version 2

app.py

@@ -1,32 +1,58 @@
 import gradio as gr
-import onnxruntime
 import numpy as np
 import pickle
-threshold = 0.5
-onnx_session = onnxruntime.InferenceSession("bert.onnx")
+
+
+
+import nltk
+from nltk.corpus import stopwords
+from nltk.tokenize import word_tokenize
+from nltk.stem import WordNetLemmatizer
+from sklearn.feature_extraction.text import CountVectorizer
+
+# Initialize NLTK resources (download if needed)
+nltk.download('punkt')
+nltk.download('wordnet')
+nltk.download('stopwords')
+
+# Text preprocessing functions
+
+def preprocess_text(text):
+    # Tokenization
+    words = word_tokenize(text.lower())  # Convert to lowercase and tokenize
+    
+    # Remove stopwords
+    stop_words = set(stopwords.words('english'))
+    words = [word for word in words if word not in stop_words]
+    
+    # Lemmatization
+    lemmatizer = WordNetLemmatizer()
+    words = [lemmatizer.lemmatize(word) for word in words]
+    
+    return ' '.join(words)
+
+
+
+
+
+def predict_tags(text):
+    return mlb[np.where(model.predict(vectorizer.transform([preprocess_text(text)])).flatten() == 1)]
+
+
+
 
 # Load the instance back
 with open('classes.pkl', 'rb') as file:
     mlb = pickle.load(file)
 
-with open('tokenizer.pkl', 'rb') as file:
-    tokenizer = pickle.load(file)
+with open('vectorizer.pkl', 'rb') as file:
+    vectorizer = pickle.load(file)
 
+with open('model.pkl', 'rb') as file:
+    model = pickle.load(file)
 
-# Create a function to predict tags using the ONNX model
-def predict_tags_onnx(text):
-    encoded_text = tokenizer(text , padding=True, truncation=True, return_tensors='pt')
-    input_ids = encoded_text["input_ids"].numpy()
-    attention_mask = encoded_text["attention_mask"].numpy()
-
-    # Run the ONNX model
-    outputs = np.asarray(onnx_session.run(None, {"input_ids": input_ids , "attention_mask":attention_mask}))
 
-    # Post-process the outputs as needed
-    #predicted_labels = torch.sigmoid(outputs).cpu().numpy()
-    predicted_tags = mlb.classes_[np.where(np.squeeze((outputs > threshold).astype(int)).flatten() == 1)]
-
-    return predicted_tags
+# Create a function to predict tags using the ONNX model
 
-iface = gr.Interface(fn=predict_tags_onnx, inputs="text", outputs="text")
+iface = gr.Interface(fn=predict_tags, inputs="text", outputs="text")
 iface.launch()

classes.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:203390ce8d1e08f4ce6f73a1216738464c89d23caec7ec32e122936a26a90412
-size 922
+oid sha256:12ef1b82b64966b26fc03ac0f6567a673ef8751474b032c8d262b9a544925633
+size 3192

model.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c98ccde9742b241457b261f8fbe2e4d190f5ef011a9fa80c5a3dfb99adda165
+size 22233200

requirements.txt

@@ -1,4 +1,3 @@
-onnxruntime==1.15.1
-torch==2.0.1
 scikit-learn==1.2.2
-transformers==4.21.2
+nltk==3.8.1
+

vectorizer.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ea212d9f95d5829baabf000004a6a425cf834cfc0bb566e37dd58a211b89da
+size 6554145