Tools

Any transformation of the data matrix that is not preprocessing. In contrast to a preprocessing function, a tool usually adds an easily interpretable annotation to the data matrix, which can then be visualized with a corresponding plotting function.

Embeddings

tools.tsne	Calculates t-SNE [vdMH08], [ADT+13], and [PVG+11].
tools.umap	Embed the neighborhood graph using UMAP [MHM18].
tools.draw_graph	Force-directed graph drawing [IKM+11], [JVHB14], and [Chi18].
tools.diffmap	Diffusion Maps [CLL+05], [HBT15], [WHP+19].
tools.embedding_density	Calculate the density of observation in an embedding (per condition).

Clustering and trajectory inference

tools.leiden	Cluster observations into subgroups [TWvE19].
tools.dendrogram	Computes a hierarchical clustering for the given groupby categories.
tools.dpt	Infer progression of observations through geodesic distance along the graph [HBW+16], [WHP+19].
tools.paga	Mapping out the coarse-grained connectivity structures of complex manifolds [WHP+19].

Feature Ranking

tools.rank_features_groups	Rank features for characterizing groups.
tools.filter_rank_features_groups	Filters out features based on fold change and fraction of features containing the feature within and outside the groupby categories.
tools.rank_features_supervised	Calculate feature importances for predicting a specified feature in adata.var.

Dataset integration

tools.ingest

Map labels and embeddings from reference data to new data.

Survival Analysis

tools.ols	Create an Ordinary Least Squares (OLS) Model from a formula and the data object.
tools.glm	Create a Generalized Linear Model (GLM) from a formula, a distribution, and the data object.
tools.kaplan_meier	Fit the Kaplan-Meier estimate for the survival function.
tools.test_kmf_logrank	Calculates the p-value for the logrank test comparing the survival functions of two groups.
tools.test_nested_f_statistic	Calculate the P value indicating if a larger GLM, encompassing a smaller GLM's parameters, adds explanatory power.
tools.cox_ph	Fit the Cox’s proportional hazard for the survival function.
tools.cox_ph_adjusted_curves	Compute CoxPH adjusted survival curves stratified by a grouping variable.
tools.weibull_aft	Fit the Weibull accelerated failure time regression for the survival function.
tools.log_logistic_aft	Fit the log logistic accelerated failure time regression for the survival function.
tools.nelson_aalen	Employ the Nelson-Aalen estimator to estimate the cumulative hazard function from censored survival data.
tools.weibull	Employ the Weibull model in univariate survival analysis to understand event occurrence dynamics.

Causal Inference

ehrapy ships a small, dependency-light set of causal inference estimators built directly on top of scikit-learn. ATE estimators handle binary treatments via inverse probability of treatment weighting (IPTW), parametric g-computation, the doubly-robust augmented IPW (AIPW), and propensity score matching. Heterogeneous treatment effects (CATE) are available via the T-, S-, and X-learner meta-learners. Two diagnostics — covariate balance and positivity — round out the toolkit.

tools.iptw	Estimate the average treatment effect by inverse probability of treatment weighting (IPTW).
tools.g_computation	Estimate the ATE by parametric g-computation (a.k.a.
tools.aipw	Estimate the ATE by the augmented inverse-probability-weighted (AIPW) doubly robust estimator.
tools.propensity_score_matching	Estimate the treatment effect by 1-to-\(k\) propensity score matching on the logit scale.
tools.t_learner	Two-model (T-learner) CATE estimator.
tools.s_learner	Single-model (S-learner) CATE estimator.
tools.x_learner	X-learner CATE estimator of Künzel et al. (2019).
tools.covariate_balance	Report standardised mean differences (SMD) for each covariate, before and after weighting.
tools.positivity_check	Diagnose the positivity assumption by inspecting the propensity score distribution.
tools.CausalEstimate	Result of a causal effect estimation.

Normalized Complexity Profile

tools.ncp

Non-negative CP (PARAFAC) decomposition of a 3D temporal EHR layer.

Cohort Tracking & summaries

tools.CohortTracker	Track cohort changes over multiple filtering or processing steps.
tools.stratified_table_one	Build a stratified "Table 1" comparing baseline characteristics across groups.