{ "cells": [ { "cell_type": "markdown", "id": "ideal-advertising", "metadata": {}, "source": [ "# Tidyverse worflow" ] }, { "cell_type": "code", "execution_count": 36, "id": "stable-tours", "metadata": { "ExecuteTime": { "end_time": "2021-03-08T18:15:38.507923Z", "start_time": "2021-03-08T18:15:38.487Z" } }, "outputs": [], "source": [ "options(warn=-1)\n", "options(messages=-1)\n", "options(tidyverse.quiet = TRUE)\n", "options(dplyr.summarise.inform = FALSE)\n", "shhh <- suppressWarnings # It's a library, so shhh!\n", "shhh(library(tidyverse))" ] }, { "cell_type": "code", "execution_count": 7, "id": "fatal-deficit", "metadata": { "ExecuteTime": { "end_time": "2021-03-08T18:01:56.489218Z", "start_time": "2021-03-08T18:01:55.992Z" } }, "outputs": [], "source": [ "## ---------------------------------------------------------------------------------------------------\n", "vow.dur <- read.table(\"https://bit.ly/2Iw7kn7\", header=TRUE, sep=\"\\t\")" ] }, { "cell_type": "code", "execution_count": 23, "id": "fatal-trustee", "metadata": { "ExecuteTime": { "end_time": "2021-03-08T18:08:26.670117Z", "start_time": "2021-03-08T18:08:26.641Z" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A data.frame: 7 × 6
vowelUS_statepositioncontextvowel_durationmean_vow_dur
<fct><fct><fct><fct><dbl><dbl>
aɪNorthCCcontextvoiceless216.6203.9143
æ NorthCCcontextvoiceless214.8203.9143
aɪNorthCVemph voiceless209.2203.9143
æ NorthCVemph voiceless202.7203.9143
æ Ohio Ccontextvoiceless198.5203.9143
e NorthCCcontextvoiceless193.9203.9143
e NorthCVemph voiceless191.7203.9143
\n" ], "text/latex": [ "A data.frame: 7 × 6\n", "\\begin{tabular}{llllll}\n", " vowel & US\\_state & position & context & vowel\\_duration & mean\\_vow\\_dur\\\\\n", " & & & & & \\\\\n", "\\hline\n", "\t aɪ & NorthC & Ccontext & voiceless & 216.6 & 203.9143\\\\\n", "\t æ & NorthC & Ccontext & voiceless & 214.8 & 203.9143\\\\\n", "\t aɪ & NorthC & Vemph & voiceless & 209.2 & 203.9143\\\\\n", "\t æ & NorthC & Vemph & voiceless & 202.7 & 203.9143\\\\\n", "\t æ & Ohio & Ccontext & voiceless & 198.5 & 203.9143\\\\\n", "\t e & NorthC & Ccontext & voiceless & 193.9 & 203.9143\\\\\n", "\t e & NorthC & Vemph & voiceless & 191.7 & 203.9143\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A data.frame: 7 × 6\n", "\n", "| vowel <fct> | US_state <fct> | position <fct> | context <fct> | vowel_duration <dbl> | mean_vow_dur <dbl> |\n", "|---|---|---|---|---|---|\n", "| aɪ | NorthC | Ccontext | voiceless | 216.6 | 203.9143 |\n", "| æ | NorthC | Ccontext | voiceless | 214.8 | 203.9143 |\n", "| aɪ | NorthC | Vemph | voiceless | 209.2 | 203.9143 |\n", "| æ | NorthC | Vemph | voiceless | 202.7 | 203.9143 |\n", "| æ | Ohio | Ccontext | voiceless | 198.5 | 203.9143 |\n", "| e | NorthC | Ccontext | voiceless | 193.9 | 203.9143 |\n", "| e | NorthC | Vemph | voiceless | 191.7 | 203.9143 |\n", "\n" ], "text/plain": [ " vowel US_state position context vowel_duration mean_vow_dur\n", "1 aɪ NorthC Ccontext voiceless 216.6 203.9143 \n", "2 æ NorthC Ccontext voiceless 214.8 203.9143 \n", "3 aɪ NorthC Vemph voiceless 209.2 203.9143 \n", "4 æ NorthC Vemph voiceless 202.7 203.9143 \n", "5 æ Ohio Ccontext voiceless 198.5 203.9143 \n", "6 e NorthC Ccontext voiceless 193.9 203.9143 \n", "7 e NorthC Vemph voiceless 191.7 203.9143 " ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# main dplyr functions\n", "vow.dur %>%\n", " filter(context == \"voiceless\" & Vow_dur_ms > mean(Vow_dur_ms, na.rm = TRUE)) %>%\n", " arrange(desc(Vow_dur_ms)) %>%\n", "# select(contains(\"_\")) %>%\n", "# explain why some vow_dur > mean\n", " mutate(mean_vow_dur = mean(Vow_dur_ms, na.rm = TRUE)) %>%\n", " rename(vowel_duration = Vow_dur_ms)" ] }, { "cell_type": "code", "execution_count": 37, "id": "continental-radius", "metadata": { "ExecuteTime": { "end_time": "2021-03-08T18:15:40.672792Z", "start_time": "2021-03-08T18:15:40.645Z" } }, "outputs": [ { "data": { "text/html": [ "\n", "\n", "\n", "\t\n", "\t\n", "\n", "\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\t\n", "\n", "
A grouped_df: 6 × 3
US_statecontextmean
<fct><fct><dbl>
NorthCvoiced 235.74
NorthCvoiceless186.26
Ohio voiced 213.90
Ohio voiceless156.94
Wisc voiced 194.59
Wisc voiceless147.14
\n" ], "text/latex": [ "A grouped\\_df: 6 × 3\n", "\\begin{tabular}{lll}\n", " US\\_state & context & mean\\\\\n", " & & \\\\\n", "\\hline\n", "\t NorthC & voiced & 235.74\\\\\n", "\t NorthC & voiceless & 186.26\\\\\n", "\t Ohio & voiced & 213.90\\\\\n", "\t Ohio & voiceless & 156.94\\\\\n", "\t Wisc & voiced & 194.59\\\\\n", "\t Wisc & voiceless & 147.14\\\\\n", "\\end{tabular}\n" ], "text/markdown": [ "\n", "A grouped_df: 6 × 3\n", "\n", "| US_state <fct> | context <fct> | mean <dbl> |\n", "|---|---|---|\n", "| NorthC | voiced | 235.74 |\n", "| NorthC | voiceless | 186.26 |\n", "| Ohio | voiced | 213.90 |\n", "| Ohio | voiceless | 156.94 |\n", "| Wisc | voiced | 194.59 |\n", "| Wisc | voiceless | 147.14 |\n", "\n" ], "text/plain": [ " US_state context mean \n", "1 NorthC voiced 235.74\n", "2 NorthC voiceless 186.26\n", "3 Ohio voiced 213.90\n", "4 Ohio voiceless 156.94\n", "5 Wisc voiced 194.59\n", "6 Wisc voiceless 147.14" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# advanced dplyr functions\n", "\n", "vow.dur %>%\n", " group_by(US_state, context) %>%\n", " summarise(mean = mean(Vow_dur_ms))" ] } ], "metadata": { "kernelspec": { "display_name": "R", "language": "R", "name": "ir" }, "language_info": { "codemirror_mode": "r", "file_extension": ".r", "mimetype": "text/x-r-source", "name": "R", "pygments_lexer": "r", "version": "3.6.3" }, "nbTranslate": { "displayLangs": [ "*" ], "hotkey": "alt-t", "langInMainMenu": true, "sourceLang": "en", "targetLang": "fr", "useGoogleTranslate": true }, "toc": { "base_numbering": 1, "nav_menu": {}, "number_sections": true, "sideBar": false, "skip_h1_title": true, "title_cell": "Table des matières", "title_sidebar": "Contents", "toc_cell": false, "toc_position": {}, "toc_section_display": true, "toc_window_display": false }, "varInspector": { "cols": { "lenName": 16, "lenType": 16, "lenVar": 40 }, "kernels_config": { "python": { "delete_cmd_postfix": "", "delete_cmd_prefix": "del ", "library": "var_list.py", "varRefreshCmd": "print(var_dic_list())" }, "r": { "delete_cmd_postfix": ") ", "delete_cmd_prefix": "rm(", "library": "var_list.r", "varRefreshCmd": "cat(var_dic_list()) " } }, "types_to_exclude": [ "module", "function", "builtin_function_or_method", "instance", "_Feature" ], "window_display": false } }, "nbformat": 4, "nbformat_minor": 5 }