updates

nn.py

@@ -11,6 +11,7 @@ import pandas as pd
 import os.path
 
 from utils import *
+# from predict import predicted_map
 
 RANDOM_SEED = 1
 
@@ -23,6 +24,11 @@ np.random.seed(RANDOM_SEED)
 
 df = pd.read_pickle('data.p')
 
+class MapHistory(keras.callbacks.Callback):
+    def on_epoch_end(self, epoch, logs):
+        print('EPOCH', epoch)
+        predicted_map('maps/{}'.format(epoch))
+
 class Model():
     def __init__(self, name, batch_size=16, shuffle_buffer_size=500, learning_rate=0.001, epochs=1):
         self.name = name
@@ -42,6 +48,8 @@ class Model():
         (training, test) = (self.dataset.take(self.TRAIN_SIZE).batch(self.batch_size).repeat(),
                             self.dataset.skip(self.TRAIN_SIZE).batch(self.batch_size).repeat())
 
+        # print(df.groupby(['biome_num']).agg({ 'biome_num': lambda x: x.count() / df.shape[0] }))
+
         print('dataset: size={}, train={}, test={}'.format(dataset_size, self.TRAIN_SIZE, self.TEST_SIZE))
         print('input_size={}'.format(features))
 
@@ -58,6 +66,7 @@ class Model():
                 # 'kernel_regularizer': keras.regularizers.l2(l=0.01)
         }
         dropout = [keras.layers.Dropout(0.1, input_shape=[self.features])]
+        # dropout = []
         self.model = keras.Sequential(dropout + [
             keras.layers.Dense(layers[0], activation=tf.nn.elu, **params)
         ] + [
@@ -69,7 +78,6 @@ class Model():
     def compile(self, loss='mse', metrics=['accuracy'], optimizer=tf.train.AdamOptimizer, load_weights=True):
         if load_weights:
             self.model.load_weights(self.path)
-            print('loaded weights')
 
         optimizer = optimizer(self.learning_rate)
 
@@ -92,16 +100,19 @@ class Model():
     def train(self):
         self.model.summary()
 
-        checkpoint = keras.callbacks.ModelCheckpoint(self.path, monitor='acc', verbose=1, mode='max')
+        checkpoint = keras.callbacks.ModelCheckpoint(self.path, monitor='val_loss', verbose=1, mode='min', save_best_only=True)
         tensorboard = keras.callbacks.TensorBoard(log_dir='./logs', update_freq='epoch')
-        map_callback = keras.callbacks.LambdaCallback(on_epoch_end=self.evaluate_print)
+        # reduce_lr = keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=5, min_lr=0.0001)
+        # map_callback = MapHistory()
 
         self.model.fit(
             self.training,
             batch_size=self.batch_size,
             epochs=self.epochs,
-            steps_per_epoch=int(self.dataset_size / self.batch_size),
+            steps_per_epoch=int(self.TRAIN_SIZE / self.batch_size),
             callbacks=[checkpoint, tensorboard],
+            validation_data=self.test,
+            validation_steps=int(self.TEST_SIZE / self.batch_size),
             verbose=1
         )
 
@@ -109,12 +120,13 @@ class Model():
         return np.argmax(self.model.predict(a), axis=1)
 
 A = Model('a', epochs=2)
-B = Model('b', learning_rate=0.001, epochs=20)
+B = Model('b', learning_rate=0.0005, epochs=50)
 
+# 24 so far
 def compile_b():
     B.prepare_dataset(df, dataframe_to_dataset_biomes)
-    B.create_model([32, 32], tf.nn.softmax)
+    B.create_model([12], tf.nn.softmax)
-    B.compile(loss='sparse_categorical_crossentropy')
+    B.compile(loss='sparse_categorical_crossentropy', load_weights=False)
 
 def compile_a():
     A.prepare_dataset(df, dataframe_to_dataset_temp_precip)

predict.py

@@ -8,13 +8,12 @@ import time
 def chunker(seq, size):
     return (seq[pos:pos + size] for pos in range(0, len(seq), size))
 
+
+def predicted_map(path=None):
     year = MAX_YEAR - 1
 
     df = pd.read_pickle('data.p')
 
-compile_b()
-
-for change in range(0, 1):
     print('TEMPERATURE MODIFICATION OF {}'.format(change))
 
     inputs = ['elevation', 'distance_to_water', 'latitude']
@@ -50,4 +49,9 @@ for change in range(0, 1):
         }, columns=columns)
         new_data = new_data.append(f)
 
-    draw(new_data)
+    draw(new_data, path=path)
+
+if __name__ == "__main__":
+    compile_b()
+    predicted_map()
+