Plotly dash - 从上传的 csv 中选择列作为下拉列表

Question

使用 plotly-dash 我可以通过选择硬编码的 csv 列来绘制图形。我尝试了不同的示例，现在我还可以从上传的文件中打印/绘制 csv。但是，我想上传一个 csv 并在下拉菜单中，我希望能够选择一列并绘制它。

有了这个，我可以通过从下拉菜单中选择一列，从硬编码的 csv 中绘制线图和箱线图。

df = pd.read_csv('df_anomaly.csv')


    html.Div([
            html.H3([
                dcc.Dropdown(
                    id = 'Dropdown',
                    options=[{'label': k, 'value': k} for k in list(df.columns.values)[1:]],
                    value='a',
                    placeholder="Name"),
            ]),

        ], className = "filter"),



    html.Div([
         html.Div([
            html.Div([
                dcc.Graph(id='Lineplot'),
            ], style={'width': '75%','display': 'inline-block', 'marginLeft': '15', 'marginTop': '15'}),

            html.Div([
                dcc.Graph(id='Boxplot')
            ], style={'width': '23.8%', 'display': 'inline-block', 'marginRight': '15','marginTop': '15','float':'right'})], style={
             'padding': '10px 15px'
         }),

    ], style={'padding': '5px 0px','backgroundColor': colors['grey'], 'marginTop': '8', 'marginBottom': '8'})

    ])

# Updating Observed Data Plot
@app.callback(
    dash.dependencies.Output('Lineplot', 'figure'),
    [dash.dependencies.Input('Dropdown', 'value')])

def update_graph(selector):
    df_selected = init_calc(selector)

    return {
        'data': [go.Scatter(
            y = np.array(df_selected['selected']),
            mode = 'lines',
            line = dict(
                color = colors['red']
            )
        )],
        'layout': go.Layout(
            height=400,
            title=go.layout.Title(
                text='Line Plot',
                font=dict(
                    color = colors['black'],
                )
            ),
            xaxis=dict(
                title='x',
                linecolor = colors['black'],
                color = colors['black'],
                ticks='inside',
                zeroline = False,
            ),
            yaxis=dict(
                title='y',
                linecolor = colors['black'],
                color = colors['black'],
                ticks='inside',
                zeroline = False,
            ),
            hovermode='closest',
        )
    }

# Updating Boxplot
@app.callback(
    dash.dependencies.Output('Boxplot', 'figure'),
    [dash.dependencies.Input('Dropdown', 'value')])

def update_boxplot(selector):

    df_selected = init_calc(selector)

    return {
        'data': [go.Box(
            name='',
            y=df_selected['selected'],
            marker = dict(
                color = colors['orange']
            )
        )],
        'layout': go.Layout(
            height=400,
            title=go.layout.Title(
                text='Boxplot', 
                font=dict(
                    color = colors['black'],
                )
            ),
            xaxis=dict(
                linecolor = colors['black'],
                color = colors['black'],
                zeroline = False,
            ),
            yaxis=dict(
                title='Traffic',
                linecolor = colors['black'],
                color = colors['black'],
                zeroline = False,
                ticks='inside',
            ),
        ),
    }

def init_calc(selector):
    df_selected = pd.DataFrame(columns=['selected'])
    df_selected['selected'] = df[str(selector)]
    return df_selected

#------------------------------------------------------------------------------------
# Running the App
if __name__ == '__main__':
    app.run_server(debug=False)

另外，如果我添加这段代码，我可以打印上传的 csv：

html.Div([
    dcc.Upload(
        id='upload-data',
        children=html.Div([
            'Drag and Drop or ',
            html.A('Select Files')
        ]),
        style={
            'width': '100%',
            'height': '60px',
            'lineHeight': '60px',
            'borderWidth': '1px',
            'borderStyle': 'dashed',
            'borderRadius': '5px',
            'textAlign': 'center',
            'margin': '2px'
        },
        # Allow multiple files to be uploaded
        multiple=True
    ),
    html.Div(id='output-data-upload'),
]),

def parse_contents(contents, filename, date):
    content_type, content_string = contents.split(',')

    decoded = base64.b64decode(content_string)

    try:
        if 'csv' in filename:
            # Assume that the user uploaded a CSV file
            df = pd.read_csv(
                io.StringIO(decoded.decode('utf-8')))
        elif 'xls' in filename:
            # Assume that the user uploaded an excel file
            df = pd.read_excel(io.BytesIO(decoded))
    except Exception as e:
        print(e)
        return html.Div([
            'There was an error processing this file.'
        ])

    return html.Div([
        html.H5(filename),
#         html.H6(datetime.fromtimestamp(date)),

        dash_table.DataTable(
            data=df[:5].to_dict('records'),
            columns=[{'name': i, 'id': i} for i in df.columns]
        ),

        html.Hr(),  # horizontal line

        # For debugging, display the raw contents provided by the web browser
#         html.Div('Raw Content'),
#         html.Pre(contents[0:200] + '...', style={
#             'whiteSpace': 'pre-wrap',
#             'wordBreak': 'break-all'
#         })
    ])


@app.callback(Output('output-data-upload', 'children'),
              [Input('upload-data', 'contents')],
              [State('upload-data', 'filename'),
               State('upload-data', 'last_modified')])
def update_output(list_of_contents, list_of_names, list_of_dates):
    if list_of_contents is not None:
        children = [
            parse_contents(c, n, d) for c, n, d in
            zip(list_of_contents, list_of_names, list_of_dates)]
        return children

通过小小的调整，我还可以手动选择列并绘制上传的 csv 列，但我希望能够像使用硬编码的那样选择上传的 csv 列。我该怎么做？

提前致谢

Answer 1

在您的函数parse_contents 中，除了用于显示内容的html 片段外，还返回df。称它为df_uploaded。

然后你有下拉列表的 html 内容，用这个 df_uploaded 替换你的 df，如下所示：

html.Div([
        html.H3([
            dcc.Dropdown(
                id = 'Dropdown',
                options=[{'label': k, 'value': k} for k in list(df_uploaded.columns.values)[1:]],
                value='a',
                placeholder="Name"),
        ]),

    ], className = "filter"),

通常我所做的是将所有图形生成函数分离到一个单独的 .py 文件中，比如 data_and_graphs.py。在这里，我通常会有返回图形对象的函数示例：

def generate_line_graph(x,y):
      l_grf = go.Fig()
      #add_trace()
      #add_layout()
      return l_grf

然后在布局中我只是 import data_and_graphs.py as grf 如果有对图表的引用，我会把它写成

dcc.Graph(
   id='graph1',
   figure=grf.l_grf
)

在同一行中，然后我将通过调用options=[{'label': k, 'value': k} for k in list(grf.df_uploaded_cols)] 来引用下拉列表中的 df 列 您可以简单地将相关列放在分配给df_uploaded_cols的列表中

希望这为调整您的代码以获取上传的 csv 列提供一些指导。