world-ecoregion/nn.py

from __future__ import absolute_import, division, print_function

# TensorFlow and tf.keras
import tensorflow as tf
from tensorflow import keras

# Helper libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
import os.path

from utils import *

RANDOM_SEED = 1

tf.enable_eager_execution()

tf.set_random_seed(RANDOM_SEED)
np.random.seed(RANDOM_SEED)

df = pd.read_pickle('data_final.p')

class Model():
    def __init__(self, name, batch_size=16, shuffle_buffer_size=500, learning_rate=0.001, epochs=1):
        self.name = name
        self.path = "checkpoints/{}.hdf5".format(name)

        self.batch_size = batch_size
        self.shuffle_buffer_size = shuffle_buffer_size
        self.learning_rate = learning_rate 
        self.epochs = epochs

    def prepare_dataset(self, df, fn):
        self.dataset_fn = fn
        dataset_size, features, output_size, dataset = fn(df)
        self.dataset = dataset.shuffle(self.shuffle_buffer_size)
        self.TRAIN_SIZE = int(dataset_size * 0.85)
        self.TEST_SIZE = dataset_size - self.TRAIN_SIZE
        (training, test) = (self.dataset.take(self.TRAIN_SIZE).batch(self.batch_size).repeat(),
                            self.dataset.skip(self.TRAIN_SIZE).batch(self.batch_size).repeat())

        self.dataset_size = dataset_size
        self.features = features
        self.output_size = output_size
        self.training = training
        self.test = test

    def create_model(self, layers, out_activation):
        params = {
                'kernel_initializer': 'lecun_uniform',
                'bias_initializer': 'zeros',
        }
        self.model = keras.Sequential([
            keras.layers.Dense(layers[0], activation=tf.nn.elu, input_shape=[self.features], **params)
        ] + [
            keras.layers.Dense(n, activation=tf.nn.elu, **params) for n in layers[1:]
        ] + [
            keras.layers.Dense(self.output_size, activation=out_activation, **params)
        ])

    def compile(self, loss='mse', metrics=['accuracy'], optimizer=tf.train.AdamOptimizer):
        # self.model.load_weights(self.path)
        optimizer = optimizer(self.learning_rate)

        self.model.compile(loss=loss,
                    optimizer=optimizer,
                    metrics=metrics)

    def evaluate(self):
        return self.model.evaluate(
            self.test,
            batch_size=self.batch_size,
            steps=int(self.dataset_size / self.batch_size),
            verbose=1
        )

    def train(self):
        self.model.summary()

        checkpoint = keras.callbacks.ModelCheckpoint(self.path, monitor='acc', verbose=1, mode='max')
        tensorboard = keras.callbacks.TensorBoard(log_dir='./logs')
        # map_callback = keras.callbacks.LambdaCallback(on_epoch_end=self.map_callback)

        self.model.fit(
            self.training,
            batch_size=self.batch_size,
            epochs=self.epochs,
            steps_per_epoch=int(self.dataset_size / self.batch_size),
            callbacks=[checkpoint, tensorboard],
            verbose=1
        )

    def predict(self, a):
        return np.argmax(self.model.predict(a), axis=1)

A = Model('a', epochs=2)
B = Model('b', learning_rate=0.005, epochs=100)

def compile_b():
    B.prepare_dataset(df, dataframe_to_dataset_biomes)
    B.create_model([64, 128], tf.nn.softmax)
    B.compile(loss='sparse_categorical_crossentropy')

def compile_a():
    A.prepare_dataset(df, dataframe_to_dataset_temp_precip)
    A.create_model([(4, tf.nn.elu)])
    A.compile(metrics=['accuracy', 'mae'])

if __name__ == "__main__":
    compile_b()
    B.train()

    # for inp, out in B.test.take(1).make_one_shot_iterator():
        # print(inp, out)

    # print(np.unique(nums))
    # print(np.unique(predictions))
    # print('loss: {}, evaluation: {}'.format(*B.evaluate()))

    compile_a()
    A.train()