| #' Installs any packages not already installed | |
| #' @examples | |
| #' \dontrun{ | |
| #' install_if_missing(c('tidyverse','github.com/stan-dev/cmdstanr')) | |
| #' } | |
| install_if_missing = function(pkgs){ | |
| missing_pkgs = NULL | |
| for(this_pkg in pkgs){ |
| ``` r | |
| library(tidyverse) | |
| iris %>% | |
| count(Species) | |
| #> # A tibble: 3 x 2 | |
| #> Species n | |
| #> <fct> <int> | |
| #> 1 setosa 50 | |
| #> 2 versicolor 50 |
What does an interpretable RF visualization look like? Out-of-the-box 📦 RF implementations in R and Python compute variable importance over all trees, but how do we get there?
In other words, what would a cumulative variable importance for a RF look like?
This GitHub gist contains instructions for the R, git & travis tutorial.
Partipants must be familar with
| --- | |
| title: "ggplot tutorial" | |
| subtitle: "with kunoichi + ninjutsu theme" | |
| author: "<br><br> Emi Tanaka" | |
| date: "<br>2018/09/16" | |
| output: | |
| xaringan::moon_reader: | |
| lib_dir: libs | |
| css: ["kunoichi", "ninjutsu"] | |
| nature: |
| data { | |
| int N; // number of rows | |
| int T; // number of inidvidual-choice sets/task combinations | |
| int I; // number of Individuals | |
| int P; // number of covariates | |
| vector<lower = 0, upper = 1>[N] choice; // binary indicator for choice | |
| matrix[N, P] X; // product attributes | |
| int task[T]; // index for tasks |
| library(tidyverse) | |
| library(ggrepel) | |
| set.seed(1234) | |
| data <- tibble(x = seq_len(100), | |
| y = cumsum(rnorm(100))) | |
| anno_data <- data %>% | |
| filter(x %% 25 == 10) %>% |
| # Load packages ----------------------------------------------------------- | |
| library(twitteR) | |
| library(dplyr) | |
| library(gganimate) | |
| library(ggplot2) | |
| library(bigrquery) | |
| # Twitter Creds ----------------------------------------------------------- | |
| consumer_key <- "" |
| """ | |
| Example TensorFlow script for finetuning a VGG model on your own data. | |
| Uses tf.contrib.data module which is in release v1.2 | |
| Based on PyTorch example from Justin Johnson | |
| (https://gist.github.com/jcjohnson/6e41e8512c17eae5da50aebef3378a4c) | |
| Required packages: tensorflow (v1.2) | |
| Download the weights trained on ImageNet for VGG: | |
| ``` | |
| wget http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz |
| """ | |
| Bi-Term Topic Model (BTM) for very short texts. | |
| Literature Reference: | |
| Xiaohui Yan, Jiafeng Guo, Yanyan Lan, and Xueqi Cheng: | |
| "A biterm topic model for short texts" | |
| In Proceedings of WWW '13, Rio de Janeiro, Brazil, pp. 1445-1456. | |
| ACM, DOI: https://doi.org/10.1145/2488388.2488514 | |
| This module requires pre-processing of textual data, |
