# !pip install geemap scikit-learn

import ee
import geemap
import pandas as pd

from geemap import ml
from sklearn import ensemble

geemap.ee_initialize()

# read the feature table to train our RandomForest model
# data taken from ee.FeatureCollection('GOOGLE/EE/DEMOS/demo_landcover_labels')

url = "https://raw.githubusercontent.com/gee-community/geemap/master/examples/data/rf_example.csv"
df = pd.read_csv(url)

df

# specify the names of the features (i.e. band names) and label
# feature names used to extract out features and define what bands

feature_names = ["B2", "B3", "B4", "B5", "B6", "B7"]
label = "landcover"

# get the features and labels into separate variables
X = df[feature_names]
y = df[label]

# create a classifier and fit
n_trees = 10
rf = ensemble.RandomForestClassifier(n_trees).fit(X, y)

# convert the estimator into a list of strings
# this function also works with the ensemble.ExtraTrees estimator
trees = ml.rf_to_strings(rf, feature_names)

# print the first tree to see the result
print(trees[0])

print(trees[1])

# number of trees we converted should equal the number of trees we defined for the model
len(trees) == n_trees

# create a ee classifier to use with ee objects from the trees
ee_classifier = ml.strings_to_classifier(trees)

# ee_classifier.getInfo()

# Make a cloud-free Landsat 8 TOA composite (from raw imagery).
l8 = ee.ImageCollection("LANDSAT/LC08/C01/T1")

image = ee.Algorithms.Landsat.simpleComposite(
    collection=l8.filterDate("2018-01-01", "2018-12-31"), asFloat=True
)

# classify the image using the classifier we created from the local training
# note: here we select the feature_names from the image that way the classifier knows which bands to use
classified = image.select(feature_names).classify(ee_classifier)

# display results
Map = geemap.Map(center=(37.75, -122.25), zoom=11)

Map.addLayer(
    image,
    {"bands": ["B7", "B5", "B3"], "min": 0.05, "max": 0.55, "gamma": 1.5},
    "image",
)
Map.addLayer(
    classified,
    {"min": 0, "max": 2, "palette": ["red", "green", "blue"]},
    "classification",
)

Map

user_id = geemap.ee_user_id()
user_id

# specify asset id where to save trees
# be sure to change <user_name> to your ee user name
asset_id = user_id + "/random_forest_strings_test"
asset_id

# kick off an export process so it will be saved to the ee asset
ml.export_trees_to_fc(trees, asset_id)

# this will kick off an export task, so wait a few minutes before moving on

# read the exported tree feature collection
rf_fc = ee.FeatureCollection(asset_id)

# convert it to a classifier, very similar to the `ml.trees_to_classifier` function
another_classifier = ml.fc_to_classifier(rf_fc)

# classify the image again but with the classifier from the persisted trees
classified = image.select(feature_names).classify(another_classifier)

# display results
# we should get the exact same results as before
Map = geemap.Map(center=(37.75, -122.25), zoom=11)

Map.addLayer(
    image,
    {"bands": ["B7", "B5", "B3"], "min": 0.05, "max": 0.55, "gamma": 1.5},
    "image",
)
Map.addLayer(
    classified,
    {"min": 0, "max": 2, "palette": ["red", "green", "blue"]},
    "classification",
)

Map

import os

out_csv = os.path.expanduser("~/Downloads/trees.csv")

ml.trees_to_csv(trees, out_csv)

another_classifier = ml.csv_to_classifier(out_csv)

classified = image.select(feature_names).classify(another_classifier)

# display results
# we should get the exact same results as before
Map = geemap.Map(center=(37.75, -122.25), zoom=11)

Map.addLayer(
    image,
    {"bands": ["B7", "B5", "B3"], "min": 0.05, "max": 0.55, "gamma": 1.5},
    "image",
)
Map.addLayer(
    classified,
    {"min": 0, "max": 2, "palette": ["red", "green", "blue"]},
    "classification",
)

Map