Algorithm Predictive Studio(APS)

APS is an Algorithm Predictive Studio. The app allows users to upload a dataset, select target variables and features, train various regression algorithms (Linear Regression, Decision Tree, Random Forest, Support Vector Machine, and k-Nearest Neighbors), and visualize evaluation metrics and predictions on new data.

Features

• Dataset Upload and Visualization
• Target Variable and Feature Selection
• Model Training
• Model Evaluation
• Provides code snippet for each selected algorithm
• Accurate Predictions

Limitations:

1. Algorithm Selection: APS is limited to Regression Algorithms only.
2. Dataset Type: APS is limited to CSV and Excel files only for now. More updates will be released with diversity across all types of datasets.
3. Limited Dataset Size: APS is designed to handle relatively small to medium-sized datasets (200MB). For large datasets with thousands of samples and numerous features, the app's performance might be compromised, leading to slower execution times and potential memory limitations.

Dependencies

• Streamlit
• sklearn.
• Pandas. Dependencies are all listed in the requirements.txt file.

Creator

Gideon Ogunbanjo.