Bokeh interactive histogram #bokeh #histogram #interactive

bokeh_interactive_histogram.py

def interactive_histogram(df,col,n_bins,bin_range,title,x_axis_label,x_tooltip):
    """Plot interactive histogram using bokeh.
    
    df: pandas dataframe
    col: column of panda dataframe to plot (eg. age of users)
    n_bins: number of bins, e.g. 9
    bin_range: list with min and max value. e.g. [10,100] age of users.
    title: title of plot. e.g. 'Airnb Users Age Distribution'
    x_axis_label: x axis label. e.g. 'Age (years)'.
    x_tooltip: x axis tooltip string. e.g. 'Age'
    
    """
    import pandas as pd
    import numpy as np
    from bokeh.plotting import figure

    from bokeh.io import show, output_notebook
    from bokeh.models import ColumnDataSource, HoverTool, CategoricalColorMapper
    from bokeh.palettes import Category10_5, Category20_16

    arr_hist, edges = np.histogram(df[col],bins=n_bins,range=bin_range)

    # Column data source
    arr_df = pd.DataFrame({'count': arr_hist, 'left': edges[:-1], 'right': edges[1:]})
    arr_df['f_count'] = ['%d' % count for count in arr_df['count']]
    arr_df['f_interval'] = ['%d to %d ' % (left, right) for left, right in zip(arr_df['left'], arr_df['right'])]

    # column data source
    arr_src = ColumnDataSource(arr_df)

    # Set up the figure same as before
    p = figure(plot_width = 500, 
               plot_height = 500,
               title = title,
               x_axis_label = x_axis_label, 
               y_axis_label = 'Count')

    # Add a quad glyph with source this time
    p.quad(bottom=0, 
           top='count', 
           left='left', 
           right='right', 
           source=arr_src,
           fill_color='red',
           hover_fill_alpha=0.7,
           hover_fill_color='blue',
           line_color='black')

    # Add style to the plot
    p.title.align = 'center'
    p.title.text_font_size = '18pt'
    p.xaxis.axis_label_text_font_size = '12pt'
    p.xaxis.major_label_text_font_size = '12pt'
    p.yaxis.axis_label_text_font_size = '12pt'
    p.yaxis.major_label_text_font_size = '12pt'

    # Add a hover tool referring to the formatted columns
    hover = HoverTool(tooltips = [(x_tooltip, '@f_interval'),
                                  ('Count', '@f_count')])

    # Add the hover tool to the graph
    p.add_tools(hover)

    return p

# next cell
from bokeh.io import show, output_notebook

# To show in notebook
output_notebook()

# Show the plot
df = users
col = 'age'
n_bins = 9
bin_range = [10,100]
title = 'Airnb Users Age Distribution'
x_axis_label = 'Age (years)'
x_tooltip = 'Age'
bp = interactive_histogram(df,col,n_bins,bin_range,title,x_axis_label,x_tooltip)
show(bp)