Function reference • augury

All functions

assert_columns(): Assert that args in ellipses are columns in df

assert_columns_unique(): Assert that column names are not identical

assert_df(): Assert that df is a data frame

assert_error_correct_avg_trend(): If using error_correct, then check that the columns are either in the formula_vars or average_cols, otherwise produce an error.

assert_function(): Assert that x is a function

assert_group_models(): Assert if group_models TRUE then group_col not NULL

assert_group_sort_col(): Assert sort column for use in average trend functions

assert_h(): Assert that h, for forecasting, is > 0

assert_inla(): Assert if INLA is installed, for use in predict_inla...() functions.

assert_model(): Assert that x is a function

assert_numeric(): Assert numeric value

assert_numeric_cols(): Assert columns in df are numeric

assert_numeric_cols_avg(): Assert columns in df are numeric, for use with average trend functions

assert_string(): Assert that x is a character vector of length n

assert_test_col(): Assert that test_col is of logical type

augury_add_columns(): Adds empty columns to df

calculate_aarr(): Extract AARR from vector of years and prevalence

calculate_sq_ch(): Calculate change error

covariates_df: Default covariates for use in augury functions.

error_correct_fn(): Use mean error to correct predictions

expand_df(): Expand input data to make explicit missing values

expand_df_filter(): Filter expand_df

expand_df_min(): Helper for expand_df_filter() to calculate min for keeping data

filter_model_data(): Filters data for modeling

fit_aarr_model(): Generate prediction from model object

fit_forecast_average_model(): Fit forecast model to averages and apply trend to original data

fit_forecast_model(): Fit forecast model to data

fit_general_average_model(): Fit general model to averages and apply trend to original data

fit_general_model(): Fit general model to data

fit_inla_average_model(): Fit INLA model to averages and apply trend to original data

fit_inla_model(): Fit INLA model to data

fit_lme4_average_model(): Fit mixed model to averages and apply trend to original data

fit_lme4_model(): Fit general model to data

forecast_series(): Forecast data series

get_average_df(): Produces averaged data frame that can then be passed for modelling.

get_forecast_data(): Get data for forecast models

get_formula_avg_cols(): Get variables that need to be averaged from formula.

get_model_data(): Minimizes dataset to data needed for modelling

interpolate_aarr(): Interpolate using AARR from vector of years and prevalence

join_covariates_df(): Join data frame with covariates data frame

map_model_behavior(): Catch instability of INLA

merge_average_df(): Merge average df with predictions with original data frame

merge_prediction(): Merge predicted data into data frame

model_error(): Get modeling error from a data frame

parse_formula(): Asserts formula and extract variables

parse_obs_filter(): Parse obs filter intro string to be evaluated

predict_aarr(): Use annual average rate of reduction (AARR) to predict prevalence

predict_average(): Use averages to impute and forecast data

predict_average_fn(): Impute data using simple averages

predict_forecast(): Use a time series model to infill and project data

predict_forecast_avg_trend(): Use predict_forecast on groups to generate average trend and apply to original data

predict_forecast_data(): Generate prediction from model object

predict_general_data(): Generate prediction from model object

predict_general_mdl(): Use a generic R model to infill and project data

predict_general_mdl_avg_trend(): Use predict_general_mdl on groups to generate average trend and apply to original data

predict_glm(): Use a generalized linear model to infill and project data

predict_glm_avg_trend(): Use predict_glm on groups to generate average trend and apply to original data

predict_glmer(): Use a generalized linear mixed-effects model to infill and project data

predict_glmer_avg_trend(): Use predict_glmer on groups to generate average trend and apply to original data

predict_holt(): Use Holt's linear trend exponential smoothing to forecast data

predict_holt_avg_trend(): Use predict_holt on groups to generate average trend and apply to original data

predict_inla(): Use Bayesian analysis of additive models to infill and project data

predict_inla_avg_trend(): Use predict_inla on groups to generate average trend and apply to original data

predict_inla_data(): Generate prediction from an INLA output object

predict_inla_me(): Use INLA for mixed effects modeling for prediction

predict_inla_ts(): Use INLA for time series prediction

predict_lm(): Use a linear model to infill and project data

predict_lm_avg_trend(): Use predict_lm on groups to generate average trend and apply to original data

predict_lme4(): Use mixed models to infill and project data

predict_lme4_avg_trend(): Use predict_lme4 on groups to generate average trend and apply to original data

predict_lme4_data(): Generate prediction from model object

predict_lmer(): Use a linear mixed-effects model to infill and project data

predict_lmer_avg_trend(): Use predict_lmer on groups to generate average trend and apply to original data

predict_nlmer(): Use a non-linear mixed-effects model to infill and project data

predict_nlmer_avg_trend(): Use predict_nlmer on groups to generate average trend and apply to original data

predict_ses(): Use simple exponential smoothing to forecast data

predict_ses_avg_trend(): Use predict_ses on groups to generate average trend and apply to original data

predict_simple(): Use linear interpolation and flat extrapolation to infill data

predict_simple_fn(): Linearly interpolate data

probit_transform(): Probit transform bounded data in a data frame

probit_vec(): Probit transformation for bounded data

remove_groups(): Remove groups from data frame if grouped

scale_transform(): Scales data in a data frame

scale_vec(): Scale a vector

simple_extrap(): Helper function to do flat extrapolation

temp_fill(): Fills vector backwards and forward, for use prior to applying average trend

trim_series(): Get latest data for forecasting