| from __future__ import annotations | |
| from contextlib import contextmanager | |
| from typing import NamedTuple, Callable, Optional, Any | |
| import numpy as np | |
| Array = Any | |
| class Node(NamedTuple): | |
| vjp: Optional[Callable] | |
| parents: List[Node] |
| using CairoMakie | |
| # using Animations | |
| using Distributions | |
| using Random | |
| using AbstractTrees | |
| CairoMakie.activate!() | |
| mutable struct Partition | |
| x | |
| y |
| '# Advent of Code 2020. Day 1 | |
| DexLang, [Lyndon White](http://oxinabox.net) | |
| ## part 1 | |
| From the list find two entries that sum to 2020, and compute their product. | |
| list = [1567, 1223, 1758, 1842, 1933, 1898, 1409, 1058, 1533, 1417, 1032, 1634, 1477, 1394, 1888, 1972, 1237, 1390, 1677, 1546, 1302, 1070, 1369, 1455, 1065, 1924, 1593, 1131, 1064, 1346, 1914, 1129, 1830, 1450, 1278, 1740, 1809, 1176, 1734, 1102, 1807, 1982, 1603, 1736, 2008, 1980, 1905, 1633, 1732, 1350, 1865, 1988, 1805, 1998, 1152, 1046, 1870, 1557, 1789, 1766, 1945, 1359, 1002, 1126, 1719, 1497, 1296, 1560, 1936, 1929, 1464, 2005, 1281, 618, 1257, 1107, 1632, 1688, 1964, 1803, 1360, 1384, 1889, 1411, 1328, 1452, 1868, 1515, 1586, 1631, 1618, 1087, 1710, 1094, 1774, 1295, 1700, 1636, 1230, 1421, 1910, 1522, 1366, 1144, 1757, 1493, 1316, 1103, 687, 1371, 1720, 1155, 1559, 1900, 989, 1367, 1999, 1066, 1773, 1787, 1402, 1047, 1806, 1956, 1219, 1555, 1307, 1419, 1706, 1884, 1109, 1181, 2010, 1298, 1730, 1078, 1848, 1398, 1687, 2007, 1550, 1664, 1225 |
| """ Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """ | |
| import numpy as np | |
| import cPickle as pickle | |
| import gym | |
| # hyperparameters | |
| H = 200 # number of hidden layer neurons | |
| batch_size = 10 # every how many episodes to do a param update? | |
| learning_rate = 1e-4 | |
| gamma = 0.99 # discount factor for reward |
| """ | |
| Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy) | |
| BSD License | |
| """ | |
| import numpy as np | |
| # data I/O | |
| data = open('input.txt', 'r').read() # should be simple plain text file | |
| chars = list(set(data)) | |
| data_size, vocab_size = len(data), len(chars) |
The following recipes are sampled from a trained neural net. You can find the repo to train your own neural net here: https://github.com/karpathy/char-rnn Thanks to Andrej Karpathy for the great code! It's really easy to setup.
The recipes I used for training the char-rnn are from a recipe collection called ffts.com And here is the actual zipped data (uncompressed ~35 MB) I used for training. The ZIP is also archived @ archive.org in case the original links becomes invalid in the future.
