primary recommendation system done

algo/recommendation.py

 from pymongo import MongoClient
 import pandas as pd
-#import ast
+import ast
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
-#import seaborn as sns
+import seaborn as sns
 import numpy as np
 import matplotlib.pyplot as plt
 
@@ -16,9 +16,8 @@ def dbToDf():
     client = MongoClient("mongodb://group3:GJF6cQqM4RLxBfNb@cs2022.lmichelin.fr:27017/group3?ssl=true")
     db = client.group3
     collection = db.movies_populated
-    cursor = collection.find()
+    cursor = collection.find({},{"_id":1, "original_title": 1, "genre": 1, "id":1, "overview":1, "popularity":1, "vote_count":1, "release_date":1, "cast": {"name":1, "order":1}})
     df=pd.DataFrame(list(cursor))
-
     return df
 
 def preFiltering(df,percent=15):
@@ -49,7 +48,7 @@ def similarity(df):
     '''
     tf_idf = TfidfVectorizer(stop_words='english')
     tf_idf_matrix = tf_idf.fit_transform(df['overview']);
-    
+    print(tf_idf_matrix)
     # calculating cosine similarity between movies
     cosine_similarity_matrix = cosine_similarity(tf_idf_matrix, tf_idf_matrix)
 
@@ -83,7 +82,6 @@ def recommendations_on_overview( original_title, df, number_of_recommendations):
 
     #calculates similarity scores of all movies
     calculated_sim = similarity(df)
-
     similarity_scores = list(enumerate(calculated_sim[index]))
     
     similarity_scores_sorted = sorted(similarity_scores, key=lambda x: x[1], reverse=True)
@@ -94,4 +92,4 @@ def recommendations_on_overview( original_title, df, number_of_recommendations):
 
 df = dbToDf()
 
-print(recommendations_on_overview( 'Batman', df, 9))
+print(recommendations_on_overview('Avatar', df, 9))
\ No newline at end of file