Uploading a CSV to Plotly Dash and rendering a bar plot based on a Pandas dataframe

Question

I'm new to the Plotly Dash framework and have attempted to build a simple dashboard that:

1. Allows the user to upload a CSV file to analyze graphically.

2. Creates a Pandas data frame based on the file uploaded in step #1.

   2a. Renders nothing if the CSV file (and resulting data frame) has not been selected.

3. Renders a basic bar plot (or scatter plot, heat map, etc.) based on the data contained in the aforementioned data frame.

The data in my CSV file looks similar to the following:

df = pd.DataFrame({'Make':['Ford', 'Ford', 'Ford', 'BMW', 'BMW', 'BMW', Mercedes', 'Mercedes', 'Mercedes'],
                          'Score':['88.6', '76.6', '100', '79.1', '86.8', '96.4', '97.3', '98.7', '98.5'],
                          'Dimension':['Speed', 'MPG', 'Styling', 'Speed', 'MPG', 'Styling', 'Speed', 'MPG', 'Styling'],
                          'Month':['Apr-19', 'Apr-19', 'Apr-19', 'Apr-19', 'Apr-19', 'Apr-19', 'Apr-19', 'Apr-19', 'Apr-19']})

My code is as follows:

import base64
import datetime
import io
import dash
from dash.dependencies import Input, Output, State
import dash_core_components as dcc
import dash_html_components as html
import plotly.graph_objects as go
import dash_table
import pandas as pd


app = dash.Dash()

app.layout = 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': '10px'
         },
        # 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.datetime.fromtimestamp(date)),

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

        html.Hr(),  # horizontal line

        #### How to get the x and y values DYNAMICALLY from the data frame to pass into the Bar() function? ####

    dcc.Graph(
        figure = go.Figure(data=[
        go.Bar(name=df.columns.values[0], x=pd.unique(df['Make']), y=[88.6, 76.6, 100], text=[88.6, 76.6, 100], textposition='auto'),
        go.Bar(name=df.columns.values[1], x=pd.unique(df['Make']), y=[92.5, 93.6, 93.4], text=[92.5, 93.6, 93.4], textposition='auto'),
        go.Bar(name=df.columns.values[2], x=pd.unique(df['Make']), y=[99.1, 99.2, 95.9], text=[99.1, 99.2, 95.9], textposition='auto'),
        ])
        ),        


        html.Hr(),

        # 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

if __name__ == '__main__':
    app.run_server(debug=True)

I'm able to upload and view the contents of the CSV file.

However, the go.Bar() function has its x and y values 'hard-coded' in. They're not necessarily DYNAMIC (ie if the number of x variables changes, etc.).

How do I get Dash to build the bar plot based on the data in the CSV file that's uploaded using the parse_contents(contents, filename, date) function?

I tried to follow along in Using dash upload component to upload csv file and generate a graph , but was unable to implement that example successfully.

Thanks in advance for helping a newbie get this toy example working!

Answer 1

Here is the answer:

import base64
import datetime
import io
import dash
from dash.dependencies import Input, Output, State
import dash_core_components as dcc
import dash_html_components as html
import plotly.express as px
import plotly.graph_objects as go
import dash_table
import pandas as pd


app = dash.Dash()

app.layout = 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': '10px'
         },
        # 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([

        dcc.Graph(
            figure = go.Figure(data=[
            go.Bar(name=df.columns.values[0], x=pd.unique(df['Make']), y=df['Score'], text=df['Score'], textposition='auto'),
            ])
            ),        


    ])

@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

if __name__ == '__main__':
    app.run_server(debug=True)