From a26b150a19baaaaaabe182409fcf6c3181a44591 Mon Sep 17 00:00:00 2001
From: jwradhe <jimmy@wradhe.com>
Date: Wed, 6 Nov 2024 22:58:36 +0100
Subject: [PATCH] Uppdatera README samt kommentar i trainmodel

---
 README.md     | 3 ++-
 trainmodel.py | 4 ++--
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/README.md b/README.md
index 6b1b38a..7a8c137 100644
--- a/README.md
+++ b/README.md
@@ -27,7 +27,8 @@ I will use a dataset from TMBD
 https://www.kaggle.com/datasets/asaniczka/full-tmdb-tv-shows-dataset-2023-150k-shows
 
 ### Model:
-I will use NearestNeighbors (NN) alhorithm together with K-NearestNeighbors alhorithm.
+I must first preprocess data with vectorization so that i can use it in NearestNeighbors (NN) alhorithm.
+I will use NearestNeighbors (NN) output as input to K-NearestNeighbors alhorithm.
 
 ### Features:
 1.  Load data from dataset and preprocessing.
diff --git a/trainmodel.py b/trainmodel.py
index 4e98ce5..667ee46 100644
--- a/trainmodel.py
+++ b/trainmodel.py
@@ -34,7 +34,7 @@ class TrainModel:
         # Preprocess title data
         preproccessed_data = self.preprocess_title_data()
 
-        # Train the NN model
+        # Train the NearestNeighbors model
         self.model.fit(preproccessed_data)
 
         stop = time.time()
@@ -51,7 +51,7 @@ class TrainModel:
         # Preprocess target data
         target_vector = self.preprocess_target_data(target_row)
 
-        # Get nearest neighbors
+        # Use NearestNeighbors model as input to K-nearest neighbors
         distances, indices = self.model.kneighbors(target_vector, n_neighbors=num_recommendations)
         recommendations = self.title_data.iloc[indices[0]].copy()
         recommendations['distance'] = distances[0]