Create app.py

app.py

@@ -0,0 +1,85 @@
+# Import libraries
+import os
+import uuid
+import pandas as pd
+import numpy as np
+from scipy.special import softmax
+import gradio as gr
+
+from google.colab import drive
+from datasets import load_dataset
+from sklearn.model_selection import train_test_split
+import torch
+from transformers import AutoTokenizer
+from transformers import AutoConfig
+from transformers import AutoModelForSequenceClassification
+from transformers import TFAutoModelForSequenceClassification
+from transformers import IntervalStrategy
+from transformers import TrainingArguments
+from transformers import EarlyStoppingCallback
+from transformers import pipeline
+from transformers import TrainingArguments
+from transformers import Trainer
+from torch import nn
+from transformers import RobertaTokenizer, RobertaForSequenceClassification
+
+
+
+# Define the model path where the pre-trained model is saved on the Hugging Face model hub
+model_path = "slickdata/finetuned-Sentiment-classfication-ROBERTA-model"
+
+# Initialize the tokenizer for the pre-trained model
+tokenizer = RobertaTokenizer.from_pretrained('roberta-base')
+
+# Load the configuration for the pre-trained model
+config = AutoConfig.from_pretrained(model_path)
+
+# Load the pre-trained model
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+# Define a function to preprocess the text data
+def preprocess(text):
+    new_text = []
+    # Replace user mentions with '@user'
+    for t in text.split(" "):
+        t = '@user' if t.startswith('@') and len(t) > 1 else t
+        # Replace links with 'http'
+        t = 'http' if t.startswith('http') else t
+        new_text.append(t)
+    # Join the preprocessed text
+    return " ".join(new_text)
+
+# Define a function to perform sentiment analysis on the input text
+def sentiment_analysis(text):
+    # Preprocess the input text
+    text = preprocess(text)
+
+    # Tokenize the input text using the pre-trained tokenizer
+    encoded_input = tokenizer(text, return_tensors='pt')
+
+    # Feed the tokenized input to the pre-trained model and obtain output
+    output = model(**encoded_input)
+
+    # Obtain the prediction scores for the output
+    scores_ = output[0][0].detach().numpy()
+
+    # Apply softmax activation function to obtain probability distribution over the labels
+    scores_ = softmax(scores_)
+
+    # Format the output dictionary with the predicted scores
+    labels = ['Negative', 'Neutral', 'Positive']
+    scores = {l:float(s) for (l,s) in zip(labels, scores_) }
+
+    # Return the scores
+    return scores
+
+# Define a Gradio interface to interact with the model
+demo = gr.Interface(
+    fn=sentiment_analysis, # Function to perform sentiment analysis
+    inputs=gr.Textbox(placeholder="Write your tweet here..."), # Text input field
+    outputs="label", # Output type (here, we only display the label with the highest score)
+    interpretation="default", # Interpretation mode
+    examples=[["This is wonderful!"]]) # Example input(s) to display on the interface
+
+# Launch the Gradio interface
+demo.launch(share=True, debug=True)