Create app.py

app.py

@@ -0,0 +1,116 @@
+!pip install -q transformers datasets streamlit
+
+from transformers import AutoModelForSequenceClassification
+from transformers import TFAutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoConfig
+import numpy as np
+from scipy.special import softmax
+
+
+tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+
+model_path = f"avichr/heBERT_sentiment_analysis"
+config = AutoConfig.from_pretrained(model_path)
+model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+# Preprocess text (username and link placeholders)
+def preprocess(text):
+    new_text = []
+    for t in text.split(" "):
+        t = '@user' if t.startswith('@') and len(t) > 1 else t
+        t = 'http' if t.startswith('http') else t
+        new_text.append(t)
+    return " ".join(new_text)
+
+# Input preprocessing
+text = "Covid cases are increasing fast!"
+text = preprocess(text)
+
+# PyTorch-based models
+encoded_input = tokenizer(text, return_tensors='pt')
+output = model(**encoded_input)
+scores = output[0][0].detach().numpy()
+scores = softmax(scores)
+
+# TensorFlow-based models
+# model = TFAutoModelForSequenceClassification.from_pretrained(model_path)
+# model.save_pretrained(model_path)
+# text = "Covid cases are increasing fast!"
+# encoded_input = tokenizer(text, return_tensors='tf')
+# output = model(encoded_input)
+# scores = output[0][0].numpy()
+# scores = softmax(scores)
+
+config.id2label = {0: 'NEGATIVE', 1: 'NEUTRAL', 2: 'POSITIVE'}
+
+# Print labels and scores
+ranking = np.argsort(scores)
+ranking = ranking[::-1]
+print(f"Classified text: {text}")
+for i in range(scores.shape[0]):
+    l = config.id2label[ranking[i]]
+    s = scores[ranking[i]]
+    print(f"{i+1}) {l} {np.round(float(s), 4)}")
+
+from transformers import AutoModelForSequenceClassification
+from transformers import TFAutoModelForSequenceClassification
+from transformers import AutoTokenizer, AutoConfig
+from scipy.special import softmax
+import streamlit as st
+
+
+def preprocess(text):
+    new_text = []
+    for t in text.split(" "):
+        t = '@user' if t.startswith('@') and len(t) > 1 else t
+        t = 'http' if t.startswith('http') else t
+        new_text.append(t)
+    return " ".join(new_text)
+
+
+def sentiment_analysis(text):
+    text = preprocess(text)
+
+    # Load the model
+    model_path = f"avichr/heBERT_sentiment_analysis"
+    tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
+    config = AutoConfig.from_pretrained(model_path)
+    model = AutoModelForSequenceClassification.from_pretrained(model_path)
+
+    # Encode text input
+    encoded_input = tokenizer(text, return_tensors='pt')
+    output = model(**encoded_input)
+    scores_ = output[0][0].detach().numpy()
+
+    # Calculate softmax probabilities
+    scores_ = softmax(scores_)
+
+    # Format output dict of scores
+    labels = ['Negative', 'Neutral', 'Positive']
+    scores = {l:float(s) for (l,s) in zip(labels, scores_) }
+
+    return scores
+
+
+import streamlit as st
+
+st.title("Sentiment Analysis for Covid Feelings")
+
+# User input field
+text = st.text_input(label="Enter your text:")
+
+# Perform sentiment analysis
+if text:
+    scores = sentiment_analysis(text)
+
+    # Display sentiment scores
+    st.subheader("Sentiment Scores")
+    for label in scores:
+        score = scores[label]
+        st.write(f"{label}: {score:.2f}")
+
+
+
+
+
+st.run(.py)