How to enter a Kaggle community competition
and improve your machine learning skills
What you will learn
Learners will learn what Kaggle, the data science website is.
Learners will learn about machine learning.
Learners will be able to enter a Kaggle community competition.
Learners will be able to make predictions on a supervised learning dataset.
Learners will be able to submit their predictions to Kaggle for scoring.
Why take this course?
In this course the learner will be educated in machine learning by going into the Kaggle website's community competitions and joining a tabular community competition. The competition that has been selected for this course is the TAMS AIS Winter 2022 competition, which is a regression problem.
the student will learn how to enter a competition and follow the machine learning process from beginning to end, to include the following steps:-
1. Define the problem statement.
2. Import libraries used in the program.
3. Load csv files used in the program.
4. Use pandas to read the csv files and concert them to dataframes.
5. Check the train and test dataframes for null values.
6. Define the target variable and use seaborn to analyse it.
7. Drop the label from the train dataframe.
8. Define the dataframe, combi, which is the test dataframe appended to the train dataframe.
9. Check the combi dataframe for the number of unique values.
10. Drop any unnecessary features from combi.
11. Create a heatmap of combi.
12. Normalise combi.
13. Define the dependent and independent variables.
14. Split the X and y variables into training and validation sets.
15. Select the model: in this instance it will be linear regression.
16. Make predictions on the validation and test set.
17. Measure model performance by calculating the error.
18. Compare actual values against predicted values and plot on a graph.
19. Prepare submission and submit to Kaggle for scoring.
Screenshots
Charts
Price
Rating
Enrollment distribution
