maui / Git / [9bc947] /doc/_build/doctrees/maui.doctree

Models:
AlyssaS/
maui
Downloads: 1
[9bc947]: / doc / _build / doctrees / maui.doctree
History
Download this file
347 lines (346 with data), 87.5 kB

ÇĽîdocutils.nodesöîdocumentöôö)üö}ö(î	rawsourceöîöîchildrenö]öhîsectionöôö)üö}ö(hhh]ö(hîtitleöôö)üö}ö(hîThe Maui Classöh]öhîTextöôöîThe Maui Classöůöüö}ö(hhîparentöhhhîsourceöNîlineöNubaî
attributesö}ö(îidsö]öîclassesö]öînamesö]öîdupnamesö]öîbackrefsö]öuîtagnameöhhhhhhî*/home/jona/work/phd/maui/maui/doc/maui.rstöhKubîsphinx.addnodesöîindexöôö)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(îsingleöîMaui (class in maui)öî	maui.MauiöhNtöauh)h,hhhhhNhNubh+îdescöôö)üö}ö(hhh]ö(h+îdesc_signatureöôö)üö}ö(hXMMaui(n_hidden=[1500], n_latent=80, batch_size=100, epochs=400, architecture='stacked', initial_beta_val=0, kappa=1.0, max_beta_val=1, learning_rate=0.0005, epsilon_std=1.0, batch_normalize_inputs=True, batch_normalize_intermediaries=True, batch_normalize_embedding=True, relu_intermediaries=True, relu_embedding=True, input_dim=None)öh]ö(h+îdesc_annotationöôö)üö}ö(hîclass öh]öhîclass öůöüö}ö(hhhhJhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öî	xml:spaceöîpreserveöuh)hHhhDhhhîB/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.MauiöhNubh+îdesc_addnameöôö)üö}ö(hîmaui.öh]öhîmaui.öůöüö}ö(hhhh]hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h[hhDhhhhZhNubh+î	desc_nameöôö)üö}ö(hîMauiöh]öhîMauiöůöüö}ö(hhhhmhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhhDhhhhZhNubh+îdesc_parameterlistöôö)üö}ö(hXGn_hidden=[1500], n_latent=80, batch_size=100, epochs=400, architecture='stacked', initial_beta_val=0, kappa=1.0, max_beta_val=1, learning_rate=0.0005, epsilon_std=1.0, batch_normalize_inputs=True, batch_normalize_intermediaries=True, batch_normalize_embedding=True, relu_intermediaries=True, relu_embedding=True, input_dim=Noneöh]öh+îdesc_parameteröôö)üö}ö(hXGn_hidden=[1500], n_latent=80, batch_size=100, epochs=400, architecture='stacked', initial_beta_val=0, kappa=1.0, max_beta_val=1, learning_rate=0.0005, epsilon_std=1.0, batch_normalize_inputs=True, batch_normalize_intermediaries=True, batch_normalize_embedding=True, relu_intermediaries=True, relu_embedding=True, input_dim=Noneöh]öhXGn_hidden=[1500], n_latent=80, batch_size=100, epochs=400, architecture='stacked', initial_beta_val=0, kappa=1.0, max_beta_val=1, learning_rate=0.0005, epsilon_std=1.0, batch_normalize_inputs=True, batch_normalize_intermediaries=True, batch_normalize_embedding=True, relu_intermediaries=True, relu_embedding=True, input_dim=Noneöůöüö}ö(hhhhâhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühh}hhhhZhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hhDhhhhZhNubh+îonlyöôö)üö}ö(hhh]öh+îpending_xreföôö)üö}ö(hhh]öhîinlineöôö)üö}ö(hhh]öhî[source]öůöüö}ö(hhhhúubah}ö(h]öh!]öî
viewcode-linköah#]öh%]öh']öuh)híhh×ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöîviewcodeöî	refdomainöîstdöîrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöhoîrefdocöîmauiöuh)hťhhÖubah}ö(h]öh!]öh#]öh%]öh']öîexpröîhtmlöuh)hŚhhDhhhNhNubeh}ö(h]öh;ah!]öh#]öh;ah%]öh']öîfirstöëîmoduleöîmauiöîclassöhîfullnameöhouh)hBhh?hhhhZhNubh+îdesc_contentöôö)üö}ö(hhh]ö(hî	paragraphöôö)üö}ö(hî1Maui (Multi-omics Autoencoder Integration) model.öh]öhî1Maui (Multi-omics Autoencoder Integration) model.öůöüö}ö(hhŢhh█hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîB/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.MauiöhKhhÍhhubh┌)üö}ö(hîLTrains a variational autoencoder to find latent factors in multi-modal data.öh]öhîLTrains a variational autoencoder to find latent factors in multi-modal data.öůöüö}ö(hhýhhŕhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hhÚhKhhÍhhubhîdefinition_listöôö)üö}ö(hhh]ö(hîdefinition_list_itemöôö)üö}ö(hî┴n_hidden: array (default [1500])
The sizes of the hidden layers of the autoencoder architecture.
Each element of the array specifies the number of nodes in successive
layers of the autoencoder
öh]ö(hîtermöôö)üö}ö(hî n_hidden: array (default [1500])öh]öhî n_hidden: array (default [1500])öůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhhÚhK
hh ubhî
definitionöôö)üö}ö(hhh]öh┌)üö}ö(hîčThe sizes of the hidden layers of the autoencoder architecture.
Each element of the array specifies the number of nodes in successive
layers of the autoencoderöh]öhîčThe sizes of the hidden layers of the autoencoder architecture.
Each element of the array specifies the number of nodes in successive
layers of the autoencoderöůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hhÚhKhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhh ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhhÚhK
hh˙ubh■)üö}ö(hîTn_latent: int (default 80)
The size of the latent layer (number of latent features)
öh]ö(j)üö}ö(hîn_latent: int (default 80)öh]öhîn_latent: int (default 80)öůöüö}ö(hj8hj6ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhhÚhK
hj2ubj)üö}ö(hhh]öh┌)üö}ö(hî8The size of the latent layer (number of latent features)öh]öhî8The size of the latent layer (number of latent features)öůöüö}ö(hjIhjGubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hhÚhK
hjDubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj2ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhhÚhK
hh˙hhubh■)üö}ö(hîYbatch_size: int (default 100)
The size of the mini-batches used for training the network
öh]ö(j)üö}ö(hîbatch_size: int (default 100)öh]öhîbatch_size: int (default 100)öůöüö}ö(hjghjeubah}ö(h]öh!]öh#]öh%]öh']öuh)jhhÚhKhjaubj)üö}ö(hhh]öh┌)üö}ö(hî:The size of the mini-batches used for training the networköh]öhî:The size of the mini-batches used for training the networköůöüö}ö(hjxhjvubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hhÚhKhjsubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjaubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhhÚhKhh˙hhubh■)üö}ö(hîPepochs: int (default 400)
The number of epoches to use for training the network
öh]ö(j)üö}ö(hîepochs: int (default 400)öh]öhîepochs: int (default 400)öůöüö}ö(hjľhjöubah}ö(h]öh!]öh#]öh%]öh']öuh)jhhÚhKhjÉubj)üö}ö(hhh]öh┌)üö}ö(hî5The number of epoches to use for training the networköh]öhî5The number of epoches to use for training the networköůöüö}ö(hjžhjąubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hhÚhKhjóubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjÉubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhhÚhKhh˙hhubh■)üö}ö(hXarchitecture:
One of 'stacked' or 'deep'. If 'stacked', will use a stacked VAE model, where
the intermediate layers are also variational. If 'deep', will train a deep VAE
where the intermediate layers are regular (ReLU) units, and only the middle
(latent) layer is variational.

öh]ö(j)üö}ö(hî
architecture:öh]öhî
architecture:öůöüö}ö(hj┼hj├ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhhÚhKhj┐ubj)üö}ö(hhh]öh┌)üö}ö(hXOne of 'stacked' or 'deep'. If 'stacked', will use a stacked VAE model, where
the intermediate layers are also variational. If 'deep', will train a deep VAE
where the intermediate layers are regular (ReLU) units, and only the middle
(latent) layer is variational.öh]öhXOne of ÔÇśstackedÔÇÖ or ÔÇśdeepÔÇÖ. If ÔÇśstackedÔÇÖ, will use a stacked VAE model, where
the intermediate layers are also variational. If ÔÇśdeepÔÇÖ, will train a deep VAE
where the intermediate layers are regular (ReLU) units, and only the middle
(latent) layer is variational.öůöüö}ö(hjÍhjďubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hhÚhKhjĐubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj┐ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhhÚhKhh˙hhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hhÍhhhhÚhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9îc_index() (maui.Maui method)öîmaui.Maui.c_indexöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî┼Maui.c_index(survival, clinical_only=True, duration_column='duration', observed_column='observed', cox_penalties=[0.1, 1, 10, 100, 1000, 10000], cv_folds=5, sel_clin_alpha=0.05, sel_clin_penalty=0)öh]ö(hl)üö}ö(hîc_indexöh]öhîc_indexöůöüö}ö(hhhj	hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjhhhîJ/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.c_indexöhNubh|)üö}ö(hîĚsurvival, clinical_only=True, duration_column='duration', observed_column='observed', cox_penalties=[0.1, 1, 10, 100, 1000, 10000], cv_folds=5, sel_clin_alpha=0.05, sel_clin_penalty=0öh]öhé)üö}ö(hîĚsurvival, clinical_only=True, duration_column='duration', observed_column='observed', cox_penalties=[0.1, 1, 10, 100, 1000, 10000], cv_folds=5, sel_clin_alpha=0.05, sel_clin_penalty=0öh]öhîĚsurvival, clinical_only=True, duration_column='duration', observed_column='observed', cox_penalties=[0.1, 1, 10, 100, 1000, 10000], cv_folds=5, sel_clin_alpha=0.05, sel_clin_penalty=0öůöüö}ö(hhhjhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjhhhjhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjhhhjhNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj6ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj3ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.c_indexöîrefdocöh└uh)hťhj0ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjhhhNhNubeh}ö(h]öjah!]öh#]öjah%]öh']öh¤ëhđîmauiöhĎhohËjOuh)hBhjhhhjhNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîsCompute's Harrell's c-Index for a Cox Proportional Hazards regression modeling
survival by the latent factors in z.öh]öhîwComputeÔÇÖs HarrellÔÇÖs c-Index for a Cox Proportional Hazards regression modeling
survival by the latent factors in z.öůöüö}ö(hjdhjbhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîJ/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.c_indexöhKhj_hhubh┌)üö}ö(hîĆz:                  pd.DataFrame (n_samples, n_latent factors)
survival:           pd.DataFrame of survival information and relevant covariatesöh]öhîĆz:                  pd.DataFrame (n_samples, n_latent factors)
survival:           pd.DataFrame of survival information and relevant covariatesöůöüö}ö(hjshjqhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphKhj_hhubhîblock_quoteöôö)üö}ö(hhh]öh┌)üö}ö(hî/(such as sex, age at diagnosis, or tumor stage)öh]öhî/(such as sex, age at diagnosis, or tumor stage)öůöüö}ö(hjćhjäubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphKhjüubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj_hhhjphNubh¨)üö}ö(hhh]ö(h■)üö}ö(hîĽclinical_only:      Compute the c-Index for a model containing only
individually clinically relevant latent factors
(see ``select_clinical_factors``)öh]ö(j)üö}ö(hîCclinical_only:      Compute the c-Index for a model containing onlyöh]öhîCclinical_only:      Compute the c-Index for a model containing onlyöůöüö}ö(hjíhjčubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjphK
hjŤubj)üö}ö(hhh]öh┌)üö}ö(hîQindividually clinically relevant latent factors
(see ``select_clinical_factors``)öh]ö(hî5individually clinically relevant latent factors
(see öůöüö}ö(hî5individually clinically relevant latent factors
(see öhj░ubhîliteralöôö)üö}ö(hî``select_clinical_factors``öh]öhîselect_clinical_factorsöůöüö}ö(hhhj╗ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj░ubhî)öůöüö}ö(hî)öhj░ubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphK
hjşubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjŤubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjphK
hjśubh■)üö}ö(hîćduration_column:    the name of the column in ``survival`` containing the
duration (time between diagnosis and death or last followup)öh]ö(j)üö}ö(hîIduration_column:    the name of the column in ``survival`` containing theöh]ö(hî.duration_column:    the name of the column in öůöüö}ö(hî.duration_column:    the name of the column in öhjńubj║)üö}ö(hî``survival``öh]öhîsurvivalöůöüö}ö(hhhjÝubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjńubhî containing theöůöüö}ö(hî containing theöhjńubeh}ö(h]öh!]öh#]öh%]öh']öuh)jhjphKhjÓubj)üö}ö(hhh]öh┌)üö}ö(hî<duration (time between diagnosis and death or last followup)öh]öhî<duration (time between diagnosis and death or last followup)öůöüö}ö(hjhj	ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphK
hjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjÓubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjphKhjśhhubh■)üö}ö(hîoobserved_column:    the name of the column in ``survival`` containing
indicating whether time of death is knownöh]ö(j)üö}ö(hîEobserved_column:    the name of the column in ``survival`` containingöh]ö(hî.observed_column:    the name of the column in öůöüö}ö(hî.observed_column:    the name of the column in öhj'ubj║)üö}ö(hî``survival``öh]öhîsurvivalöůöüö}ö(hhhj0ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj'ubhî containingöůöüö}ö(hî containingöhj'ubeh}ö(h]öh!]öh#]öh%]öh']öuh)jhjphKhj#ubj)üö}ö(hhh]öh┌)üö}ö(hî)indicating whether time of death is knownöh]öhî)indicating whether time of death is knownöůöüö}ö(hjNhjLubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphKhjIubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj#ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjphKhjśhhubh■)üö}ö(hî¬cox_penalties:      penalty coefficient in Cox PH solver (see ``lifelines.CoxPHFitter``)
to try. Returns the best c given by the different penalties
(by cross-validation)öh]ö(j)üö}ö(hîXcox_penalties:      penalty coefficient in Cox PH solver (see ``lifelines.CoxPHFitter``)öh]ö(hî>cox_penalties:      penalty coefficient in Cox PH solver (see öůöüö}ö(hî>cox_penalties:      penalty coefficient in Cox PH solver (see öhjjubj║)üö}ö(hî``lifelines.CoxPHFitter``öh]öhîlifelines.CoxPHFitteröůöüö}ö(hhhjsubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjjubhî)öůöüö}ö(hj═hjjubeh}ö(h]öh!]öh#]öh%]öh']öuh)jhjphKhjfubj)üö}ö(hhh]öh┌)üö}ö(hîQto try. Returns the best c given by the different penalties
(by cross-validation)öh]öhîQto try. Returns the best c given by the different penalties
(by cross-validation)öůöüö}ö(hjÉhjÄubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphKhjőubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjfubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjphKhjśhhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hj_hhhjphNubh┌)üö}ö(hîĐcv_folds:           number of cross-validation folds to compute C
sel_clin_penalty:   CPH penalizer to use when selecting clinical factors
sel_clin_alpha:     significance level when selecting clinical factorsöh]öhîĐcv_folds:           number of cross-validation folds to compute C
sel_clin_penalty:   CPH penalizer to use when selecting clinical factors
sel_clin_alpha:     significance level when selecting clinical factorsöůöüö}ö(hj░hj«hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphKhj_hhubh¨)üö}ö(hhh]öh■)üö}ö(hîhcs: array, Harrell's c-Index, an auc-like metric for survival prediction accuracy.
one value per cv_foldöh]ö(j)üö}ö(hîRcs: array, Harrell's c-Index, an auc-like metric for survival prediction accuracy.öh]öhîTcs: array, HarrellÔÇÖs c-Index, an auc-like metric for survival prediction accuracy.öůöüö}ö(hj┼hj├ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjphKhj┐ubj)üö}ö(hhh]öh┌)üö}ö(hîone value per cv_foldöh]öhîone value per cv_foldöůöüö}ö(hjÍhjďubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjphKhjĐubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj┐ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjphKhj╝ubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hj_hhhjphNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhjhhhjhNubeh}ö(h]öh!]öh#]öh%]öh']öîdomainöîpyöîobjtypeöîmethodöîdesctypeöjînoindexöëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9îcluster() (maui.Maui method)öîmaui.Maui.clusteröhNtöauh)h,hhÍhhhîJ/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.clusteröhNubh>)üö}ö(hhh]ö(hC)üö}ö(hîâMaui.cluster(k=None, optimal_k_method='ami', optimal_k_range=range(3, 10), ami_y=None, kmeans_kwargs={'n_init': 1000, 'n_jobs': 2})öh]ö(hl)üö}ö(hîclusteröh]öhîclusteröůöüö}ö(hhhjhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjhhhîJ/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.clusteröhNubh|)üö}ö(hîuk=None, optimal_k_method='ami', optimal_k_range=range(3, 10), ami_y=None, kmeans_kwargs={'n_init': 1000, 'n_jobs': 2}öh]ö(hé)üö}ö(hîk=Noneöh]öhîk=Noneöůöüö}ö(hhhj/ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubhé)üö}ö(hîoptimal_k_method='ami'öh]öhîoptimal_k_method='ami'öůöüö}ö(hhhj=ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubhé)üö}ö(hîoptimal_k_range=range(3öh]öhîoptimal_k_range=range(3öůöüö}ö(hhhjKubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubhé)üö}ö(hî10)öh]öhî10)öůöüö}ö(hhhjYubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubhé)üö}ö(hî
ami_y=Noneöh]öhî
ami_y=Noneöůöüö}ö(hhhjgubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubhé)üö}ö(hîkmeans_kwargs={'n_init': 1000öh]öhîkmeans_kwargs={'n_init': 1000öůöüö}ö(hhhjuubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubhé)üö}ö(hî'n_jobs': 2}öh]öhî'n_jobs': 2}öůöüö}ö(hhhjâubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj+ubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjhhhj*hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhjŁubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhjÜubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.clusteröîrefdocöh└uh)hťhjŚubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjhhhNhNubeh}ö(h]öjah!]öh#]öjah%]öh']öh¤ëhđîmauiöhĎhohËjÂuh)hBhjhhhj*hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hî>Cluster the samples using k-means based on the latent factors.öh]öhî>Cluster the samples using k-means based on the latent factors.öůöüö}ö(hj╦hj╔hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjĂhhubh¨)üö}ö(hhh]ö(h■)üö}ö(hîkk:                  optional, the number of clusters to find.
if not given, will attempt to find optimal k.öh]ö(j)üö}ö(hî=k:                  optional, the number of clusters to find.öh]öhî=k:                  optional, the number of clusters to find.öůöüö}ö(hjÓhjŮubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjhKhj┌ubj)üö}ö(hhh]öh┌)üö}ö(hî-if not given, will attempt to find optimal k.öh]öhî-if not given, will attempt to find optimal k.öůöüö}ö(hj˝hj´ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjýubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj┌ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjhKhjÎubh■)üö}ö(hXZoptimal_k_method:   supported methods are 'ami' and 'silhouette'. Otherwise, callable.
if 'ami', will pick K which gives the best AMI
(adjusted mutual information) with external labels.
if 'silhouette' will pick the K which gives the best
mean silhouette coefficient.
if callable, should have signature ``scorer(yhat)``
and return a scalar score.öh]ö(j)üö}ö(hîVoptimal_k_method:   supported methods are 'ami' and 'silhouette'. Otherwise, callable.öh]öhî^optimal_k_method:   supported methods are ÔÇśamiÔÇÖ and ÔÇśsilhouetteÔÇÖ. Otherwise, callable.öůöüö}ö(hjhj
ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjhKhj	ubj)üö}ö(hhh]öh┌)üö}ö(hXif 'ami', will pick K which gives the best AMI
(adjusted mutual information) with external labels.
if 'silhouette' will pick the K which gives the best
mean silhouette coefficient.
if callable, should have signature ``scorer(yhat)``
and return a scalar score.öh]ö(hîÓif ÔÇśamiÔÇÖ, will pick K which gives the best AMI
(adjusted mutual information) with external labels.
if ÔÇśsilhouetteÔÇÖ will pick the K which gives the best
mean silhouette coefficient.
if callable, should have signature öůöüö}ö(hîěif 'ami', will pick K which gives the best AMI
(adjusted mutual information) with external labels.
if 'silhouette' will pick the K which gives the best
mean silhouette coefficient.
if callable, should have signature öhjubj║)üö}ö(hî``scorer(yhat)``öh]öhîscorer(yhat)öůöüö}ö(hhhj'ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjubhî
and return a scalar score.öůöüö}ö(hî
and return a scalar score.öhjubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj	ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjhKhjÎhhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hjĂhhhjhNubh┌)üö}ö(hîĽoptimal_k_range:    array-like, range of Ks to try to find optimal K among
ami_y:              array-like (n_samples), the ground-truth labels to useöh]öhîĽoptimal_k_range:    array-like, range of Ks to try to find optimal K among
ami_y:              array-like (n_samples), the ground-truth labels to useöůöüö}ö(hjThjRhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjĂhhubjÇ)üö}ö(hhh]öh┌)üö}ö(hî9when picking K by "best AMI against ground-truth" method.öh]öhî=when picking K by ÔÇťbest AMI against ground-truthÔÇŁ method.öůöüö}ö(hjehjcubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhj`ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjĂhhhjhNubh┌)üö}ö(hîQkmeans_kwargs:      optional, kwargs for initialization of sklearn.cluster.KMeansöh]öhîQkmeans_kwargs:      optional, kwargs for initialization of sklearn.cluster.KMeansöůöüö}ö(hjyhjwhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjĂhhubh┌)üö}ö(hî9yhat:   Series (n_samples) cluster labels for each sampleöh]öhî9yhat:   Series (n_samples) cluster labels for each sampleöůöüö}ö(hjçhjůhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjĂhhubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhjhhhj*hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjjájëuh)h=hhhhÍhjhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î compute_auc() (maui.Maui method)öîmaui.Maui.compute_aucöhNtöauh)h,hhÍhhhîN/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.compute_aucöhNubh>)üö}ö(hhh]ö(hC)üö}ö(hîMaui.compute_auc(y, **kwargs)öh]ö(hl)üö}ö(hîcompute_aucöh]öhîcompute_aucöůöüö}ö(hhhjĚhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhj│hhhîN/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.compute_aucöhNubh|)üö}ö(hîy, **kwargsöh]ö(hé)üö}ö(hîyöh]öhîyöůöüö}ö(hhhj╩ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjĂubhé)üö}ö(hî**kwargsöh]öhî**kwargsöůöüö}ö(hhhjěubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjĂubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hj│hhhj┼hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj˛ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj´ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.compute_aucöîrefdocöh└uh)hťhjýubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhj│hhhNhNubeh}ö(h]öjşah!]öh#]öjşah%]öh']öh¤ëhđîmauiöhĎhohËjuh)hBhj░hhhj┼hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hînCompute area under the ROC curve for predicting the labels in y using the
latent features previously inferred.öh]öhînCompute area under the ROC curve for predicting the labels in y using the
latent features previously inferred.öůöüö}ö(hj hjhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj»hKhjhhubh┌)üö}ö(hîGy:          labels to predict
**kwargs:   arguments for ``compute_roc``öh]ö(hîy:          labels to predict
öůöüö}ö(hîy:          labels to predict
öhj,hhhNhNubhîproblematicöôö)üö}ö(hî**öh]öhî**öůöüö}ö(hhhj7ubah}ö(h]öîid2öah!]öh#]öh%]öh']öîrefidöîid1öuh)j5hj,ubhîkwargs:   arguments for öůöüö}ö(hîkwargs:   arguments for öhj,hhhNhNubj║)üö}ö(hî``compute_roc``öh]öhîcompute_rocöůöüö}ö(hhhjMubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj,ubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj»hKhjhhubh┌)üö}ö(hî0aucs:   pd.Series, auc per class as well as meanöh]öhî0aucs:   pd.Series, auc per class as well as meanöůöüö}ö(hjchjahhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj»hKhjhhubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj░hhhj┼hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjj|jëuh)h=hhhhÍhj»hNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î compute_roc() (maui.Maui method)öîmaui.Maui.compute_rocöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hîMaui.compute_roc(y, **kwargs)öh]ö(hl)üö}ö(hîcompute_rocöh]öhîcompute_rocöůöüö}ö(hhhjĺhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjÄhhhîN/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.compute_rocöhNubh|)üö}ö(hîy, **kwargsöh]ö(hé)üö}ö(hj╠h]öhîyöůöüö}ö(hhhjąubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjíubhé)üö}ö(hî**kwargsöh]öhî**kwargsöůöüö}ö(hhhj▓ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjíubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjÄhhhjáhNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj╠ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj╔ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.compute_rocöîrefdocöh└uh)hťhjĂubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjÄhhhNhNubeh}ö(h]öjëah!]öh#]öjëah%]öh']öh¤ëhđîmauiöhĎhohËjňuh)hBhjőhhhjáhNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hXśCompute Receiver Operating Characteristics curve for SVM prediction
of labels ``y`` from the latent factors. Computes both the ROC curves
(true positive rate, true negative rate), and the area under the roc (auc).
ROC and auROC computed for each class (the classes are inferred from ``y``),
as well as a "mean" ROC, computed by averaging the class ROCs. Only samples
in the index of ``y`` will be considered.öh]ö(hîNCompute Receiver Operating Characteristics curve for SVM prediction
of labels öůöüö}ö(hîNCompute Receiver Operating Characteristics curve for SVM prediction
of labels öhj°hhhNhNubj║)üö}ö(hî``y``öh]öhîyöůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj°ubhî╚ from the latent factors. Computes both the ROC curves
(true positive rate, true negative rate), and the area under the roc (auc).
ROC and auROC computed for each class (the classes are inferred from öůöüö}ö(hî╚ from the latent factors. Computes both the ROC curves
(true positive rate, true negative rate), and the area under the roc (auc).
ROC and auROC computed for each class (the classes are inferred from öhj°hhhNhNubj║)üö}ö(hî``y``öh]öhîyöůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj°ubhîc),
as well as a ÔÇťmeanÔÇŁ ROC, computed by averaging the class ROCs. Only samples
in the index of öůöüö}ö(hî_),
as well as a "mean" ROC, computed by averaging the class ROCs. Only samples
in the index of öhj°hhhNhNubj║)üö}ö(hî``y``öh]öhîyöůöüö}ö(hhhj'ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj°ubhî will be considered.öůöüö}ö(hî will be considered.öhj°hhhNhNubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîN/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.compute_rocöhKhj§hhubh┌)üö}ö(hîyy:          array-like (n_samples,), the labels of the samples to predict
**kwargs:   arguments for ``utils.compute_roc``öh]ö(hîJy:          array-like (n_samples,), the labels of the samples to predict
öůöüö}ö(hîJy:          array-like (n_samples,), the labels of the samples to predict
öhjAhhhNhNubj6)üö}ö(hî**öh]öhî**öůöüö}ö(hhhjJubah}ö(h]öîid4öah!]öh#]öh%]öh']öîrefidöîid3öuh)j5hjAubhîkwargs:   arguments for öůöüö}ö(hîkwargs:   arguments for öhjAhhhNhNubj║)üö}ö(hî``utils.compute_roc``öh]öhîutils.compute_rocöůöüö}ö(hhhj`ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjAubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj@hK
hj§hhubh¨)üö}ö(hhh]öh■)üö}ö(hîŻroc_curves: dict, one key per class as well as "mean", each value is a dataframe
containing the tpr (true positive rate) and fpr (falce positive rate)
defining that class (or the mean) ROC.öh]ö(j)üö}ö(hîProc_curves: dict, one key per class as well as "mean", each value is a dataframeöh]öhîTroc_curves: dict, one key per class as well as ÔÇťmeanÔÇŁ, each value is a dataframeöůöüö}ö(hj}hj{ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj@hKhjwubj)üö}ö(hhh]öh┌)üö}ö(hîlcontaining the tpr (true positive rate) and fpr (falce positive rate)
defining that class (or the mean) ROC.öh]öhîlcontaining the tpr (true positive rate) and fpr (falce positive rate)
defining that class (or the mean) ROC.öůöüö}ö(hjÄhjîubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj@hKhjëubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjwubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj@hKhjtubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hj§hhhj@hNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhjőhhhjáhNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjj╣jëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î/drop_unexplanatory_factors() (maui.Maui method)öî$maui.Maui.drop_unexplanatory_factorsöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî/Maui.drop_unexplanatory_factors(threshold=0.02)öh]ö(hl)üö}ö(hîdrop_unexplanatory_factorsöh]öhîdrop_unexplanatory_factorsöůöüö}ö(hhhj¤hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhj╦hhhî]/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.drop_unexplanatory_factorsöhNubh|)üö}ö(hîthreshold=0.02öh]öhé)üö}ö(hîthreshold=0.02öh]öhîthreshold=0.02öůöüö}ö(hhhjÔubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjŮubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hj╦hhhjŢhNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhjŘubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj¨ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.drop_unexplanatory_factorsöîrefdocöh└uh)hťhj÷ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhj╦hhhNhNubeh}ö(h]öjĂah!]öh#]öjĂah%]öh']öh¤ëhđîmauiöhĎhohËjuh)hBhj╚hhhjŢhNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîŐDrops factors which have a low R^2 score in a univariate linear model
predicting the features `x` from a column of the latent factors `z`.öh]ö(hî^Drops factors which have a low R^2 score in a univariate linear model
predicting the features öůöüö}ö(hî^Drops factors which have a low R^2 score in a univariate linear model
predicting the features öhj(hhhNhNubhîtitle_referenceöôö)üö}ö(hî`x`öh]öhîxöůöüö}ö(hhhj3ubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hj(ubhî% from a column of the latent factors öůöüö}ö(hî% from a column of the latent factors öhj(hhhNhNubj2)üö}ö(hî`z`öh]öhîzöůöüö}ö(hhhjFubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hj(ubhî.öůöüö}ö(hî.öhj(hhhNhNubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hî]/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.drop_unexplanatory_factorsöhKhj%hhubh¨)üö}ö(hhh]öh■)üö}ö(hîPthreshold:  threshold for R^2, latent factors below this threshold
are dropped.
öh]ö(j)üö}ö(hîBthreshold:  threshold for R^2, latent factors below this thresholdöh]öhîBthreshold:  threshold for R^2, latent factors below this thresholdöůöüö}ö(hjihjgubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj_hKhjcubj)üö}ö(hhh]öh┌)üö}ö(hîare dropped.öh]öhîare dropped.öůöüö}ö(hjzhjxubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj_hKhjuubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjcubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj_hKhj`ubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hj%hhhj_hNubh¨)üö}ö(hhh]öh■)üö}ö(hî█z_filt:     (n_samples, n_factors) DataFrame of latent factor values,
with only those columns from the input `z` which have an R^2
above the threshold when using that column as an input
to a linear model predicting `x`.öh]ö(j)üö}ö(hîEz_filt:     (n_samples, n_factors) DataFrame of latent factor values,öh]öhîEz_filt:     (n_samples, n_factors) DataFrame of latent factor values,öůöüö}ö(hjíhjčubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj_hK
hjŤubj)üö}ö(hhh]öh┌)üö}ö(hîĽwith only those columns from the input `z` which have an R^2
above the threshold when using that column as an input
to a linear model predicting `x`.öh]ö(hî'with only those columns from the input öůöüö}ö(hî'with only those columns from the input öhj░ubj2)üö}ö(hî`z`öh]öhîzöůöüö}ö(hhhj╣ubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hj░ubhîg which have an R^2
above the threshold when using that column as an input
to a linear model predicting öůöüö}ö(hîg which have an R^2
above the threshold when using that column as an input
to a linear model predicting öhj░ubj2)üö}ö(hî`x`öh]öhîxöůöüö}ö(hhhj╠ubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hj░ubhî.öůöüö}ö(hjXhj░ubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj_hKhjşubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjŤubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj_hK
hjśubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hj%hhhj_hNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj╚hhhjŢhNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjj	jëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9îfit() (maui.Maui method)öî
maui.Maui.fitöhNtöauh)h,hhÍhhhîF/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.fitöhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî&Maui.fit(X, y=None, X_validation=None)öh]ö(hl)üö}ö(hîfitöh]öhîfitöůöüö}ö(hhhj	hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhj	hhhîF/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.fitöhNubh|)üö}ö(hîX, y=None, X_validation=Noneöh]ö(hé)üö}ö(hîXöh]öhîXöůöüö}ö(hhhj-	ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj)	ubhé)üö}ö(hîy=Noneöh]öhîy=Noneöůöüö}ö(hhhj;	ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj)	ubhé)üö}ö(hîX_validation=Noneöh]öhîX_validation=Noneöůöüö}ö(hhhjI	ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj)	ubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hj	hhhj(	hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhjc	ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj`	ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.fitöîrefdocöh└uh)hťhj]	ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhj	hhhNhNubeh}ö(h]öj	ah!]öh#]öj	ah%]öh']öh¤ëhđîmauiöhĎhohËj|	uh)hBhj	hhhj(	hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîTrain autoencoder modelöh]öhîTrain autoencoder modelöůöüö}ö(hjĹ	hjĆ	hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj	hKhjî	hhubh¨)üö}ö(hhh]ö(h■)üö}ö(hîÎX:  dict with multi-modal dataframes, containing training data, e.g.
{'mRNA': df1, 'SNP': df2},
df1, df2, etc. are (n_features, n_samples) pandas.DataFrame's.
The sample names must match, the feature names need not.öh]ö(j)üö}ö(hîDX:  dict with multi-modal dataframes, containing training data, e.g.öh]öhîDX:  dict with multi-modal dataframes, containing training data, e.g.öůöüö}ö(hjŽ	hjĄ	ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj	hKhjá	ubj)üö}ö(hhh]öh┌)üö}ö(hîĺ{'mRNA': df1, 'SNP': df2},
df1, df2, etc. are (n_features, n_samples) pandas.DataFrame's.
The sample names must match, the feature names need not.öh]öhîť{ÔÇśmRNAÔÇÖ: df1, ÔÇśSNPÔÇÖ: df2},
df1, df2, etc. are (n_features, n_samples) pandas.DataFrameÔÇÖs.
The sample names must match, the feature names need not.öůöüö}ö(hjĚ	hjÁ	ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj	hKhj▓	ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjá	ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj	hKhjŁ	ubh■)üö}ö(hîőX_validation: optional, dict with multi-modal dataframes, containing validation data
will be used to compute validation loss under trainingöh]ö(j)üö}ö(hîTX_validation: optional, dict with multi-modal dataframes, containing validation dataöh]öhîTX_validation: optional, dict with multi-modal dataframes, containing validation dataöůöüö}ö(hjŇ	hjË	ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj	hK	hj¤	ubj)üö}ö(hhh]öh┌)üö}ö(hî6will be used to compute validation loss under trainingöh]öhî6will be used to compute validation loss under trainingöůöüö}ö(hjŠ	hjń	ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj	hK
hjß	ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj¤	ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj	hK	hjŁ	hhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hjî	hhhj	hNubh┌)üö}ö(hî
y:  Not used.öh]öhî
y:  Not used.öůöüö}ö(hj
hj
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj	hKhjî	hhubh┌)üö}ö(hîself : Maui objectöh]öhîself : Maui objectöůöüö}ö(hj
hj
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj	hKhjî	hhubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj	hhhj(	hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjj-
jëuh)h=hhhhÍhj	hNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î"fit_transform() (maui.Maui method)öîmaui.Maui.fit_transformöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî@Maui.fit_transform(X, y=None, X_validation=None, encoder='mean')öh]ö(hl)üö}ö(hî
fit_transformöh]öhî
fit_transformöůöüö}ö(hhhjC
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhj?
hhhîP/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.fit_transformöhNubh|)üö}ö(hî,X, y=None, X_validation=None, encoder='mean'öh]ö(hé)üö}ö(hj/	h]öhîXöůöüö}ö(hhhjV
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjR
ubhé)üö}ö(hîy=Noneöh]öhîy=Noneöůöüö}ö(hhhjc
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjR
ubhé)üö}ö(hîX_validation=Noneöh]öhîX_validation=Noneöůöüö}ö(hhhjq
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjR
ubhé)üö}ö(hîencoder='mean'öh]öhîencoder='mean'öůöüö}ö(hhhj
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjR
ubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hj?
hhhjQ
hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhjÖ
ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhjľ
ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.fit_transformöîrefdocöh└uh)hťhjô
ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhj?
hhhNhNubeh}ö(h]öj:
ah!]öh#]öj:
ah%]öh']öh¤ëhđîmauiöhĎhohËj▓
uh)hBhj<
hhhjQ
hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîSTrain autoencoder model, and return the latent factor representation
of the data X.öh]öhîSTrain autoencoder model, and return the latent factor representation
of the data X.öůöüö}ö(hjă
hj┼
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîP/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.fit_transformöhKhj┬
hhubh¨)üö}ö(hhh]ö(h■)üö}ö(hîÎX:  dict with multi-modal dataframes, containing training data, e.g.
{'mRNA': df1, 'SNP': df2},
df1, df2, etc. are (n_samples, n_features) pandas.DataFrame's.
The sample names must match, the feature names need not.öh]ö(j)üö}ö(hîDX:  dict with multi-modal dataframes, containing training data, e.g.öh]öhîDX:  dict with multi-modal dataframes, containing training data, e.g.öůöüö}ö(hjŢ
hj█
ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjË
hKhjÎ
ubj)üö}ö(hhh]öh┌)üö}ö(hîĺ{'mRNA': df1, 'SNP': df2},
df1, df2, etc. are (n_samples, n_features) pandas.DataFrame's.
The sample names must match, the feature names need not.öh]öhîť{ÔÇśmRNAÔÇÖ: df1, ÔÇśSNPÔÇÖ: df2},
df1, df2, etc. are (n_samples, n_features) pandas.DataFrameÔÇÖs.
The sample names must match, the feature names need not.öůöüö}ö(hjţ
hjý
ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjË
hKhjÚ
ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjÎ
ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjË
hKhjď
ubh■)üö}ö(hîőX_validation: optional, dict with multi-modal dataframes, containing validation data
will be used to compute validation loss under trainingöh]ö(j)üö}ö(hîTX_validation: optional, dict with multi-modal dataframes, containing validation dataöh]öhîTX_validation: optional, dict with multi-modal dataframes, containing validation dataöůöüö}ö(hjhj
ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjË
hK
hjubj)üö}ö(hhh]öh┌)üö}ö(hî6will be used to compute validation loss under trainingöh]öhî6will be used to compute validation loss under trainingöůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjË
hKhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjË
hK
hjď
hhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hj┬
hhhjË
hNubh┌)üö}ö(hî
y:  Not used.öh]öhî
y:  Not used.öůöüö}ö(hj=hj;hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjË
hKhj┬
hhubh¨)üö}ö(hhh]öh■)üö}ö(hîXz:  DataFrame (n_samples, n_latent_factors)
Latent factors representation of the data X.öh]ö(j)üö}ö(hî+z:  DataFrame (n_samples, n_latent_factors)öh]öhî+z:  DataFrame (n_samples, n_latent_factors)öůöüö}ö(hjRhjPubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjË
hKhjLubj)üö}ö(hhh]öh┌)üö}ö(hî,Latent factors representation of the data X.öh]öhî,Latent factors representation of the data X.öůöüö}ö(hjchjaubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjË
hKhj^ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjLubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjË
hKhjIubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hj┬
hhhjË
hNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj<
hhhjQ
hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjjÄjëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î'get_linear_weights() (maui.Maui method)öîmaui.Maui.get_linear_weightsöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hîMaui.get_linear_weights()öh]ö(hl)üö}ö(hîget_linear_weightsöh]öhîget_linear_weightsöůöüö}ö(hhhjĄhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjáhhhîU/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.get_linear_weightsöhNubh|)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjáhhhj▓hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj┬ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj┐ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.get_linear_weightsöîrefdocöh└uh)hťhj╝ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjáhhhNhNubeh}ö(h]öjŤah!]öh#]öjŤah%]öh']öh¤ëhđîmauiöhĎhohËj█uh)hBhjŁhhhj▓hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hî├Get linear model coefficients obtained from fitting linear models
predicting feature values from latent factors. One model is fit per latent
factor, and the coefficients are stored in the matrix.öh]öhî├Get linear model coefficients obtained from fitting linear models
predicting feature values from latent factors. One model is fit per latent
factor, and the coefficients are stored in the matrix.öůöüö}ö(hjhjţhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîU/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.get_linear_weightsöhKhjŰhhubh¨)üö}ö(hhh]öh■)üö}ö(hîÜW:  (n_features, n_latent_factors) DataFrame
w_{ij} is the coefficient associated with feature `i` in a linear model
predicting it from latent factor `j`.öh]ö(j)üö}ö(hî,W:  (n_features, n_latent_factors) DataFrameöh]öhî,W:  (n_features, n_latent_factors) DataFrameöůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjŘhKhjubj)üö}ö(hhh]öh┌)üö}ö(hîmw_{ij} is the coefficient associated with feature `i` in a linear model
predicting it from latent factor `j`.öh]ö(hî2w_{ij} is the coefficient associated with feature öůöüö}ö(hî2w_{ij} is the coefficient associated with feature öhjubj2)üö}ö(hî`i`öh]öhîiöůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hjubhî4 in a linear model
predicting it from latent factor öůöüö}ö(hî4 in a linear model
predicting it from latent factor öhjubj2)üö}ö(hî`j`öh]öhîjöůöüö}ö(hhhj1ubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hjubhî.öůöüö}ö(hjXhjubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjŘhKhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjŘhKhjřubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hjŰhhhjŘhNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhjŁhhhj▓hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjjhjëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î load() (maui.Maui static method)öîmaui.Maui.loadöhNtöauh)h,hhÍhhhîG/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.loadöhNubh>)üö}ö(hhh]ö(hC)üö}ö(hîMaui.load(dir)öh]ö(hI)üö}ö(hîstatic öh]öhîstatic öůöüö}ö(hhhjhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hHhj{hhhîG/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.loadöhNubhl)üö}ö(hîloadöh]öhîloadöůöüö}ö(hhhjÄhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhj{hhhjŹhNubh|)üö}ö(hîdiröh]öhé)üö}ö(hîdiröh]öhîdiröůöüö}ö(hhhjáubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjťubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hj{hhhjŹhNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj║ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhjĚubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöî	Maui.loadöîrefdocöh└uh)hťhj┤ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhj{hhhNhNubeh}ö(h]öjuah!]öh#]öjuah%]öh']öh¤ëhđîmauiöhĎhohËjËuh)hBhjxhhhjŹhNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîHLoad a maui model from disk, which was previously saved using ``save()``öh]ö(hî>Load a maui model from disk, which was previously saved using öůöüö}ö(hî>Load a maui model from disk, which was previously saved using öhjŠhhhNhNubj║)üö}ö(hî
``save()``öh]öhîsave()öůöüö}ö(hhhj´ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjŠubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjwhKhjŃhhubh┌)üö}ö(hî7dir:    The directory from which to load the maui modelöh]öhî7dir:    The directory from which to load the maui modelöůöüö}ö(hj
hj
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjwhKhjŃhhubh┌)üö}ö(hî:maui_model: a maui model that was previously saved to disköh]öhî:maui_model: a maui model that was previously saved to disköůöüö}ö(hj
hj
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjwhKhjŃhhubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhjxhhhjŹhNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîstaticmethodöjj,
jëuh)h=hhhhÍhjwhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î1merge_similar_latent_factors() (maui.Maui method)öî&maui.Maui.merge_similar_latent_factorsöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî╩Maui.merge_similar_latent_factors(distance_in='z', distance_metric='correlation', linkage_method='complete', distance_threshold=0.17, merge_fn=<function mean>, plot_dendrogram=True, plot_dendro_ax=None)öh]ö(hl)üö}ö(hîmerge_similar_latent_factorsöh]öhîmerge_similar_latent_factorsöůöüö}ö(hhhjB
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhj>
hhhî_/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.merge_similar_latent_factorsöhNubh|)üö}ö(hîždistance_in='z', distance_metric='correlation', linkage_method='complete', distance_threshold=0.17, merge_fn=<function mean>, plot_dendrogram=True, plot_dendro_ax=Noneöh]ö(hé)üö}ö(hîdistance_in='z'öh]öhîdistance_in='z'öůöüö}ö(hhhjU
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubhé)üö}ö(hîdistance_metric='correlation'öh]öhîdistance_metric='correlation'öůöüö}ö(hhhjc
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubhé)üö}ö(hîlinkage_method='complete'öh]öhîlinkage_method='complete'öůöüö}ö(hhhjq
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubhé)üö}ö(hîdistance_threshold=0.17öh]öhîdistance_threshold=0.17öůöüö}ö(hhhj
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubhé)üö}ö(hîmerge_fn=<function mean>öh]öhîmerge_fn=<function mean>öůöüö}ö(hhhjŹ
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubhé)üö}ö(hîplot_dendrogram=Trueöh]öhîplot_dendrogram=Trueöůöüö}ö(hhhjŤ
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubhé)üö}ö(hîplot_dendro_ax=Noneöh]öhîplot_dendro_ax=Noneöůöüö}ö(hhhję
ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjQ
ubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hj>
hhhjP
hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj├
ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj└
ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöî!Maui.merge_similar_latent_factorsöîrefdocöh└uh)hťhjŻ
ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhj>
hhhNhNubeh}ö(h]öj9
ah!]öh#]öj9
ah%]öh']öh¤ëhđîmauiöhĎhohËj▄
uh)hBhj;
hhhjP
hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîąMerge latent factorz in z whose distance is below a certain threshold.
Used to squeeze down latent factor representations if there are many co-linear
latent factors.öh]öhîąMerge latent factorz in z whose distance is below a certain threshold.
Used to squeeze down latent factor representations if there are many co-linear
latent factors.öůöüö}ö(hj˝
hj´
hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hî_/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.merge_similar_latent_factorsöhKhjý
hhubh¨)üö}ö(hhh]ö(h■)üö}ö(hîĂdistance_in:        If 'z', latent factors will be merged based on their distance
to each other in 'z'. If 'w', favtors will be merged based
on their distance in 'w' (see :func:`get_linear_weights`)öh]ö(j)üö}ö(hîQdistance_in:        If 'z', latent factors will be merged based on their distanceöh]öhîUdistance_in:        If ÔÇśzÔÇÖ, latent factors will be merged based on their distanceöůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hKhjubj)üö}ö(hhh]öh┌)üö}ö(hîtto each other in 'z'. If 'w', favtors will be merged based
on their distance in 'w' (see :func:`get_linear_weights`)öh]ö(hîeto each other in ÔÇśzÔÇÖ. If ÔÇśwÔÇÖ, favtors will be merged based
on their distance in ÔÇśwÔÇÖ (see öůöüö}ö(hîYto each other in 'z'. If 'w', favtors will be merged based
on their distance in 'w' (see öhjubhŁ)üö}ö(hî:func:`get_linear_weights`öh]öj║)üö}ö(hj!h]öhîget_linear_weights()öůöüö}ö(hhhj#ubah}ö(h]öh!]ö(îxreföîpyöîpy-funcöeh#]öh%]öh']öuh)j╣hjubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöîfuncöî	refdomainöj.îrefexplicitöëî	py:moduleöjŰ
îpy:classöhoî	reftargetöîget_linear_weightsöîrefdocöh└îrefwarnöëuh)hťhjř
hKhjubhî)öůöüö}ö(hj═hjubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hKhj■
ubh■)üö}ö(hîÄdistance_metric:    The distance metric based on which to merge latent factors.
One which is supported by :func:`scipy.spatial.distance.pdist`öh]ö(j)üö}ö(hîOdistance_metric:    The distance metric based on which to merge latent factors.öh]öhîOdistance_metric:    The distance metric based on which to merge latent factors.öůöüö}ö(hj_hj]ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hK
hjYubj)üö}ö(hhh]öh┌)üö}ö(hî>One which is supported by :func:`scipy.spatial.distance.pdist`öh]ö(hîOne which is supported by öůöüö}ö(hîOne which is supported by öhjnubhŁ)üö}ö(hî$:func:`scipy.spatial.distance.pdist`öh]öj║)üö}ö(hjyh]öhîscipy.spatial.distance.pdist()öůöüö}ö(hhhj{ubah}ö(h]öh!]ö(j-îpyöîpy-funcöeh#]öh%]öh']öuh)j╣hjwubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöîfuncöî	refdomainöjůîrefexplicitöëj=jŰ
j>hoj?îscipy.spatial.distance.pdistöjAh└jBëuh)hťhjř
hKhjnubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhjkubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjYubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hK
hj■
hhubh■)üö}ö(hîëlinkage_method:     The linkage method used to cluster latent factors. One which
is supported by :func:`scipy.cluster.hierarchy.linkage`.öh]ö(j)üö}ö(hîPlinkage_method:     The linkage method used to cluster latent factors. One whichöh]öhîPlinkage_method:     The linkage method used to cluster latent factors. One whichöůöüö}ö(hjşhjźubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hKhjžubj)üö}ö(hhh]öh┌)üö}ö(hî8is supported by :func:`scipy.cluster.hierarchy.linkage`.öh]ö(hîis supported by öůöüö}ö(hîis supported by öhj╝ubhŁ)üö}ö(hî':func:`scipy.cluster.hierarchy.linkage`öh]öj║)üö}ö(hjăh]öhî!scipy.cluster.hierarchy.linkage()öůöüö}ö(hhhj╔ubah}ö(h]öh!]ö(j-îpyöîpy-funcöeh#]öh%]öh']öuh)j╣hj┼ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöîfuncöî	refdomainöjËîrefexplicitöëj=jŰ
j>hoj?îscipy.cluster.hierarchy.linkageöjAh└jBëuh)hťhjř
hK
hj╝ubhî.öůöüö}ö(hjXhj╝ubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hK
hj╣ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjžubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hKhj■
hhubh■)üö}ö(hîTdistance_threshold: Latent factors with distance below this threshold
will be mergedöh]ö(j)üö}ö(hîEdistance_threshold: Latent factors with distance below this thresholdöh]öhîEdistance_threshold: Latent factors with distance below this thresholdöůöüö}ö(hj hjřubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hKhj¨ubj)üö}ö(hhh]öh┌)üö}ö(hîwill be mergedöh]öhîwill be mergedöůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj¨ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hKhj■
hhubh■)üö}ö(hî╣merge_fn:           Function used to determine value of merged latent factor.
The default is :func:`numpy.mean`, meaning the merged
latent factor will have the mean value of the inputs.öh]ö(j)üö}ö(hîMmerge_fn:           Function used to determine value of merged latent factor.öh]öhîMmerge_fn:           Function used to determine value of merged latent factor.öůöüö}ö(hj.hj,ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hKhj(ubj)üö}ö(hhh]öh┌)üö}ö(hîkThe default is :func:`numpy.mean`, meaning the merged
latent factor will have the mean value of the inputs.öh]ö(hîThe default is öůöüö}ö(hîThe default is öhj=ubhŁ)üö}ö(hî:func:`numpy.mean`öh]öj║)üö}ö(hjHh]öhînumpy.mean()öůöüö}ö(hhhjJubah}ö(h]öh!]ö(j-îpyöîpy-funcöeh#]öh%]öh']öuh)j╣hjFubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöîfuncöî	refdomainöjTîrefexplicitöëj=jŰ
j>hoj?î
numpy.meanöjAh└jBëuh)hťhjř
hKhj=ubhîJ, meaning the merged
latent factor will have the mean value of the inputs.öůöüö}ö(hîJ, meaning the merged
latent factor will have the mean value of the inputs.öhj=ubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhj:ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj(ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hKhj■
hhubh■)üö}ö(hî}plot_dendrogram:    Boolean. If true, a dendrogram will be plotted showing
which latent factors are merged and the threshold.öh]ö(j)üö}ö(hîJplot_dendrogram:    Boolean. If true, a dendrogram will be plotted showingöh]öhîJplot_dendrogram:    Boolean. If true, a dendrogram will be plotted showingöůöüö}ö(hjühjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hKhj{ubj)üö}ö(hhh]öh┌)üö}ö(hî2which latent factors are merged and the threshold.öh]öhî2which latent factors are merged and the threshold.öůöüö}ö(hjĺhjÉubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhjŹubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj{ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hKhj■
hhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hjý
hhhjř
hNubh┌)üö}ö(hîQplot_dendro_ax:     A matplotlib axis object to plot the dendrogram on (optional)öh]öhîQplot_dendro_ax:     A matplotlib axis object to plot the dendrogram on (optional)öůöüö}ö(hj▓hj░hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhjý
hhubh¨)üö}ö(hhh]öh■)üö}ö(hîez:                  (n_samples, n_factors) pd.DataFrame of latent factors
where some have been mergedöh]ö(j)üö}ö(hîIz:                  (n_samples, n_factors) pd.DataFrame of latent factorsöh]öhîIz:                  (n_samples, n_factors) pd.DataFrame of latent factorsöůöüö}ö(hjăhj┼ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjř
hKhj┴ubj)üö}ö(hhh]öh┌)üö}ö(hîwhere some have been mergedöh]öhîwhere some have been mergedöůöüö}ö(hjěhjÍubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjř
hKhjËubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj┴ubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjř
hKhjżubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hjý
hhhjř
hNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj;
hhhjP
hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjjjëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9îsave() (maui.Maui method)öîmaui.Maui.saveöhNtöauh)h,hhÍhhhîG/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.saveöhNubh>)üö}ö(hhh]ö(hC)üö}ö(hîMaui.save(destdir)öh]ö(hl)üö}ö(hîsaveöh]öhîsaveöůöüö}ö(hhhjhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjhhhîG/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.saveöhNubh|)üö}ö(hîdestdiröh]öhé)üö}ö(hîdestdiröh]öhîdestdiröůöüö}ö(hhhj-ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj)ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjhhhj(hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhjGubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhjDubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöî	Maui.saveöîrefdocöh└uh)hťhjAubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjhhhNhNubeh}ö(h]öjah!]öh#]öjah%]öh']öh¤ëhđîmauiöhĎhohËj`uh)hBhjhhhj(hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîLSave a maui model to disk, so that it may be reloaded later using ``load()``öh]ö(hîBSave a maui model to disk, so that it may be reloaded later using öůöüö}ö(hîBSave a maui model to disk, so that it may be reloaded later using öhjshhhNhNubj║)üö}ö(hî
``load()``öh]öhîload()öůöüö}ö(hhhj|ubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjsubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjphhubh┌)üö}ö(hî>destdir:    destination directory in which to save model filesöh]öhî>destdir:    destination directory in which to save model filesöůöüö}ö(hjĺhjÉhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhKhjphhubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhjhhhj(hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjjźjëuh)h=hhhhÍhjhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9î,select_clinical_factors() (maui.Maui method)öî!maui.Maui.select_clinical_factorsöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî{Maui.select_clinical_factors(survival, duration_column='duration', observed_column='observed', alpha=0.05, cox_penalizer=0)öh]ö(hl)üö}ö(hîselect_clinical_factorsöh]öhîselect_clinical_factorsöůöüö}ö(hhhj┴hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjŻhhhîZ/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.select_clinical_factorsöhNubh|)üö}ö(hî]survival, duration_column='duration', observed_column='observed', alpha=0.05, cox_penalizer=0öh]ö(hé)üö}ö(hîsurvivalöh]öhîsurvivalöůöüö}ö(hhhjďubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjđubhé)üö}ö(hîduration_column='duration'öh]öhîduration_column='duration'öůöüö}ö(hhhjÔubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjđubhé)üö}ö(hîobserved_column='observed'öh]öhîobserved_column='observed'öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjđubhé)üö}ö(hî
alpha=0.05öh]öhî
alpha=0.05öůöüö}ö(hhhj■ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjđubhé)üö}ö(hîcox_penalizer=0öh]öhîcox_penalizer=0öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühjđubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjŻhhhj¤hNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhj&ubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhj#ubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.select_clinical_factorsöîrefdocöh└uh)hťhj ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjŻhhhNhNubeh}ö(h]öjŞah!]öh#]öjŞah%]öh']öh¤ëhđîmauiöhĎhohËj?uh)hBhj║hhhj¤hNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hX'Select latent factors which are predictive of survival. This is
accomplished by fitting a Cox Proportional Hazards (CPH) model to each
latent factor, while controlling for known covariates, and only keeping
those latent factors whose coefficient in the CPH is nonzero (adjusted
p-value < alpha).öh]öhX'Select latent factors which are predictive of survival. This is
accomplished by fitting a Cox Proportional Hazards (CPH) model to each
latent factor, while controlling for known covariates, and only keeping
those latent factors whose coefficient in the CPH is nonzero (adjusted
p-value < alpha).öůöüö}ö(hjThjRhhhNhNubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîZ/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.select_clinical_factorsöhKhjOhhubh¨)üö}ö(hhh]ö(h■)üö}ö(hîÇsurvival:           pd.DataFrame of survival information and relevant covariates
(such as sex, age at diagnosis, or tumor stage)öh]ö(j)üö}ö(hîPsurvival:           pd.DataFrame of survival information and relevant covariatesöh]öhîPsurvival:           pd.DataFrame of survival information and relevant covariatesöůöüö}ö(hjjhjhubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj`hK	hjdubj)üö}ö(hhh]öh┌)üö}ö(hî/(such as sex, age at diagnosis, or tumor stage)öh]öhî/(such as sex, age at diagnosis, or tumor stage)öůöüö}ö(hj{hjyubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj`hK
hjvubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjdubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj`hK	hjaubh■)üö}ö(hîćduration_column:    the name of the column in ``survival`` containing the
duration (time between diagnosis and death or last followup)öh]ö(j)üö}ö(hîIduration_column:    the name of the column in ``survival`` containing theöh]ö(hî.duration_column:    the name of the column in öůöüö}ö(hî.duration_column:    the name of the column in öhjŚubj║)üö}ö(hî``survival``öh]öhîsurvivalöůöüö}ö(hhhjáubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjŚubhî containing theöůöüö}ö(hî containing theöhjŚubeh}ö(h]öh!]öh#]öh%]öh']öuh)jhj`hKhjôubj)üö}ö(hhh]öh┌)üö}ö(hî<duration (time between diagnosis and death or last followup)öh]öhî<duration (time between diagnosis and death or last followup)öůöüö}ö(hjżhj╝ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj`hKhj╣ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjôubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj`hKhjahhubh■)üö}ö(hîoobserved_column:    the name of the column in ``survival`` containing
indicating whether time of death is knownöh]ö(j)üö}ö(hîEobserved_column:    the name of the column in ``survival`` containingöh]ö(hî.observed_column:    the name of the column in öůöüö}ö(hî.observed_column:    the name of the column in öhj┌ubj║)üö}ö(hî``survival``öh]öhîsurvivalöůöüö}ö(hhhjŃubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hj┌ubhî containingöůöüö}ö(hî containingöhj┌ubeh}ö(h]öh!]öh#]öh%]öh']öuh)jhj`hK
hjÍubj)üö}ö(hhh]öh┌)üö}ö(hî)indicating whether time of death is knownöh]öhî)indicating whether time of death is knownöůöüö}ö(hjhj ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj`hKhjŘubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjÍubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj`hK
hjahhubh■)üö}ö(hîualpha:              threshold for p-value of CPH coefficients to call a latent
factor clinically relevant (p < alpha)öh]ö(j)üö}ö(hîNalpha:              threshold for p-value of CPH coefficients to call a latentöh]öhîNalpha:              threshold for p-value of CPH coefficients to call a latentöůöüö}ö(hjhjubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj`hKhjubj)üö}ö(hhh]öh┌)üö}ö(hî&factor clinically relevant (p < alpha)öh]öhî&factor clinically relevant (p < alpha)öůöüö}ö(hj0hj.ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj`hKhj+ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhj`hKhjahhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hjOhhhj`hNubh┌)üö}ö(hîXcox_penalizer:      penalty coefficient in Cox PH solver (see ``lifelines.CoxPHFitter``)öh]ö(hî>cox_penalizer:      penalty coefficient in Cox PH solver (see öůöüö}ö(hî>cox_penalizer:      penalty coefficient in Cox PH solver (see öhjNhhhNhNubj║)üö}ö(hî``lifelines.CoxPHFitter``öh]öhîlifelines.CoxPHFitteröůöüö}ö(hhhjWubah}ö(h]öh!]öh#]öh%]öh']öuh)j╣hjNubhî)öůöüö}ö(hj═hjNhhhNhNubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj`hKhjOhhubh¨)üö}ö(hhh]öh■)üö}ö(hî«z_clinical: pd.DataFrame, subset of the latent factors which have been
determined to have clinical value (are individually predictive
of survival, controlling for covariates)öh]ö(j)üö}ö(hîFz_clinical: pd.DataFrame, subset of the latent factors which have beenöh]öhîFz_clinical: pd.DataFrame, subset of the latent factors which have beenöůöüö}ö(hjxhjvubah}ö(h]öh!]öh#]öh%]öh']öuh)jhj`hKhjrubj)üö}ö(hhh]öh┌)üö}ö(hîgdetermined to have clinical value (are individually predictive
of survival, controlling for covariates)öh]öhîgdetermined to have clinical value (are individually predictive
of survival, controlling for covariates)öůöüö}ö(hjëhjçubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj`hKhjäubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjrubeh}ö(h]öh!]öĽęUh#]öh%]öh']öuh)hřhj`hKhjoubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hjOhhhj`hNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj║hhhj¤hNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjj┤jëuh)h=hhhhÍhNhNubh-)üö}ö(hhh]öh}ö(h]öh!]öh#]öh%]öh']öîentriesö]ö(h9îtransform() (maui.Maui method)öîmaui.Maui.transformöhNtöauh)h,hhÍhhhNhNubh>)üö}ö(hhh]ö(hC)üö}ö(hî!Maui.transform(X, encoder='mean')öh]ö(hl)üö}ö(hî	transformöh]öhî	transformöůöüö}ö(hhhj╩hhhNhNubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hkhjĂhhhîL/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.transformöhNubh|)üö}ö(hîX, encoder='mean'öh]ö(hé)üö}ö(hj/	h]öhîXöůöüö}ö(hhhjŢubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj┘ubhé)üö}ö(hîencoder='mean'öh]öhîencoder='mean'öůöüö}ö(hhhjŕubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)hühj┘ubeh}ö(h]öh!]öh#]öh%]öh']öhXhYuh)h{hjĂhhhjěhNubhś)üö}ö(hhh]öhŁ)üö}ö(hhh]öhó)üö}ö(hhh]öhî[source]öůöüö}ö(hhhjubah}ö(h]öh!]öhşah#]öh%]öh']öuh)híhjubah}ö(h]öh!]öh#]öh%]öh']öîreftypeöhŞî	refdomainöh║îrefexplicitöëî	reftargetöî_modules/maui/modelöîrefidöîMaui.transformöîrefdocöh└uh)hťhj■ubah}ö(h]öh!]öh#]öh%]öh']öîexpröh╚uh)hŚhjĂhhhNhNubeh}ö(h]öj┴ah!]öh#]öj┴ah%]öh']öh¤ëhđîmauiöhĎhohËjuh)hBhj├hhhjěhNubhŇ)üö}ö(hhh]ö(h┌)üö}ö(hîŐTransform X into the latent space that was previously learned using
`fit` or `fit_transform`, and return the latent factor representation.öh]ö(hîDTransform X into the latent space that was previously learned using
öůöüö}ö(hîDTransform X into the latent space that was previously learned using
öhj0hhhNhNubj2)üö}ö(hî`fit`öh]öhîfitöůöüö}ö(hhhj9ubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hj0ubhî or öůöüö}ö(hî or öhj0hhhNhNubj2)üö}ö(hî`fit_transform`öh]öhî
fit_transformöůöüö}ö(hhhjLubah}ö(h]öh!]öh#]öh%]öh']öuh)j1hj0ubhî., and return the latent factor representation.öůöüö}ö(hî., and return the latent factor representation.öhj0hhhNhNubeh}ö(h]öh!]öh#]öh%]öh']öuh)h┘hîL/home/jona/work/phd/maui/maui/maui/model.py:docstring of maui.Maui.transformöhKhj-hhubh¨)üö}ö(hhh]ö(h■)üö}ö(hîŽX:          dict with multi-modal dataframes, containing training data, e.g.
{'mRNA': df1, 'SNP': df2},
df1, df2, etc. are (n_features, n_samples) pandas.DataFrame's.öh]ö(j)üö}ö(hîLX:          dict with multi-modal dataframes, containing training data, e.g.öh]öhîLX:          dict with multi-modal dataframes, containing training data, e.g.öůöüö}ö(hjohjmubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjehKhjiubj)üö}ö(hhh]öh┌)üö}ö(hîY{'mRNA': df1, 'SNP': df2},
df1, df2, etc. are (n_features, n_samples) pandas.DataFrame's.öh]öhîc{ÔÇśmRNAÔÇÖ: df1, ÔÇśSNPÔÇÖ: df2},
df1, df2, etc. are (n_features, n_samples) pandas.DataFrameÔÇÖs.öůöüö}ö(hjÇhj~ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjehKhj{ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjiubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjehKhjfubh■)üö}ö(hXCencoder:    the mode of the encoder to be used. one of 'mean' or 'sample',
where 'mean' indicates the encoder network only uses the mean
estimates for each successive layer. 'sample' indicates the
encoder should sample from the distribution specified from each
successive layer, and results in non-reproducible embeddings.
öh]ö(j)üö}ö(hîJencoder:    the mode of the encoder to be used. one of 'mean' or 'sample',öh]öhîRencoder:    the mode of the encoder to be used. one of ÔÇśmeanÔÇÖ or ÔÇśsampleÔÇÖ,öůöüö}ö(hj×hjťubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjehK
hjśubj)üö}ö(hhh]öh┌)üö}ö(hî¸where 'mean' indicates the encoder network only uses the mean
estimates for each successive layer. 'sample' indicates the
encoder should sample from the distribution specified from each
successive layer, and results in non-reproducible embeddings.öh]öhî where ÔÇśmeanÔÇÖ indicates the encoder network only uses the mean
estimates for each successive layer. ÔÇśsampleÔÇÖ indicates the
encoder should sample from the distribution specified from each
successive layer, and results in non-reproducible embeddings.öůöüö}ö(hj»hjşubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjehK
hj¬ubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjśubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjehK
hjfhhubeh}ö(h]öh!]öh#]öh%]öh']öuh)h°hj-hhhjehNubh¨)üö}ö(hhh]öh■)üö}ö(hîXz:  DataFrame (n_samples, n_latent_factors)
Latent factors representation of the data X.öh]ö(j)üö}ö(hî+z:  DataFrame (n_samples, n_latent_factors)öh]öhî+z:  DataFrame (n_samples, n_latent_factors)öůöüö}ö(hjÍhjďubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjehKhjđubj)üö}ö(hhh]öh┌)üö}ö(hî,Latent factors representation of the data X.öh]öhî,Latent factors representation of the data X.öůöüö}ö(hjšhjňubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjehKhjÔubah}ö(h]öh!]öh#]öh%]öh']öuh)jhjđubeh}ö(h]öh!]öh#]öh%]öh']öuh)hřhjehKhj═ubah}ö(h]öh!]öh#]öh%]öh']öuh)h°hj-hhhjehNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhj├hhhjěhNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîmethodöjjjëuh)h=hhhhÍhNhNubeh}ö(h]öh!]öh#]öh%]öh']öuh)hďhh?hhhhZhNubeh}ö(h]öh!]öh#]öh%]öh']öjîpyöjîclassöjj jëuh)h=hhhhhNhNubeh}ö(h]öîthe-maui-classöah!]öh#]öîthe maui classöah%]öh']öuh)h	hhhhhh*hKubah}ö(h]öh!]öh#]öh%]öh']öîsourceöh*uh)hîcurrent_sourceöNîcurrent_lineöNîsettingsöîdocutils.frontendöîValuesöôö)üö}ö(hNî	generatoröNî	datestampöNîsource_linköNî
source_urlöNî
toc_backlinksöîentryöîfootnote_backlinksöKî
sectnum_xformöKîstrip_commentsöNîstrip_elements_with_classesöNî
strip_classesöNîreport_levelöKî
halt_levelöKîexit_status_levelöKîdebugöNîwarning_streamöNî	tracebacköłîinput_encodingöî	utf-8-sigöîinput_encoding_error_handleröîstrictöîoutput_encodingöîutf-8öîoutput_encoding_error_handleröjLîerror_encodingöîUTF-8öîerror_encoding_error_handleröîbackslashreplaceöî
language_codeöîenöîrecord_dependenciesöNîconfigöNî	id_prefixöhîauto_id_prefixöîidöî
dump_settingsöNîdump_internalsöNîdump_transformsöNîdump_pseudo_xmlöNîexpose_internalsöNîstrict_visitoröNî_disable_configöNî_sourceöh*î_destinationöNî
_config_filesö]öîpep_referencesöNîpep_base_urlöî https://www.python.org/dev/peps/öîpep_file_url_templateöîpep-%04döîrfc_referencesöNîrfc_base_urlöîhttps://tools.ietf.org/html/öî	tab_widthöKîtrim_footnote_reference_spaceöëîfile_insertion_enabledöłîraw_enabledöKîsyntax_highlightöîlongöîsmart_quotesöłîsmartquotes_localesö]öîcharacter_level_inline_markupöëîdoctitle_xformöëî
docinfo_xformöKîsectsubtitle_xformöëîembed_stylesheetöëîcloak_email_addressesöłîenvöNubîreporteröNîindirect_targetsö]öîsubstitution_defsö}öîsubstitution_namesö}öîrefnamesö}öîrefidsö}öînameidsö}ö(j&j#h;h;jjjjjşjşjëjëjĂjĂj	j	j:
j:
jŤjŤjujuj9
j9
jjjŞjŞj┴j┴uî	nametypesö}ö(j&Nh;łjłjłjşłjëłjĂłj	łj:
łjŤłjułj9
łjłjŞłj┴łuh}ö(j#hh;hDjjjjjşj│jGhîsystem_messageöôö)üö}ö(hhh]öh┌)üö}ö(hî.Inline strong start-string without end-string.öh]öhî.Inline strong start-string without end-string.öůöüö}ö(hhhjôubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjÉubah}ö(h]öjGah!]öh#]öh%]öh']öjAaîlevelöKîtypeöîWARNINGöîlineöKîsourceöj»uh)jÄhjhhhj»hKubjAj7jëjÄjZjĆ)üö}ö(hhh]öh┌)üö}ö(hî.Inline strong start-string without end-string.öh]öhî.Inline strong start-string without end-string.öůöüö}ö(hhhj»ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjČubah}ö(h]öjZah!]öh#]öh%]öh']öjTaîlevelöKîtypeöjęîlineöK
îsourceöj@uh)jÄhj§hhhj@hKubjTjJjĂj╦j	j	j:
j?
jŤjájuj{j9
j>
jjjŞjŻj┴jĂuî
footnote_refsö}öî
citation_refsö}öî
autofootnotesö]öîautofootnote_refsö]öîsymbol_footnotesö]öîsymbol_footnote_refsö]öî	footnotesö]öî	citationsö]öîautofootnote_startöKîsymbol_footnote_startöKîid_startöKîparse_messagesö]ö(jĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj▀ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj▄ubhî
literal_blocköôö)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhj´ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj▄hhÚubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöîSEVEREöîsourceöhÚîlineöKuh)jÄhhÍhhhhÚhKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjhjpubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjpîlineöKuh)jÄhj_hhhjphKubjĆ)üö}ö(hhh]öh┌)üö}ö(hîUnexpected indentation.öh]öhîUnexpected indentation.öůöüö}ö(hhhj4ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj1ubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöîERRORöîsourceöjpîlineöKuh)jÄhj_hhhjphKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî;Block quote ends without a blank line; unexpected unindent.öh]öhî;Block quote ends without a blank line; unexpected unindent.öůöüö}ö(hhhjPubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjMubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöK	îsourceöjpuh)jÄhj_hhhjphNubjĆ)üö}ö(hhh]öh┌)üö}ö(hî?Definition list ends without a blank line; unexpected unindent.öh]öhî?Definition list ends without a blank line; unexpected unindent.öůöüö}ö(hhhjkubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjhubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjpuh)jÄhj_hhhjphKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjćubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjâubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhjöubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjâhjpubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjpîlineöKuh)jÄhj_hhhjphKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj»ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjČubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjŻubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjČhjubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjîlineöKuh)jÄhjĂhhhjhKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî?Definition list ends without a blank line; unexpected unindent.öh]öhî?Definition list ends without a blank line; unexpected unindent.öůöüö}ö(hhhjěubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjŇubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjuh)jÄhjĂhhhjhK
ubjĆ)üö}ö(hhh]öh┌)üö}ö(hîUnexpected indentation.öh]öhîUnexpected indentation.öůöüö}ö(hhhjˇubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjJîsourceöjîlineöKuh)jÄhjĂhhhjhKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî;Block quote ends without a blank line; unexpected unindent.öh]öhî;Block quote ends without a blank line; unexpected unindent.öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjuh)jÄhjĂhhhjhNubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj)ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj&ubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhj7ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj&hjubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjîlineöKuh)jÄhjĂhhhjhKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjRubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjOubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhj`ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjOhj»ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj»îlineöKuh)jÄhjhhhj»hKubjÉjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj{ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjxubjţ)üö}ö(hîReturns:
--------öh]öhîReturns:
--------öůöüö}ö(hhhjëubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjxhj»ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj»îlineöK
uh)jÄhjhhhj»hK
ubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjĄubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjíubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhj▓ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjíhj@ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj@îlineöK	uh)jÄhj§hhhj@hK	ubjČjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj═ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj╩ubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhj█ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj╩hj@ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj@îlineöKuh)jÄhj§hhhj@hKubjĆ)üö}ö(hhh]öh┌)üö}ö(hhh]öhî┴duplicate object description of maui.Maui.drop_unexplanatory_factors, other instance in /home/jona/work/phd/maui/maui/doc/filtering-and-merging-latent-factors.rst, use :noindex: for one of themöůöüö}ö(hhhj÷ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjˇubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjŢuh)jÄubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj
ubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj
hj_ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj_îlineöKuh)jÄhj%hhhj_hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj9ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj6ubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhjGubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj6hj_ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj_îlineöK
uh)jÄhj%hhhj_hK
ubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjbubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj_ubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjpubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj_hj	ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj	îlineöKuh)jÄhjî	hhhj	hKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî?Definition list ends without a blank line; unexpected unindent.öh]öhî?Definition list ends without a blank line; unexpected unindent.öůöüö}ö(hhhjőubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjłubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöj	uh)jÄhjî	hhhj	hK
ubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjŽubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjúubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhj┤ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjúhj	ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj	îlineöKuh)jÄhjî	hhhj	hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj¤ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj╠ubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjŢubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj╠hjË
ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjË
îlineöKuh)jÄhj┬
hhhjË
hKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî?Definition list ends without a blank line; unexpected unindent.öh]öhî?Definition list ends without a blank line; unexpected unindent.öůöüö}ö(hhhj°ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj§ubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjË
uh)jÄhj┬
hhhjË
hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhj!ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjhjË
ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjË
îlineöKuh)jÄhj┬
hhhjË
hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj<ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj9ubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhjJubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj9hjŘubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjŘîlineöKuh)jÄhjŰhhhjŘhKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjeubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjbubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjsubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjbhjwubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjwîlineöKuh)jÄhjŃhhhjwhKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjÄubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjőubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhjťubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjőhjwubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjwîlineöK	uh)jÄhjŃhhhjwhK	ubjĆ)üö}ö(hhh]öh┌)üö}ö(hhh]öhî├duplicate object description of maui.Maui.merge_similar_latent_factors, other instance in /home/jona/work/phd/maui/maui/doc/filtering-and-merging-latent-factors.rst, use :noindex: for one of themöůöüö}ö(hhhjĚubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj┤ubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjP
uh)jÄubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjĐubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj╬ubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhj▀ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj╬hjř
ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjř
îlineöKuh)jÄhjý
hhhjř
hKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî?Definition list ends without a blank line; unexpected unindent.öh]öhî?Definition list ends without a blank line; unexpected unindent.öůöüö}ö(hhhj˙ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj¸ubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöjř
uh)jÄhjý
hhhjř
hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhj#ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjhjř
ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjř
îlineöKuh)jÄhjý
hhhjř
hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhj>ubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj;ubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjLubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj;hjubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjîlineöKuh)jÄhjphhhjhKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjgubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjdubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjuubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjdhj`ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj`îlineöKuh)jÄhjOhhhj`hKubjĆ)üö}ö(hhh]öh┌)üö}ö(hî?Definition list ends without a blank line; unexpected unindent.öh]öhî?Definition list ends without a blank line; unexpected unindent.öůöüö}ö(hhhjÉubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjŹubah}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjęîlineöKîsourceöj`uh)jÄhjOhhhj`hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjźubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjĘubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhj╣ubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjĘhj`ubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöj`îlineöKuh)jÄhjOhhhj`hKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjďubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hjĐubjţ)üö}ö(hîParameters
----------öh]öhîParameters
----------öůöüö}ö(hhhjÔubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhjĐhjeubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjeîlineöKuh)jÄhj-hhhjehKubjĆ)üö}ö(hhh]ö(h┌)üö}ö(hîUnexpected section title.öh]öhîUnexpected section title.öůöüö}ö(hhhjřubah}ö(h]öh!]öh#]öh%]öh']öuh)h┘hj˙ubjţ)üö}ö(hîReturns
-------öh]öhîReturns
-------öůöüö}ö(hhhjubah}ö(h]öh!]öh#]öh%]öh']öhXhYuh)jÝhj˙hjeubeh}ö(h]öh!]öh#]öh%]öh']öîlevelöKîtypeöjîsourceöjeîlineöKuh)jÄhj-hhhjehKubeîtransform_messagesö]öîtransformeröNî
decorationöNhhub.