Chnages

Resume_Screening.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:708b72cc94a0f506e7caccabf87d57e389f002518539ee5d47815d8d9b9767b3
+size 27504290

Word_Vec_Resume.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac33f24793786403e4bce07b891d5bf48b5eb61b6e1c9ef08f2f18e9d23617a7
+size 135853

app.py

@@ -1,7 +1,45 @@
 import gradio as gr
+import fitz
+import os
+import re
+from joblib import load
+from sklearn.feature_extraction.text import TfidfVectorizer
 
-def greet(name):
-    return "Hello " + name + "!!"
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+def extract_text_from_pdf(file_path):
+    text = ""
+    doc = fitz.open(file_path)
+    for page in doc:
+        text += page.get_text()
+    return text
+
+def preprocess_text(text):
+    resumeText = re.sub('https\+S\s*','',text) 
+    resumeText = re.sub('RT|cc','',resumeText)
+    resumeText = re.sub('#\S+','',resumeText)
+    resumeText = re.sub('@\+S','',resumeText)
+    resumeText = re.sub('[%s]' % re.escape("""!"#$%&'()*+,-./:;<=>?@[\]^_`{|}~"""), ' ', resumeText)
+    resumeText = re.sub(r'[^\x00-\x7f]',r' ', resumeText) 
+    resumeText = re.sub('\s+', ' ', resumeText)
+    return resumeText
+
+def load_model():
+    model = load('Resume_Screening.joblib') 
+    return model
+
+vectorizer=load('Word_Vec_Resume.joblib')
+def predict(file_path):
+    text = extract_text_from_pdf(file_path)
+    text = preprocess_text(text)
+    text_vectorized = vectorizer.transform([text])
+    model = load_model()
+    result = model.predict(text_vectorized)
+    return result[0]
+
+iface = gr.Interface(
+    fn=predict,
+    inputs="file",
+    outputs="text"  
+)
+
 iface.launch()

reuirements.txt

@@ -0,0 +1,5 @@
+joblib
+gradio
+os
+re
+sci-kit-learn