AAUT1IA
Earlier this week we reviewed everything that has been done in preprocessing.
After this analysis we made the following exports to CSV:
- X_unprocessed (csv with general columns before the alterations)
- y_unprocessed (csv with column of hits before the alterations)
- X_train_selected (shows general columns for training)
- y_train (shows column of hits for training)
- X_test_selected (shows general columns for testing)
- y_test (shows column of hits for testing)
Concluding the export we also closed the algorithms that will be used, such as:
- Logistic Regression
- Decision Tree
- Support Vector Machine (Linear Kernel)
- Support Vector Machine (RBF Kernel)
- Support Vector Machine (Polynomial Kernel)
- Neural Network
- Random Forest
PLNTDIA
We’ve been organizing ideas of what algorithms to use to get to the desired solution. We chose to use Topsis, however, we were not able to achieve everything we wanted using it, so we decided to include the KNN model. The KNN at the beginning will tell which songs are most similar to the music passed by the user, then Topsis will analyze the likeness of songs and whether it is hit or not and orders them in the best way.