Recommendations System - Course for +2 Students

 Recommendation System using pandas and Sklearn

Student Dataset1.csv

id,gender,stream,subject,marks,course,specialization
1,m,science,physics,78,btech,civil
2,f,commerce,maths,56,bsc,maths
3,m,humanities,history,79,ba,history
4,f,commerce,economics,88,bcom,hons
5,m,science,chemistry,79,bsc,biology
6,m,science,maths,98,btech,mech
7,f,commerce,physics,56,bsc,maths
8,m,humanities,history,79,ba,history
9,f,commerce,commerce,76,bcom,hons
10,m,science,physics,89,bsc,biology

Code snippet (Thanks to  Siddharth Sachdeva — August 25, 2021, Analytics Vidya)

#S1 importing necessary libraries.
import pandas as pd
data = pd.read_csv(r"dataset1.csv")
#s2
descriptions =data['gender'] +' '+ data['subject'] + ' ' + data['stream'] +' '+ data['marks'].apply(str)
#Printing the first description
print(descriptions[0])
# s3 similarity matrix
#import sklearn.TfidfVector
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.metrics.pairwise import linear_kernel
def create_similarity_matrix(new_description, overall_descriptions):
        overall_descriptions.append(new_description)
        # Define a tfidf [Term Frequency Inverse document frequency]  vectorizer and remove all stopwords.
        tfidf = TfidfVectorizer(stop_words="english")
        tfidf_matrix = tfidf.fit_transform(overall_descriptions)
        tfidf_matrix.shape
        cosine_sim = linear_kernel(tfidf_matrix,tfidf_matrix)
        return cosine_sim
#s5 Sim Matrix reco
def get_recommendations(new_description,overall_descriptions):

        cosine_sim = create_similarity_matrix(new_description,overall_descriptions)
        sim_scores = list(enumerate(cosine_sim[-1]))
        sim_scores = sorted(sim_scores,key =lambda x:x[1],reverse= True )
        sim_scores = sim_scores[1:10]
        indices = [i[0]for i in sim_scores]
        return data.iloc[indices]
# s6 Recommendations
new_description = pd.Series('m physics science 78')
recommendation= get_recommendations(new_description,descriptions)
print(recommendation[0:3])
"""
   id gender    stream    subject  marks course specialization
0   1      m   science    physics     78  btech          civil
6   7      f  commerce    physics     56    bsc          maths
4   5      m   science  chemistry     79    bsc        biology
"""

Simple not refined. But throw some light on basics of Recommendation System.