Upload 2 files

app.py

@@ -0,0 +1,61 @@
+import re
+import nltk
+import pickle
+import string
+import numpy as np
+import gradio as gr
+
+from nltk.corpus import stopwords
+from keras.models import load_model
+from keras.preprocessing.sequence import pad_sequences
+
+nltk.download('stopwords')
+
+# Load Model and Tokenizer
+model = load_model("sentiment_analysis_best.keras")
+
+with open("tokenizer.pkl", "rb") as f:
+    tokenizer = pickle.load(f)
+
+MAX_LEN = 100
+
+negations = {"not", "no", "nor", "never", "n't"}
+stop_words = set(stopwords.words("english")) - negations
+
+# Preprocessing Function
+def preprocess(text):
+    text = text.lower()
+    text = re.sub(r"\d+", "", text)
+    text = text.translate(str.maketrans('', '', string.punctuation))
+    words = [w for w in text.split() if w not in stop_words]
+    return " ".join(words)
+
+# Prediction Function
+def predict_sentiment(text):
+    text = preprocess(text)
+    seq = tokenizer.texts_to_sequences([text])
+    pad = pad_sequences(seq, maxlen=MAX_LEN, padding='post')
+    pred = model.predict(pad)
+
+    label_idx = np.argmax(pred, axis=1)[0]
+    confidence = pred[0][label_idx] * 100
+
+    labels = ["Negative", "Positive", "Neutral"]
+
+    return f"{labels[label_idx]} {confidence:.2f}%"
+
+# Gradio  Interface
+interface = gr.Interface(
+    fn=predict_sentiment,
+    inputs=gr.Textbox(lines=3, placeholder="Type your sentence here..."),
+    outputs=gr.Textbox(label="Prediction"),
+    title="Sentiment Analysis System",
+    description="Outputs sentiment analysis along with model confidence.",
+    examples=[
+        ["I really love this product"],
+        ["This is the worst experience ever"],
+        ["It is okay, not good not bad"]
+    ]
+)
+
+interface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+numpy
+nltk
+tensorflow
+keras
+gradio