datashader

Links: notebook, html, PDF, python, slides, GitHub

datashader plots huge volume of data.

documentation source tutorial

from jyquickhelper import add_notebook_menu
add_notebook_menu()

import bokeh.plotting as bp
bp.output_notebook()

Loading BokehJS ...

import datashader
datashader.__version__

'0.6.4dev1'

The version should be higher than 0.6.4.

short example

From 4_Trajectories.ipynb.

import pandas as pd
import numpy as np
import xarray as xr
# On Windows, you must run the notebook with admin right
# otherwise the following instruction does not end.
import datashader
import datashader as ds
import datashader.transfer_functions as tf

# Constants
np.random.seed(1)
n = 1000000 # Number of points
f = filter_width = 5000 # momentum or smoothing parameter, for a moving average filter

# filtered random walk
xs = np.convolve(np.random.normal(0, 0.1, size=n), np.ones(f)/f).cumsum()
ys = np.convolve(np.random.normal(0, 0.1, size=n), np.ones(f)/f).cumsum()

# Add "mechanical" wobble on the x axis
xs += 0.1*np.sin(0.1*np.array(range(n-1+f)))

# Add "measurement" noise
xs += np.random.normal(0, 0.005, size=n-1+f)
ys += np.random.normal(0, 0.005, size=n-1+f)

# Add a completely incorrect value
xs[int(len(xs)/2)] = 100
ys[int(len(xs)/2)] = 0

# Create a dataframe
df = pd.DataFrame(dict(x=xs,y=ys))

# Default plot ranges:
x_range = (xs.min(), xs.max())
y_range = (ys.min(), ys.max())

df.tail()

	x	y
1004994	65.164829	-105.064056
1004995	65.177603	-105.069781
1004996	65.190898	-105.071699
1004997	65.194054	-105.054657
1004998	65.204752	-105.073366

def create_image(x_range=x_range, y_range=y_range, w=500, h=500):
    cvs = ds.Canvas(x_range=x_range, y_range=y_range, plot_height=h, plot_width=w)
    agg = cvs.line(df, 'x', 'y', agg=ds.any())
    return tf.shade(agg)

%time create_image()

Wall time: 1.1 s

from datashader.bokeh_ext import InteractiveImage
import bokeh.plotting as bp


def base_plot(tools='pan,wheel_zoom,reset'):
    p = bp.figure(tools=tools, plot_width=500, plot_height=500,
        x_range=x_range, y_range=y_range, outline_line_color=None,
        min_border=0, min_border_left=0, min_border_right=0,
        min_border_top=0, min_border_bottom=0)
    p.xgrid.grid_line_color = None
    p.ygrid.grid_line_color = None
    return p

p = base_plot()
InteractiveImage(p, create_image)