diff --git a/ML/18_PCA/pca_exercise.md b/ML/18_PCA/pca_exercise.md
index 413d70e8..01fe69bf 100644
--- a/ML/18_PCA/pca_exercise.md
+++ b/ML/18_PCA/pca_exercise.md
@@ -1,4 +1,4 @@
-Download heart disease dataset heart.csv in Exercise folder and do following, (credits of dataset:  https://www.kaggle.com/fedesoriano/heart-failure-prediction)
+Download heart disease dataset heart.csv in [Exercise](https://github.com/codebasics/py/tree/master/ML/18_PCA/Exercise) folder and do following, (credits of dataset:  https://www.kaggle.com/fedesoriano/heart-failure-prediction)
 
 1. Load heart disease dataset in pandas dataframe
 1. Remove outliers using Z score. Usual guideline is to remove anything that has Z score > 3 formula or Z score < -3
@@ -8,7 +8,7 @@ Download heart disease dataset heart.csv in Exercise folder and do following, (c
 1. Now use PCA to reduce dimensions, retrain your model and see what impact it has on your model in terms of accuracy. Keep in mind that many times doing PCA reduces the accuracy but computation is much lighter and that's the trade off you need to consider while building models in real life
 
 
-[Solution Link]()
+[Solution Link](https://github.com/codebasics/py/blob/master/ML/18_PCA/Exercise/PCA_heart_disease_prediction_exercise_solution.ipynb)