1
pip install earthpy

1
import osimport matplotlib.pyplot as pltimport earthpy as etimport earthpy.plot as epimport rioxarray
2
# Download sample datadata = et.data.get_data('colorado-flood')
3
# Set working directory to earthpy data directoryos.chdir(os.path.join(et.io.HOME, 'earth-analytics', 'data'))
4
# Define path to filedem_pre_path = os.path.join("colorado-flood",                             "spatial",                            "boulder-leehill-rd",                             "pre-flood",                             "lidar",                            "pre_DTM.tif")
5
# Read the data using rioxarraydem_pre = rioxarray.open_rasterio(dem_pre_path, masked=True).squeeze()
6
# Plot DEMfig, ax = plt.subplots(figsize=(10, 6))ep.plot_bands(dem_pre,               cmap='terrain',               title="Lidar Digital Elevation Model (DEM) \n Boulder Flood 2013",               ax=ax)plt.show()

1
import earthpy as ep
2
ep.data.path = "."ep.data.get_data('colorado-flood')
3
im = epp.plot_bands(arr_st, cmap='RdYlGn', figsize=(12, 12))
4
plt.show()

1
import earthpy.plot as epp
2
data = ep.data.get_data('vignette-landsat') landsat_path = glob("vignette-landsat/LC08_L1TP_034032_20160621_20170221_01_T1_sr_band*_crop.tif")landsat_path.sort()
3
# Stacking Bandsarr_st, meta = es.stack(landsat_path, nodata=-9999)
4
colors = ['tomato', 'navy', 'MediumSpringGreen', 'lightblue', 'orange', 'maroon', 'yellow']
5
epp.hist(arr_st, colors = colors, title=[f'Band-{i}' for i in range(1, 8)], cols=3, alpha=0.5, figsize = (12, 10), )
6
plt.show()

1
# Landsat 8 red band is band 4 at [3]# Landsat 8 near-infrared band is band 5 at [4]
2
ndvi = es.normalized_diff(arr_st[4], arr_st[3])
3
titles = ["Landsat 8 - Normalized Difference Vegetation Index (NDVI)"]
4
epp.plot_bands(ndvi, cmap="RdYlGn", cols=1, title=titles, vmin=-1, vmax=1, figsize=(10, 10))
5
plt.show()

1
ndvi_class_bins = [-np.inf, 0, 0.15, 0.23, 0.6, np.inf]
2

3
ndvi_landsat_class = np.digitize(ndvi, ndvi_class_bins)
4
# Apply the nodata mask to the newly classified NDVI datandvi_landsat_class = np.ma.masked_where(np.ma.getmask(ndvi), ndvi_landsat_class)
5
np.unique(ndvi_landsat_class)
6
nbr_colors = ["gray", "y", "yellowgreen", "g", "darkgreen"]nbr_cmap = ListedColormap(nbr_colors)
7
# Define class namesndvi_cat_names = [    "No Vegetation",    "Bare Area",    "Low Vegetation",    "Moderate Vegetation",    "High Vegetation",]
8
# Get list of classesclasses = np.unique(ndvi_landsat_class)
9
classes = classes.tolist()
10
# The mask returns a value of none in the classes. remove thatclasses = classes[0:5]
11
# Plot the datafig, ax = plt.subplots(figsize=(10, 10))
12
im = ax.imshow(ndvi_landsat_class, cmap=nbr_cmap)
13
epp.draw_legend(im_ax=im, classes=classes, titles=ndvi_cat_names)
14
ax.set_title(    "Landsat 8 - Normalized Difference Vegetation Index (NDVI) Classes",    fontsize=14,)
15
ax.set_axis_off()
16
# Auto adjust subplot to fit figure size
17
plt.tight_layout()