Upload 11 files

app.py

@@ -0,0 +1,45 @@
+# -*- coding: utf-8 -*-
+"""
+Created on Fri Apr 19 16:58:55 2024
+
+@author: phonoDS
+"""
+
+import streamlit as st
+from transformers import AutoTokenizer, AutoModelForSequenceClassification, pipeline
+import tensorflow as tf
+tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)
+
+# Load pre-trained model and tokenizer
+saved_directory = "C:/Users/phonoDS/FineTuned_Roberta_Sentiment_Analysis"
+tokenizer = AutoTokenizer.from_pretrained(saved_directory)
+model = AutoModelForSequenceClassification.from_pretrained(saved_directory)
+nlp = pipeline("sentiment-analysis", model=model, tokenizer=tokenizer)
+
+# Define function to analyze sentiment
+def analyze_sentiment(text):
+    result = nlp(text)
+    return result[0]['label'], result[0]['score']
+
+# Streamlit UI
+st.set_page_config(page_title="Sentiment Analysis", layout="wide")
+col1, col2 = st.columns([6, 1])  # Divide the screen into two columns
+
+with col2:  # Right-aligned column for the logo
+    st.image("C:/Users/phonoDS/Downloads/oryx_logo.png", width=200, use_column_width=False)  # Provide the path to your company logo
+
+with col1:  # Main content area
+    st.title("Sentiment Analysis Prototype Tool by orYx Models")
+    user_input = st.text_area("Enter text to analyze:", height=200)
+    
+    submit_button = st.button("Analyze:")
+
+    if submit_button and user_input:
+        sentiment, score = analyze_sentiment(user_input)
+        st.markdown("Sentiment Analysis Result:")
+        st.write(f"Sentiment:  {sentiment}")
+        st.write(f"Confidence:  {score*100:.2f}%")
+    
+    # Text titles below the text box
+    st.markdown("This sentiment analysis model serves as a testing prototype, specifically developed for LDS to assess the variability and precision of OrYx Models' sentiment analysis tool.")
+    st.markdown("All feedback gathered from LDS, including both structured and unstructured data, will be incorporated into the model to enhance its domain specificity and maximize accuracy.")

config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "cardiffnlp/twitter-roberta-base-sentiment-latest",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "Negative",
+    "1": "Neutral",
+    "2": "Positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "Negative": 0,
+    "Neutral": 1,
+    "Positive": 2
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9da21d807887f79bb60459d235858ea7e7b071a00bdddf9ad1181066c7d9da5e
+size 498615900

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+transformers>=4.10.3
+pytorch-accelerated>=0.2.0

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd86fc62056e79d68962e3c60129b318c8e83ca97cef2539515991940da43ea9
+size 4920