Update app.py

app.py

@@ -6,9 +6,16 @@ import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sentence_transformers import SentenceTransformer
 import spacy
+import os
 
 # Load SpaCy model for Named Entity Recognition
-nlp = spacy.load("en_core_web_sm")  # You can also use a larger model for better accuracy
+try:
+    nlp = spacy.load("en_core_web_sm")
+except OSError:
+    os.system("python -m spacy download en_core_web_sm")
+    nlp = spacy.load("en_core_web_sm")
+
+# Load Sentence Transformer model
 sentence_model = SentenceTransformer('all-MiniLM-L6-v2')
 
 def extract_text_from_txt(txt_file):
@@ -22,7 +29,7 @@ def extract_text_from_pdf(pdf_file):
     reader = PyPDF2.PdfReader(pdf_file)
     text = ''
     for page in reader.pages:
-        text += page.extract_text()
+        text += page.extract_text() or ''  # Ensure we handle cases where extract_text() returns None
     return text
 
 def extract_years_of_experience(resume_text):
@@ -50,6 +57,12 @@ def evaluate_with_tfidf(resumes, required_skills):
     similarities = (tfidf_matrix[-1] * tfidf_matrix[:-1].T).toarray().flatten()
     return similarities
 
+def cosine_similarity(a, b):
+    """Calculate cosine similarity between two vectors."""
+    a = a / np.linalg.norm(a)
+    b = b / np.linalg.norm(b)
+    return np.dot(a, b)
+
 def analyze_resumes(resume_files, job_desc_file, required_skills, required_experience_years):
     """Analyzes resumes based on job description and required criteria."""
     # Read the job description
@@ -94,12 +107,6 @@ def analyze_resumes(resume_files, job_desc_file, required_skills, required_exper
 
     return results
 
-def cosine_similarity(a, b):
-    """Calculate cosine similarity between two vectors."""
-    a = a / np.linalg.norm(a)
-    b = b / np.linalg.norm(b)
-    return np.dot(a, b)
-
 # Gradio interface
 def build_app():
     with gr.Blocks() as app: