Plotly，为什么我的泡泡都是一样的颜色？

Question

我的数据中有一个名为 Pizza Shops 的列，其中包含按州划分的数字，范围从 10k 到超过 100 万（数字是由组成的）。出于某种原因，每个气泡虽然看起来大小合适，但都显示为相同的颜色（红色）。我的代码import plotly.graph_objects as goimport pandas as pdimport osxl_path = "path to XLSX file"df = pd.read_excel(open(xl_path, 'rb'), sheet_name='Data')df.head()scale = 5000limits = [(0,15000),(15000,50000),(50000,100000),(100000,500000),(500000,2000000)]colors = ["red","orange","yellow","green","blue"]df['Text'] = df['State'] + '<br>Number of Pizza Shops ' + (df['Pizza Shops']).astype(str)fig = go.Figure()for i in range(len(limits)):    lim = limits[i]    df_sub = df[lim[0]:lim[1]]    fig.add_trace(go.Scattergeo(        locationmode = 'USA-states',        locations=df['State Code'],        text = df_sub['Text'],        marker = dict(            size = df_sub['Pizza Shops']/scale,            color = colors[i],            line_color='rgb(40,40,40)',            line_width=0.5,            sizemode = 'area'        ),        name = '{0} - {1}'.format(lim[0],lim[1])))fig.update_layout(        title_text = '2019 US Number of Pizza Shops<br>(Click legend to toggle traces)',        showlegend = True,        geo = dict(            scope = 'usa',            landcolor = 'rgb(217, 217, 217)',        )    )fig.show()样本数据：| State     | State Code | Pizza Shops |----------------------------------------  Texas           TX         13256  California      CA         500235  Idaho           ID         4000  ....           ....        .... and so on

Answer 1

问题在于，df_sub = df[lim[0]:lim[1]]您是根据行索引而不是根据商店数量对数据框进行子集化。如果您的数据框的行数少于 15,000，则所有数据点都将落入第一个存储桶中，并显示为红色。

如果要根据应替换为的商店数量对数据框进行子集df_sub = df[lim[0]:lim[1]]化 df_sub = df[(df["Pizza Shops"] >= lim[0]) & (df["Pizza Shops"] < lim[1])]。

import plotly.graph_objects as go

import pandas as pd

df = pd.DataFrame({"State": ["Texas", "California", "Idaho", "Alabama", "Arizona", "Georgia", "Washington"],

                   "State Code": ["TX", "CA", "ID", "AL", "AZ", "GA", "WA"],

                   "Pizza Shops": [12500, 25000, 75000, 250000, 1000000, 15000, 100000]})

df["Text"] = df["State"] + "<br>Number of Pizza Shops " + (df["Pizza Shops"]).astype(str)

scale = 2000

limits = [(0,15000),(15000,50000),(50000,100000),(100000,500000),(500000,2000000)]

colors = ["red", "orange", "yellow", "green", "blue"]

fig = go.Figure()

for i in range(len(limits)):

    lim = limits[i]

    df_sub = df[(df["Pizza Shops"] >= lim[0]) & (df["Pizza Shops"] < lim[1])]

    fig.add_trace(go.Scattergeo(

        locationmode="USA-states",

        locations=df_sub["State Code"],

        text=df_sub["Text"],

        marker=dict(

            size=df_sub["Pizza Shops"]/scale,

            color=colors[i],

            line_color="rgb(40,40,40)",

            line_width=0.5,

            sizemode="area"),

        name="{0} - {1}".format(lim[0],lim[1])))

fig.update_layout(

    title_text="2019 US Number of Pizza Shops<br>(Click legend to toggle traces)",

    showlegend=True,

    geo=dict(scope="usa", landcolor="rgb(217, 217, 217)")

)

fig.show()