frontend

frontend/about.py

@@ -0,0 +1,27 @@
+import streamlit as st
+
+
+def about_me_ui():
+    st.title("About Me 🙋‍♂️ ")
+    st.write("""
+Hello! 👋 I'm **R. Sarath Kumar**, and I'm thrilled to have you here! I’m a dedicated and passionate professional in **Data Science** and **Machine Learning** 🤖.  
+With a strong foundation in statistics, machine learning, and MLOps, I love transforming data into valuable insights and building predictive models that solve real-world problems. My work spans across multiple domains, and I’m always excited to explore new tools and techniques to make data-driven decisions more effective and impactful.
+
+Feel free to browse through my projects, where you’ll find some of the most exciting applications of AI and machine learning, and don't hesitate to reach out if you’d like to connect or discuss potential collaborations!
+""")
+
+
+
+    st.subheader("Contact Information")
+    
+    
+    st.write("🔗LinkedIn: [LinkedIn](https://www.linkedin.com/in/r-sarath-kumar-666084257)") 
+    st.write("🔗Github:[Github](https://www.github.com/sarathkumar1304)") 
+
+    
+    st.write("📧 Email: [sarathkumarrathnam@gmail.com](mailto:sarathkumarrathnam@gmail.com)")  
+    
+    st.write("📞 Phone: 7780651312")  
+    
+
+    

frontend/home.py

@@ -0,0 +1,45 @@
+import streamlit as st
+
+
+def home_ui():
+
+    # Streamlit app title
+    st.title("Transformer-Based Text Classification Project 🌟")
+
+    # Objective section
+    st.header("🔍 Objective")
+    st.write("""
+    The primary objective of this project is to classify text into positive or negative sentiment using a 
+    **Transformer-based pre-trained model**. This model helps in understanding the sentiment of user-provided text, 
+    which can be useful in applications like customer feedback analysis, review classification, and more.
+    """)
+
+    # Tools used
+    st.header("🛠️ Tools Used")
+    st.write("""
+    This project leverages the following tools and technologies:
+    - **Python**: For data preprocessing and backend logic.
+    - **Hugging Face Transformers**: For leveraging pre-trained Transformer models.
+    - **PyTorch**: For model operations and predictions.
+    - **Docker** (optional): To containerize the application for deployment.
+    - **Mlflow** : For model tracking and version control.
+    - **Git**: For version control and collaboration.
+    - **Streamlit**: To create an interactive and user-friendly UI.
+    """)
+
+    # Architecture section
+    st.header("🏗️ Project Architecture")
+    st.write("""
+    The architecture of this project can be summarized in the following flow:
+    """)
+
+    # Display architecture image
+    # architecture_image_path = "path_to_your_architecture_image.png"  # Replace with your image path
+    # st.image(architecture_image_path, caption="Project Architecture", use_column_width=True)
+
+    # Footer or additional information
+    st.write("---")
+    st.write("""
+    💡 This application is designed to showcase the integration of **NLP** and **Machine Learning** with 
+    an easy-to-use web interface. The predictions are generated in real-time, providing insights into text sentiments.
+    """)

frontend/main.py

@@ -0,0 +1,25 @@
+import streamlit as st
+import pandas as pd
+from streamlit_option_menu import option_menu
+from about import about_me_ui
+from project import project_ui
+from home import home_ui
+
+
+with st.sidebar:
+    selected = option_menu(
+        menu_title="Main Menu",
+        options=["Home", "Project","About Me"],
+        icons=["house", "app-indicator" ,"person-video3"],
+        menu_icon="cast",
+        default_index=1,
+    )
+
+if selected == "Home":
+    home_ui()
+
+if selected == "Project":
+    project_ui()
+
+if selected == "About Me":
+    about_me_ui()

frontend/project.py

@@ -0,0 +1,105 @@
+import streamlit as st
+from transformers import pipeline
+from streamlit_echarts import st_echarts
+
+def project_ui():
+    # Load the pre-trained sentiment analysis model
+    model_name = "saved_model"
+    classifier = pipeline("sentiment-analysis", model=model_name)
+
+    # App title and description
+    st.title("Transformer-Based Text Classification")
+    st.write("""
+    This app uses a pre-trained Transformer model to classify text. Enter your text below to get the classification result.
+    """)
+
+    # User input
+    user_input = st.text_area("Enter your text here", height=150)
+
+    # Prediction button
+    if st.button("Predict"):
+        if user_input.strip():
+            try:
+                # Perform text classification
+                predictions = classifier(user_input)
+
+                # Extract label and score
+                label = predictions[0]['label']
+                score = predictions[0]['score']
+
+                # Calculate positive and negative scores
+                if label == 'LABEL_0':
+                    negative_score = score
+                    positive_score = 1 - score
+                else:
+                    positive_score = score
+                    negative_score = 1 - score
+
+                # Display sentiment prediction and scores
+                if label == 'LABEL_0':
+                    st.error("Prediction: 😔 Negative")
+                else:
+                    st.success("Prediction: 😊 Positive")
+
+                st.write("### Sentiment Scores")
+                st.write(f"Positive Score: {positive_score * 100:.2f}%")
+                st.write(f"Negative Score: {negative_score * 100:.2f}%")
+
+                # Display interactive sentiment analysis indicator
+                options = {
+                    "series": [
+                        {
+                            "type": "gauge",
+                            "startAngle": 180,
+                            "endAngle": 0,
+                            "radius": "100%",
+                            "pointer": {"show": True, "length": "60%", "width": 5},
+                            "progress": {
+                                "show": True,
+                                "overlap": False,
+                                "roundCap": True,
+                                "clip": False
+                            },
+                            "axisLine": {
+                                "lineStyle": {
+                                    "width": 10,
+                                    "color": [
+                                        [0.5, "#FF6F61"],  # Negative (Red)
+                                        [1, "#6AA84F"]   # Positive (Green)
+                                    ]
+                                }
+                            },
+                            "axisTick": {"show": False},
+                            "splitLine": {"show": False},
+                            "axisLabel": {"distance": 15, "fontSize": 10},
+                            "data": [
+                                {"value": positive_score * 100, "name": "Positive"},
+                            ],
+                            "title": {"fontSize": 14},
+                            "detail": {
+                                "valueAnimation": True,
+                                "formatter": "{value}%",
+                                "fontSize": 12
+                            },
+                            "animation": True,  # Enable animation
+                            "animationDuration": 2000,  # Duration in ms
+                            "animationEasing": "cubicOut"  # Smooth animation
+                        }
+                    ]
+                }
+
+                st.write("### Interactive Sentiment Analysis Indicator")
+                st_echarts(options, height="300px")
+
+                # Warning if confidence is below 60%
+                if score < 0.6:
+                    st.warning("The confidence level of the prediction is below 60%. The result may not be reliable.")
+                
+            except Exception as e:
+                st.error(f"An error occurred during prediction: {e}")
+        else:
+            st.warning("Please enter some text for prediction.")
+
+# Run the Streamlit app
+if __name__ == "__main__":
+    project_ui()