在mutate中添加变量标签

Question

我正在重新处理一些旧代码，以便于学习tidyverse。在先前的代码中，我将从当前变量派生新变量，并使用label包中的Hmisc为这些新变量赋予标签属性。看起来像这样。

library(Hmisc)

iris$new <- ifelse(iris$Species == 'setosa', 1, 0)
label(iris$new) <- "New Variable"

给出此结果

> str(iris$new)
 'labelled' num [1:150] 1 1 1 1 1 1 1 1 1 1 ...
 - attr(*, "label")= chr "New Variable"

我想知道是否有一种方法可以在mutate调用中应用这种类型的东西。

Answer 1

我们可以使用structure()：

library(Hmisc)
library(dplyr)

iris <- iris %>% 
  mutate(new = structure(ifelse(iris$Species == 'setosa', 1, 0), label = "New Variable"))

label(iris$new)
#[1] "New Variable"

Answer 2

有点丑陋，你也可以做

 from bokeh.server.server import Server
 from bokeh.application import Application
 from bokeh.application.handlers.function import FunctionHandler
 from bokeh.plotting import figure, ColumnDataSource
 from bokeh.core.properties import field
 from bokeh.models import (HoverTool, SingleIntervalTicker,
                           Slider, Button, Label, CategoricalColorMapper)
 from bokeh.palettes import Spectral6 
 import numpy as np
 import pandas as pd

def process_data():
    from bokeh.sampledata.gapminder import fertility, life_expectancy, population, regions

    # Make the column names ints not strings for handling
    columns = list(fertility.columns)
    years = list(range(int(columns[0]), int(columns[-1])))
    rename_dict = dict(zip(columns, years))

    fertility = fertility.rename(columns=rename_dict)
    life_expectancy = life_expectancy.rename(columns=rename_dict)
    population = population.rename(columns=rename_dict)
    regions = regions.rename(columns=rename_dict)

    regions_list = list(regions.Group.unique())

    # Turn population into bubble sizes. Use min_size and factor to tweak.
    scale_factor = 200
    population_size = np.sqrt(population / np.pi) / scale_factor
    min_size = 3
    population_size = population_size.where(population_size >= min_size).fillna(min_size)

    return fertility, life_expectancy, population_size, regions, years, regions_list


def make_document(doc):

    fertility_df, life_expectancy_df, population_df_size, regions_df, years, regions_list = process_data()

    df = pd.concat({'fertility': fertility_df,
                'life': life_expectancy_df,
                'population': population_df_size},
               axis=1)    
    data = {}

    regions_df.rename({'Group':'region'}, axis='columns', inplace=True)
    for year in years:
        df_year = df.iloc[:,df.columns.get_level_values(1)==year]
        df_year.columns = df_year.columns.droplevel(1)
        data[year] = df_year.join(regions_df.region).reset_index().to_dict('series')

    source = ColumnDataSource(data=data[years[0]])

    plot = figure(x_range=(1, 9), y_range=(20, 100), title='Gapminder Data', plot_height=300)
    plot.xaxis.ticker = SingleIntervalTicker(interval=1)
    plot.xaxis.axis_label = "Children per woman (total fertility)"
    plot.yaxis.ticker = SingleIntervalTicker(interval=20)
    plot.yaxis.axis_label = "Life expectancy at birth (years)"

    label = Label(x=1.1, y=18, text=str(years[0]), text_font_size='70pt', text_color='#eeeeee')
    plot.add_layout(label)

    color_mapper = CategoricalColorMapper(palette=Spectral6, factors=regions_list)
    plot.circle(
      x='fertility',
      y='life',
      size='population',
      source=source,
      fill_color={'field': 'region', 'transform': color_mapper},
      fill_alpha=0.8,
      line_color='#7c7e71',
      line_width=0.5,
      line_alpha=0.5,
      legend=field('region'),
    )
    plot.add_tools(HoverTool(tooltips="@Country", show_arrow=False,  point_policy='follow_mouse'))

    def animate_update():
        year = slider.value + 1
        if year > years[-1]:
            year = years[0]
        slider.value = year    

    def slider_update(attrname, old, new):
        year = slider.value
        label.text = str(year)
        source.data = data[year]

    slider = Slider(start=years[0], end=years[-1], value=years[0], step=1, title="Year")
    slider.on_change('value', slider_update)

    callback_id = None

    def animate():
        global callback_id
        if button.label == '► Play':
            button.label = '❚❚ Pause'
            callback_id = doc.add_periodic_callback(animate_update, 200)
        else:
            button.label = '► Play'
            doc.remove_periodic_callback(callback_id)

    button = Button(label='► Play', width=60)
    button.on_click(animate)    

    doc.add_root(button)
    doc.add_root(slider)
    doc.add_root(plot)

apps = {'/': Application(FunctionHandler(make_document))}

server = Server(apps, port=5000)
server.start()

这不会绕过iris %>% mutate(new =`label<-`(ifelse(Species == 'setosa', 1, 0), value="New Variable")) 默认情况下会跳过结构的任何检查。您也可以将其包装在一个函数中以使其更整洁。

label<-