Search code examples
javascriptpythonbokehpapaparse

Load CSV file into static Python Bokeh Web app with JavaScript Papa Parse


I have a static Bokeh web app for local use and I want to be able to load a file using javascript without running python. The idea is to be able to share Bokeh output_html file with other non-python users to run it and load their data with a file selector for interactive visualization. I made a very rough code based on this post and this post

I have no knowledge in JS and I apologize in advance for the bad implementation. Please feel free if you have a similar example or a simpler approach to read a file without bokeh server.

from bokeh.models.widgets import Toggle
from bokeh.plotting import figure, output_file, show

output_file("load_data_buttons.html")

x = [0]
y = x

source = ColumnDataSource(data=dict(x=x, y=y))

plot = figure(plot_width=400, plot_height=400)
plot.line('x', 'y', source=source, line_width=3, line_alpha=0.6)

callback = CustomJS(args=dict(source=source), code="""
       // initialize our parsed_csv to be used wherever we want
var parsed_csv;
var start_time, end_time;

        // document.ready
        $(function() {

          $('.load-file').on('click', function(e) {
            start_time = performance.now();
            $('#report').text('Processing...');

            console.log('initialize worker');

            var worker = new Worker('worker.js');
            worker.addEventListener('message', function(ev) {
              console.log('received raw CSV, now parsing...');

              // Parse our CSV raw text
              Papa.parse(ev.data, {
                header: true,
                dynamicTyping: true,
                complete: function (results) {
                    // Save result in a globally accessible var
                  parsed_csv = results;
                  console.log('parsed CSV!');
                  console.log(parsed_csv);

                  $('#report').text(parsed_csv.data.length + ' rows processed');
                  end_time = performance.now();
                  console.log('Took ' + (end_time - start_time) + " milliseconds to load and process the CSV file.")
                }
              });

              // Terminate our worker
              worker.terminate();
            }, false);

            // Submit our file to load
            var file_to_load = document.getElementById("myFile").files[0];

            console.log('call our worker');
            worker.postMessage({file: file_to_load});
          });

        });

        x =  parsed_csv.data['x']
        y =  parsed_csv.data['y']
        #load data stored in the file name and assign to x and y
        source.trigger('change');
    """)

toggle1 = Toggle(label="Load data file 1", callback=callback)

layout = Row(toggle1, plot)

show(layout)

worker.js

self.addEventListener('message', function(e) {
    console.log('worker is running');

    var file = e.data.file;
    var reader = new FileReader();

    reader.onload = function (fileLoadedEvent) {
        console.log('file loaded, posting back from worker');

        var textFromFileLoaded = fileLoadedEvent.target.result;

        // Post our text file back from the worker
        self.postMessage(textFromFileLoaded);
    };

    // Actually load the text file
    reader.readAsText(file, "UTF-8");
}, false);

The csv file has x,y data

x   y
0   0
1   1
2   2
3   3
4   4

Solution

  • You don't need Web Workers to achieve it, especially if you're not comfortable with JavaScript. Here's how I would do it:

    from bokeh.layouts import row, column
    from bokeh.models import Div, ColumnDataSource, CustomJS, FileInput
    from bokeh.plotting import figure, save
    
    source = ColumnDataSource(data=dict(x=[0], y=[0]))
    
    plot = figure(plot_width=400, plot_height=400)
    plot.line('x', 'y', source=source, line_width=3, line_alpha=0.6)
    
    fi_label = Div(text='Load data file 1')
    fi = FileInput()
    status = Div()
    
    callback = CustomJS(args=dict(source=source,
                                  status=status),
                        code="""
    status.text = 'Loading...';
    Papa.parse(atob(cb_obj.value), {
        // For some reason, Papa didn't detect it automatically.
        delimiter: '\t',
        header: true,
        dynamicTyping: true,
        complete: function (results) {
            const acc = results.meta.fields.reduce((acc, f) => {
                acc[f] = [];
                return acc;
            }, {});
            source.data = results.data.reduce((acc, row) => {
                for (const k in acc) {
                    acc[k].push(row[k]);
                }
                return acc;
            }, acc);
            status.text = 'Ready!';
        }
    });
    """)
    
    fi.js_on_change('value', callback)
    
    template = """\
    {% block preamble %}
    <script src="https://cdnjs.cloudflare.com/ajax/libs/PapaParse/5.1.0/papaparse.min.js"
            integrity="sha256-Fh801SO9gqegfUdkDxyzXzIUPWzO/Vatqj8uN+5xcL4="
            crossorigin="anonymous"></script>
    {% endblock %}
    """
    # Cannot use `show` because it doesn't have the `template` argument.
    save(column(row(fi_label, fi), plot), template=template)