Upload 6 files

Model/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "transformers_version": "4.45.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

Model/tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4077865c0fdbde540ae3a4c99f5495340564aae31e646f0a354f1988e66565c
+size 438223128

Tokenizer/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

Tokenizer/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

app.py

@@ -0,0 +1,118 @@
+import streamlit as st
+from transformers import TFBertForSequenceClassification, BertTokenizer
+import tensorflow as tf
+import numpy as np
+
+# Set layout to wide
+st.set_page_config(layout="wide")
+
+
+# Load the trained BERT model and tokenizer
+@st.cache(allow_output_mutation=True)
+def load_model():
+    model = TFBertForSequenceClassification.from_pretrained('C:/Users/Pranit/PycharmProjects/customer/Model')
+    tokenizer = BertTokenizer.from_pretrained('C:/Users/Pranit/PycharmProjects/customer/Tokenizer')
+    return model, tokenizer
+
+
+model, tokenizer = load_model()
+
+
+# Tokenize and encode the input text
+def encode_input(text, max_length=128):
+    encoded_input = tokenizer.encode_plus(
+        text,
+        add_special_tokens=True,
+        max_length=max_length,
+        padding='max_length',  # Updated for compatibility with TensorFlow
+        return_attention_mask=True,
+        return_tensors='tf'
+    )
+    return encoded_input['input_ids'], encoded_input['attention_mask']
+
+
+# Prediction function
+def predict_sentiment(text):
+    input_ids, attention_mask = encode_input(text)
+    prediction = model.predict([input_ids, attention_mask])[0]
+    pred_label = np.argmax(prediction, axis=1)
+    return pred_label[0], prediction[0]  # Return prediction scores
+
+
+# Apply custom CSS for enhanced UI
+st.markdown("""
+    <style>
+    /* Background color */
+    body {
+        background-color: #f0f2f6;
+    }
+    /* Header font color */
+    .stTitle {
+        color: #3A3F44;
+    }
+    /* Text area color and font */
+    .stTextArea {
+        background-color: #ffffff;
+        font-size: 18px;
+    }
+    /* Button color */
+    div.stButton > button {
+        background-color: #00A86B;
+        color: white;
+        border-radius: 8px;
+        padding: 10px;
+        font-weight: bold;
+    }
+    /* Custom results style */
+    .results {
+        font-size: 20px;
+        color: #007bff;
+        font-weight: bold;
+    }
+    /* Icon style */
+    .icon {
+        vertical-align: middle;
+        margin-right: 5px;
+    }
+    </style>
+""", unsafe_allow_html=True)
+
+# Streamlit App UI
+st.title("Sentiment Classifier with BERT")
+
+# Add icons from Font Awesome
+st.write("""
+    <div style='display: flex; align-items: center;'>
+        <img src='https://img.icons8.com/ios-filled/50/000000/sentiment-analysis.png' class='icon' />
+        <h3>Enter a sentence below and the model will predict whether it's Positive or Negative:</h3>
+    </div>
+""", unsafe_allow_html=True)
+
+# User input
+user_input = st.text_area("Enter Text:", "")
+
+if st.button("🧠 Classify Sentiment"):
+    if user_input:
+        pred_label, prediction_scores = predict_sentiment(user_input)
+        sentiment = "Positive" if pred_label == 1 else "Negative"
+
+        # Display results
+        st.markdown(f"<div class='results'>Predicted Sentiment: **{sentiment}**</div>", unsafe_allow_html=True)
+
+        # Visualizations
+        st.subheader("Text Analysis Results")
+        st.write(f"**Word Count:** {len(user_input.split())}")
+        st.write(f"**Character Count:** {len(user_input)}")
+
+        # Display prediction scores
+        st.write(f"**Positive Score:** {prediction_scores[1]:.2f}")
+        st.write(f"**Negative Score:** {prediction_scores[0]:.2f}")
+
+        # Visualize the sentiment scores
+        st.bar_chart(prediction_scores)
+
+    else:
+        st.write("Please enter text to classify.")
+
+st.write("---")
+st.write("BERT Model fine-tuned for Sentiment Classification")