Plot GBIF parakeet observation data

gbifparakeet.py

import os, sys, csv
import numpy as np
import pandas as pd

from matplotlib.backends.backend_pdf import PdfPages
import matplotlib.pyplot as plt
import imageio

###################################################################################
# config:

specieslist = {
	"Psittacula krameri": {'color':'g', 'label': 'rr parakeet'},
	"Actitis hypoleucos": {'color':'y', 'label': 'c sandpiper'},
}

srcfiles = [os.path.expanduser(fpath) for fpath in [
	"~/Documents/gbif/0028923-190918142434337-rrparakeet.csv",
	"~/Documents/gbif/0029141-190918142434337-commonsandpiper.csv",
]]

yearmin = 2000
yearmax = 2019

###################################################################################
# load two sets of GBIF CSV data, trimming to only those with years in range, and observation positive

data = None

for asrc in srcfiles:
	print("Loading file %s" % asrc)
	df = pd.read_csv(asrc, sep='\t')  #, dtype={'year':int})
	print("   %i rows" % len(df))
	# ensure trimmed to desired years and species, and also drop absence records
	df = df[(df['verbatimScientificName'].isin(specieslist.keys())) & (df['year']>=yearmin) & (df['year']<yearmax) & (df['occurrenceStatus']!='absent')]
	print("   %i rows after trimming" % len(df))
	df.loc[df.individualCount.isna(),'individualCount'] = 1  # This is an assumption - if not mentioned, assuming they refer to one bird seen. Really, it's "presence" rather than "count".

	if data is None:
		data = df
	else:
		data = pd.concat([data, df])

print("%i rows in overall loaded dataset" % len(data))

###################################################################################
# Now iterate through the years, plotting

pdf = PdfPages("plot_gbif_parakeet.pdf")
animdata = []

if True:
	for year in range(yearmin, yearmax):
		fig, ax = plt.subplots(figsize=(6, 10))

		for binom, spdata in specieslist.items():
			subset = data[(data.year==year) & (data.verbatimScientificName==binom)]
			plt.scatter(subset['decimalLongitude'], subset['decimalLatitude'], marker='.', alpha=0.4, color=spdata['color'], label=spdata['label'])

		plt.legend()
		plt.ylabel('Longitude')
		plt.xlabel('Latitude')
		plt.xlim(-6, 2)
		plt.ylim(50, 58)
		plt.title("%i" % (year))
		pdf.savefig(fig)

		fig.canvas.draw()
		image = np.frombuffer(fig.canvas.tostring_rgb(), dtype='uint8')
		image  = image.reshape(fig.canvas.get_width_height()[::-1] + (3,))
		animdata.append(image)

		plt.close()

pdf.close()

imageio.mimsave('plot_gbif_parakeet.gif', animdata, fps=1)