schemas - bossanova

DataFrame schemas for model outputs using Polars Schema.

Provides Polars Schema definitions for type-safe DataFrame construction and validation across model output properties. All column name constants live in the Col namespace class for single-point-of-change renames.

Attributes:

Name	Type	Description
`AugmentedDataCols`
`ComparisonAic`
`ComparisonBic`
`ComparisonCv`
`ComparisonDevianceChi2`
`ComparisonDevianceF`
`ComparisonFTest`
`ComparisonLrt`
`DiagnosticsCvCols`
`DiagnosticsGaussian`
`DiagnosticsGlm`
`DiagnosticsLmer`
`DiagnosticsPredCvCols`
`EffectsAsympCols`
`EffectsBaseCols`
`EffectsBootCols`
`EffectsPermCols`
`MetadataBase`
`MetadataMixed`
`ParamsAsymp`
`ParamsBase`
`ParamsBoot`
`ParamsCv`
`ParamsPerm`
`PowerSummaryCols`
`PredictionsAsymp`
`PredictionsBase`
`PredictionsCv`
`ResamplesRawSchema`
`SimulationsInferCols`
`VaryingCorrSchema`
`VaryingOffsetsBaseCols`
`VaryingOffsetsInferSuffix`
`VaryingParamsBaseCols`
`VaryingSpreadBase`
`VaryingSpreadInfer`
`VifSchema`

Classes:

Name	Description
`Col`	Namespace for all column name constants used across DataFrame outputs.

Attributes¶

AugmentedDataCols¶

AugmentedDataCols = (Col.FITTED, Col.RESID, Col.HAT, Col.STD_RESID, Col.COOKSD)

ComparisonAic¶

ComparisonAic = Schema({Col.MODEL: String, Col.NPAR: Int64, Col.LOGLIK: Float64, Col.DEVIANCE: Float64, Col.AIC_R: Float64, Col.BIC_R: Float64, Col.DELTA_AIC: Float64, Col.WEIGHT: Float64})

ComparisonBic¶

ComparisonBic = Schema({Col.MODEL: String, Col.NPAR: Int64, Col.LOGLIK: Float64, Col.DEVIANCE: Float64, Col.AIC_R: Float64, Col.BIC_R: Float64, Col.DELTA_BIC: Float64, Col.WEIGHT: Float64})

ComparisonCv¶

ComparisonCv = Schema({Col.MODEL: String, Col.PRE_R: Float64, Col.T_STAT: Float64, Col.CV_SCORE: Float64, Col.CV_SE: Float64, Col.DIFF: Float64, Col.DIFF_SE: Float64, Col.P_VALUE: Float64})

ComparisonDevianceChi2¶

ComparisonDevianceChi2 = Schema({Col.MODEL: String, Col.CHI2: Float64, Col.DEV_DIFF: Float64, Col.DEVIANCE: Float64, Col.DF: Float64, Col.DF_RESID: Float64, Col.P_VALUE: Float64})

ComparisonDevianceF¶

ComparisonDevianceF = Schema({Col.MODEL: String, Col.F_STAT: Float64, Col.DEV_DIFF: Float64, Col.DEVIANCE: Float64, Col.DF: Float64, Col.DF_RESID: Float64, Col.P_VALUE: Float64})

ComparisonFTest¶

ComparisonFTest = Schema({Col.MODEL: String, Col.PRE_R: Float64, Col.F_STAT: Float64, Col.RSS: Float64, Col.SS: Float64, Col.DF: Float64, Col.DF_RESID: Float64, Col.P_VALUE: Float64})

ComparisonLrt¶

ComparisonLrt = Schema({Col.MODEL: String, Col.CHI2: Float64, Col.NPAR: Int64, Col.AIC_R: Float64, Col.BIC_R: Float64, Col.LOGLIK: Float64, Col.DEVIANCE: Float64, Col.DF: Int64, Col.P_VALUE: Float64})

DiagnosticsCvCols¶

DiagnosticsCvCols = (Col.CV_RMSE, Col.CV_MAE, Col.CV_RSQUARED, Col.CV_K)

DiagnosticsGaussian¶

DiagnosticsGaussian = Schema({Col.DF_MODEL: Float64, Col.DF_RESID: Float64, Col.RSQUARED: Float64, Col.RSQUARED_ADJ: Float64, Col.FSTATISTIC: Float64, Col.FSTATISTIC_PVALUE: Float64, Col.SIGMA: Float64, Col.NULL_DEVIANCE: Float64, Col.DEVIANCE: Float64, Col.DISPERSION: Float64, Col.PSEUDO_RSQUARED: Float64, Col.AIC: Float64, Col.BIC: Float64, Col.LOGLIK: Float64})

DiagnosticsGlm¶

DiagnosticsGlm = Schema({Col.DF_MODEL: Float64, Col.DF_RESID: Float64, Col.NULL_DEVIANCE: Float64, Col.DEVIANCE: Float64, Col.DISPERSION: Float64, Col.PSEUDO_RSQUARED: Float64, Col.AIC: Float64, Col.BIC: Float64, Col.LOGLIK: Float64})

DiagnosticsLmer¶

DiagnosticsLmer = Schema({Col.DF_MODEL: Float64, Col.DF_RESID: Float64, Col.SIGMA: Float64, Col.DEVIANCE: Float64, Col.RSQUARED_MARGINAL: Float64, Col.RSQUARED_CONDITIONAL: Float64, Col.ICC: Float64, Col.AIC: Float64, Col.BIC: Float64, Col.LOGLIK: Float64})

DiagnosticsPredCvCols¶

DiagnosticsPredCvCols = (Col.CV_RMSE, Col.CV_RMSE_SD, Col.CV_MAE, Col.CV_MAE_SD, Col.CV_RSQUARED, Col.CV_RSQUARED_SD, Col.CV_K)

EffectsAsympCols¶

EffectsAsympCols = (Col.ESTIMATE, Col.SE, Col.CI_LOWER, Col.CI_UPPER, Col.STATISTIC, Col.DF, Col.P_VALUE)

EffectsBaseCols¶

EffectsBaseCols = (Col.ESTIMATE,)

EffectsBootCols¶

EffectsBootCols = (Col.ESTIMATE, Col.SE, Col.CI_LOWER, Col.CI_UPPER, Col.STATISTIC, Col.DF)

EffectsPermCols¶

EffectsPermCols = (Col.ESTIMATE, Col.SE, Col.STATISTIC, Col.DF, Col.P_VALUE)

MetadataBase¶

MetadataBase = Schema({Col.NOBS: Int64, Col.NOBS_TOTAL: Int64, Col.NOBS_MISSING: Int64, Col.NPARAMS: Int64})

MetadataMixed¶

MetadataMixed = Schema({Col.NOBS: Int64, Col.NOBS_TOTAL: Int64, Col.NOBS_MISSING: Int64, Col.NPARAMS: Int64, Col.NGROUPS: Int64})

ParamsAsymp¶

ParamsAsymp = Schema({Col.TERM: String, Col.ESTIMATE: Float64, Col.SE: Float64, Col.CI_LOWER: Float64, Col.CI_UPPER: Float64, Col.STATISTIC: Float64, Col.DF: Float64, Col.P_VALUE: Float64})

ParamsBase¶

ParamsBase = Schema({Col.TERM: String, Col.ESTIMATE: Float64})

ParamsBoot¶

ParamsBoot = Schema({Col.TERM: String, Col.ESTIMATE: Float64, Col.SE: Float64, Col.CI_LOWER: Float64, Col.CI_UPPER: Float64, Col.STATISTIC: Float64, Col.DF: Float64, Col.P_VALUE: Float64})

ParamsCv¶

ParamsCv = Schema({Col.TERM: String, Col.ESTIMATE: Float64, Col.PRE: Float64, Col.PRE_SD: Float64})

ParamsPerm¶

ParamsPerm = Schema({Col.TERM: String, Col.ESTIMATE: Float64, Col.SE: Float64, Col.CI_LOWER: Float64, Col.CI_UPPER: Float64, Col.STATISTIC: Float64, Col.DF: Float64, Col.P_VALUE: Float64})

PowerSummaryCols¶

PowerSummaryCols = (Col.TERM, Col.TRUE_VALUE, Col.POWER, Col.POWER_CI_LOWER, Col.POWER_CI_UPPER, Col.COVERAGE, Col.BIAS, Col.RMSE, Col.MEAN_SE, Col.EMPIRICAL_SE, Col.N_SIMS, Col.N_FAILED)

PredictionsAsymp¶

PredictionsAsymp = Schema({Col.FITTED: Float64, Col.SE: Float64, Col.CI_LOWER: Float64, Col.CI_UPPER: Float64})

PredictionsBase¶

PredictionsBase = Schema({Col.FITTED: Float64})

PredictionsCv¶

PredictionsCv = Schema({Col.FITTED: Float64, Col.CV_FITTED: Float64, Col.CV_RESIDUAL: Float64, Col.CV_FOLD: Int32})

ResamplesRawSchema¶

ResamplesRawSchema = Schema({Col.RESAMPLE: Int64, Col.TERM: String, Col.VALUE: Float64})

SimulationsInferCols¶

SimulationsInferCols = (Col.SIM_MEAN, Col.SIM_SD, Col.SIM_Q025, Col.SIM_Q975)

VaryingCorrSchema¶

VaryingCorrSchema = Schema({Col.GROUP: String, Col.EFFECT1: String, Col.EFFECT2: String, Col.CORR: Float64})

VaryingOffsetsBaseCols¶

VaryingOffsetsBaseCols = (Col.GROUP, Col.LEVEL)

VaryingOffsetsInferSuffix¶

VaryingOffsetsInferSuffix = (Col.PI_LOWER_PREFIX, Col.PI_UPPER_PREFIX)

VaryingParamsBaseCols¶

VaryingParamsBaseCols = (Col.GROUP, Col.LEVEL)

VaryingSpreadBase¶

VaryingSpreadBase = Schema({Col.COMPONENT: String, Col.ESTIMATE: Float64})

VaryingSpreadInfer¶

VaryingSpreadInfer = Schema({Col.COMPONENT: String, Col.ESTIMATE: Float64, Col.CI_LOWER: Float64, Col.CI_UPPER: Float64, Col.CI_METHOD: String})

VifSchema¶

VifSchema = Schema({Col.TERM: String, Col.VIF: Float64, Col.CI_INCREASE_FACTOR: Float64})

Classes¶

Col¶

Namespace for all column name constants used across DataFrame outputs.

Organized by category. Use Col.XXX everywhere column names appear (schema definitions, dict keys, tuple constants) so that renaming a column is a single-point change.

Attributes:

Name	Type	Description
`AIC`	`str`
`AIC_R`	`str`
`BIAS`	`str`
`BIC`	`str`
`BIC_R`	`str`
`CHI2`	`str`
`CHISQ`	`str`
`CI_INCREASE_FACTOR`	`str`
`CI_LOWER`	`str`
`CI_METHOD`	`str`
`CI_UPPER`	`str`
`COHENS_D`	`str`
`COMPONENT`	`str`
`CONTRAST`	`str`
`CONVERGED`	`str`
`COOKSD`	`str`
`CORR`	`str`
`COVERAGE`	`str`
`CV_DEVIANCE`	`str`
`CV_FITTED`	`str`
`CV_FOLD`	`str`
`CV_K`	`str`
`CV_MAE`	`str`
`CV_MAE_SD`	`str`
`CV_RESIDUAL`	`str`
`CV_RMSE`	`str`
`CV_RMSE_SD`	`str`
`CV_RSQUARED`	`str`
`CV_RSQUARED_SD`	`str`
`CV_SCORE`	`str`
`CV_SE`	`str`
`DELTA_AIC`	`str`
`DELTA_BIC`	`str`
`DEVIANCE`	`str`
`DEV_DIFF`	`str`
`DF`	`str`
`DF1`	`str`
`DF2`	`str`
`DF_MODEL`	`str`
`DF_RESID`	`str`
`DIFF`	`str`
`DIFF_SE`	`str`
`DISPERSION`	`str`
`D_LOWER`	`str`
`D_UPPER`	`str`
`EFFECT1`	`str`
`EFFECT2`	`str`
`EMPIRICAL_SE`	`str`
`ESTIMATE`	`str`
`ETA_SQ`	`str`
`FITTED`	`str`
`FSTATISTIC`	`str`
`FSTATISTIC_PVALUE`	`str`
`F_RATIO`	`str`
`F_STAT`	`str`
`GROUP`	`str`
`HAT`	`str`
`ICC`	`str`
`IS_SINGULAR`	`str`
`LEVEL`	`str`
`LINK`	`str`
`LOGLIK`	`str`
`MEAN_SE`	`str`
`MODEL`	`str`
`N`	`str`
`NGROUPS`	`str`
`NOBS`	`str`
`NOBS_MISSING`	`str`
`NOBS_TOTAL`	`str`
`NPAR`	`str`
`NPARAMS`	`str`
`NULL_DEVIANCE`	`str`
`N_FAILED`	`str`
`N_ITER`	`str`
`N_SIMS`	`str`
`N_THETA`	`str`
`OBSERVED`	`str`
`ODDS_RATIO`	`str`
`OPTIMIZER`	`str`
`PI_LOWER_PREFIX`	`str`
`PI_UPPER_PREFIX`	`str`
`POWER`	`str`
`POWER_CI_LOWER`	`str`
`POWER_CI_UPPER`	`str`
`PRE`	`str`
`PRE_R`	`str`
`PRE_SD`	`str`
`PSEUDO_RSQUARED`	`str`
`P_VALUE`	`str`
`RESAMPLE`	`str`
`RESID`	`str`
`RHO_PREFIX`	`str`
`RHS_CONTRAST`	`str`
`RMSE`	`str`
`RSQUARED`	`str`
`RSQUARED_ADJ`	`str`
`RSQUARED_CONDITIONAL`	`str`
`RSQUARED_MARGINAL`	`str`
`RSS`	`str`
`R_SEMI`	`str`
`SE`	`str`
`SIGMA`	`str`
`SIGMA2`	`str`
`SIM_MEAN`	`str`
`SIM_Q025`	`str`
`SIM_Q975`	`str`
`SIM_SD`	`str`
`SS`	`str`
`STATISTIC`	`str`
`STD_RESID`	`str`
`TAU2_PREFIX`	`str`
`TERM`	`str`
`TERM_TYPE`	`str`
`TRUE_VALUE`	`str`
`T_STAT`	`str`
`VALUE`	`str`
`VIF`	`str`
`WEIGHT`	`str`

Attributes¶

AIC¶

AIC: str = 'aic'

AIC_R¶

AIC_R: str = 'AIC'

BIAS¶

BIAS: str = 'bias'

BIC¶

BIC: str = 'bic'

BIC_R¶

BIC_R: str = 'BIC'

CHI2¶

CHI2: str = 'chi2'

CHISQ¶

CHISQ: str = 'Chisq'

CI_INCREASE_FACTOR¶

CI_INCREASE_FACTOR: str = 'ci_increase_factor'

CI_LOWER¶

CI_LOWER: str = 'ci_lower'

CI_METHOD¶

CI_METHOD: str = 'ci_method'

CI_UPPER¶

CI_UPPER: str = 'ci_upper'

COHENS_D¶

COHENS_D: str = 'd'

COMPONENT¶

COMPONENT: str = 'component'

CONTRAST¶

CONTRAST: str = 'contrast'

CONVERGED¶

CONVERGED: str = 'converged'

COOKSD¶

COOKSD: str = 'cooksd'

CORR¶

CORR: str = 'corr'

COVERAGE¶

COVERAGE: str = 'coverage'

CV_DEVIANCE¶

CV_DEVIANCE: str = 'cv_deviance'

CV_FITTED¶

CV_FITTED: str = 'cv_fitted'

CV_FOLD¶

CV_FOLD: str = 'cv_fold'

CV_K¶

CV_K: str = 'cv_k'

CV_MAE¶

CV_MAE: str = 'cv_mae'

CV_MAE_SD¶

CV_MAE_SD: str = 'cv_mae_sd'

CV_RESIDUAL¶

CV_RESIDUAL: str = 'cv_residual'

CV_RMSE¶

CV_RMSE: str = 'cv_rmse'

CV_RMSE_SD¶

CV_RMSE_SD: str = 'cv_rmse_sd'

CV_RSQUARED¶

CV_RSQUARED: str = 'cv_rsquared'

CV_RSQUARED_SD¶

CV_RSQUARED_SD: str = 'cv_rsquared_sd'

CV_SCORE¶

CV_SCORE: str = 'cv_score'

CV_SE¶

CV_SE: str = 'cv_se'

DELTA_AIC¶

DELTA_AIC: str = 'delta_AIC'

DELTA_BIC¶

DELTA_BIC: str = 'delta_BIC'

DEVIANCE¶

DEVIANCE: str = 'deviance'

DEV_DIFF¶

DEV_DIFF: str = 'dev_diff'

DF¶

DF: str = 'df'

DF1¶

DF1: str = 'df1'

DF2¶

DF2: str = 'df2'

DF_MODEL¶

DF_MODEL: str = 'df_model'

DF_RESID¶

DF_RESID: str = 'df_resid'

DIFF¶

DIFF: str = 'diff'

DIFF_SE¶

DIFF_SE: str = 'diff_se'

DISPERSION¶

DISPERSION: str = 'dispersion'

D_LOWER¶

D_LOWER: str = 'd_lower'

D_UPPER¶

D_UPPER: str = 'd_upper'

EFFECT1¶

EFFECT1: str = 'effect1'

EFFECT2¶

EFFECT2: str = 'effect2'

EMPIRICAL_SE¶

EMPIRICAL_SE: str = 'empirical_se'

ESTIMATE¶

ESTIMATE: str = 'estimate'

ETA_SQ¶

ETA_SQ: str = 'eta_sq'

FITTED¶

FITTED: str = 'fitted'

FSTATISTIC¶

FSTATISTIC: str = 'fstatistic'

FSTATISTIC_PVALUE¶

FSTATISTIC_PVALUE: str = 'fstatistic_pvalue'

F_RATIO¶

F_RATIO: str = 'f_ratio'

F_STAT¶

F_STAT: str = 'F'

GROUP¶

GROUP: str = 'group'

HAT¶

HAT: str = 'hat'

ICC¶

ICC: str = 'icc'

IS_SINGULAR¶

IS_SINGULAR: str = 'is_singular'

LEVEL¶

LEVEL: str = 'level'

LINK¶

LINK: str = 'link'

LOGLIK¶

LOGLIK: str = 'loglik'

MEAN_SE¶

MEAN_SE: str = 'mean_se'

MODEL¶

MODEL: str = 'model'

N¶

N: str = 'n'

NGROUPS¶

NGROUPS: str = 'ngroups'

NOBS¶

NOBS: str = 'nobs'

NOBS_MISSING¶

NOBS_MISSING: str = 'nobs_missing'

NOBS_TOTAL¶

NOBS_TOTAL: str = 'nobs_total'

NPAR¶

NPAR: str = 'npar'

NPARAMS¶

NPARAMS: str = 'nparams'

NULL_DEVIANCE¶

NULL_DEVIANCE: str = 'null_deviance'

N_FAILED¶

N_FAILED: str = 'n_failed'

N_ITER¶

N_ITER: str = 'n_iter'

N_SIMS¶

N_SIMS: str = 'n_sims'

N_THETA¶

N_THETA: str = 'n_theta'

OBSERVED¶

OBSERVED: str = 'observed'

ODDS_RATIO¶

ODDS_RATIO: str = 'odds_ratio'

OPTIMIZER¶

OPTIMIZER: str = 'optimizer'

PI_LOWER_PREFIX¶

PI_LOWER_PREFIX: str = 'pi_lower_'

PI_UPPER_PREFIX¶

PI_UPPER_PREFIX: str = 'pi_upper_'

POWER¶

POWER: str = 'power'

POWER_CI_LOWER¶

POWER_CI_LOWER: str = 'power_ci_lower'

POWER_CI_UPPER¶

POWER_CI_UPPER: str = 'power_ci_upper'

PRE¶

PRE: str = 'pre'

PRE_R¶

PRE_R: str = 'PRE'

PRE_SD¶

PRE_SD: str = 'pre_sd'

PSEUDO_RSQUARED¶

PSEUDO_RSQUARED: str = 'pseudo_rsquared'

P_VALUE¶

P_VALUE: str = 'p_value'

RESAMPLE¶

RESAMPLE: str = 'resample'

RESID¶

RESID: str = 'resid'

RHO_PREFIX¶

RHO_PREFIX: str = 'rho_'

RHS_CONTRAST¶

RHS_CONTRAST: str = 'rhs_contrast'

RMSE¶

RMSE: str = 'rmse'

RSQUARED¶

RSQUARED: str = 'rsquared'

RSQUARED_ADJ¶

RSQUARED_ADJ: str = 'rsquared_adj'

RSQUARED_CONDITIONAL¶

RSQUARED_CONDITIONAL: str = 'rsquared_conditional'

RSQUARED_MARGINAL¶

RSQUARED_MARGINAL: str = 'rsquared_marginal'

RSS¶

RSS: str = 'rss'

R_SEMI¶

R_SEMI: str = 'r_semi'

SE¶

SE: str = 'se'

SIGMA¶

SIGMA: str = 'sigma'

SIGMA2¶

SIGMA2: str = 'sigma2'

SIM_MEAN¶

SIM_MEAN: str = 'sim_mean'

SIM_Q025¶

SIM_Q025: str = 'sim_q025'

SIM_Q975¶

SIM_Q975: str = 'sim_q975'

SIM_SD¶

SIM_SD: str = 'sim_sd'

SS¶

SS: str = 'ss'

STATISTIC¶

STATISTIC: str = 'statistic'

STD_RESID¶

STD_RESID: str = 'std_resid'

TAU2_PREFIX¶

TAU2_PREFIX: str = 'tau2_'

TERM¶

TERM: str = 'term'

TERM_TYPE¶

TERM_TYPE: str = 'term_type'

TRUE_VALUE¶

TRUE_VALUE: str = 'true_value'

T_STAT¶

T_STAT: str = 't_stat'

VALUE¶

VALUE: str = 'value'

VIF¶

VIF: str = 'vif'

WEIGHT¶

WEIGHT: str = 'weight'