This Case Study is based on a Kaggle dataset - https://www.kaggle.com/c/mercari-price-suggestion-challenge
Here is the detailed blog - https://towardsdatascience.com/mercari-price-recommendation-for-online-retail-sellers-979c4d07f45c
Contents of the Code Files are given below :-
Code File | Description |
---|---|
kaggle_sub.py | Executable .py file for kaggle submission |
final(colab).ipynb | Function 1 - takes input X, returns prediction Y |
final(colab).ipynb | Function 2 - takes input (X,Y), returns evaluation metric (RMSLE) |
All Experimentation and Models are in .ipynb files. Table of Contents and sections in .ipynb files as below :-
S.No: | Section | Notebook(.ipynb) |
---|---|---|
1. | Business Problem | 1_eda.ipynb |
2. | Exploratory Data Analysis | 1_eda.ipynb |
3. | Data Processing | 2_process.ipynb |
4. | Feature Engineering | 2_process.ipynb |
5. | Correlation heatmap | 2_process.ipynb |
6. | Final Data Preparation | 3_baseline_machine_learning_models.ipynb |
7. | Evaluation Metiric | 3_baseline_machine_learning_models.ipynb |
8. | Baseline Ridge Model | 3_baseline_machine_learning_models.ipynb |
9. | Baseline LGBM Model | 3_baseline_machine_learning_models.ipynb |
10. | Baseline Ensemble Model | 3_baseline_machine_learning_models.ipynb |
11. | Baseline LSTM (Colab) | 4_baseline_lstm(colab).ipynb |
12. | Baseline MLP (Colab) | 5_baseline_mlp(colab).ipynb |
13. | Final Models | 6_final_models.ipynb |
14. | Final Summary | 6_final_models.ipynb |