根据在散点图上选择的数据点创建熊猫数据框

Question

Plotly Figure Widget帮助我创建一个交互式的散点图，即，我可以在散点图上选择数据点，然后基于该选择，我的表格小部件将显示记录。我需要帮助将此表转换为熊猫数据框。

import plotly.graph_objs as go
import plotly.offline as py

import pandas as pd
import numpy as np
from ipywidgets import interactive, HBox, VBox

py.init_notebook_mode()

df = pd.read_csv('https://raw.githubusercontent.com/jonmmease/plotly_ipywidget_notebooks/master/notebooks/data/cars/cars.csv')

f = go.FigureWidget([go.Scatter(y = df['City mpg'], x = df['City mpg'], mode = 'markers')])
scatter = f.data[0]
N = len(df)
scatter.x = scatter.x + np.random.rand(N)/10 *(df['City mpg'].max() - df['City mpg'].min())
scatter.y = scatter.y + np.random.rand(N)/10 *(df['City mpg'].max() - df['City mpg'].min())
scatter.marker.opacity = 0.5

def update_axes(xaxis, yaxis):
    scatter = f.data[0]
    scatter.x = df[xaxis]
    scatter.y = df[yaxis]
    with f.batch_update():
        f.layout.xaxis.title = xaxis
        f.layout.yaxis.title = yaxis
        scatter.x = scatter.x + np.random.rand(N)/10 *(df[xaxis].max() - df[xaxis].min())
        scatter.y = scatter.y + np.random.rand(N)/10 *(df[yaxis].max() - df[yaxis].min())

axis_dropdowns = interactive(update_axes, yaxis = df.select_dtypes('int64').columns, xaxis = df.select_dtypes('int64').columns)

# Create a table FigureWidget that updates on selection from points in the scatter plot of f
t = go.FigureWidget([go.Table(
    header=dict(values=['ID','Classification','Driveline','Hybrid'],
                fill = dict(color='#C2D4FF'),
                align = ['left'] * 5),
    cells=dict(values=[df[col] for col in ['ID','Classification','Driveline','Hybrid']],
               fill = dict(color='#F5F8FF'),
               align = ['left'] * 5))])

def selection_fn(trace,points,selector):
    t.data[0].cells.values = [df.loc[points.point_inds][col] for col in ['ID','Classification','Driveline','Hybrid']]

scatter.on_selection(selection_fn)

# Put everything together
VBox((HBox(axis_dropdowns.children),f,t))

只希望在选择散点图上的点到熊猫数据框后创建表。

Output

Answer 1

假设下面的代码突出显示了您关心的重点：

def selection_fn(trace,points,selector):
    t.data[0].cells.values = [df.loc[points.point_inds][col] for col in ['ID','Classification','Driveline','Hybrid']]

更改为返回数据框：

def selection_fn(trace,points,selector):
    return pd.df([df.loc[points.point_inds][col] for col in ['ID','Classification','Driveline','Hybrid']])