Upload 5 files

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+import pickle
+import docx
+import PyPDF2
+import re
+
+# Load pre-trained model and TF-IDF vectorizer
+svc_model = pickle.load(open('clf.pkl', 'rb'))  # Update with your model path
+tfidf = pickle.load(open('tfidf.pkl', 'rb'))  # Update with your vectorizer path
+le = pickle.load(open('encoder.pkl', 'rb'))  # Update with your encoder path
+
+# Function to clean resume text
+def clean_resume(txt):
+    clean_text = re.sub('http\S+\s', ' ', txt)
+    clean_text = re.sub('RT|cc', ' ', clean_text)
+    clean_text = re.sub('#\S+\s', ' ', clean_text)
+    clean_text = re.sub('@\S+', '  ', clean_text)
+    clean_text = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\\]^_`{|}~"""), ' ', clean_text)
+    clean_text = re.sub(r'[^\x00-\x7f]', ' ', clean_text)
+    clean_text = re.sub('\s+', ' ', clean_text)
+    return clean_text
+
+# Function to extract text from PDF
+def extract_text_from_pdf(file):
+    pdf_reader = PyPDF2.PdfReader(file)
+    text = ''
+    for page in pdf_reader.pages:
+        text += page.extract_text()
+    return text
+
+# Function to extract text from DOCX
+def extract_text_from_docx(file):
+    doc = docx.Document(file)
+    text = ''
+    for paragraph in doc.paragraphs:
+        text += paragraph.text + '\n'
+    return text
+
+# Function to extract text from TXT
+def extract_text_from_txt(file):
+    try:
+        text = file.read().decode('utf-8')
+    except UnicodeDecodeError:
+        text = file.read().decode('latin-1')
+    return text
+
+# Function to handle file upload and extraction
+def handle_file_upload(uploaded_file):
+    file_extension = uploaded_file.name.split('.')[-1].lower()
+    if file_extension == 'pdf':
+        text = extract_text_from_pdf(uploaded_file)
+    elif file_extension == 'docx':
+        text = extract_text_from_docx(uploaded_file)
+    elif file_extension == 'txt':
+        text = extract_text_from_txt(uploaded_file)
+    else:
+        raise ValueError("Unsupported file type. Please upload a PDF, DOCX, or TXT file.")
+    return text
+
+# Function to predict the category of a resume
+def predict_category(file):
+    try:
+        resume_text = handle_file_upload(file)
+        cleaned_text = clean_resume(resume_text)
+        vectorized_text = tfidf.transform([cleaned_text])
+        vectorized_text = vectorized_text.toarray()
+        predicted_category = svc_model.predict(vectorized_text)
+        predicted_category_name = le.inverse_transform(predicted_category)
+        return f"Predicted Category: {predicted_category_name[0]}"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+# Define Gradio interface
+inputs = gr.File(label="Upload Resume (PDF, DOCX, TXT)")
+outputs = gr.Textbox(label="Prediction")
+
+interface = gr.Interface(fn=predict_category, inputs=inputs, outputs=outputs, title="Resume Classifier",
+                         description="Upload your resume to predict its job category using an AI model.")
+
+# Launch the interface
+if __name__ == "__main__":
+    interface.launch()

clf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49b82e1edfab39d145c10403c1b05fbdbac8535b9597beaf925af7d405f59db1
+size 236270022

encoder.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fdd7cd3001ca6d1137cec3b41f8d385546de4fb01541feb147d9cb68eeac9e3
+size 632

tfidf.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8b9aee87992110d9a0d61f58b191d8681a69c32b9450ace117728a88aef3571
+size 213493