network trains and tests but slow? -- investigate

library.py

@@ -1,16 +1,9 @@
 import os
 os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'
 
+import numpy as np
 import tensorflow as tf
 tf.compat.v1.logging.set_verbosity(tf.compat.v1.logging.ERROR)  # STFU!
-# from nltk.corpus import stopwords
-# from nltk.tokenize import word_tokenize
-from mynet import load_mnist, onehot
-
-
-def word_tokenize(s: str):
-    l = ''.join(c.lower() if c.isalpha() else ' ' for c in s)
-    return l.split()
 
 
 HERE = os.path.abspath(os.path.dirname(__file__))
@@ -20,10 +13,38 @@ VOCAB = os.path.join(HERE, 'vocab.txt')
 vocab = {
     w: i for i, w in enumerate(open(VOCAB).read().splitlines(keepends=False))
 }
-# inv_vocab = [vocab[i] for i in range(len(vocab))]
 inv_vocab = sorted(vocab, key=vocab.get)
 
 
+def onehot(oh_store, idx):
+    oh_store[:] = 0
+    oh_store[np.arange(len(idx)), idx.astype(np.int)] = 1
+
+
+def word_tokenize(s: str):
+    l = ''.join(c.lower() if c.isalpha() else ' ' for c in s)
+    return l.split()
+
+
+def create_test_dataset(win):
+    S = 1000
+    with open(CORPUS) as f:
+        ds = np.array([vocab[w] for w in word_tokenize(f.read())
+                       if w in vocab])
+    idx = np.random.choice(np.arange(win, len(ds) - win), S)
+    oh_store = np.zeros((S, len(vocab)), dtype=np.float32)
+    onehot(oh_store, ds[idx])
+    return (
+        # X
+        np.stack([
+            np.concatenate([ds[i-win:i], ds[i+1:i+win+1]])
+            for i in idx
+        ], axis=0).astype(np.float32),
+
+        #y
+        oh_store
+    )
+
 def create_mnist_network():
     model = tf.keras.models.Sequential([
         tf.keras.layers.Dense(30, input_shape=(784,), activation='relu'),
@@ -35,8 +56,8 @@ def create_mnist_network():
 
 
 def create_cbow_network(win, embed):
-    ctxt = tf.keras.layers.Input(shape=[win])
-    ed = tf.keras.layers.Embedding(len(vocab), embed, input_length=win)(ctxt)
+    ctxt = tf.keras.layers.Input(shape=[2*win])
+    ed = tf.keras.layers.Embedding(len(vocab), embed, input_length=2*win)(ctxt)
     cbow = tf.keras.layers.Lambda(lambda x: tf.reduce_mean(x, axis=1))(ed)
     blowup = tf.keras.layers.Dense(len(vocab), activation='softmax')(cbow)
     mod = tf.keras.Model(inputs=ctxt, outputs=blowup)
@@ -44,7 +65,6 @@ def create_cbow_network(win, embed):
         optimizer='sgd',
         loss='categorical_crossentropy',
     )
-    print(mod, flush=True)
     return mod