Create inference.py

inference.py

@@ -0,0 +1,58 @@
+import pickle
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+from typing import List, Dict
+
+# Function to load model components
+def load_model_components(model_path):
+    with open(model_path, 'rb') as f:
+        model_components = pickle.load(f)
+    return model_components
+
+# Function to recommend jobs based on input skills and major
+def recommend_jobs_for_input_skills(input_hard_skills: str, input_soft_skills: str, input_major: str,
+                                    jobs_data: pd.DataFrame, model_path: str) -> List[str]:
+    # Load saved model components
+    tfidf_vectorizer_skills, tfidf_vectorizer_majors, companies_skills_vec, companies_majors_vec = load_model_components(model_path)
+
+    # Vectorize input skills and major
+    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_jobs = jobs_data.iloc[sorted_company_indices]['Major'].values[:3]
+
+    return recommended_jobs.tolist()
+
+# Example usage for testing
+if __name__ == "__main__":
+    input_hard_skills = "Python, Java, Finance, Excel"
+    input_soft_skills = "Communication, Teamwork"
+    input_major = "Computer Science"
+
+    jobs_data = pd.read_csv("jobs_data.csv")
+    model_path = "recommendation_model.pkl"
+
+    recommended_jobs = recommend_jobs_for_input_skills(input_hard_skills, input_soft_skills, input_major, jobs_data, model_path)
+    print("Recommended Jobs based on input skills and major:")
+    print(recommended_jobs)