valuable tool for improving written communication across various settings.</p>
+    <p>This capability is beneficial for students, professionals, and anyone who needs to ensure their writing is grammatically correct. The T5 model’s efficiency in correcting errors makes it a powerful asset for enhancing the quality of written content.</p>
+</div>
+""", unsafe_allow_html=True)
+
+# Implementation Section
+st.markdown('<div class="sub-title">Implementing Grammar Correction</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>The following example demonstrates how to implement a grammar correction pipeline using Spark NLP. The pipeline includes a document assembler and the T5 model for performing grammar corrections.</p>
+</div>
+""", unsafe_allow_html=True)
+
+st.code('''
+import sparknlp 
+from sparknlp.base import *
+from sparknlp.annotator import *
+from pyspark.ml import Pipeline
+
+# Initialize Spark NLP
+spark = sparknlp.start()
+
+# Define the pipeline stages
+documentAssembler = DocumentAssembler()\\
+    .setInputCol("text")\\
+    .setOutputCol("documents")
+
+t5 = T5Transformer.pretrained("t5_grammar_error_corrector")\\
+    .setTask("gec:")\\
+    .setInputCols(["documents"])\\
+    .setMaxOutputLength(200)\\
+    .setOutputCol("corrections")
+
+pipeline = Pipeline().setStages([documentAssembler, t5])
+
+# Input data example
+data = spark.createDataFrame([["She don't knows nothing about what's happening in the office."]]).toDF("text")
+
+# Apply the pipeline for grammar correction
+result = pipeline.fit(data).transform(data)
+result.select("corrections.result").show(truncate=False)
+''', language='python')
+
+# Example Output
+st.text("""
++---------------------------------------------------------------+
+|corrections.result                                             |
++---------------------------------------------------------------+
+|[She doesn't know anything about what's happening in the office.]|
++---------------------------------------------------------------+
+""")
+
+# Model Info Section
+st.markdown('<div class="sub-title">Choosing the Right T5 Model for Grammar Correction</div>', unsafe_allow_html=True)
+
+st.markdown("""
+<div class="section">
+    <p>For correcting grammar errors, we use the model: "t5_grammar_error_corrector". This model is fine-tuned to detect and correct various types of grammatical errors in English sentences.</p>
+    <p>Explore other T5 models tailored for different NLP tasks on the <a class="link" href="https://sparknlp.org/models?annotator=T5Transformer" target="_blank">Spark NLP Models Hub</a> to find the best fit for your specific needs.</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://ai.googleblog.com/2020/02/exploring-transfer-learning-with-t5.html" target="_blank">Google AI Blog</a>: Exploring Transfer Learning with T5</li>
+        <li><a class="link" href="https://sparknlp.org/models?annotator=T5Transformer" target="_blank">Spark NLP Model Hub</a>: Explore T5 models</li>
+        <li>Model used for Grammar Correction: <a class="link" href="https://sparknlp.org/2022/11/28/t5_grammar_error_corrector_en.html" target="_blank">t5_grammar_error_corrector</a></li>
+        <li><a class="link" href="https://github.com/google-research/text-to-text-transfer-transformer" target="_blank">GitHub</a>: T5 Transformer repository</li>
+        <li><a class="link" href="https://arxiv.org/abs/1910.10683" target="_blank">T5 Paper</a>: Detailed insights from the developers</li>
+    </ul>
+</div>
+""", unsafe_allow_html=True)
+
+# Community & Support Section
+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://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)
+
+# Quick Links Section
+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