Which library suits my project?

AI Library Finder

Describe your project in a sentence or two, in Arabic or English, and the guide will suggest the core and supporting libraries from the encyclopedia with the reason for each choice, the difficulty level, requirements, alternatives, examples and a learning path.

Recommendation: Analysing imbalanced tabular medical data

Detected tasks:Tabular data analysisImbalanced dataMedical image analysis

Core libraries

  • Scikit-learn — Models, stratified cross-validation and metrics

    Reliable evaluation tools such as PR-AUC and stratified validation.

  • Imbalanced-learn — Resampling inside a Pipeline

    Prevents data leakage by applying SMOTE only inside each fold.

Supporting libraries

  • Pandas — Cleaning and preparing data

    Handling missing values and features.

  • XGBoost — A strong model with class weights

    scale_pos_weight as an alternative to resampling.

  • SHAP — Explaining the influential factors

    Important for the model to be accepted medically.

  • Optuna — Hyperparameter tuning with a suitable metric

    Optimising PR-AUC instead of accuracy.

Difficulty level: Medium

Requirements: A CPU is usually enough.

Alternatives

Suggested learning path

  1. Exploratory analysis and class ratios
  2. Stratified patient-level splitting
  3. Suitable metrics (PR-AUC, sensitivity)
  4. Class weights or resampling inside a Pipeline
  5. Explanation with SHAP and calibration

Ready-made examples to start with

Suggested new addition to the encyclopedia

Well-known tools for this task that are not listed in the encyclopedia yet, so we have not verified their data:

Compare the suggested libraries

Library stacks for complete projects

A medical image classification project from start to deployment
  1. Data processing

  2. Data augmentation

  3. Building the model

  4. Training

  5. Evaluation

  6. Explanation

  7. Deployment