Default Pipeline

This notebook shows how you can use aikit to directly get a default pipeline that you can fit on your data

from aikit.datasets.datasets import load_dataset, DatasetEnum
Xtrain, y_train, _ ,_ , _ = load_dataset(DatasetEnum.titanic)

from aikit.ml_machine import get_default_pipeline
model = get_default_pipeline(Xtrain, y_train)
model

Matplotlib won't work

C:\HOMEWARE\Anaconda3-Windows-x86_64\lib\site-packages\gensim\utils.py:1197: UserWarning: detected Windows; aliasing chunkize to chunkize_serial
  warnings.warn("detected Windows; aliasing chunkize to chunkize_serial")

GraphPipeline(edges=[('ColumnsSelector', 'NumImputer'),
                     ('CountVectorizerWrapper', 'NumImputer'),
                     ('NumericalEncoder', 'NumImputer',
                      'RandomForestClassifier')],
              models={'ColumnsSelector': ColumnsSelector(columns_to_drop=None,
                                                         columns_to_use=['pclass',
                                                                         'age',
                                                                         'sibsp',
                                                                         'parch',
                                                                         'fare',
                                                                         'body'],
                                                         raise_if_shape_differs=True,
                                                         regex_match=False),
                      'CountVectorizerWrapper'...
                      'RandomForestClassifier': RandomForestClassifier(bootstrap=True,
                                                                       class_weight=None,
                                                                       criterion='gini',
                                                                       max_depth=None,
                                                                       max_features='auto',
                                                                       max_leaf_nodes=None,
                                                                       min_impurity_decrease=0.0,
                                                                       min_impurity_split=None,
                                                                       min_samples_leaf=1,
                                                                       min_samples_split=2,
                                                                       min_weight_fraction_leaf=0.0,
                                                                       n_estimators=100,
                                                                       n_jobs=None,
                                                                       oob_score=False,
                                                                       random_state=123,
                                                                       verbose=0,
                                                                       warm_start=False)},
              no_concat_nodes=None, verbose=False)

model.graphviz

model.fit(Xtrain, y_train)

GraphPipeline(edges=[('ColumnsSelector', 'NumImputer'),
                     ('CountVectorizerWrapper', 'NumImputer'),
                     ('NumericalEncoder', 'NumImputer',
                      'RandomForestClassifier')],
              models={'ColumnsSelector': ColumnsSelector(columns_to_drop=None,
                                                         columns_to_use=['pclass',
                                                                         'age',
                                                                         'sibsp',
                                                                         'parch',
                                                                         'fare',
                                                                         'body'],
                                                         raise_if_shape_differs=True,
                                                         regex_match=False),
                      'CountVectorizerWrapper'...
                      'RandomForestClassifier': RandomForestClassifier(bootstrap=True,
                                                                       class_weight=None,
                                                                       criterion='gini',
                                                                       max_depth=None,
                                                                       max_features='auto',
                                                                       max_leaf_nodes=None,
                                                                       min_impurity_decrease=0.0,
                                                                       min_impurity_split=None,
                                                                       min_samples_leaf=1,
                                                                       min_samples_split=2,
                                                                       min_weight_fraction_leaf=0.0,
                                                                       n_estimators=100,
                                                                       n_jobs=None,
                                                                       oob_score=False,
                                                                       random_state=123,
                                                                       verbose=0,
                                                                       warm_start=False)},
              no_concat_nodes=None, verbose=False)