2025.03.18.post3

app_main_hf.py

@@ -1,7 +1,19 @@
+from streamlit_extras.bottom_container import bottom
+from streamlit_extras.app_logo import add_logo
+from streamlit_extras.add_vertical_space import add_vertical_space
+from streamlit_extras.stylable_container import stylable_container
+from emotion_analysis import show_emotion_analysis
+from sentiment_analysis.sentiment_analysis_main import show_sentiment_analysis
+from dashboard import show_dashboard
+from imports import *
 import streamlit as st
+from streamlit_option_menu import option_menu
 import os
 import asyncio
 import sys
+import shutil
+import gc
+from transformers.utils.hub import TRANSFORMERS_CACHE
 
 if sys.platform == "win32":
     asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
@@ -18,36 +30,152 @@ import importlib.util
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), )))
 
-from imports import *
 
+# from text_transformation import show_text_transformation
 
+st.set_page_config(
+    page_title="Tachygraphy Microtext Analysis & Normalization",
+    # layout="wide"
+)
 
 
-from dashboard import show_dashboard
-from sentiment_analysis.sentiment_analysis_main import show_sentiment_analysis
-from emotion_analysis import show_emotion_analysis
-# from text_transformation import show_text_transformation
+def free_memory():
+    #  """Free up CPU & GPU memory before loading a new model."""
+    global current_model, current_tokenizer
+
+    if current_model is not None:
+        del current_model  # Delete the existing model
+        current_model = None  # Reset reference
+
+    if current_tokenizer is not None:
+        del current_tokenizer  # Delete the tokenizer
+        current_tokenizer = None
+
+    gc.collect()  # Force garbage collection for CPU memory
+
+    if torch.cuda.is_available():
+        torch.cuda.empty_cache()  # Free GPU memory
+        torch.cuda.ipc_collect()  # Clean up PyTorch GPU cache
+
+    # If running on CPU, reclaim memory using OS-level commands
+    try:
+        if torch.cuda.is_available() is False:
+            psutil.virtual_memory()  # Refresh memory stats
+    except Exception as e:
+        print(f"Memory cleanup error: {e}")
+
+    # Delete cached Hugging Face models
+    try:
+        cache_dir = TRANSFORMERS_CACHE
+        if os.path.exists(cache_dir):
+            shutil.rmtree(cache_dir)
+            print("Cache cleared!")
+    except Exception as e:
+        print(f"❌ Cache cleanup error: {e}")
+
 
 
 def main():
+    # selection = option_menu(
+    #     menu_title="Navigation",
+    #     options=[
+    #         "Dashboard",
+    #         "Stage 1: Sentiment Polarity Analysis",
+    #         "Stage 2: Emotion Mood-tag Analysis",
+    #         "Stage 3: Text Transformation & Normalization"
+    #     ],
+    #     icons=["joystick", "bar-chart", "emoji-laughing", "pencil"],
+    #     styles={
+    #         "container": {}},
+    #     menu_icon="menu-button-wide-fill",
+    #     default_index=0,
+    #     orientation="horizontal"
+    # )
+
     st.sidebar.title("Navigation")
-    selection = st.sidebar.radio("Go to", ["Dashboard", "Stage 1: Sentiment Polarity Analysis", "Stage 2: Emotion Mood-tag Analysis", "Stage 3: Text Transformation & Normalization"])
+    with st.sidebar:
+        selection = option_menu(
+            menu_title=None,          # No title for a sleek look
+            options=["Dashboard", "Stage 1: Sentiment Polarity Analysis", "Stage 2: Emotion Mood-tag Analysis", "Stage 3: Text Transformation & Normalization"],
+            icons=None,
+            menu_icon="cast",          # Main menu icon
+            default_index=0,           # Highlight the first option
+            orientation="vertical",
+            styles={
+                "container": {"padding": "0!important", "background-color": "#f8f9fa"},
+                "icon": {"color": "#6c757d", "font-size": "18px"},
+                "nav-link": {
+                    "font-size": "16px",
+                    "text-align": "center",
+                    "margin": "0px",
+                    "color": "#6c757d",
+                    "transition": "0.3s",
+                },
+                "nav-link-selected": {
+                    "background-color": "#FF4B4B",
+                    "color": "white",
+                    "font-weight": "bold",
+                    "border-radius": "8px",
+                },
+            }
+        )
+
+    # st.sidebar.title("Navigation")
+    # selection = st.sidebar.radio("Go to", ["Dashboard", "Stage 1: Sentiment Polarity Analysis", "Stage 2: Emotion Mood-tag Analysis", "Stage 3: Text Transformation & Normalization"])
+
+    # if selection == "Dashboard":
+    #     show_dashboard()
+    # elif selection == "Stage 1: Sentiment Polarity Analysis":
+    #     show_sentiment_analysis()
+    # elif selection == "Stage 2: Emotion Mood-tag Analysis":
+    #     # show_emotion_analysis()
+    #     st.write("This section is under development.")
+    # elif selection == "Stage 3: Text Transformation & Normalization":
+    #     # show_text_transformation()
+    #     st.write("This section is under development.")
 
     if selection == "Dashboard":
+        st.cache_resource.clear()
+        free_memory()
         show_dashboard()
+
     elif selection == "Stage 1: Sentiment Polarity Analysis":
+        st.cache_resource.clear()
+        free_memory()
         show_sentiment_analysis()
+
     elif selection == "Stage 2: Emotion Mood-tag Analysis":
+        st.cache_resource.clear()
+        free_memory()
         # show_emotion_analysis()
         st.write("This section is under development.")
+
     elif selection == "Stage 3: Text Transformation & Normalization":
+        st.cache_resource.clear()
+        free_memory()
         # show_text_transformation()
         st.write("This section is under development.")
 
+
+
+    # st.sidebar.title("Navigation")
+    # selection = st.sidebar.radio("Go to", ["Dashboard", "Stage 1: Sentiment Polarity Analysis", "Stage 2: Emotion Mood-tag Analysis", "Stage 3: Text Transformation & Normalization"])
+
+    # if selection == "Dashboard":
+    #     show_dashboard()
+    # elif selection == "Stage 1: Sentiment Polarity Analysis":
+    #     show_sentiment_analysis()
+    # elif selection == "Stage 2: Emotion Mood-tag Analysis":
+    #     # show_emotion_analysis()
+    #     st.write("This section is under development.")
+    # elif selection == "Stage 3: Text Transformation & Normalization":
+    #     # show_text_transformation()
+    #     st.write("This section is under development.")
+
     st.sidebar.title("About")
     st.sidebar.info("""
         **Contributors:**
-        - Archisman Karmakar 
+        - Archisman Karmakar
             - [LinkedIn](https://www.linkedin.com/in/archismankarmakar/)
             - [GitHub](https://www.github.com/ArchismanKarmakar)
             - [Kaggle](https://www.kaggle.com/archismancoder)
@@ -70,4 +198,4 @@ def main():
     """)
 
 if __name__ == "__main__":
-    main()
+    main()

dashboard.py

@@ -40,6 +40,39 @@ def free_memory():
     except Exception as e:
         print(f"❌ Cache cleanup error: {e}")
 
+
+def create_footer():
+    st.divider()
+
+    # 🛠️ Layout using Streamlit columns
+    col1, col2, col3 = st.columns([1, 1, 1])
+
+    # 🚀 Contributors Section
+    with col1:
+        st.markdown("### 🚀 Contributors")
+        st.write("**Archisman Karmakar**")
+        st.write("[🔗 LinkedIn](https://www.linkedin.com/in/archismankarmakar/) | [🐙 GitHub](https://www.github.com/ArchismanKarmakar) | [📊 Kaggle](https://www.kaggle.com/archismancoder)")
+
+        st.write("**Sumon Chatterjee**")
+        st.write("[🔗 LinkedIn](https://www.linkedin.com/in/sumon-chatterjee-3b3b43227) | [🐙 GitHub](https://github.com/Sumon670) | [📊 Kaggle](https://www.kaggle.com/sumonchatterjee)")
+
+    # 🎓 Mentors Section
+    with col2:
+        st.markdown("### 🎓 Mentors")
+        st.write("**Prof. Anupam Mondal**")
+        st.write("[🔗 LinkedIn](https://www.linkedin.com/in/anupam-mondal-ph-d-8a7a1a39/) | [📚 Google Scholar](https://scholar.google.com/citations?user=ESRR9o4AAAAJ&hl=en) | [🌐 Website](https://sites.google.com/view/anupammondal/home)")
+
+        st.write("**Prof. Sainik Kumar Mahata**")
+        st.write("[🔗 LinkedIn](https://www.linkedin.com/in/mahatasainikk) | [📚 Google Scholar](https://scholar.google.co.in/citations?user=OcJDM50AAAAJ&hl=en) | [🌐 Website](https://sites.google.com/view/sainik-kumar-mahata/home)")
+
+    # 📌 Research Project Info Section
+    with col3:
+        st.markdown("### 📝 About the Project")
+        st.write("This is our research project for our **B.Tech final year** and a **journal** which is yet to be published.")
+        st.write("Built with 💙 using **Streamlit**.")
+
+# 🚀 Display Footer
+
 def show_dashboard():
     # free_memory()
     st.title("Tachygraphy Micro-text Analysis & Normalization")
@@ -50,6 +83,8 @@ def show_dashboard():
         3. Text Transformation & Normalization
     """)
 
+    create_footer()
+
 
 def __main__():
     show_dashboard()

imports.py

@@ -14,6 +14,7 @@ import importlib.util
 import asyncio
 import sys
 import pytorch_lightning as pl
+from transformers.utils.hub import TRANSFORMERS_CACHE
 
 
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), )))

poetry.lock

@@ -1116,6 +1116,18 @@ files = [
 [package.extras]
 dev = ["coverage", "pytest (>=7.4.4)"]
 
+[[package]]
+name = "entrypoints"
+version = "0.4"
+description = "Discover and load entry points from installed packages."
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "entrypoints-0.4-py3-none-any.whl", hash = "sha256:f174b5ff827504fd3cd97cc3f8649f3693f51538c7e4bdf3ef002c8429d42f9f"},
+    {file = "entrypoints-0.4.tar.gz", hash = "sha256:b706eddaa9218a19ebcd67b56818f05bb27589b1ca9e8d797b74affad4ccacd4"},
+]
+
 [[package]]
 name = "et-xmlfile"
 version = "2.0.0"
@@ -1179,6 +1191,21 @@ files = [
 [package.extras]
 tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich ; python_version >= \"3.11\""]
 
+[[package]]
+name = "faker"
+version = "37.0.0"
+description = "Faker is a Python package that generates fake data for you."
+optional = false
+python-versions = ">=3.9"
+groups = ["main"]
+files = [
+    {file = "faker-37.0.0-py3-none-any.whl", hash = "sha256:2598f78b76710a4ed05e197dda5235be409b4c291ba5c9c7514989cfbc7a5144"},
+    {file = "faker-37.0.0.tar.gz", hash = "sha256:d2e4e2a30d459a8ec0ae52a552aa51c48973cb32cf51107dee90f58a8322a880"},
+]
+
+[package.dependencies]
+tzdata = "*"
+
 [[package]]
 name = "fastjsonschema"
 version = "2.21.1"
@@ -1194,6 +1221,22 @@ files = [
 [package.extras]
 devel = ["colorama", "json-spec", "jsonschema", "pylint", "pytest", "pytest-benchmark", "pytest-cache", "validictory"]
 
+[[package]]
+name = "favicon"
+version = "0.7.0"
+description = "Get a website's favicon."
+optional = false
+python-versions = "*"
+groups = ["main"]
+files = [
+    {file = "favicon-0.7.0-py2.py3-none-any.whl", hash = "sha256:7fec0617c73dcb8521ea788e1d38cdc7226c7cb8e28c81e11625d85fa1534880"},
+    {file = "favicon-0.7.0.tar.gz", hash = "sha256:6d6b5a78de2a0d0084589f687f384b2ecd6a6527093fec564403b1a30605d7a8"},
+]
+
+[package.dependencies]
+beautifulsoup4 = ">=4.7.0"
+requests = ">=2.21.0"
+
 [[package]]
 name = "filelock"
 version = "3.18.0"
@@ -1652,6 +1695,17 @@ files = [
 [package.dependencies]
 numpy = ">=1.19.3"
 
+[[package]]
+name = "htbuilder"
+version = "0.9.0"
+description = "A purely-functional HTML builder for Python. Think JSX rather than templates."
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "htbuilder-0.9.0.tar.gz", hash = "sha256:58c0bc5502c1a46b42ae9e074c43ec0f6fdc24ed334936cb17e1ed5a8938aee2"},
+]
+
 [[package]]
 name = "httpcore"
 version = "1.0.7"
@@ -2497,6 +2551,27 @@ profiling = ["gprof2dot"]
 rtd = ["jupyter_sphinx", "mdit-py-plugins", "myst-parser", "pyyaml", "sphinx", "sphinx-copybutton", "sphinx-design", "sphinx_book_theme"]
 testing = ["coverage", "pytest", "pytest-cov", "pytest-regressions"]
 
+[[package]]
+name = "markdownlit"
+version = "0.0.7"
+description = "markdownlit adds a couple of lit Markdown capabilities to your Streamlit apps"
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "markdownlit-0.0.7-py3-none-any.whl", hash = "sha256:b58bb539dcb52e0b040ab2fed32f1f3146cbb2746dc3812940d9dd359c378bb6"},
+    {file = "markdownlit-0.0.7.tar.gz", hash = "sha256:553e2db454e2be4567caebef5176c98a40a7e24f7ea9c2fe8a1f05c1d9ea4005"},
+]
+
+[package.dependencies]
+favicon = "*"
+htbuilder = "*"
+lxml = "*"
+markdown = "*"
+pymdown-extensions = "*"
+streamlit = "*"
+streamlit-extras = "*"
+
 [[package]]
 name = "markupsafe"
 version = "3.0.2"
@@ -3835,6 +3910,21 @@ docs = ["sphinx (>=1.7.1)"]
 redis = ["redis"]
 tests = ["pytest (>=5.4.1)", "pytest-cov (>=2.8.1)", "pytest-mypy (>=0.8.0)", "pytest-rerunfailures (>=15.0)", "pytest-timeout (>=2.1.0)", "redis", "sphinx (>=6.0.0)", "types-redis"]
 
+[[package]]
+name = "prometheus-client"
+version = "0.21.1"
+description = "Python client for the Prometheus monitoring system."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "prometheus_client-0.21.1-py3-none-any.whl", hash = "sha256:594b45c410d6f4f8888940fe80b5cc2521b305a1fafe1c58609ef715a001f301"},
+    {file = "prometheus_client-0.21.1.tar.gz", hash = "sha256:252505a722ac04b0456be05c05f75f45d760c2911ffc45f2a06bcaed9f3ae3fb"},
+]
+
+[package.extras]
+twisted = ["twisted"]
+
 [[package]]
 name = "prompt-toolkit"
 version = "3.0.50"
@@ -4175,6 +4265,25 @@ files = [
 [package.extras]
 windows-terminal = ["colorama (>=0.4.6)"]
 
+[[package]]
+name = "pymdown-extensions"
+version = "10.14.3"
+description = "Extension pack for Python Markdown."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "pymdown_extensions-10.14.3-py3-none-any.whl", hash = "sha256:05e0bee73d64b9c71a4ae17c72abc2f700e8bc8403755a00580b49a4e9f189e9"},
+    {file = "pymdown_extensions-10.14.3.tar.gz", hash = "sha256:41e576ce3f5d650be59e900e4ceff231e0aed2a88cf30acaee41e02f063a061b"},
+]
+
+[package.dependencies]
+markdown = ">=3.6"
+pyyaml = "*"
+
+[package.extras]
+extra = ["pygments (>=2.19.1)"]
+
 [[package]]
 name = "pyparsing"
 version = "3.2.1"
@@ -5264,6 +5373,36 @@ files = [
     {file = "soupsieve-2.6.tar.gz", hash = "sha256:e2e68417777af359ec65daac1057404a3c8a5455bb8abc36f1a9866ab1a51abb"},
 ]
 
+[[package]]
+name = "st-annotated-text"
+version = "4.0.2"
+description = "A simple component to display annotated text in Streamlit apps."
+optional = false
+python-versions = ">=3.5"
+groups = ["main"]
+files = [
+    {file = "st_annotated_text-4.0.2-py3-none-any.whl", hash = "sha256:712c45821f020eccafad3a58c10b9d2d51d449f4db999a06308ecf39a753a4df"},
+    {file = "st_annotated_text-4.0.2.tar.gz", hash = "sha256:b0134dcf734697cc3dbdb11862c4174071e7fb6f365af55a37c710d357fd88a5"},
+]
+
+[package.dependencies]
+htbuilder = "*"
+
+[[package]]
+name = "st-theme"
+version = "1.2.3"
+description = "A component that returns the active theme of the Streamlit app."
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "st-theme-1.2.3.tar.gz", hash = "sha256:ca97aece1a48ded6e83fd742c27cb0851e1bce2100ab4b6c37c7b6e003b65b42"},
+    {file = "st_theme-1.2.3-py3-none-any.whl", hash = "sha256:0a54d9817dd5f8a6d7b0d071b25ae72eacf536c63a5fb97374923938021b1389"},
+]
+
+[package.dependencies]
+streamlit = ">=1.33"
+
 [[package]]
 name = "stack-data"
 version = "0.6.3"
@@ -5319,6 +5458,213 @@ watchdog = {version = ">=2.1.5,<7", markers = "platform_system != \"Darwin\""}
 [package.extras]
 snowflake = ["snowflake-connector-python (>=3.3.0) ; python_version < \"3.12\"", "snowflake-snowpark-python[modin] (>=1.17.0) ; python_version < \"3.12\""]
 
+[[package]]
+name = "streamlit-avatar"
+version = "0.1.3"
+description = "Component to display avatar icon in Streamlit"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "streamlit_avatar-0.1.3-py3-none-any.whl", hash = "sha256:873e6f0022635eda29d6b76e570adcbc095d8e6d23f18dd1e288720b4736364d"},
+    {file = "streamlit_avatar-0.1.3.tar.gz", hash = "sha256:023893bd80db5a923d397fc64d27c7a972107da4f0bea0feb99a32f9363f2691"},
+]
+
+[package.dependencies]
+streamlit = ">=0.63"
+
+[package.extras]
+devel = ["wheel"]
+
+[[package]]
+name = "streamlit-camera-input-live"
+version = "0.2.0"
+description = "Alternative version of st.camera_input which returns the webcam images live, without any button press needed"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "streamlit-camera-input-live-0.2.0.tar.gz", hash = "sha256:20ceb952b98410084176fcfeb9148e02ea29033a88d4a923161ac7890cedae0f"},
+    {file = "streamlit_camera_input_live-0.2.0-py3-none-any.whl", hash = "sha256:dacb56cdedbb0d6c07e35a66b755b9145b5023e5c855c64193c3d3e73198e9be"},
+]
+
+[package.dependencies]
+jinja2 = "*"
+streamlit = ">=1.2"
+
+[[package]]
+name = "streamlit-card"
+version = "1.0.2"
+description = "A streamlit component, to make UI cards"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "streamlit_card-1.0.2-py3-none-any.whl", hash = "sha256:f5d01ce57d6481eb3ba44e504146f56a7b82907d6700f0c19266ed6381a9c58f"},
+    {file = "streamlit_card-1.0.2.tar.gz", hash = "sha256:8001cd5edd8a6e2db36ee81f37dc645f08f78c21a2ba968403176c68b4f33cb1"},
+]
+
+[package.dependencies]
+streamlit = ">=0.63"
+
+[[package]]
+name = "streamlit-elements"
+version = "0.1.0"
+description = "React Components for Streamlit."
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "streamlit-elements-0.1.0.tar.gz", hash = "sha256:5f9f116f22df3ce4a8636b1dee7c2fd3dc3cb0c66267fd28c3e0314aa1d303a7"},
+    {file = "streamlit_elements-0.1.0-py3-none-any.whl", hash = "sha256:593c4b88c399c55879aa76f7f42970f30106f66acaa4baada6338ae5571790df"},
+]
+
+[package.dependencies]
+streamlit = ">=1.4.0"
+
+[[package]]
+name = "streamlit-embedcode"
+version = "0.1.2"
+description = "Streamlit component for embedded code snippets"
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "streamlit-embedcode-0.1.2.tar.gz", hash = "sha256:22a50eb43407bab3d0ed2d4b58e89819da477cd0592ef87edbd373c286712e3a"},
+    {file = "streamlit_embedcode-0.1.2-py3-none-any.whl", hash = "sha256:b3c9520c1b48f2eef3c702b5a967f64c9a8ff2ea8e74ebb26c0e9195965bb923"},
+]
+
+[package.dependencies]
+streamlit = ">=0.63"
+
+[[package]]
+name = "streamlit-extras"
+version = "0.6.0"
+description = "A library to discover, try, install and share Streamlit extras"
+optional = false
+python-versions = "!=2.7.*,!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,!=3.5.*,!=3.6.*,!=3.7.*,>=3.8"
+groups = ["main"]
+files = [
+    {file = "streamlit_extras-0.6.0-py3-none-any.whl", hash = "sha256:b80134871046586a55dd155079c2971d2be47024b6a330fd077a7b505b81d470"},
+    {file = "streamlit_extras-0.6.0.tar.gz", hash = "sha256:3cfa5cf7f17428b53a1d963a8c84903a1ba6f21173364d1664d58b6a58ee91b9"},
+]
+
+[package.dependencies]
+entrypoints = ">=0.4"
+htbuilder = ">=0.6.2"
+markdownlit = ">=0.0.5"
+plotly = ">=1.0.0"
+prometheus-client = ">=0.14.0"
+protobuf = "!=3.20.2"
+st-annotated-text = ">=3.0.0"
+st-theme = ">=1.0.1"
+streamlit = ">=1.0.0"
+streamlit-avatar = ">=0.1.3"
+streamlit-camera-input-live = ">=0.2.0"
+streamlit-card = ">=0.0.4"
+streamlit-embedcode = ">=0.1.2"
+streamlit-faker = ">=0.0.2"
+streamlit-image-coordinates = ">=0.1.1,<0.2.0"
+streamlit-keyup = ">=0.1.9"
+streamlit-toggle-switch = ">=1.0.2"
+streamlit-vertical-slider = ">=2.5.5"
+validators = ">=0.20.0"
+
+[[package]]
+name = "streamlit-faker"
+version = "0.0.3"
+description = "streamlit-faker is a library to very easily fake Streamlit commands"
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "streamlit_faker-0.0.3-py3-none-any.whl", hash = "sha256:caf410867b55b4877d8fe73cc987d089e1938f8e63594f1eb579e28015844215"},
+    {file = "streamlit_faker-0.0.3.tar.gz", hash = "sha256:bff0f053aa514a99313a3699746183b41111891c82d6e9b41b1c69a7d719bf2f"},
+]
+
+[package.dependencies]
+faker = "*"
+matplotlib = "*"
+streamlit = "*"
+streamlit-extras = "*"
+
+[[package]]
+name = "streamlit-image-coordinates"
+version = "0.1.9"
+description = "Streamlit component that displays an image and returns the coordinates when you click on it"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "streamlit_image_coordinates-0.1.9-py3-none-any.whl", hash = "sha256:e577d475707ce8a3f7be1825027af6b4d7b609a456f4b25b794756ed2436ab06"},
+    {file = "streamlit_image_coordinates-0.1.9.tar.gz", hash = "sha256:825e1f49053f1363913014a4e9130a03b9ca01fb5f7bd269b17afe8162d2ba37"},
+]
+
+[package.dependencies]
+jinja2 = "*"
+streamlit = ">=1.2"
+
+[[package]]
+name = "streamlit-keyup"
+version = "0.3.0"
+description = "Text input that renders on keyup"
+optional = false
+python-versions = ">=3.7"
+groups = ["main"]
+files = [
+    {file = "streamlit_keyup-0.3.0-py3-none-any.whl", hash = "sha256:ec7221617b1c832526db52859196c417578d6b4285942fbd10a0b2ff313899b3"},
+    {file = "streamlit_keyup-0.3.0.tar.gz", hash = "sha256:8595a14892423243669e5d50e982853ffb7eb201b65952a48676133ab9bbc937"},
+]
+
+[package.dependencies]
+jinja2 = "*"
+streamlit = ">=1.2"
+
+[[package]]
+name = "streamlit-option-menu"
+version = "0.4.0"
+description = "streamlit-option-menu is a simple Streamlit component that allows users to select a single item from a list of options in a menu."
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "streamlit-option-menu-0.4.0.tar.gz", hash = "sha256:48ec69d59e547fa2fa4bfae001620df8af56a80de2f765ddbb9fcbfb84017129"},
+    {file = "streamlit_option_menu-0.4.0-py3-none-any.whl", hash = "sha256:a55fc7554047b6db371595af2182e435b8a2c715ee6124e8543685bd4670b07e"},
+]
+
+[package.dependencies]
+streamlit = ">=1.36"
+
+[[package]]
+name = "streamlit-toggle-switch"
+version = "1.0.2"
+description = "Creates a customizable toggle"
+optional = false
+python-versions = ">=3.6"
+groups = ["main"]
+files = [
+    {file = "streamlit_toggle_switch-1.0.2-py3-none-any.whl", hash = "sha256:0081212d80d178bda337acf2432425e2016d757f57834b18645d4c5b928d4c0f"},
+    {file = "streamlit_toggle_switch-1.0.2.tar.gz", hash = "sha256:991b103cd3448b0f6507f8051777b996a17b4630956d5b6fa13344175b20e572"},
+]
+
+[package.dependencies]
+streamlit = ">=0.63"
+
+[[package]]
+name = "streamlit-vertical-slider"
+version = "2.5.5"
+description = "Creates a customizable vertical slider"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "streamlit_vertical_slider-2.5.5-py3-none-any.whl", hash = "sha256:8182e861444fcd69e05c05e7109a636d459560c249f1addf78b58e525a719cb6"},
+    {file = "streamlit_vertical_slider-2.5.5.tar.gz", hash = "sha256:d6854cf81a606f5c021df2037d2c49036df2d03ce5082a5227a2acca8322ca74"},
+]
+
+[package.dependencies]
+streamlit = ">=1.22.0"
+
 [[package]]
 name = "sympy"
 version = "1.13.1"
@@ -5941,6 +6287,21 @@ h2 = ["h2 (>=4,<5)"]
 socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
 zstd = ["zstandard (>=0.18.0)"]
 
+[[package]]
+name = "validators"
+version = "0.34.0"
+description = "Python Data Validation for Humans™"
+optional = false
+python-versions = ">=3.8"
+groups = ["main"]
+files = [
+    {file = "validators-0.34.0-py3-none-any.whl", hash = "sha256:c804b476e3e6d3786fa07a30073a4ef694e617805eb1946ceee3fe5a9b8b1321"},
+    {file = "validators-0.34.0.tar.gz", hash = "sha256:647fe407b45af9a74d245b943b18e6a816acf4926974278f6dd617778e1e781f"},
+]
+
+[package.extras]
+crypto-eth-addresses = ["eth-hash[pycryptodome] (>=0.7.0)"]
+
 [[package]]
 name = "virtualenv"
 version = "20.29.3"
@@ -6517,4 +6878,4 @@ cffi = ["cffi (>=1.11)"]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.12"
-content-hash = "9ade3fb8187ce4c308f17adf7e0534b6ed471446c3dd1f908c9cb029c795fbd6"
+content-hash = "0a2b37985beb5aa45fe5004098180bab465570c2e58665ae770b0793c37b4e3d"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tachygraphy-microtext-analysis-and-normalization"
-version = "2025.03.18.post1"
+version = "2025.03.18.post3"
 description = ""
 authors = [
     { name = "Archisman Karmakar", email = "[email protected]" },
@@ -194,6 +194,9 @@ dependencies = [
     "zstandard (>=0.23.0,<0.24.0)",
     "asyncio (>=3.4.3,<4.0.0)",
     "pytorch-lightning (>=2.5.0.post0,<3.0.0)",
+    "streamlit-option-menu (>=0.4.0,<0.5.0)",
+    "streamlit-elements (>=0.1.0,<0.2.0)",
+    "streamlit-extras (>=0.6.0,<0.7.0)",
 ]
 
 

pyprojectOLD.toml

@@ -1,6 +1,8 @@
 [project]
 name = "tachygraphy-microtext-analysis-and-normalization"
-version = "2025.03.17.post1"
+version = "2025.03.18.post2"
+# version = "2025.03.18.post1"
+# version = "2025.03.17.post1"
 # version = "2025.03.16.post3"
 # version = "2025.03.16.post2"
 # version = "2025.03.16.post1"

requirements.txt

@@ -37,10 +37,13 @@ distlib==0.3.9 ; python_version >= "3.12"
 distributed==2025.2.0 ; python_version >= "3.12"
 dulwich==0.22.8 ; python_version >= "3.12"
 emoji==2.14.1 ; python_version >= "3.12"
+entrypoints==0.4 ; python_version >= "3.12"
 et-xmlfile==2.0.0 ; python_version >= "3.12"
 evaluate==0.4.3 ; python_version >= "3.12"
 executing==2.2.0 ; python_version >= "3.12"
+faker==37.0.0 ; python_version >= "3.12"
 fastjsonschema==2.21.1 ; python_version >= "3.12"
+favicon==0.7.0 ; python_version >= "3.12"
 filelock==3.18.0 ; python_version >= "3.12"
 findpython==0.6.3 ; python_version >= "3.12"
 flatbuffers==25.2.10 ; python_version >= "3.12"
@@ -55,6 +58,7 @@ grpcio==1.71.0 ; python_version >= "3.12"
 h11==0.14.0 ; python_version >= "3.12"
 h2o==3.46.0.6 ; python_version >= "3.12"
 h5py==3.13.0 ; python_version >= "3.12"
+htbuilder==0.9.0 ; python_version >= "3.12"
 httpcore==1.0.7 ; python_version >= "3.12"
 httpx==0.28.1 ; python_version >= "3.12"
 huggingface-hub==0.29.3 ; python_version >= "3.12"
@@ -86,6 +90,7 @@ locket==1.0.0 ; python_version >= "3.12"
 lxml==5.3.1 ; python_version >= "3.12"
 markdown-it-py==3.0.0 ; python_version >= "3.12"
 markdown==3.7 ; python_version >= "3.12"
+markdownlit==0.0.7 ; python_version >= "3.12"
 markupsafe==3.0.2 ; python_version >= "3.12"
 matplotlib-inline==0.1.7 ; python_version >= "3.12"
 matplotlib==3.10.1 ; python_version >= "3.12"
@@ -132,6 +137,7 @@ pkginfo==1.12.1.2 ; python_version >= "3.12"
 platformdirs==4.3.6 ; python_version >= "3.12"
 plotly==6.0.0 ; python_version >= "3.12"
 portalocker==3.1.1 ; python_version >= "3.12"
+prometheus-client==0.21.1 ; python_version >= "3.12"
 prompt-toolkit==3.0.50 ; python_version >= "3.12"
 propcache==0.3.0 ; python_version >= "3.12"
 protobuf==5.29.3 ; python_version >= "3.12"
@@ -143,13 +149,14 @@ pycparser==2.22 ; (sys_platform == "linux" or implementation_name == "pypy" or p
 pycurl==7.45.6 ; python_version >= "3.12"
 pydeck==0.9.1 ; python_version >= "3.12"
 pygments==2.19.1 ; python_version >= "3.12"
+pymdown-extensions==10.14.3 ; python_version >= "3.12"
 pyparsing==3.2.1 ; python_version >= "3.12"
 pyproject-hooks==1.2.0 ; python_version >= "3.12"
 python-dateutil==2.9.0.post0 ; python_version >= "3.12"
 pytorch-lightning==2.5.0.post0 ; python_version >= "3.12"
 pytz==2025.1 ; python_version >= "3.12"
-pywin32-ctypes==0.2.3 ; python_version >= "3.12"
-pywin32==309 ; python_version >= "3.12"
+pywin32-ctypes==0.2.3 ; python_version >= "3.12" and sys_platform == "win32"
+pywin32==309 ; python_version >= "3.12" and sys_platform == "win32"
 pyyaml==6.0.2 ; python_version >= "3.12"
 pyzmq==26.3.0 ; python_version >= "3.12"
 rapidfuzz==3.12.2 ; python_version >= "3.12"
@@ -174,7 +181,21 @@ smmap==5.0.2 ; python_version >= "3.12"
 sniffio==1.3.1 ; python_version >= "3.12"
 sortedcontainers==2.4.0 ; python_version >= "3.12"
 soupsieve==2.6 ; python_version >= "3.12"
+st-annotated-text==4.0.2 ; python_version >= "3.12"
+st-theme==1.2.3 ; python_version >= "3.12"
 stack-data==0.6.3 ; python_version >= "3.12"
+streamlit-avatar==0.1.3 ; python_version >= "3.12"
+streamlit-camera-input-live==0.2.0 ; python_version >= "3.12"
+streamlit-card==1.0.2 ; python_version >= "3.12"
+streamlit-elements==0.1.0 ; python_version >= "3.12"
+streamlit-embedcode==0.1.2 ; python_version >= "3.12"
+streamlit-extras==0.6.0 ; python_version >= "3.12"
+streamlit-faker==0.0.3 ; python_version >= "3.12"
+streamlit-image-coordinates==0.1.9 ; python_version >= "3.12"
+streamlit-keyup==0.3.0 ; python_version >= "3.12"
+streamlit-option-menu==0.4.0 ; python_version >= "3.12"
+streamlit-toggle-switch==1.0.2 ; python_version >= "3.12"
+streamlit-vertical-slider==2.5.5 ; python_version >= "3.12"
 streamlit==1.43.2 ; python_version >= "3.12"
 sympy==1.13.1 ; python_version >= "3.12"
 tabulate==0.9.0 ; python_version >= "3.12"
@@ -202,6 +223,7 @@ trove-classifiers==2025.3.13.13 ; python_version >= "3.12"
 typing-extensions==4.12.2 ; python_version >= "3.12"
 tzdata==2025.1 ; python_version >= "3.12"
 urllib3==2.3.0 ; python_version >= "3.12"
+validators==0.34.0 ; python_version >= "3.12"
 virtualenv==20.29.3 ; python_version >= "3.12"
 watchdog==6.0.0 ; python_version >= "3.12"
 wcwidth==0.2.13 ; python_version >= "3.12"

requirements_windows.txt

@@ -0,0 +1,215 @@
+absl-py==2.1.0 ; python_version >= "3.12"
+accelerate==1.5.2 ; python_version >= "3.12"
+aiohappyeyeballs==2.6.1 ; python_version >= "3.12"
+aiohttp==3.11.14 ; python_version >= "3.12"
+aiosignal==1.3.2 ; python_version >= "3.12"
+altair==5.5.0 ; python_version >= "3.12"
+anyio==4.9.0 ; python_version >= "3.12"
+appnope==0.1.4 ; python_version >= "3.12" and platform_system == "Darwin"
+asttokens==3.0.0 ; python_version >= "3.12"
+astunparse==1.6.3 ; python_version >= "3.12"
+asyncio==3.4.3 ; python_version >= "3.12"
+attrs==25.3.0 ; python_version >= "3.12"
+autograd==1.7.0 ; python_version >= "3.12"
+beautifulsoup4==4.13.3 ; python_version >= "3.12"
+blinker==1.9.0 ; python_version >= "3.12"
+bs4==0.0.2 ; python_version >= "3.12"
+build==1.2.2.post1 ; python_version >= "3.12"
+cachecontrol==0.14.2 ; python_version >= "3.12"
+cachetools==5.5.2 ; python_version >= "3.12"
+certifi==2025.1.31 ; python_version >= "3.12"
+cffi==1.17.1 ; (sys_platform == "linux" or implementation_name == "pypy" or platform_python_implementation == "PyPy") and python_version >= "3.12"
+charset-normalizer==3.4.1 ; python_version >= "3.12"
+click==8.1.8 ; python_version >= "3.12"
+cloudpickle==3.1.1 ; python_version >= "3.12"
+colorama==0.4.6 ; python_version >= "3.12"
+comm==0.2.2 ; python_version >= "3.12"
+contourpy==1.3.1 ; python_version >= "3.12"
+cryptography==44.0.2 ; python_version >= "3.12" and sys_platform == "linux"
+cycler==0.12.1 ; python_version >= "3.12"
+dask==2025.2.0 ; python_version >= "3.12"
+datasets==3.4.0 ; python_version >= "3.12"
+debugpy==1.8.13 ; python_version >= "3.12"
+decorator==5.2.1 ; python_version >= "3.12"
+diffusers==0.32.2 ; python_version >= "3.12"
+dill==0.3.8 ; python_version >= "3.12"
+distlib==0.3.9 ; python_version >= "3.12"
+distributed==2025.2.0 ; python_version >= "3.12"
+dulwich==0.22.8 ; python_version >= "3.12"
+emoji==2.14.1 ; python_version >= "3.12"
+et-xmlfile==2.0.0 ; python_version >= "3.12"
+evaluate==0.4.3 ; python_version >= "3.12"
+executing==2.2.0 ; python_version >= "3.12"
+fastjsonschema==2.21.1 ; python_version >= "3.12"
+filelock==3.18.0 ; python_version >= "3.12"
+findpython==0.6.3 ; python_version >= "3.12"
+flatbuffers==25.2.10 ; python_version >= "3.12"
+fonttools==4.56.0 ; python_version >= "3.12"
+frozenlist==1.5.0 ; python_version >= "3.12"
+fsspec==2024.12.0 ; python_version >= "3.12"
+gast==0.6.0 ; python_version >= "3.12"
+gitdb==4.0.12 ; python_version >= "3.12"
+gitpython==3.1.44 ; python_version >= "3.12"
+google-pasta==0.2.0 ; python_version >= "3.12"
+grpcio==1.71.0 ; python_version >= "3.12"
+h11==0.14.0 ; python_version >= "3.12"
+h2o==3.46.0.6 ; python_version >= "3.12"
+h5py==3.13.0 ; python_version >= "3.12"
+httpcore==1.0.7 ; python_version >= "3.12"
+httpx==0.28.1 ; python_version >= "3.12"
+huggingface-hub==0.29.3 ; python_version >= "3.12"
+idna==3.10 ; python_version >= "3.12"
+importlib-metadata==8.6.1 ; python_version >= "3.12"
+importlib==1.0.4 ; python_version >= "3.12"
+installer==0.7.0 ; python_version >= "3.12"
+ipykernel==6.29.5 ; python_version >= "3.12"
+ipython-pygments-lexers==1.1.1 ; python_version >= "3.12"
+ipython==9.0.2 ; python_version >= "3.12"
+jaraco-classes==3.4.0 ; python_version >= "3.12"
+jaraco-context==6.0.1 ; python_version >= "3.12"
+jaraco-functools==4.1.0 ; python_version >= "3.12"
+jedi==0.19.2 ; python_version >= "3.12"
+jeepney==0.9.0 ; python_version >= "3.12" and sys_platform == "linux"
+jinja2==3.1.6 ; python_version >= "3.12"
+joblib==1.4.2 ; python_version >= "3.12"
+jsonschema-specifications==2024.10.1 ; python_version >= "3.12"
+jsonschema==4.23.0 ; python_version >= "3.12"
+jupyter-client==8.6.3 ; python_version >= "3.12"
+jupyter-core==5.7.2 ; python_version >= "3.12"
+kagglehub==0.3.10 ; python_version >= "3.12"
+keras==3.9.0 ; python_version >= "3.12"
+keyring==25.6.0 ; python_version >= "3.12"
+kiwisolver==1.4.8 ; python_version >= "3.12"
+libclang==18.1.1 ; python_version >= "3.12"
+lightning-utilities==0.14.1 ; python_version >= "3.12"
+locket==1.0.0 ; python_version >= "3.12"
+lxml==5.3.1 ; python_version >= "3.12"
+markdown-it-py==3.0.0 ; python_version >= "3.12"
+markdown==3.7 ; python_version >= "3.12"
+markupsafe==3.0.2 ; python_version >= "3.12"
+matplotlib-inline==0.1.7 ; python_version >= "3.12"
+matplotlib==3.10.1 ; python_version >= "3.12"
+mdurl==0.1.2 ; python_version >= "3.12"
+ml-dtypes==0.5.1 ; python_version >= "3.12"
+more-itertools==10.6.0 ; python_version >= "3.12"
+mpi4py==4.0.3 ; python_version >= "3.12"
+mpmath==1.3.0 ; python_version >= "3.12"
+msgpack==1.1.0 ; python_version >= "3.12"
+multidict==6.1.0 ; python_version >= "3.12"
+multiprocess==0.70.16 ; python_version >= "3.12"
+namex==0.0.8 ; python_version >= "3.12"
+narwhals==1.30.0 ; python_version >= "3.12"
+nest-asyncio==1.6.0 ; python_version >= "3.12"
+networkx==3.4.2 ; python_version >= "3.12"
+nltk==3.9.1 ; python_version >= "3.12"
+numpy==2.1.3 ; python_version >= "3.12"
+nvidia-cublas-cu12==12.4.5.8 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cuda-cupti-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cuda-nvrtc-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cuda-runtime-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cudnn-cu12==9.1.0.70 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cufft-cu12==11.2.1.3 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-curand-cu12==10.3.5.147 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cusolver-cu12==11.6.1.9 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cusparse-cu12==12.3.1.170 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-cusparselt-cu12==0.6.2 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-nccl-cu12==2.21.5 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-nvjitlink-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+nvidia-nvtx-cu12==12.4.127 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+onnx==1.17.0 ; python_version >= "3.12"
+openpyxl==3.1.5 ; python_version >= "3.12"
+opt-einsum==3.4.0 ; python_version >= "3.12"
+optree==0.14.1 ; python_version >= "3.12"
+packaging==24.2 ; python_version >= "3.12"
+pandas==2.2.3 ; python_version >= "3.12"
+parso==0.8.4 ; python_version >= "3.12"
+partd==1.4.2 ; python_version >= "3.12"
+pbs-installer==2025.3.11 ; python_version >= "3.12"
+peft==0.14.0 ; python_version >= "3.12"
+pexpect==4.9.0 ; python_version >= "3.12" and sys_platform != "win32" and sys_platform != "emscripten"
+pillow==11.1.0 ; python_version >= "3.12"
+pkginfo==1.12.1.2 ; python_version >= "3.12"
+platformdirs==4.3.6 ; python_version >= "3.12"
+plotly==6.0.0 ; python_version >= "3.12"
+portalocker==3.1.1 ; python_version >= "3.12"
+prompt-toolkit==3.0.50 ; python_version >= "3.12"
+propcache==0.3.0 ; python_version >= "3.12"
+protobuf==5.29.3 ; python_version >= "3.12"
+psutil==7.0.0 ; python_version >= "3.12"
+ptyprocess==0.7.0 ; python_version >= "3.12" and sys_platform != "win32" and sys_platform != "emscripten"
+pure-eval==0.2.3 ; python_version >= "3.12"
+pyarrow==19.0.1 ; python_version >= "3.12"
+pycparser==2.22 ; (sys_platform == "linux" or implementation_name == "pypy" or platform_python_implementation == "PyPy") and python_version >= "3.12"
+pycurl==7.45.6 ; python_version >= "3.12"
+pydeck==0.9.1 ; python_version >= "3.12"
+pygments==2.19.1 ; python_version >= "3.12"
+pyparsing==3.2.1 ; python_version >= "3.12"
+pyproject-hooks==1.2.0 ; python_version >= "3.12"
+python-dateutil==2.9.0.post0 ; python_version >= "3.12"
+pytorch-lightning==2.5.0.post0 ; python_version >= "3.12"
+pytz==2025.1 ; python_version >= "3.12"
+pywin32-ctypes==0.2.3 ; python_version >= "3.12"
+pywin32==309 ; python_version >= "3.12"
+pyyaml==6.0.2 ; python_version >= "3.12"
+pyzmq==26.3.0 ; python_version >= "3.12"
+rapidfuzz==3.12.2 ; python_version >= "3.12"
+referencing==0.36.2 ; python_version >= "3.12"
+regex==2024.11.6 ; python_version >= "3.12"
+requests-toolbelt==1.0.0 ; python_version >= "3.12"
+requests==2.32.3 ; python_version >= "3.12"
+rich==13.9.4 ; python_version >= "3.12"
+rouge-score==0.1.2 ; python_version >= "3.12"
+rpds-py==0.23.1 ; python_version >= "3.12"
+sacrebleu==2.5.1 ; python_version >= "3.12"
+safetensors==0.5.3 ; python_version >= "3.12"
+scikit-learn==1.6.1 ; python_version >= "3.12"
+scipy==1.15.2 ; python_version >= "3.12"
+secretstorage==3.3.3 ; python_version >= "3.12" and sys_platform == "linux"
+sentence-transformers==3.4.1 ; python_version >= "3.12"
+sentencepiece==0.2.0 ; python_version >= "3.12"
+setuptools==76.0.0 ; python_version >= "3.12"
+shellingham==1.5.4 ; python_version >= "3.12"
+six==1.17.0 ; python_version >= "3.12"
+smmap==5.0.2 ; python_version >= "3.12"
+sniffio==1.3.1 ; python_version >= "3.12"
+sortedcontainers==2.4.0 ; python_version >= "3.12"
+soupsieve==2.6 ; python_version >= "3.12"
+stack-data==0.6.3 ; python_version >= "3.12"
+streamlit==1.43.2 ; python_version >= "3.12"
+sympy==1.13.1 ; python_version >= "3.12"
+tabulate==0.9.0 ; python_version >= "3.12"
+tblib==3.0.0 ; python_version >= "3.12"
+tenacity==9.0.0 ; python_version >= "3.12"
+tensorboard-data-server==0.7.2 ; python_version >= "3.12"
+tensorboard==2.19.0 ; python_version >= "3.12"
+tensorflow==2.19.0 ; python_version >= "3.12"
+termcolor==2.5.0 ; python_version >= "3.12"
+threadpoolctl==3.6.0 ; python_version >= "3.12"
+tiktoken==0.9.0 ; python_version >= "3.12"
+tokenizers==0.21.1 ; python_version >= "3.12"
+toml==0.10.2 ; python_version >= "3.12"
+tomlkit==0.13.2 ; python_version >= "3.12"
+toolz==1.0.0 ; python_version >= "3.12"
+torch==2.6.0 ; python_version >= "3.12"
+torchmetrics==1.6.3 ; python_version >= "3.12"
+torchvision==0.21.0 ; python_version >= "3.12"
+tornado==6.4.2 ; python_version >= "3.12"
+tqdm==4.67.1 ; python_version >= "3.12"
+traitlets==5.14.3 ; python_version >= "3.12"
+transformers==4.49.0 ; python_version >= "3.12"
+triton==3.2.0 ; platform_system == "Linux" and platform_machine == "x86_64" and python_version >= "3.12"
+trove-classifiers==2025.3.13.13 ; python_version >= "3.12"
+typing-extensions==4.12.2 ; python_version >= "3.12"
+tzdata==2025.1 ; python_version >= "3.12"
+urllib3==2.3.0 ; python_version >= "3.12"
+virtualenv==20.29.3 ; python_version >= "3.12"
+watchdog==6.0.0 ; python_version >= "3.12"
+wcwidth==0.2.13 ; python_version >= "3.12"
+werkzeug==3.1.3 ; python_version >= "3.12"
+wheel==0.45.1 ; python_version >= "3.12"
+wrapt==1.17.2 ; python_version >= "3.12"
+xxhash==3.5.0 ; python_version >= "3.12"
+yarl==1.18.3 ; python_version >= "3.12"
+zict==3.0.0 ; python_version >= "3.12"
+zipp==3.21.0 ; python_version >= "3.12"
+zstandard==0.23.0 ; python_version >= "3.12"

sentiment_analysis/config/stage1_models.json

@@ -8,6 +8,7 @@
         "model_class": "DebertaV2ForSequenceClassification",
         "problem_type": "multi_label_classification",
         "base_model": "microsoft/deberta-v3-base",
+        "base_model_class": "DebertaV2ForSequenceClassification",
         "num_labels": 3,
         "device": "cpu",
         "load_function": "load_model",
@@ -22,6 +23,22 @@
         "model_class": "SentimentModel",
         "problem_type": "multi_label_classification",
         "base_model": "microsoft/deberta-v3-base",
+        "base_model_class": "DebertaV2Model",
+        "num_labels": 3,
+        "device": "cpu",
+        "load_function": "load_model",
+        "predict_function": "predict"
+    },
+    "3": {
+        "name": "BERT Base Uncased Custom Model",
+        "type": "bert_base_uncased_custom",
+        "module_path": "hmv_cfg_base_stage1.model3",
+        "hf_location": "https://huggingface.co/tachygraphy-microtrext-norm-org/BERT-LV1-SentimentPolarities/resolve/main/saved_weights.pt",
+        "tokenizer_class": "AutoTokenizer",
+        "model_class": "BERT_architecture",
+        "problem_type": "multi_label_classification",
+        "base_model": "bert-base-uncased",
+        "base_model_class": "AutoModel",
         "num_labels": 3,
         "device": "cpu",
         "load_function": "load_model",

sentiment_analysis/hmv_cfg_base_stage1/model1.py

@@ -16,6 +16,7 @@ MODEL_OPTIONS = {
         "model_class": "DebertaV2ForSequenceClassification",
         "problem_type": "multi_label_classification",
         "base_model": "microsoft/deberta-v3-base",
+        "base_model_class": "DebertaV2ForSequenceClassification",
         "num_labels": 3,
         "device": "cpu",
         "load_function": "load_model",
@@ -24,15 +25,16 @@ MODEL_OPTIONS = {
 }
 
 
-@st.cache_resource
+model_key = "1"
+model_info = MODEL_OPTIONS[model_key]
+hf_location = model_info["hf_location"]
+
+tokenizer_class = globals()[model_info["tokenizer_class"]]
+model_class = globals()[model_info["model_class"]]
 
-def load_model():
-    model_key = "1"
-    model_info = MODEL_OPTIONS[model_key]
-    hf_location = model_info["hf_location"]
 
-    tokenizer_class = globals()[model_info["tokenizer_class"]]
-    model_class = globals()[model_info["model_class"]]
+@st.cache_resource
+def load_model():
     tokenizer = tokenizer_class.from_pretrained(hf_location)
     print("Loading model 1")
     model = model_class.from_pretrained(hf_location,
@@ -71,5 +73,5 @@ def predict(text, model, tokenizer, device, max_len=128):
 
 
 if __name__ == "__main__":
-    model, tokenizer = load_model("1")
+    model, tokenizer = load_model()
     print("Model and tokenizer loaded successfully.")

sentiment_analysis/hmv_cfg_base_stage1/model2.py

@@ -30,6 +30,7 @@ MODEL_OPTIONS = {
         "model_class": "SentimentModel",
         "problem_type": "multi_label_classification",
         "base_model": "microsoft/deberta-v3-base",
+        "base_model_class": "DebertaV2Model",
         "num_labels": 3,
         "device": "cpu",
         "load_function": "load_model",
@@ -37,83 +38,6 @@ MODEL_OPTIONS = {
     }
 }
 
-
-# class SentimentModel(nn.Module):
-#     def __init__(self, roberta_model=DebertaV2Model.from_pretrained(
-#             'microsoft/deberta-v3-base',
-#             device_map=torch.device("cuda" if torch.cuda.is_available() else "cpu")
-#         ), n_classes=3, dropout_rate=0.2):
-#         super(SentimentModel, self).__init__()
-
-#         self.roberta = roberta_model
-#         self.drop = nn.Dropout(p=dropout_rate)
-#         self.fc1 = nn.Linear(self.roberta.config.hidden_size, 256)  # Reduced neurons
-#         self.relu = nn.ReLU()
-#         self.out = nn.Linear(256, n_classes)
-
-#     def forward(self, input_ids, attention_mask):
-#         output = self.roberta(input_ids=input_ids, attention_mask=attention_mask)
-#         cls_token_state = output.last_hidden_state[:, 0, :]
-#         output = self.drop(cls_token_state)
-#         output = self.relu(self.fc1(output))
-#         return self.out(output)
-
-#     def save_pretrained(self, save_directory):
-#         os.makedirs(save_directory, exist_ok=True)
-
-#         # Save model weights using safetensors
-#         model_weights = self.state_dict()
-#         save_file(model_weights, os.path.join(save_directory, "model.safetensors"))
-
-#         # Save model config
-#         config = {
-#             "hidden_size": self.roberta.config.hidden_size,
-#             "num_labels": self.out.out_features,
-#             "dropout_rate": self.drop.p,
-#             "roberta_model": self.roberta.name_or_path
-#         }
-#         with open(os.path.join(save_directory, "config.json"), "w") as f:
-#             json.dump(config, f)
-
-#         print(f"Model saved in {save_directory}")
-
-#     @classmethod
-#     def load_pretrained(cls, model_path_or_repo, roberta_model):
-#         # if model_path_or_repo.startswith("http") or "/" not in model_path_or_repo:
-#         #     # Load from Hugging Face Hub
-#         #     model_config_path = hf_hub_download(model_path_or_repo, "config.json")
-#         #     model_weights_path = hf_hub_download(model_path_or_repo, "model.safetensors")
-#         # else:
-#         #     # Load from local directory
-#         #     model_config_path = os.path.join(model_path_or_repo, "config.json")
-#         #     model_weights_path = os.path.join(model_path_or_repo, "model.safetensors")
-
-#         model_config_path = hf_hub_download(model_path_or_repo, "config.json")
-#         model_weights_path = hf_hub_download(model_path_or_repo, "model.safetensors")
-
-#         # Load model config
-#         with open(model_config_path, "r") as f:
-#             config = json.load(f)
-
-#         # Load RoBERTa model
-#         roberta_model = DebertaV2Model.from_pretrained(config["roberta_model"])
-
-#         # Initialize SentimentModel
-#         model = cls(
-#             roberta_model,
-#             n_classes=config["num_labels"],
-#             dropout_rate=config["dropout_rate"]
-#         )
-
-#         # Load safetensors weights
-#         with safe_open(model_weights_path, framework="pt", device="cpu") as f:
-#             model_weights = {key: f.get_tensor(key) for key in f.keys()}
-#         model.load_state_dict(model_weights)
-
-#         print(f"Model loaded from {model_path_or_repo}")
-#         return model
-
-
 class SentimentModel(nn.Module):
     def __init__(self, roberta_model, n_classes=3, dropout_rate=0.2):
         super(SentimentModel, self).__init__()
@@ -176,42 +100,19 @@ class SentimentModel(nn.Module):
 
         print(f"Model loaded from {model_path_or_repo}")
         return model
+    
 
+model_key = "2"
+model_info = MODEL_OPTIONS[model_key]
+hf_location = model_info["hf_location"]
+base_model = model_info["base_model"]
 
-@st.cache_resource
-
-# def load_pretrained(model_path_or_repo):
-
-#     model_config_path = hf_hub_download(model_path_or_repo, "config.json")
-#     model_weights_path = hf_hub_download(model_path_or_repo, "model.safetensors")
-
-#     with open(model_config_path, "r") as f:
-#         config = json.load(f)
-
-#     roberta_model = DebertaV2Model.from_pretrained(
-#         config["roberta_model"],
-#     )
-
-#     model = SentimentModel(
-#         roberta_model, n_classes=config["num_labels"], dropout_rate=config["dropout_rate"]
-#     )
-
-#     with safe_open(model_weights_path, framework="pt", device="cpu") as f:
-#         model_weights = {key: f.get_tensor(key) for key in f.keys()}
-#     model.load_state_dict(model_weights)
-
-#     print(f"Model loaded from {model_path_or_repo}")
-#     return model
+tokenizer_class = globals()[model_info["tokenizer_class"]]
+model_class = globals()[model_info["model_class"]]
 
     
-
+@st.cache_resource
 def load_model():
-    model_key = "2"
-    model_info = MODEL_OPTIONS[model_key]
-    hf_location = model_info["hf_location"]
-
-    tokenizer_class = globals()[model_info["tokenizer_class"]]
-    model_class = globals()[model_info["model_class"]]
     tokenizer = tokenizer_class.from_pretrained(hf_location)
     print("Loading model 2")
     model = SentimentModel.load_pretrained(hf_location)
@@ -227,7 +128,6 @@ def predict(text, model, tokenizer, device, max_len=128):
     # Tokenize and pad the input text
     inputs = tokenizer(
         text,
-        None,
         add_special_tokens=True,
         padding=True,
         truncation=False,
@@ -246,5 +146,112 @@ def predict(text, model, tokenizer, device, max_len=128):
 
 
 if __name__ == "__main__":
-    model, tokenizer = load_model("2")
+    model, tokenizer = load_model()
     print("Model and tokenizer loaded successfully.")
+
+
+### COMMENTED CODE ###
+
+
+# @st.cache_resource
+
+# def load_pretrained(model_path_or_repo):
+
+#     model_config_path = hf_hub_download(model_path_or_repo, "config.json")
+#     model_weights_path = hf_hub_download(model_path_or_repo, "model.safetensors")
+
+#     with open(model_config_path, "r") as f:
+#         config = json.load(f)
+
+#     roberta_model = DebertaV2Model.from_pretrained(
+#         config["roberta_model"],
+#     )
+
+#     model = SentimentModel(
+#         roberta_model, n_classes=config["num_labels"], dropout_rate=config["dropout_rate"]
+#     )
+
+#     with safe_open(model_weights_path, framework="pt", device="cpu") as f:
+#         model_weights = {key: f.get_tensor(key) for key in f.keys()}
+#     model.load_state_dict(model_weights)
+
+#     print(f"Model loaded from {model_path_or_repo}")
+#     return model
+
+
+
+
+# class SentimentModel(nn.Module):
+#     def __init__(self, roberta_model=DebertaV2Model.from_pretrained(
+#             'microsoft/deberta-v3-base',
+#             device_map=torch.device("cuda" if torch.cuda.is_available() else "cpu")
+#         ), n_classes=3, dropout_rate=0.2):
+#         super(SentimentModel, self).__init__()
+
+#         self.roberta = roberta_model
+#         self.drop = nn.Dropout(p=dropout_rate)
+#         self.fc1 = nn.Linear(self.roberta.config.hidden_size, 256)  # Reduced neurons
+#         self.relu = nn.ReLU()
+#         self.out = nn.Linear(256, n_classes)
+
+#     def forward(self, input_ids, attention_mask):
+#         output = self.roberta(input_ids=input_ids, attention_mask=attention_mask)
+#         cls_token_state = output.last_hidden_state[:, 0, :]
+#         output = self.drop(cls_token_state)
+#         output = self.relu(self.fc1(output))
+#         return self.out(output)
+
+#     def save_pretrained(self, save_directory):
+#         os.makedirs(save_directory, exist_ok=True)
+
+#         # Save model weights using safetensors
+#         model_weights = self.state_dict()
+#         save_file(model_weights, os.path.join(save_directory, "model.safetensors"))
+
+#         # Save model config
+#         config = {
+#             "hidden_size": self.roberta.config.hidden_size,
+#             "num_labels": self.out.out_features,
+#             "dropout_rate": self.drop.p,
+#             "roberta_model": self.roberta.name_or_path
+#         }
+#         with open(os.path.join(save_directory, "config.json"), "w") as f:
+#             json.dump(config, f)
+
+#         print(f"Model saved in {save_directory}")
+
+#     @classmethod
+#     def load_pretrained(cls, model_path_or_repo, roberta_model):
+#         # if model_path_or_repo.startswith("http") or "/" not in model_path_or_repo:
+#         #     # Load from Hugging Face Hub
+#         #     model_config_path = hf_hub_download(model_path_or_repo, "config.json")
+#         #     model_weights_path = hf_hub_download(model_path_or_repo, "model.safetensors")
+#         # else:
+#         #     # Load from local directory
+#         #     model_config_path = os.path.join(model_path_or_repo, "config.json")
+#         #     model_weights_path = os.path.join(model_path_or_repo, "model.safetensors")
+
+#         model_config_path = hf_hub_download(model_path_or_repo, "config.json")
+#         model_weights_path = hf_hub_download(model_path_or_repo, "model.safetensors")
+
+#         # Load model config
+#         with open(model_config_path, "r") as f:
+#             config = json.load(f)
+
+#         # Load RoBERTa model
+#         roberta_model = DebertaV2Model.from_pretrained(config["roberta_model"])
+
+#         # Initialize SentimentModel
+#         model = cls(
+#             roberta_model,
+#             n_classes=config["num_labels"],
+#             dropout_rate=config["dropout_rate"]
+#         )
+
+#         # Load safetensors weights
+#         with safe_open(model_weights_path, framework="pt", device="cpu") as f:
+#             model_weights = {key: f.get_tensor(key) for key in f.keys()}
+#         model.load_state_dict(model_weights)
+
+#         print(f"Model loaded from {model_path_or_repo}")
+#         return model

sentiment_analysis/hmv_cfg_base_stage1/model3.py

@@ -8,7 +8,7 @@ import joblib
 import torch
 import torch.nn as nn
 import torch.functional as F
-from transformers import DebertaV2Model, DebertaV2Tokenizer
+from transformers import DebertaV2Model, DebertaV2Tokenizer, AutoModel, AutoTokenizer
 import safetensors
 # from safetensors import load_file, save_file
 import json
@@ -23,13 +23,14 @@ CONFIG_STAGE1 = os.path.join(BASE_DIR, "..", "config", "stage1_models.json")
 MODEL_OPTIONS = {
     "3": {
         "name": "BERT Base Uncased Custom Model",
-        "type": "db3_base_custom",
-        "module_path": "hmv_cfg_base_stage1.model2",
-        "hf_location": "tachygraphy-microtrext-norm-org/DeBERTa-v3-Base-Cust-LV1-SentimentPolarities-minRegLoss",
-        "tokenizer_class": "DebertaV2Tokenizer",
+        "type": "bert_base_uncased_custom",
+        "module_path": "hmv_cfg_base_stage1.model3",
+        "hf_location": "https://huggingface.co/tachygraphy-microtrext-norm-org/BERT-LV1-SentimentPolarities/resolve/main/saved_weights.pt",
+        "tokenizer_class": "AutoTokenizer",
         "model_class": "BERT_architecture",
         "problem_type": "multi_label_classification",
-        "base_model": "google/bert-base-uncased",
+        "base_model": "bert-base-uncased",
+        "base_model_class": "AutoModel",
         "num_labels": 3,
         "device": "cpu",
         "load_function": "load_model",
@@ -37,26 +38,23 @@ MODEL_OPTIONS = {
     }
 }
 
-
 class BERT_architecture(nn.Module):
 
-    def __init__(self, bert=AutoModel.from_pretrained("bert-base-uncased",
-                                                      device_map=torch.device("cuda" if torch.cuda.is_available() else "cpu"))):
+    def __init__(self, bert):
         super(BERT_architecture, self).__init__()
         self.bert = bert
-
+        
         self.dropout = nn.Dropout(0.3)  # Increased dropout for regularization
         self.layer_norm = nn.LayerNorm(768)  # Layer normalization
-
+        
         self.fc1 = nn.Linear(768, 256)  # Dense layer
         self.fc2 = nn.Linear(256, 3)  # Output layer with 3 classes
-
+        
         self.relu = nn.ReLU()
         self.softmax = nn.LogSoftmax(dim=1)
 
     def forward(self, sent_id, mask, token_type_ids):
-        _, cls_hs = self.bert(sent_id, attention_mask=mask,
-                              token_type_ids=token_type_ids, return_dict=False)
+        _, cls_hs = self.bert(sent_id, attention_mask=mask, token_type_ids=token_type_ids, return_dict=False)
         x = self.layer_norm(cls_hs)
         x = self.fc1(x)
         x = self.relu(x)
@@ -64,3 +62,85 @@ class BERT_architecture(nn.Module):
         x = self.fc2(x)
         x = self.softmax(x)
         return x
+    
+
+model_key = "3"
+model_info = MODEL_OPTIONS[model_key]
+hf_location = model_info["hf_location"]
+base_model = model_info["base_model"]
+base_model_class = globals()[model_info["base_model_class"]]
+
+tokenizer_class = globals()[model_info["tokenizer_class"]]
+model_class = globals()[model_info["model_class"]]
+    
+
+@st.cache_resource
+def load_model():
+    bert = base_model_class.from_pretrained(base_model)
+    tokenizer = tokenizer_class.from_pretrained(base_model)
+    print("Loading model 3")
+
+    model = BERT_architecture(bert)
+    state_dict = torch.hub.load_state_dict_from_url(
+        hf_location,
+        map_location = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+    )
+    model.load_state_dict(state_dict)
+    print("Model 3 loaded")
+    
+    return model, tokenizer
+
+
+def predict(input_text, model, tokenizer, device, max_seq_len=128):
+    inputs = tokenizer(
+        input_text,
+        add_special_tokens=True,
+        padding=True,
+        truncation=True,  # Ensure dynamic length truncation
+        max_length=max_seq_len,
+        return_attention_mask=True,
+        return_token_type_ids=True,
+        return_tensors='pt',
+    ).to(device)
+
+
+    with torch.no_grad():
+        # outputs = model(**inputs)
+
+        outputs = model(
+            sent_id=inputs["input_ids"],             # input_ids → sent_id
+            mask=inputs["attention_mask"],           # attention_mask → mask
+            token_type_ids=inputs["token_type_ids"]  # token_type_ids → token_type_ids
+        )
+    #     preds = outputs.cpu().numpy()
+    #     pred = np.argmax(preds, axis=1)
+    
+    # return pred
+
+    # Ensure output shape consistency
+    # if outputs.dim() == 1:
+    #     # Reshape to [1, num_classes] if it's a single prediction
+    #     outputs = outputs.unsqueeze(0)
+
+    # Apply softmax here if you need probabilities
+    # probabilities = torch.softmax(outputs, dim=1).cpu().numpy()
+
+    ## TO RETURN ARGMAX VALUE
+    # pred_class = torch.argmax(outputs, dim=1).cpu().numpy()
+
+    # num_classes=3
+
+    # probabilities = np.zeros((1, num_classes))
+    # probabilities[0, pred_class] = 1.0
+
+    ## TO RETURN PROBABILITIES FROM LOG SOFTMAX OF MODEL
+    probabilities = torch.exp(outputs).cpu().numpy()
+
+    print(probabilities)
+    
+    return probabilities
+
+
+if __name__ == "__main__":
+    model, tokenizer = load_model()
+    print("Model and tokenizer loaded successfully.")

sentiment_analysis/sentiment_analysis_main.py

@@ -29,7 +29,7 @@ current_tokenizer = None
 # Enabling Resource caching
 
 
-@st.cache_resource
+# @st.cache_resource
 def load_model_config():
     with open(CONFIG_STAGE1, "r") as f:
         model_data = json.load(f)
@@ -91,9 +91,9 @@ def free_memory():
 def load_selected_model(model_name):
     global current_model, current_tokenizer
 
-    st.cache_resource.clear()
+    # st.cache_resource.clear()
 
-    free_memory()
+    # free_memory()
 
     # st.write("DEBUG: Available Models:", MODEL_OPTIONS.keys())  # ✅ See available models
     # st.write("DEBUG: Selected Model:", MODEL_OPTIONS[model_name])  # ✅ Check selected model
@@ -123,6 +123,41 @@ def load_selected_model(model_name):
     return model, tokenizer, predict_func
 
 
+def disable_ui():
+    st.components.v1.html(
+        """
+        <style>
+        #ui-disable-overlay {
+            position: fixed;
+            top: 0;
+            left: 0;
+            width: 100vw;
+            height: 100vh;
+            background-color: rgba(200, 200, 200, 0.5);
+            z-index: 9999;
+        }
+        </style>
+        <div id="ui-disable-overlay"></div>
+        """,
+        height=0,
+        scrolling=False
+    )
+
+
+def enable_ui():
+    st.components.v1.html(
+        """
+        <script>
+        var overlay = document.getElementById("ui-disable-overlay");
+        if (overlay) {
+            overlay.parentNode.removeChild(overlay);
+        }
+        </script>
+        """,
+        height=0,
+        scrolling=False
+    )
+
 # Function to increment progress dynamically
 def update_progress(progress_bar, start, end, delay=0.1):
     for i in range(start, end + 1, 5):  # Increment in steps of 5%
@@ -156,12 +191,10 @@ if "model_changed" not in st.session_state:
 if "text_changed" not in st.session_state:
     st.session_state.text_changed = False
 if "processing" not in st.session_state:
-    st.session_state.processing = False
+    st.session_state.disabled = False
 
 
 def show_sentiment_analysis():
-    st.cache_resource.clear()
-    free_memory()
 
     st.title("Stage 1: Sentiment Polarity Analysis")
     st.write("This section handles sentiment analysis.")
@@ -182,6 +215,9 @@ def show_sentiment_analysis():
     # 2. The text has changed OR the model has changed
     if user_input.strip() and (st.session_state.text_changed or st.session_state.model_changed):
 
+        # disable_ui()
+
+
         # Reset session state flags
         st.session_state.last_processed_input = user_input
         st.session_state.model_changed = False
@@ -228,10 +264,11 @@ def show_sentiment_analysis():
         # Display raw predictions
         st.write(f"**Predicted Sentiment Scores:** {predictions_array}")
 
+        # enable_ui()
+
         # Display binary classification result
         st.write(f"**Predicted Sentiment:**")
-        st.write(
-            f"**NEGATIVE:** {binary_predictions[0]}, **NEUTRAL:** {binary_predictions[1]}, **POSITIVE:** {binary_predictions[2]}")
+        st.write(f"**NEGATIVE:** {binary_predictions[0]}, **NEUTRAL:** {binary_predictions[1]}, **POSITIVE:** {binary_predictions[2]}")
         # st.write(f"**NEUTRAL:** {binary_predictions[1]}")
         # st.write(f"**POSITIVE:** {binary_predictions[2]}")
 
@@ -272,6 +309,281 @@ if __name__ == "__main__":
     show_sentiment_analysis()
 
 
+
+
+
+
+
+
+
+
+#########
+
+
+# def show_sentiment_analysis():
+#     st.cache_resource.clear()
+#     free_memory()
+
+#     st.title("Stage 1: Sentiment Polarity Analysis")
+#     st.write("This section handles sentiment analysis.")
+
+#     # Model selection with change detection
+#     selected_model = st.selectbox(
+#         "Choose a model:", list(MODEL_OPTIONS.keys()), key="selected_model", on_change=on_model_change
+#     )
+
+#     # Text input with change detection
+#     user_input = st.text_input(
+#         "Enter text for sentiment analysis:", key="user_input", on_change=on_text_change
+#     )
+#     user_input_copy = user_input
+
+#     # Only run inference if:
+#     # 1. The text is NOT empty
+#     # 2. The text has changed OR the model has changed
+#     if user_input.strip() and (st.session_state.text_changed or st.session_state.model_changed):
+
+#         # Reset session state flags
+#         st.session_state.last_processed_input = user_input
+#         st.session_state.model_changed = False
+#         st.session_state.text_changed = False   # Store selected model
+
+#         # ADD A DYNAMIC PROGRESS BAR
+#         progress_bar = st.progress(0)
+#         update_progress(progress_bar, 0, 10)
+#         # status_text = st.empty()
+
+#         # update_progress(0, 10)
+#         # status_text.text("Loading model...")
+
+#         # Make prediction
+
+#         # model, tokenizer = load_model()
+#         # model, tokenizer = load_selected_model(selected_model)
+#         with st.spinner("Please wait..."):
+#             model, tokenizer, predict_func = load_selected_model(selected_model)
+#             device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+#             if model is None:
+#                 st.error(
+#                     "⚠️ Error: Model failed to load! Check model selection or configuration.")
+#                 st.stop()
+
+#             model.to(device)
+
+#             # predictions = predict(user_input, model, tokenizer, device)
+
+#             predictions = predict_func(user_input, model, tokenizer, device)
+
+#             # Squeeze predictions to remove extra dimensions
+#             predictions_array = predictions.squeeze()
+
+#             # Convert to binary predictions (argmax)
+#             binary_predictions = np.zeros_like(predictions_array)
+#             max_indices = np.argmax(predictions_array)
+#             binary_predictions[max_indices] = 1
+
+#             # Update progress bar for prediction and model loading
+#             update_progress(progress_bar, 10, 100)
+
+#         # Display raw predictions
+#         st.write(f"**Predicted Sentiment Scores:** {predictions_array}")
+
+#         # Display binary classification result
+#         st.write(f"**Predicted Sentiment:**")
+#         st.write(
+#             f"**NEGATIVE:** {binary_predictions[0]}, **NEUTRAL:** {binary_predictions[1]}, **POSITIVE:** {binary_predictions[2]}")
+#         # st.write(f"**NEUTRAL:** {binary_predictions[1]}")
+#         # st.write(f"**POSITIVE:** {binary_predictions[2]}")
+
+#         # 1️⃣ **Polar Plot (Plotly)**
+#         sentiment_polarities = predictions_array.tolist()
+#         fig_polar = px.line_polar(
+#             pd.DataFrame(dict(r=sentiment_polarities,
+#                          theta=SENTIMENT_POLARITY_LABELS)),
+#             r='r', theta='theta', line_close=True
+#         )
+#         st.plotly_chart(fig_polar)
+
+#         # 2️⃣ **Normalized Horizontal Bar Chart (Matplotlib)**
+#         normalized_predictions = predictions_array / predictions_array.sum()
+
+#         fig, ax = plt.subplots(figsize=(8, 2))
+#         left = 0
+#         for i in range(len(normalized_predictions)):
+#             ax.barh(0, normalized_predictions[i], color=plt.cm.tab10(
+#                 i), left=left, label=SENTIMENT_POLARITY_LABELS[i])
+#             left += normalized_predictions[i]
+
+#         # Configure the chart
+#         ax.set_xlim(0, 1)
+#         ax.set_yticks([])
+#         ax.set_xticks(np.arange(0, 1.1, 0.1))
+#         ax.legend(loc='upper center', bbox_to_anchor=(
+#             0.5, -0.15), ncol=len(SENTIMENT_POLARITY_LABELS))
+#         plt.title("Sentiment Polarity Prediction Distribution")
+
+#         # Display in Streamlit
+#         st.pyplot(fig)
+
+#         progress_bar.empty()
+
+######
+########
+
+
+
+# def show_sentiment_analysis():
+#     st.cache_resource.clear()
+#     free_memory()
+
+#     st.title("Stage 1: Sentiment Polarity Analysis")
+#     st.write("This section handles sentiment analysis.")
+
+#     # Model selection with change detection
+#     selected_model = st.selectbox(
+#         "Choose a model:", list(MODEL_OPTIONS.keys()), key="selected_model", on_change=on_model_change, disabled=st.session_state.disabled
+#     )
+
+#     # Text input with change detection
+#     user_input = st.text_input(
+#         "Enter text for sentiment analysis:", key="user_input", on_change=on_text_change, disabled=st.session_state.disabled
+#     )
+#     user_input_copy = user_input
+
+#     # progress_bar = st.progress(0)
+#     progress_bar = st.empty()
+
+#     if st.session_state.disabled is False and st.session_state.predictions is not None:
+#         st.write(f"**Predicted Sentiment Scores:** {st.session_state.predictions}")
+#         st.write(f"**NEGATIVE:** {st.session_state.binary_predictions[0]}, **NEUTRAL:** {st.session_state.binary_predictions[1]}, **POSITIVE:** {st.session_state.binary_predictions[2]}")
+#         st.plotly_chart(st.session_state.polar_plot)
+#         st.pyplot(st.session_state.bar_chart)
+
+#         update_progress(progress_bar, 95, 100)
+
+#         st.session_state.predictions = None
+#         st.session_state.binary_predictions = None
+#         st.session_state.polar_plot = None
+#         st.session_state.bar_chart = None
+        
+#         st.session_state.disabled = False
+            
+#         progress_bar.empty()
+
+
+#     if user_input.strip() and (st.session_state.text_changed or st.session_state.model_changed) and st.session_state.disabled is False:
+#         st.session_state.disabled = True
+#         st.rerun()
+#         return
+        
+    
+#     if user_input.strip() and (st.session_state.text_changed or st.session_state.model_changed) and st.session_state.disabled is True:
+#         # Mark processing as True to
+        
+
+#         # Reset session state flags
+#         st.session_state.last_processed_input = user_input
+#         st.session_state.model_changed = False
+#         st.session_state.text_changed = False   # Store selected model
+
+#         # ADD A DYNAMIC PROGRESS BAR
+#         progress_bar = st.progress(0)
+#         update_progress(progress_bar, 0, 10)
+#         # status_text = st.empty()
+
+#         # update_progress(0, 10)
+#         # status_text.text("Loading model...")
+
+#         # Make prediction
+
+#         # model, tokenizer = load_model()
+#         # model, tokenizer = load_selected_model(selected_model)
+#         with st.spinner("Please wait..."):
+#             model, tokenizer, predict_func = load_selected_model(selected_model)
+#             device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+
+#             if model is None:
+#                 st.error(
+#                     "⚠️ Error: Model failed to load! Check model selection or configuration.")
+#                 st.session_state.disabled = False
+#                 st.rerun()
+#                 st.stop()
+#                 return
+
+#             model.to(device)
+
+#             # predictions = predict(user_input, model, tokenizer, device)
+
+#             predictions = predict_func(user_input, model, tokenizer, device)
+
+#             # Squeeze predictions to remove extra dimensions
+#             predictions_array = predictions.squeeze()
+
+#             # Convert to binary predictions (argmax)
+#             binary_predictions = np.zeros_like(predictions_array)
+#             max_indices = np.argmax(predictions_array)
+#             binary_predictions[max_indices] = 1
+
+#             # Update progress bar for prediction and model loading
+#             update_progress(progress_bar, 10, 75)
+
+#         # Display raw predictions
+#         # st.write(f"**Predicted Sentiment Scores:** {predictions_array}")
+#         st.session_state.predictions = predictions_array
+
+#         # Display binary classification result
+#         # st.write(f"**Predicted Sentiment:**")
+#         # st.write(f"**NEGATIVE:** {binary_predictions[0]}, **NEUTRAL:** {binary_predictions[1]}, **POSITIVE:** {binary_predictions[2]}")
+#         st.session_state.binary_predictions = binary_predictions
+
+
+#         # 1️⃣ **Polar Plot (Plotly)**
+#         sentiment_polarities = predictions_array.tolist()
+#         fig_polar = px.line_polar(
+#             pd.DataFrame(dict(r=sentiment_polarities,
+#                         theta=SENTIMENT_POLARITY_LABELS)),
+#             r='r', theta='theta', line_close=True
+#         )
+#         # st.plotly_chart(fig_polar)
+#         st.session_state.polar_plot = fig_polar
+
+#         # 2️⃣ **Normalized Horizontal Bar Chart (Matplotlib)**
+#         normalized_predictions = predictions_array / predictions_array.sum()
+
+#         fig, ax = plt.subplots(figsize=(8, 2))
+#         left = 0
+#         for i in range(len(normalized_predictions)):
+#             ax.barh(0, normalized_predictions[i], color=plt.cm.tab10(
+#                 i), left=left, label=SENTIMENT_POLARITY_LABELS[i])
+#             left += normalized_predictions[i]
+
+#         # Configure the chart
+#         ax.set_xlim(0, 1)
+#         ax.set_yticks([])
+#         ax.set_xticks(np.arange(0, 1.1, 0.1))
+#         ax.legend(loc='upper center', bbox_to_anchor=(
+#             0.5, -0.15), ncol=len(SENTIMENT_POLARITY_LABELS))
+#         # plt.title("Sentiment Polarity Prediction Distribution")
+#         # st.pyplot(fig)
+#         st.session_state.bar_chart = fig
+#         update_progress(progress_bar, 75, 95)
+
+#         # progress_bar.empty()
+
+#         if st.session_state.disabled is True:
+#             st.session_state.disabled = False
+#             st.rerun()
+#             return
+#         else:
+#             return
+        
+
+
+
+#####
+
+
 ### COMMENTED OUT CODE ###