PyLandStats

Overview

Open-source Pythonic library to compute landscape metrics within the PyData stack (NumPy, pandas, matplotlib...)

Features

Read GeoTiff files of land use/cover

import pylandstats as pls

ls = pls.read_geotiff('data/vaud_g100_clc00_V18_5.tif')

ls.plot_landscape(legend=True)

Compute pandas DataFrames of landscape metrics at the patch, class and landscape level

patch_metrics_df = ls.compute_patch_metrics_df()
patch_metrics_df.head()

class_metrics_df = ls.compute_class_metrics_df(metrics=['proportion_of_landscape', 'edge_density'])
class_metrics_df

Also analyze the spatio-temporal evolution of the landscape:

input_fnames = [
    'data/vaud_g100_clc00_V18_5.tif',
    'data/vaud_g100_clc06_V18_5a.tif',
    'data/vaud_g100_clc12_V18_5a.tif'
]

sta = pls.SpatioTemporalAnalysis(
    input_fnames, metrics=[
        'proportion_of_landscape',
        'edge_density',
        'fractal_dimension_am',
        'landscape_shape_index',
        'shannon_diversity_index'
    ], classes=[1], dates=[2000, 2006, 2012], 
)

fig, axes = sta.plot_metrics(
    class_val=1,
    metrics=['proportion_of_landscape', 'edge_density', 'fractal_dimension_am'],
    num_cols=3)
fig.suptitle('Class-level metrics (urban)')

See the pylandstats-notebooks repository for a more complete overview

Installation

To install use pip:

$ pip install pylandstats

Or clone the repo:

$ git clone https://github.com/martibosch/pylandstats.git
$ python setup.py install