10 Mistakes to avoid as a Data Science Fresher

These are the Mistakes that I generally did and learned from that.

1. Undermining the Power of Statistics and Probability.
2. Ignoring the Outliers and Missing Values or Using a general method to treat them. they have a strong pattern hidden inside them, so do not take them lightly.
3. It is more Important to make our Data better instead of using fancy models. because if data is poor, the results will be
   worse.
4. Label Encoding for Cyclic Features, can kill up the patterns hidden in the data.
5. Not Experimenting up with the data, and directly using a general solution for all types of problems.
6. Using the Same algorithm for all the Data sets, for ex Random Forest mainly. No Doubt It works very well but, It is important to check other models as well.
7. Relying upon Mean Squared Error for Regression and Accuracy for Classification is again a big mistake, there are so many different kind of problems which require different performance metrics.
8. Not focusing on Programming or Problem Solving, It is very important to constantly practice Problem Solving.
9. Solely Relying on the Performance Metrics.
10. Using Algorithms without knowing them.
    
    
    Credit - Roshan Sharma.