2025.03.24.post1

dashboard.py

@@ -46,7 +46,7 @@ def free_memory():
 
 def create_sample_example1():
     st.write("""
-        ## Sample Example 1
+        #### Sample Example 1
         """)
     graph = """
     digraph {
@@ -64,7 +64,7 @@ def create_sample_example1():
         Disgust [label="Disgust: 0.015257259", fillcolor="#deffe1", fontcolor="black"];
         Fear [label="Fear: 0.601871967", fillcolor="#deffe1", fontcolor="black"];
         Joy [label="Joy: 0.00410547", fillcolor="#deffe1", fontcolor="black"];
-        NeutralE [label="Neutral: 0.0341026", fillcolor="#deffe1", fontcolor="black"];
+        Neutral [label="Neutral: 0.0341026", fillcolor="#deffe1", fontcolor="black"];
         Sadness [label="Sadness: 0.245294735", fillcolor="#deffe1", fontcolor="black"];
         Surprise [label="Surprise: 0.019189769", fillcolor="#deffe1", fontcolor="black"];
 
@@ -74,13 +74,14 @@ def create_sample_example1():
         // Establish the tree structure
         Input -> Output;
         Input -> Sentiment;
-        Sentiment -> Anger;
-        Sentiment -> Disgust;
-        Sentiment -> Fear;
-        Sentiment -> Joy;
-        Sentiment -> NeutralE;
-        Sentiment -> Sadness;
-        Sentiment -> Surprise;
+        Sentiment -> Emotion
+        Emotion -> Anger;
+        Emotion -> Disgust;
+        Emotion -> Fear;
+        Emotion -> Joy;
+        Emotion -> Neutral;
+        Emotion -> Sadness;
+        Emotion -> Surprise;
     }
     """
     st.graphviz_chart(graph)
@@ -88,7 +89,7 @@ def create_sample_example1():
 
 def create_sample_example2():
     st.write("""
-        ## Sample Example 2
+        #### Sample Example 2
         """)
     graph = """
     digraph {
@@ -98,7 +99,7 @@ def create_sample_example2():
 
         // Define nodes with custom colors
         Input [label="Input:\nu rlly think all that talk means u tough? lol, when I step up, u ain't gon say sh*t", fillcolor="#ffe6de", fontcolor="black"];
-        Output [label="Output:\nyou really think all that talk makes you tough lol when i step up you are not going to say anything", fillcolor="#ffe6de", fontcolor="black"];
+        Output [label="Output:\nyou really think all that talk makes you tough [lol](laughed out loud) when i step up you are not going to say anything", fillcolor="#ffe6de", fontcolor="black"];
         Sentiment [label="Sentiment:\nNEGATIVE", fillcolor="#ecdeff", fontcolor="black"];
 
         // Emotion nodes with a uniform style
@@ -106,7 +107,7 @@ def create_sample_example2():
         Disgust [label="Disgust: 0.039282672", fillcolor="#deffe1", fontcolor="black"];
         Fear [label="Fear: 0.014349542", fillcolor="#deffe1", fontcolor="black"];
         Joy [label="Joy: 0.048965044", fillcolor="#deffe1", fontcolor="black"];
-        NeutralE [label="Neutral: 0.494852662", fillcolor="#deffe1", fontcolor="black"];
+        Neutral [label="Neutral: 0.494852662", fillcolor="#deffe1", fontcolor="black"];
         Sadness [label="Sadness: 0.021111647", fillcolor="#deffe1", fontcolor="black"];
         Surprise [label="Surprise: 0.237405464", fillcolor="#deffe1", fontcolor="black"];
 
@@ -116,13 +117,14 @@ def create_sample_example2():
         // Establish the tree structure
         Input -> Output;
         Input -> Sentiment;
-        Sentiment -> Anger;
-        Sentiment -> Disgust;
-        Sentiment -> Fear;
-        Sentiment -> Joy;
-        Sentiment -> NeutralE;
-        Sentiment -> Sadness;
-        Sentiment -> Surprise;
+        Sentiment -> Emotion
+        Emotion -> Anger;
+        Emotion -> Disgust;
+        Emotion -> Fear;
+        Emotion -> Joy;
+        Emotion -> Neutral;
+        Emotion -> Sadness;
+        Emotion -> Surprise;
     }
     """
     st.graphviz_chart(graph)
@@ -147,19 +149,19 @@ def create_footer():
     # 🚀 Contributors Section
     with col1:
         st.markdown("### 🚀 Contributors")
-        st.write("**Archisman Karmakar**")
+        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("##### **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("##### **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("##### **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
@@ -174,21 +176,25 @@ def create_footer():
 def show_dashboard():
     # free_memory()
     st.title("Tachygraphy Micro-text Analysis & Normalization")
-    st.write("""
-        Welcome to the Tachygraphy Micro-text Analysis & Normalization Project. This application is designed to analyze text data through three stages:
-        1. Sentiment Polarity Analysis
-        2. Emotion Mood-tag Analysis
-        3. Text Transformation & Normalization
-    """)
-
-    st.write("""
-             - Training Source: [GitHub @ Tachygraphy Micro-text Analysis & Normalization](https://github.com/ArchismanKarmakar/Tachygraphy-Microtext-Analysis-And-Normalization)
-             - Kaggle Collections: [Kaggle @ Tachygraphy Micro-text Analysis & Normalization](https://www.kaggle.com/datasets/archismancoder/dataset-tachygraphy/data?select=Tachygraphy_MicroText-AIO-V3.xlsx)
-             - Hugging Face Org: [Hugging Face @ Tachygraphy Micro-text Analysis & Normalization](https://huggingface.co/Tachygraphy-Microtext-Normalization-IEMK25)
-             - Deployment Source: [GitHub](https://github.com/ArchismanKarmakar/Tachygraphy-Microtext-Analysis-And-Normalization-Deployment-Source-HuggingFace_Streamlit_JPX14032025)
-             - Streamlit Deployemnt: [Streamlit](https://tachygraphy-microtext.streamlit.app/)
-             - Hugging Face Space Deployment: [Hugging Face Space](https://huggingface.co/spaces/Tachygraphy-Microtext-Normalization-IEMK25/Tachygraphy-Microtext-Analysis-and-Normalization-ArchismanCoder)
-             """)
+    st.write(f"""Welcome to the Tachygraphy Micro-text Analysis & Normalization Project. This application is designed to analyze text data through three stages:""")
+    coltl1, coltl2 = st.columns(2)
+    with coltl1:
+        st.write("""
+            1. Sentiment Polarity Analysis
+            2. Emotion Mood-tag Analysis
+            3. Text Transformation & Normalization
+            4. Stacked all 3 stages with their best models
+            5. Data Correction & Collection
+        """)
+    with coltl2:
+        st.write("""
+                - Training Source: [GitHub @ Tachygraphy Micro-text Analysis & Normalization](https://github.com/ArchismanKarmakar/Tachygraphy-Microtext-Analysis-And-Normalization)
+                - Kaggle Collections: [Kaggle @ Tachygraphy Micro-text Analysis & Normalization](https://www.kaggle.com/datasets/archismancoder/dataset-tachygraphy/data?select=Tachygraphy_MicroText-AIO-V3.xlsx)
+                - Hugging Face Org: [Hugging Face @ Tachygraphy Micro-text Analysis & Normalization](https://huggingface.co/Tachygraphy-Microtext-Normalization-IEMK25)
+                - Deployment Source: [GitHub](https://github.com/ArchismanKarmakar/Tachygraphy-Microtext-Analysis-And-Normalization-Deployment-Source-HuggingFace_Streamlit_JPX14032025)
+                - Streamlit Deployemnt: [Streamlit](https://tachygraphy-microtext.streamlit.app/)
+                - Hugging Face Space Deployment: [Hugging Face Space](https://huggingface.co/spaces/Tachygraphy-Microtext-Normalization-IEMK25/Tachygraphy-Microtext-Analysis-and-Normalization-ArchismanCoder)
+                """)
 
     create_footer()
 
@@ -196,7 +202,7 @@ def show_dashboard():
 
     create_sample_example1()
 
-    # create_sample_example2()
+    create_sample_example2()
 
 
 def __main__():

data_collection_form/data_collector.py

@@ -250,7 +250,7 @@ def show_data_collector():
         col1, col2 = st.columns(2)
         with col1:
             feedback = st.text_input(
-                "Enter the correct expanded standard formal English text:",
+                "Enter the correct / actual expanded standard formal English text:",
                 key="feedback_input"
             )
         with col2:
@@ -260,11 +260,11 @@ def show_data_collector():
             )
 
         st.warning(
-        "The correct slider is for the probability of actual label and wrong slider is the probability predicted by any model which is wrong for that label.")
+        "The correct slider is for the actual probability of the label and wrong slider is the predicted probability by any model which is wrong for that label.")
 
 
             
-        st.write("#### Sentiment Polarity Feedback (Select values between 0 and 1)")
+        st.write("#### Sentiment Polarity Probabilities (Select values between 0 and 1)")
         SENTIMENT_POLARITY_LABELS = ["negative", "neutral", "positive"]
 
         model_names1 = list(MODEL_OPTIONS1.keys())
@@ -277,7 +277,7 @@ def show_data_collector():
         sentiment_cols = st.columns(len(SENTIMENT_POLARITY_LABELS))
         for idx, label in enumerate(SENTIMENT_POLARITY_LABELS):
             with sentiment_cols[idx]:
-                st.write(f"**{label.capitalize()}**")
+                st.write(f"##### **{label.capitalize()}**")
                 # Create two subcolumns for "Correct" and "Wrong"
                 subcol_correct, subcol_wrong = st.columns(2)
                 with subcol_correct:
@@ -308,7 +308,7 @@ def show_data_collector():
         # ---------------------------
         # Emotion Feedback
         # ---------------------------
-        st.write("#### Emotion Feedback (Select values between 0 and 1)")
+        st.write("#### Emotion Probabilities (Select values between 0 and 1)")
         EMOTION_MOODTAG_LABELS = [
             "anger", "disgust", "fear", "joy", "neutral",
             "sadness", "surprise"
@@ -331,7 +331,7 @@ def show_data_collector():
             main_cols = st.columns(len(row_labels))
             for idx, label in enumerate(row_labels):
                 with main_cols[idx]:
-                    st.write(f"**{label.capitalize()}**")
+                    st.write(f"##### **{label.capitalize()}**")
                     # Create two subcolumns for correct and wrong values.
                     subcol_correct, subcol_wrong = st.columns(2)
                     with subcol_correct:
@@ -358,7 +358,7 @@ def show_data_collector():
 
 
         # Use form_submit_button instead of st.button inside a form
-        submit_feedback = st.form_submit_button("Submit Feedback")
+        submit_feedback = st.form_submit_button("Submit Data")
 
         if submit_feedback and feedback.strip() and feedback2.strip():
             # Prepare data to insert
@@ -370,7 +370,7 @@ def show_data_collector():
                 "sentiment_feedback": sentiment_feedback,
                 "emotion_feedback": emotion_feedback
             }
-            st.error("Feedback submission is disabled in debug logging mode.")
+            st.error("Submission is disabled in debug logging mode.")
             # try:
             #     from supabase import create_client, Client
             #     from dotenv import load_dotenv

imports.py

@@ -4,7 +4,9 @@ import sys
 sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), )))
 
 import streamlit as st
-from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModel, DebertaV2Tokenizer, DebertaV2ForSequenceClassification
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, AutoModel, AutoModelForSeq2SeqLM, DebertaV2Tokenizer, DebertaV2ForSequenceClassification, DebertaV2Model
+from transformers import pipeline
+
 # import torch
 import numpy as np
 import matplotlib.pyplot as plt

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "tachygraphy-microtext-analysis-and-normalization"
-version = "2025.03.25.post1"
+version = "2025.03.26.post1"
 description = ""
 authors = [
     { name = "Archisman Karmakar", email = "[email protected]" },

pyprojectOLD.toml

@@ -1,6 +1,7 @@
 [project]
 name = "tachygraphy-microtext-analysis-and-normalization"
-version = "2025.03.24.post1"
+version = "2025.03.25.post1"
+# version = "2025.03.24.post1"
 # version = "2025.03.22.post1"
 # version = "2025.03.21.post1"
 # version = "2025.03.18.post5"

stacked_stacking_stages/stacking_stages.py

@@ -347,9 +347,9 @@ def get_sentiment_emotion_graph_code(input_text, normalized_text, sentiment_arra
                 penwidth_map[label] = 5
     else:
         # For three distinct probabilities, assign 1 to the smallest, 3 to the middle, 5 to the largest.
-        penwidth_map[sentiment_sorted[0][0]] = 1
-        penwidth_map[sentiment_sorted[1][0]] = 3
-        penwidth_map[sentiment_sorted[2][0]] = 5
+        penwidth_map[sentiment_sorted[0][0]] = 0.2
+        penwidth_map[sentiment_sorted[1][0]] = 0.3
+        penwidth_map[sentiment_sorted[2][0]] = 1
 
     # Build the basic Graphviz structure
     graph_code = f'''
@@ -358,9 +358,9 @@ def get_sentiment_emotion_graph_code(input_text, normalized_text, sentiment_arra
         node [shape=box, style="rounded,filled", fontname="Helvetica", fontsize=12];
         
         Input [label="Input Text:\\n{input_text.replace('"', '\\"')}", fillcolor="#ffe6de", fontcolor="#000000"];
-        Normalized [label="Normalized Text:\\n{normalized_text.replace('"', '\\"')}", fillcolor="#ffe6de", fontcolor="#000000"];
-        Sentiment [label="Sentiment"];
-        Emotion [label="Emotion"];
+        Normalized [label="Normalized Text:\\n{normalized_text.replace('"', '\\"')}", fillcolor="#f8ffde", fontcolor="#000000"];
+        Sentiment [label="Sentiment", fillcolor="#ffefde", fontcolor="black"];
+        Emotion [label="Emotion", fillcolor="#ffefde", fontcolor="black"];
         
         Input -> Normalized;
         Input -> Sentiment;
@@ -370,7 +370,7 @@ def get_sentiment_emotion_graph_code(input_text, normalized_text, sentiment_arra
     # Add sentiment nodes (displaying full values without truncation)
     for label, prob in sentiment_pairs:
         node_id = f"S_{label}"
-        graph_code += f'\n    {node_id} [label="{label}: {prob}", fillcolor="#ecdeff", fontcolor="black"];'
+        graph_code += f'\n    {node_id} [label="{label}: {prob}", fillcolor="#f6edfc", fontcolor="black"];'
         graph_code += f'\n    Sentiment -> {node_id};'
     
     # Add emotion nodes (displaying full values)
@@ -378,7 +378,7 @@ def get_sentiment_emotion_graph_code(input_text, normalized_text, sentiment_arra
         if i < len(emotion_flat):
             prob = emotion_flat[i]
             node_id = f"E_{label}"
-            graph_code += f'\n    {node_id} [label="{label}: {prob}", fillcolor="#deffe1", fontcolor="black"];'
+            graph_code += f'\n    {node_id} [label="{label}: {prob}", fillcolor="#edfcef", fontcolor="black"];'
             graph_code += f'\n    Emotion -> {node_id};'
     
     # Add arrows from each sentiment node to the Emotion node with fixed penwidth based on ranking
@@ -605,7 +605,7 @@ def show_stacking_stages():
 
     # Text input with change detection
     user_input = st.text_input(
-        "Enter text for emotions mood-tag analysis:", key="user_input_stage3", on_change=on_text_change
+        "Enter text for all in one inference:", key="user_input_stage3", on_change=on_text_change
     )
 
     if st.session_state.get("last_processed_input", "") != user_input:

transformation_and_Normalization/transformationNormalization_main.py

@@ -351,7 +351,7 @@ def transform_and_normalize():
 
     # Text input with change detection
     user_input = st.text_input(
-        "Enter text for emotions mood-tag analysis:", key="user_input_stage3", on_change=on_text_change
+        "Enter text for normalization:", key="user_input_stage3", on_change=on_text_change
     )
 
     if st.session_state.get("last_processed_input", "") != user_input: