Function reference • bdb2021

All functions
`add_receiver_target_rates()`	add_receiver_target_rates calculate how frequently receivers are targeted in entire dataset
`add_throw_vector_to_positions()`	add_throw_vector_to_positions takes player positions at release along with throw information to calculate how close the player is to the throw
`aggregate_week_files()`	aggregate_week_files aggregate all of the PBP data
`build_final_leaderboard()`	build_final_leaderboard The top-15 leaderboard in the final report
`build_raw_stat_table()`	build_raw_stat_table Get data on speed, acceleration to use in shiny app
`build_target_prob_tune_results()`	build_target_prob_tune_results function to create target prob tuning results from stored file
`build_target_results()`	build_target_results output all of the results of the target models to be used
`build_weather_df()`	build_weather_df returns a dataframe with parsed weather information for each gameId
`catch_prob_diagnostic_plots()`	catch_prob_diagnostic_plots make catch prob model diagnostic plots
`connect_to_heroku_postgres()`	connect_to_heroku_postgres
`convert_secret()`	convert_secret
`create_throw_vectors()`	create_throw_vectors returns a data frame with throw vectors
`divvy_credit()`	divvy_credit divvy credit between defenders
`do_catch_prob_arrival_feat_eng()`	do_catch_prob_arrival_feat_eng build a data frame of catch prob features
`do_catch_prob_throw_feat_eng()`	do_catch_prob_throw_feat_eng build a data frame of catch prob features
`do_target_prob_feature_eng()`	do_target_prob_feat_eng build a data frame of target prob features
`fit_catch_prob_xgb()`	fit_catch_prob_xgb fit the xgboost catch prob model
`fit_logit_platt_scaler()`	fit_logit_platt_scaler fit the Platt scaler to calibrate the xgboost predictions
`fit_logit_target_platt_scaler()`	fit_logit_target_platt_scaler fit the Platt scaler to calibrate the xgboost predictions
`fit_prior_target_prob()`	fit_prior_target_prob create an estimate of the likelihood a receiver is targeted before the play starts
`fit_target_prob_rf()`	fit_target_prob_rf fit the rf target prob model
`fit_target_prob_xgb()`	fit_target_prob_xgb fit the xgb target prob model
`generate_man_zone_class()`	full feature engineering and classification for man v zone coverages WARNING: this takes a lot of time to run
`get_constants()`	get_constants get project-wide constants
`get_defense_locs_at_arrival()`	get_defense_locs_at_arrival returns a data from of the locations of the defense at throw time
`get_defense_locs_at_throw()`	get_defense_locs_at_throw returns a data from of the locations of the defense at throw time
`get_football_location_at_arrival()` `get_football_location_at_arrival()`	get_football_location_at_arrival returns a data frame of the location of the football on each play
`get_football_locations()`	get_football_locations get a data frame of the location of the football on each play
`get_heights()`	get_heights returns a data frame of player heights
`get_max_throw_velo()`	get_max_throw_velo returns a data frame of maximum throw velos for each play
`get_pi_and_sack()`	get_pi_and_sack returns a data frame of pass interferences and sacks
`get_play_outcomes()`	get_play_outcomes returns a data frame of play outcomes
`get_target_location_at_arrival()`	get_target_location_at_arrival returns a data frame of the locations of the targeted receiver at throw time on each play
`get_target_location_at_throw()`	get_target_location_at_throw returns a data frame of the locations of the targeted receiver at throw time on each play
`get_targeted_receiver()`	get_targeted_receiver get a data frame of the targeted receiver on each play
`get_throw_dists()`	get_throw_dists returns a data frame of throw distances on each play
`get_weather()`	get_weather return the weather forecast in a given week
`gt_theme_538()`	gt_theme_538 the Fivethirtyeight GT theme Credit to Thomas Mock: https://themockup.blog/posts/2020-09-26-functions-and-themes-for-gt-tables/#fivethirtyeight
`heroku_postgres_inserts()`	heroku_postgres_inserts
`load_encrypted()`	load_encrypted
`load_key_and_nonce()`	load_key_and_nonce
`load_player_summary_table()`	load_player_summary_table Function that builds the overall results
`make_catch_prob_table()`	make_catch_prob_table makes the drops added table
`make_tendency_table()`	make_tendency_table makes the deterrence table
`read_from_data()`	read_from_data load data from csv file
`read_individual_week()`	read_individual_week load a single week of PBP data
`read_non_week_files()`	read_non_week_files read all of the non-PBP data
`read_pff()`	read_pff load PFF grades
`recalc_prob()`	recalc_prob recalculate the catch probabilities after removing a defender
`run_catch_prob_tuning_pipeline()`	run_catch_prob_tuning_pipeline runs the catch prob tuning pipeline
`run_catch_prob_tuning_pipelines()`	run_catch_prob_tuning_pipeline runs the catch prob tuning pipeline
`run_target_prob_tuning_pipeline()`	run_target_prob_tuning_pipeline pipeline for target prob model
`save_encrypted()`	save_encrypted
`standardize_position_coordinates()`	standardize_position_coordinates Takes raw position data and normalizes it so that drives only go one way and X coordinates are relative to goal line rather than back of end zone
`stepwise_catch_prob_predict()`	stepwise_catch_prob_predict Make calibrated predictions from xgboost + Platt scaling
`stepwise_target_prob_predict()`	stepwise_target_prob_predict Make calibrated predictions from rf + Platt scaling
`stepwise_target_prob_predict_xgb()`	stepwise_target_prob_predict Make calibrated predictions from rf + Platt scaling
`target_prob_diagnostic_plots()`	target_prob_diagnostic_plots same diagnostic plots for target probs
`tune_catch_prob_xgb()`	tune_catch_prob_xgb tune the xgboost catch prob model
`tune_target_prob_rf()`	tune_target_prob_rf tune the rf target prob model
`tune_target_prob_xgb()`	tune_target_prob_xgb tune the XGB target probability model TODO: actually document this rather than just copy paste

Reference

All functions