'clf__penalty': ['l2'], 'clf__tol': uniform(0.0001, 0.01), 'clf__verbose': [0], } param_grid.update(text_grid) cv_kwargs = dict(n_iter=30, scoring=None, fit_params=None, n_jobs=4, iid=True, refit=True, cv=None, verbose=3, pre_dispatch='2*n_jobs', error_score=0) if __name__ == "__main__": for level, (X, y), n_classes_ in iterate_heirarchy(): gridsearch = CustomGridSearch(pipeline, param_grid, n_classes_, random=True, **cv_kwargs) gridsearch \ .set_data(X, y) \ .fit() \ .generate_report(name="LinearSVC", level=level, notes="") \ .write_to_mongo()
} param_grid.update(text_grid) cv_kwargs = dict( n_iter=50, scoring=None, fit_params=None, n_jobs=4, iid=True, refit=True, cv=None, verbose=3, pre_dispatch='2*n_jobs', error_score=0 ) if __name__ == "__main__": print(param_grid) for level, (X, y), n_classes_ in iterate_heirarchy(): gridsearch = CustomGridSearch(pipeline, param_grid, n_classes_, random=True, **cv_kwargs) gridsearch.set_data(X, y)\ .fit()\ .generate_report( name="LogisticRegression_LDA_NORM", level=level, notes="added 1300 + topics")\ .write_to_mongo()