sensAI - the Python library for sensible AI

Guides and Tutorials

Introduction to sensAI: Supervised Learning with VectorModels
Neural Networks
- Image Classification
  - Applying Predefined Models
  - Creating a Custom CNN Model
    - Wrapping a Custom torch.nn.Module Instance
    - Creating an Input-/Output-Adaptive Custom Model

Modules

Modules
- catboost
- clustering
  - clustering_base
  - greedy_clustering
  - sklearn_clustering
- columngen
- data
- data_transformation
  - dft
  - sklearn_transformer
  - value_transformation
- distance_metric
- ensemble
  - ensemble_base
  - models
- evaluation
  - crossval
  - eval_stats
  - eval_util
  - evaluator
  - evaluator_clustering
  - metric_computation
- feature_importance
- feature_selection
  - rfe
- featuregen
  - feature_generator
  - feature_generator_registry
- geoanalytics
  - geo_clustering
  - geo_coords
  - geopandas
  - local_coords
  - map_tiles
- hyperopt
- lightgbm
- local_search
- minizinc
- multi_model
- naive_bayes
- nearest_neighbors
- normalisation
- pytorch_lightning
  - pl_models
- sklearn
  - sklearn_base
  - sklearn_classification
  - sklearn_regression
- sklearn_quantile
- tensor_model
- tensorflow
  - tf_base
  - tf_mlp
- torch
  - torch_base
  - torch_data
  - torch_enums
  - torch_eval_util
  - torch_models
  - torch_modules
  - torch_opt
  - torchtext
- tracking
  - azure_tracking
  - clearml_tracking
  - mlflow_tracking
  - tracking_base
- util
  - aggregation
  - cache
  - cache_azure
  - cache_mysql
  - datastruct
  - deprecation
  - dtype
  - hash
  - helper
  - io
  - jscode
  - logging
  - math
  - multiprocessing
  - pandas
  - pickle
  - plot
  - profiling
  - sequences
  - string
  - test
  - time
  - typing
  - version
- vector_model
- vectoriser
- xgboost

Indices and tables