python - 如何在 plotly scattergeo 美国 map 中使用离散色标

Question

当我使用 plotly(在 python 中)时，我正在尝试使用离散色阶。我需要一个离散色标，因为我为特定城市绘制的某些值与所有其他城市相比太大了，因此离散色标可以帮助我轻松地可视化所有值。这是一个更好地解释我的情况的例子:我有一个数据集，其中包含按城市(在美国)划分的某些事件的详细信息。该事件在纽约市发生了 50000 次，而在美国其他城市，同一事件发生的次数不到 1000 次。当我使用连续色标时，所有其他城市的值都下降到低端，纽约市是唯一使用色标顶部颜色的值。

提前感谢您的帮助!此致，里沙布

Answer 1

对于几个商店的 10 个不同的集群 ID，我就是这样生成 10 个离散的自定义色标的:

import matplotlib

def matplotlib_to_plotly(cmap, pl_entries):
# Converts matplotlib colormap to plotly colormap. It also shuffles the color map

    h = 1.0/(pl_entries)
    pl_colorscale = []
    c_order = h * np.arange(pl_entries+1)
    c_order_shuffled = c_order.copy()
    # Shuffles the colormap
    np.random.shuffle(c_order_shuffled)
    for i in range(pl_entries):
        C = map(np.uint8, np.array(cmap(c_order_shuffled[i])[:3])*255)
        pl_colorscale.append([c_order[i], 'rgb'+str((C[0], C[1], C[2]))])
        # To have clear boundaries between colors in the colorbar
        if i < (pl_entries):
             pl_colorscale.append([c_order[i+1], 'rgb'+str((C[0], C[1], C[2]))])
    return pl_colorscale

# Sets the colormap of your choice 
cmap = matplotlib.cm.get_cmap('jet')
# Passes the number of distinct colors you need to generate. In this case we have 10 cluster ids in stores_info_df
custom_colorscale = matplotlib_to_plotly(cmap, stores_info_df['CLUSTER_ID'].max())
custom_colorscale

然后，我在 plot 函数中使用了上面的色标:

def visualize_geo_store_clusters(stores_info_df, fig_name='store_similarity_US_map', cluster_id = 'CLUSTER_ID'):

    max_cluster_id = stores_info_df[cluster_id].max()

    data = [ dict(
        type = 'scattergeo',
        locationmode = 'USA-states',
        lon = stores_info_df['LONGTITUDE'],
        lat = stores_info_df['LATITUDE'],
        text = stores_info_df['TEXT'],
        mode = 'markers',
        marker = dict(
            colorscale= custom_colorscale, 
            cmin = stores_info_df[cluster_id].min(),
            color = stores_info_df[cluster_id],
            cmax = max_cluster_id,
            colorbar = dict(
                title = 'Cluster ID',
                titleside = 'top',
                tickmode = 'array',
                tickvals =  np.arange(1, max_cluster_id+1),
                ticktext = np.arange(1, max_cluster_id+1),
                #ticks = 'outside',
            )

        ))]

     layout = dict(
        title = 'Similarity between Stores',
        geo = dict(
            scope='usa',
            projection=dict( type='albers usa' ),
            showland = True,
            landcolor = "rgb(250, 250, 250)",
            subunitcolor = "rgb(217, 217, 217)",
            countrycolor = "rgb(217, 217, 217)",
            countrywidth = 0.5,
            subunitwidth = 0.5
        ),
    )

fig = dict(data=data, layout=layout)
plotly.offline.iplot(fig, validate=False)

它生成以下图。