Update job_recommendation_inference.py

job_recommendation_inference.py

@@ -2,52 +2,45 @@ import numpy as np
 import pandas as pd
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
-
-# Load data
+import json
 
 def recommend_jobs_for_input_skills(input_hard_skills, input_soft_skills, input_major, companies, tfidf_vectorizer_skills, tfidf_vectorizer_majors, companies_skills_vec, companies_majors_vec):
     input_hard_skills_vec = tfidf_vectorizer_skills.transform([input_hard_skills])
     input_soft_skills_vec = tfidf_vectorizer_skills.transform([input_soft_skills])
     input_major_vec = tfidf_vectorizer_majors.transform([input_major])
 
-    # Average the vectorized hard and soft skills
     input_skills_vec = (input_hard_skills_vec + input_soft_skills_vec) / 2
 
-    # Compute similarities
     skills_similarity = cosine_similarity(input_skills_vec, companies_skills_vec)
     major_similarity = cosine_similarity(input_major_vec, companies_majors_vec)
 
-    # Ensure the number of companies in both similarities is aligned
     if skills_similarity.shape[1] != major_similarity.shape[1]:
         min_dim = min(skills_similarity.shape[1], major_similarity.shape[1])
         skills_similarity = skills_similarity[:, :min_dim]
         major_similarity = major_similarity[:, :min_dim]
 
-    # Combine similarities
     combined_similarity = (skills_similarity + major_similarity) / 2
 
-    # Get top 3 job recommendations
     sorted_company_indices = np.argsort(-combined_similarity[0])
     recommended_companies = companies.iloc[sorted_company_indices]['Major'].values[:3]
 
     return recommended_companies
 
-# Example usage if run as a script
-if __name__ == "__main__":
-    # Load necessary data (you may need to adjust paths based on your actual data location)
-    users_data = "1st_train.csv"
+def handler(event, context):
+    input_data = json.loads(event['body'])
+    input_hard_skills = input_data["input_hard_skills"]
+    input_soft_skills = input_data["input_soft_skills"]
+    input_major = input_data["input_major"]
+
+    users_data = "/path/to/your/1st_train.csv"
     applicants = pd.read_csv(users_data)
 
-    jobs_data = "jobs_data.csv"
+    jobs_data = "/path/to/your/jobs_data.csv"
     companies = pd.read_csv(jobs_data)
 
-    # Preprocess data as needed
-
-    # Vectorize skills and majors
     tfidf_vectorizer_skills = TfidfVectorizer()
     tfidf_vectorizer_majors = TfidfVectorizer()
 
-    # Fit vectorizers on all skills and majors
     all_skills = pd.concat([applicants['final_hard_skill'], applicants['final_soft_skill'],
                             companies['final_hard_skill'], companies['final_soft_skill']])
     all_majors = pd.concat([applicants['candidate_field'], companies['Major']])
@@ -55,21 +48,18 @@ if __name__ == "__main__":
     all_skills_vectorized = tfidf_vectorizer_skills.fit_transform(all_skills)
     all_majors_vectorized = tfidf_vectorizer_majors.fit_transform(all_majors)
 
-    # Split the TF-IDF vectors back into applicants and companies
     num_applicants = len(applicants)
     num_companies = len(companies)
 
-    applicants_skills_vectorized = all_skills_vectorized[:num_applicants*2]  # because each applicant has 2 skill entries
+    applicants_skills_vectorized = all_skills_vectorized[:num_applicants*2]
     companies_skills_vectorized = all_skills_vectorized[num_applicants*2:]
 
     applicants_majors_vectorized = all_majors_vectorized[:num_applicants]
     companies_majors_vectorized = all_majors_vectorized[num_applicants:]
 
-    # Example input
-    input_hard_skills = "Business, Finance, Excel"
-    input_soft_skills = "Communication, Teamwork"
-    input_major = "Marketing"
-
     recommended_jobs = recommend_jobs_for_input_skills(input_hard_skills, input_soft_skills, input_major, companies, tfidf_vectorizer_skills, tfidf_vectorizer_majors, companies_skills_vectorized, companies_majors_vectorized)
-    print("Recommended Jobs based on input skills and major:")
-    print(recommended_jobs)
+
+    return {
+        'statusCode': 200,
+        'body': json.dumps(recommended_jobs.tolist())
+    }