world-ecoregion/biomes/data.py

import geopandas
import rasterio
import pandas as pd
import numpy as np
import time
from matplotlib import pyplot
from shapely.geometry import Point
from constants import *


def read_temp_data(year):
    return pd.read_csv(os.path.join(TEMP, 'air_temp.{}'.format(year)), sep='\s+', header=None,
                       names=['longitude', 'latitude', 'january',
                              'february', 'march', 'april',
                              'may', 'june', 'july', 'august',
                              'september', 'november', 'october',
                              'december', 'yearly_avg'])

def read_precip_data(year):
    return pd.read_csv(os.path.join(PRECIP, 'precip.{}'.format(year)), sep='\s+', header=None,
                       names=['longitude', 'latitude', 'january',
                              'february', 'march', 'april',
                              'may', 'june', 'july', 'august',
                              'september', 'november', 'october',
                              'december', 'yearly_avg'])

eco = geopandas.read_file(ECOREGIONS)

elevation = rasterio.open(ELEVATION)
elevation_data = elevation.read(1)

temp = {}
precip = {}
for year in range(MIN_YEAR, MAX_YEAR + 1):
    temp[year] = read_temp_data(year)
    precip[year] = read_precip_data(year)
    precip[year]['yearly_avg'] = precip[year].mean(axis=1)
    

world = geopandas.read_file(geopandas.datasets.get_path('naturalearth_lowres'))[['geometry']].unary_union
boundary = world.boundary

temp_precip_columns = []

for year in range(MIN_YEAR, MAX_YEAR + 1):
    for s in SEASONS:
        temp_precip_columns += ['temp_{}_{}'.format(s, year), 'precip_{}_{}'.format(s, year)]

columns = ['longitude', 'latitude', 'biome_num', 'biome_name', 'elevation', 'distance_to_water'] + temp_precip_columns
final_data = pd.DataFrame(columns=columns)

def get_point_information(longitude, latitude):
    item = {}
    p = Point(longitude, latitude)
    ecoregion = eco.loc[lambda c: c.geometry.contains(p)]
    if ecoregion.empty:
        return False

    item['longitude'] = longitude
    item['latitude'] = latitude
    item['biome_num'] = ecoregion.BIOME_NUM.iloc[0]
    item['biome_name'] = ecoregion.BIOME_NAME.iloc[0]

    elev = elevation_data[elevation.index(longitude, latitude)]
    item['elevation'] = elev

    distance_to_sea = p.distance(boundary)
    item['distance_to_water'] = distance_to_sea

    t = np.argmin(np.array((temp[MIN_YEAR].longitude - longitude)**2 + (temp[MIN_YEAR].latitude - latitude)**2))
    p = np.argmin(np.array((precip[MIN_YEAR].longitude - longitude)**2 + (precip[MIN_YEAR].latitude - latitude)**2))

    yearly_temp = {}
    yearly_precip = {}
    for year in range(MIN_YEAR, MAX_YEAR + 1):
        yearly_temp[year] = yt = temp[year].iloc[t, 2:]
        yearly_precip[year] = yp = precip[year].iloc[p, 2:]
        winter_temp = [yt.january, yt.february] + ([yearly_temp[year - 1].december] if year > MIN_YEAR else [])
        winter_precip = [yp.january, yp.february] + ([yearly_precip[year - 1].december] if year > MIN_YEAR else [])

        spring_temp = [yt[month] for month in SPRING_MONTHS]
        spring_precip = [yp[month] for month in SPRING_MONTHS]

        summer_temp = [yt[month] for month in SUMMER_MONTHS]
        summer_precip = [yp[month] for month in SUMMER_MONTHS]

        autumn_temp = [yt[month] for month in AUTUMN_MONTHS]
        autumn_precip = [yp[month] for month in AUTUMN_MONTHS]

        item['temp_winter_{}'.format(year)] = np.mean(winter_temp)
        item['precip_winter_{}'.format(year)] = np.mean(winter_precip)

        item['temp_spring_{}'.format(year)] = np.mean(spring_temp)
        item['precip_spring_{}'.format(year)] = np.mean(spring_precip)

        item['temp_summer_{}'.format(year)] = np.mean(summer_temp)
        item['precip_summer_{}'.format(year)] = np.mean(summer_precip)

        item['temp_autumn_{}'.format(year)] = np.mean(autumn_temp)
        item['precip_autumn_{}'.format(year)] = np.mean(autumn_precip)

    return item

data = {}
for col in columns:
    data[col] = []

# i = 0

start_time = time.time()

for longitude in range(-179, 179):
    print('-', end='')
    for latitude in range(-89, 89):

        # generate data and save to file
        d = get_point_information(longitude, latitude)
        if d == False:
            print('.', end='')
            continue

        for key, value in d.items():
            data[key].append(value)

        print('+', end='')

    print('')

print("--- Calculations: %s seconds ---" % (time.time() - start_time))

start_time = time.time()
df = pd.DataFrame(data)
print("--- Generating DataFrame: %s seconds ---" % (time.time() - start_time))
print(df)
start_time = time.time()
df.to_pickle('data.p')
print("--- Pickling DataFrame: %s seconds ---" % (time.time() - start_time))