如何在 Dash 中显示数据集的大小？

Question

我有这样一个数据集。用户可以通过滑块选择一定的时间间隔来调整时间间隔（以分钟为单位）。我想在网页的开头显示数据集的大小。 如果用户更改时间间隔，数据集的大小应动态更改，并显示动态删除了多少数据点。

import random
import pandas as pd
import numpy as np
import plotly.express as px
from plotly.subplots import make_subplots
from dash import Dash, html, dcc, Input, Output,dash_table

df = pd.DataFrame({'DATE_TIME':pd.date_range('2022-11-01', '2022-11-06 23:00:00',freq='20min'),
                   'ID':[random.randrange(1, 3) for n in range(430)]})
df['VALUE1'] = [random.uniform(110, 160) for n in range(430)]
df['VALUE2'] = [random.uniform(50, 80) for n in range(430)]
df['INSPECTION'] = df['DATE_TIME'].dt.day

df['MODE'] = np.select([df['INSPECTION']==1, df['INSPECTION'].isin([2,3])], ['A', 'B'], 'C')
df['TIME'] = df['DATE_TIME'].dt.time
df['TIME'] = df['TIME'].astype('str')
df['TIMEINTERVAL'] = df.DATE_TIME.diff().astype('timedelta64[m]')
df['TIMEINTERVAL'] = df['TIMEINTERVAL'].fillna(0)



def to_day_period(s):
    bins = ['0', '06:00:00', '13:00:00', '18:00:00', '23:00:00', '24:00:00']
    labels = ['Nighttime', 'Daytime', 'Daytime', 'Nighttime', 'Nighttime']

    return pd.cut(
        pd.to_timedelta(s),
        bins=list(map(pd.Timedelta, bins)),
        labels=labels, right=False, ordered=False
    )


df['TIME_OF_DAY'] = to_day_period(df['TIME'])
app = Dash(__name__)

app.layout = html.Div([
    html.H4('Interactive Scatter Plot'),
    html.P("Select ID:"),
    dcc.Dropdown(df.ID.unique(), id='pandas-dropdown-1'),  # for choosing ID,
    html.P("Filter by time interval during nighttime (18:00-6:00):"),
    dcc.RangeSlider(
        id='range-slider-night',
        min=0, max=600, step=10,
        marks={0: '0', 50: '50', 100: '100', 150: '150', 200: '200', 250: '250', 300: '300', 350: '350', 400: '400',
               450: '450', 500: '500', 550: '550', 600: '600'},
        value=[0, 600]
    ),
    html.P("Filter by time interval during daytime (6:00-18:00):"),
    dcc.RangeSlider(
        id='range-slider-morning',
        min=0, max=600, step=10,
        marks={0: '0', 50: '50', 100: '100', 150: '150', 200: '200', 250: '250', 300: '300', 350: '350', 400: '400',
               450: '450', 500: '500', 550: '550', 600: '600'},
        value=[0, 600]
    ),
    dcc.Graph(id="scatter-plot", style={'width': '130vh', 'height': '80vh'}),
    html.Div(id='dd-output-container')
])


@app.callback(
    Output("scatter-plot", "figure"),
    Input("pandas-dropdown-1", "value"),
    Input("range-slider-night", "value"),
    Input("range-slider-morning", "value"),
    prevent_initial_call=True)

def update_lineplot(value, slider_range_night, slider_range_morning):
    low_night, high_night = slider_range_night
    low_morning, high_morning = slider_range_morning
    df_night = df.query("ID == @value & TIME_OF_DAY == 'Night' & TIMEINTERVAL >= @low_night & TIMEINTERVAL < @high_night").copy()
    df_morning = df.query("ID == @value & TIME_OF_DAY == 'Morning' & TIMEINTERVAL >= @low_morning & TIMEINTERVAL < @high_morning").copy()
    df1 = pd.concat([df_night, df_morning], axis=0).sort_values(['DATE_TIME'])

    if df1.shape[0] != 0:
        fig = px.line(df1, x="DATE_TIME", y=["VALUE1", "VALUE2"],
                         facet_col='INSPECTION',
                         facet_col_wrap=2,
                         symbol='MODE',hover_data=['TIMEINTERVAL'],
                         facet_row_spacing=0.1,
                         facet_col_spacing=0.09)

        fig.update_xaxes(matches=None, showticklabels=True)

        return fig
    else:
        return no_update

app.run_server(debug=True, use_reloader=False)

我知道我可以在 Flask 中完成这样的任务就像这个链接一样。但我该如何在 Dash 中采用这个解决方案呢？

Answer 1

请尝试一下并告诉我这是否是您想要做的：

import random
import pandas as pd
import numpy as np
import plotly.express as px
from plotly.subplots import make_subplots
from dash import Dash, html, dcc, Input, Output,dash_table, no_update

df = pd.DataFrame({'DATE_TIME':pd.date_range('2022-11-01', '2022-11-06 23:00:00',freq='20min'),
                   'ID':[random.randrange(1, 3) for n in range(430)]})
df['VALUE1'] = [random.uniform(110, 160) for n in range(430)]
df['VALUE2'] = [random.uniform(50, 80) for n in range(430)]
df['INSPECTION'] = df['DATE_TIME'].dt.day

df['MODE'] = np.select([df['INSPECTION']==1, df['INSPECTION'].isin([2,3])], ['A', 'B'], 'C')
df['TIME'] = df['DATE_TIME'].dt.time
df['TIME'] = df['TIME'].astype('str')
df['TIMEINTERVAL'] = df.DATE_TIME.diff().astype('timedelta64[m]')
df['TIMEINTERVAL'] = df['TIMEINTERVAL'].fillna(0)



def to_day_period(s):
    bins = ['0', '06:00:00', '13:00:00', '18:00:00', '23:00:00', '24:00:00']
    labels = ['Nighttime', 'Daytime', 'Daytime', 'Nighttime', 'Nighttime']

    return pd.cut(
        pd.to_timedelta(s),
        bins=list(map(pd.Timedelta, bins)),
        labels=labels, right=False, ordered=False
    )


df['TIME_OF_DAY'] = to_day_period(df['TIME'])
app = Dash(__name__)

app.layout = html.Div([
    html.H4('Interactive Scatter Plot'),
    html.Div('Size of dataset = '+str(len(df)),id='size',style={'whiteSpace': 'pre-wrap'}),
    html.P("Select ID:"),
    dcc.Dropdown(df.ID.unique(), id='pandas-dropdown-1'),  # for choosing ID,
    html.P("Filter by time interval during nighttime (18:00-6:00):"),
    dcc.RangeSlider(
        id='range-slider-night',
        min=0, max=600, step=10,
        marks={0: '0', 50: '50', 100: '100', 150: '150', 200: '200', 250: '250', 300: '300', 350: '350', 400: '400',
               450: '450', 500: '500', 550: '550', 600: '600'},
        value=[0, 600]
    ),
    html.P("Filter by time interval during daytime (6:00-18:00):"),
    dcc.RangeSlider(
        id='range-slider-morning',
        min=0, max=600, step=10,
        marks={0: '0', 50: '50', 100: '100', 150: '150', 200: '200', 250: '250', 300: '300', 350: '350', 400: '400',
               450: '450', 500: '500', 550: '550', 600: '600'},
        value=[0, 600]
    ),
    dcc.Graph(id="scatter-plot", style={'width': '130vh', 'height': '80vh'}),
    html.Div(id='dd-output-container')
])


@app.callback(
    Output("scatter-plot", "figure"),
    Output("size", "children"),
    Input("pandas-dropdown-1", "value"),
    Input("range-slider-night", "value"),
    Input("range-slider-morning", "value"),
    prevent_initial_call=True)

def update_lineplot(value, slider_range_night, slider_range_morning):
    low_night, high_night = slider_range_night
    low_morning, high_morning = slider_range_morning
    df_night = df.query("(ID == @value) & (TIME_OF_DAY == 'Nighttime') & (TIMEINTERVAL >= @low_night) & (TIMEINTERVAL < @high_night)").copy()
    df_morning = df.query("(ID == @value) & (TIME_OF_DAY == 'Daytime') & (TIMEINTERVAL >= @low_morning) & (TIMEINTERVAL < @high_morning)").copy()
    df1 = pd.concat([df_night, df_morning], axis=0).sort_values(['DATE_TIME'])
    
    
    text = f"The size of dataset = {len(df)} \n Selected points = {len(df1)}, unselected points = {len(df) - len(df1)}, \n df_night = {len(df_night)}, df_morning = {len(df_morning)}"
    
    if df1.shape[0] != 0:
        fig = px.line(df1, x="DATE_TIME", y=["VALUE1", "VALUE2"],
                         facet_col='INSPECTION',
                         facet_col_wrap=2,
                         symbol='MODE',hover_data=['TIMEINTERVAL'],
                         facet_row_spacing=0.1,
                         facet_col_spacing=0.09)

        fig.update_xaxes(matches=None, showticklabels=True)

        return fig,text
    else:
        return no_update
    

app.run_server(debug=True, use_reloader=False)

输出：

您可以在这里找到我如何计算尺寸；

text = f"The size of dataset = {len(df)} \n Selected points = {len(df1)}, unselected points = {len(df) - len(df1)}, \n df_night = {len(df_night)}, df_morning = {len(df_morning)}"