Package index • blabr

All functions

add_lena_stats(): Add LENA stats to each interval in a dataframe

add_vtc_speaker_stats(): Calculate per-speaker statistics based on the VTC output and add it to the original tibble. Do the same calculation as get_vtc_speaker_stats but keep all the original columns.

add_vtc_stats(): Add ctc calculated based on the vtc annotations

all_errors(): A closure to keep track of al the errors from reading the csv files. There might be a more elegant way to concatenate and print all errors from all files, but this seems to do the job for now.

assign_time_windows(): Assigns binned fixations to specified time windows

big_aggregate(): Add aggregations columns into an all_basiclevel tibble

calculate_lena_like_stats(): Calculate stats similar to those in LENA's 5min.csv files

characters_to_factors(): Convert all character columns to factors

collect_bl_files(): Collect basic level files

concat_all_bl(): Concatenate all the basic level files

concat_month_bl(): Concatenate basic level files by month

fixations_to_timeseries(): Convert a dataframe of fixation intervals to an evenly spaced timeseries

get_all_basiclevel(): Get the all_basiclevel data from the all_basiclevel repo

get_blab_share_path(): Find BLab share

get_cdi_spreadsheet(): Get the CDI spreadsheet for SEEDLingS babies

get_current_commit_date(): Get the date of the currently checked out commit

get_current_tag(): Find tag label of the currently checked out commit.

get_dataset_version(): Get the version tag of the last downloaded version of a dataset

get_df_file(): Downloads and optionally loads a csv/feather file from a specified version of a dataset

get_global_bl_mappings(): Get the global basic level spreadsheets

get_late_target_onset(): (no docs yet) Find late target onsets and create a doc to check and potentially correct them

get_latest_tag(): Finds the latest version tag

get_latest_version(): Find latest version available for downloading?

get_lena_speaker_stats(): Calculate per-speaker statistics based on the .its file

get_mesrep(): (no docs yet) Create message report with corrected key presses

get_motor_spreadsheet(): The the motor questionaire spreadsheet for the SEEDLingS babies

get_reliability(): Get the reliability spreadsheets

get_repo_path(): Absolute path to a dataset folder

get_seedlings_nouns() get_seedlings_nouns_extra() get_seedlings_nouns_codebook(): Load data from the SEEDLingS - Nouns dataset

get_seedlings_speaker_stats(): Calculates the number of Seedlings annotations in each interval (by speaker)

get_versions(): List available versions

get_vihi_annotations(): Load VIHI annotation data

get_vtc_speaker_stats(): Calculate per-speaker statistics based on the VTC output. This function does not keep all of the original columns, check add_vtc_speaker_stats for that.

handle_dataset_version(): Handles the version.

join_full_audio_video(): Join the audio and video dataframes into one big dataframe

keypress_issues(): (no docs yet) Find key press issues and create a doc to check and potentially correct them

keypress_retrieved(): (no docs yet) Load file with manually corrected key presses or late target onsets

late_target_retrieved(): (no docs yet) Load file with manually corrected late target onsets

list_rename(): dplyr::rename for lists

make_five_min_approximation(): Approximate LENA's 5min.csv output

merge_split_reports(): Merge tables from split fixation and message reports

prepare_intervals(): Prepare intervals to potentially be annotated later

process_concat_bl(): Post-processing for the full basic level dataframe

read_fixation_report(): Read EyeLink fixation report file

read_message_report(): Read EyeLink message report file

read_rttm(): Read an .rttm file produced by Voice Type Classifier

read_seedlings_audio_annotations(): Read audio sparse code csv from the Seedlings annotations.

run_git_command(): Run a git command in a dataset repository

sample_intervals_periodically(): Sample intervals periodically, e.g. every hour

sample_intervals_randomly(): Sample intervals randomly

sample_intervals_with_highest(): Sample intervals that are highest on a given metric

split_fixation_report(): Split a fixation report into a list of hierarchical dataframes

split_message_report(): Split a message report into a list of hierarchical dataframes

tag_low_data_trials(): Tag low-data trials based on fixation timeseries

theme_AMERICA(): Theme "AMERICA" for ggplot2

theme_blab(): Theme "blab" for ggplot2

theme_spooky(): Theme "spooky" for ggplot2

update_global_basic_levels(): Updates global basic levels in all_basiclevel_na

update_tags(): Fetches dataset tags from GitHub

write_rttm(): Write a tibble to an .rttm file

write_seedlings_audio_annotations(): Write the seedlings audio annotation tibble back to the csv file