jprdonnelly/pyscript
1
0
Fork 0
mirror of https://github.com/pyscript/pyscript.git synced 2025-12-19 18:27:29 -05:00
Code Issues Projects Releases Wiki Activity

Micrograd example (#116)

Browse Source 
* added micrograd_ai.html and micrograd_ai.py to examples

* added micrograd_ai.html and micrograd_ai.py to examples fix typo
This commit is contained in:
matdmiller
2022-05-05 16:44:14 -05:00
committed by GitHub
parent ac7ee85838
commit f4ed3591ca
2 changed files with 334 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

192
pyscriptjs/examples/micrograd_ai.html Normal file
View File

@@ -0,0 +1,192 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8" />
<link rel="icon" type="image/x-icon" href="./favicon.png">
<title>micrograd</title>
<link rel="stylesheet" href="../build/pyscript.css" />
<script defer src="../build/pyscript.js"></script>
<py-env>
- micrograd
- numpy
- matplotlib
</py-env>
<link href="https://cdn.jsdelivr.net/npm/bootstrap@5.1.3/dist/css/bootstrap.min.css" rel="stylesheet" crossorigin="anonymous">
</head>
<body style="padding-top: 20px; padding-right: 20px; padding-bottom: 20px; padding-left: 20px">
<h1>Micrograd - A tiny Autograd engine (with a bite! :))</h1><br>
<div>
<p>
<a href="https://github.com/karpathy/micrograd">Micrograd</a> is a tiny Autograd engine created
by <a href="https://twitter.com/karpathy">Andrej Karpathy</a>. This app recreates the
<a href="https://github.com/karpathy/micrograd/blob/master/demo.ipynb">demo</a>
he prepared for this package using pyscript to train a basic model, written in Python, natively in
the browser. <br>
</p>
</div>
<div>
<p>
You may run each Python REPL cell interactively by pressing (Shift + Enter) or (Ctrl + Enter).
You can also modify the code directly as you wish. If you want to run all the code at once,
not each cell individually, you may instead click the 'Run All' button. Training the model
takes between 1-2 min if you decide to 'Run All' at once. 'Run All' is your only option if
you are running this on a mobile device where you cannot press (Shift + Enter). After the
model is trained, a plot image should be displayed depicting the model's ability to
classify the data. <br>
</p>
<p>
Currently the <code>&gt;</code> symbol is being imported incorrectly as <code>&ampgt;</code> into the REPL's.
In this app the <code>&gt;</code> symbol has been replaced with <code>().__gt__()</code> so you can run the code
without issue. Ex: intead of <code>a &gt; b</code>, you will see <code>(a).__gt__(b)</code> instead. <br>
</p>
<p>
<py-script>import js; js.document.getElementById('python-status').innerHTML = 'Python is now ready. You may proceed.'</py-script>
<div id="python-status">Python is currently starting. Please wait...</div>
</p>
<p>
<button id="run-all-button" class="btn btn-primary" type="submit" pys-onClick="run_all_micrograd_demo">Run All</button><br>
<py-script src="/micrograd_ai.py"></py-script>
<div id="micrograd-run-all-print-div"></div><br>
<div id="micrograd-run-all-fig1-div"></div>
<div id="micrograd-run-all-fig2-div"></div><br>
</p>
</div>
<py-repl auto-generate="false">
import random
import numpy as np
import matplotlib.pyplot as plt
</py-repl><br>
<py-repl auto-generate="false">
from micrograd.engine import Value
from micrograd.nn import Neuron, Layer, MLP
</py-repl><br>
<py-repl auto-generate="true">
np.random.seed(1337)
random.seed(1337)
</py-repl><br>
<py-repl auto-generate="true">
#An adaptation of sklearn's make_moons function https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_moons.html
def make_moons(n_samples=100, noise=None):
n_samples_out, n_samples_in = n_samples, n_samples
outer_circ_x = np.cos(np.linspace(0, np.pi, n_samples_out))
outer_circ_y = np.sin(np.linspace(0, np.pi, n_samples_out))
inner_circ_x = 1 - np.cos(np.linspace(0, np.pi, n_samples_in))
inner_circ_y = 1 - np.sin(np.linspace(0, np.pi, n_samples_in)) - 0.5
X = np.vstack([np.append(outer_circ_x, inner_circ_x), np.append(outer_circ_y, inner_circ_y)]).T
y = np.hstack([np.zeros(n_samples_out, dtype=np.intp), np.ones(n_samples_in, dtype=np.intp)])
if noise is not None: X += np.random.normal(loc=0.0, scale=noise, size=X.shape)
return X, y
X, y = make_moons(n_samples=100, noise=0.1)
</py-repl><br>
<py-repl auto-generate="true">
y = y*2 - 1 # make y be -1 or 1
# visualize in 2D
plt.figure(figsize=(5,5))
plt.scatter(X[:,0], X[:,1], c=y, s=20, cmap='jet')
plt
</py-repl><br>
<py-repl auto-generate="true">
model = MLP(2, [16, 16, 1]) # 2-layer neural network
print(model)
print("number of parameters", len(model.parameters()))
</py-repl><br>
<div>
Line 24 has been changed from: <br>
<code>accuracy = [(yi &gt; 0) == (scorei.data &gt; 0) for yi, scorei in zip(yb, scores)]</code><br>
to: <br>
<code>accuracy = [((yi).__gt__(0)) == ((scorei.data).__gt__(0)) for yi, scorei in zip(yb, scores)]</code><br>
</div>
<py-repl auto-generate="true">
# loss function
def loss(batch_size=None):
# inline DataLoader :)
if batch_size is None:
Xb, yb = X, y
else:
ri = np.random.permutation(X.shape[0])[:batch_size]
Xb, yb = X[ri], y[ri]
inputs = [list(map(Value, xrow)) for xrow in Xb]
# forward the model to get scores
scores = list(map(model, inputs))
# svm "max-margin" loss
losses = [(1 + -yi*scorei).relu() for yi, scorei in zip(yb, scores)]
data_loss = sum(losses) * (1.0 / len(losses))
# L2 regularization
alpha = 1e-4
reg_loss = alpha * sum((p*p for p in model.parameters()))
total_loss = data_loss + reg_loss
# also get accuracy
accuracy = [((yi).__gt__(0)) == ((scorei.data).__gt__(0)) for yi, scorei in zip(yb, scores)]
return total_loss, sum(accuracy) / len(accuracy)
total_loss, acc = loss()
print(total_loss, acc)
</py-repl><br>
<py-repl auto-generate="true">
# optimization
for k in range(20): #was 100. Accuracy can be further improved w/ more epochs (to 100%).
# forward
total_loss, acc = loss()
# backward
model.zero_grad()
total_loss.backward()
# update (sgd)
learning_rate = 1.0 - 0.9*k/100
for p in model.parameters():
p.data -= learning_rate * p.grad
if k % 1 == 0:
print(f"step {k} loss {total_loss.data}, accuracy {acc*100}%")
</py-repl><br>
<div>
<p>
Please wait for the training loop above to complete. It will not print out stats until it
has completely finished. This typically takes 1-2 min. <br><br>
Line 9 has been changed from: <br>
<code>Z = np.array([s.data &gt; 0 for s in scores])</code><br>
to: <br>
<code>Z = np.array([(s.data).__gt__(0) for s in scores])</code><br>
</p>
</div>
<py-repl auto-generate="true">
h = 0.25
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
Xmesh = np.c_[xx.ravel(), yy.ravel()]
inputs = [list(map(Value, xrow)) for xrow in Xmesh]
scores = list(map(model, inputs))
Z = np.array([(s.data).__gt__(0) for s in scores])
Z = Z.reshape(xx.shape)
fig = plt.figure()
plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral, alpha=0.8)
plt.scatter(X[:, 0], X[:, 1], c=y, s=40, cmap=plt.cm.Spectral)
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
plt
</py-repl><br>
<py-repl auto-generate="true">
1+1
</py-repl><br>
</body>
</html>
<!-- Adapted by Mat Miller -->

142
pyscriptjs/examples/micrograd_ai.py Normal file
View File

@@ -0,0 +1,142 @@
#Credit: https://github.com/karpathy/micrograd/blob/master/demo.ipynb
#cell
import random
import numpy as np
import matplotlib.pyplot as plt
import datetime
#cell
from micrograd.engine import Value
from micrograd.nn import Neuron, Layer, MLP
print_statements = []
def run_all_micrograd_demo(*args,**kwargs):
result = micrograd_demo()
pyscript.write('micrograd-run-all-fig2-div', result)
def print_div(o):
o = str(o)
print_statements.append(o + ' \n<br>')
pyscript.write('micrograd-run-all-print-div', ''.join(print_statements))
#All code is wrapped in this run_all function so it optionally executed (called)
#from pyscript when a button is pressed.
def micrograd_demo(*args,**kwargs):
"""
Runs the micrograd demo.
*args and **kwargs do nothing and are only there to capture any parameters passed
from pyscript when this function is called when a button is clicked.
"""
#cell
start = datetime.datetime.now()
print_div('Starting...')
#cell
np.random.seed(1337)
random.seed(1337)
#cell
#An adaptation of sklearn's make_moons function https://scikit-learn.org/stable/modules/generated/sklearn.datasets.make_moons.html
def make_moons(n_samples=100, noise=None):
n_samples_out, n_samples_in = n_samples, n_samples
outer_circ_x = np.cos(np.linspace(0, np.pi, n_samples_out))
outer_circ_y = np.sin(np.linspace(0, np.pi, n_samples_out))
inner_circ_x = 1 - np.cos(np.linspace(0, np.pi, n_samples_in))
inner_circ_y = 1 - np.sin(np.linspace(0, np.pi, n_samples_in)) - 0.5
X = np.vstack([np.append(outer_circ_x, inner_circ_x), np.append(outer_circ_y, inner_circ_y)]).T
y = np.hstack([np.zeros(n_samples_out, dtype=np.intp), np.ones(n_samples_in, dtype=np.intp)])
if noise is not None: X += np.random.normal(loc=0.0, scale=noise, size=X.shape)
return X, y
X, y = make_moons(n_samples=100, noise=0.1)
#cell
y = y*2 - 1 # make y be -1 or 1
# visualize in 2D
plt.figure(figsize=(5,5))
plt.scatter(X[:,0], X[:,1], c=y, s=20, cmap='jet')
plt
pyscript.write('micrograd-run-all-fig1-div', plt)
#cell
model = MLP(2, [16, 16, 1]) # 2-layer neural network
print_div(model)
print_div(("number of parameters", len(model.parameters())))
#cell
# loss function
def loss(batch_size=None):
# inline DataLoader :)
if batch_size is None:
Xb, yb = X, y
else:
ri = np.random.permutation(X.shape[0])[:batch_size]
Xb, yb = X[ri], y[ri]
inputs = [list(map(Value, xrow)) for xrow in Xb]
# forward the model to get scores
scores = list(map(model, inputs))
# svm "max-margin" loss
losses = [(1 + -yi*scorei).relu() for yi, scorei in zip(yb, scores)]
data_loss = sum(losses) * (1.0 / len(losses))
# L2 regularization
alpha = 1e-4
reg_loss = alpha * sum((p*p for p in model.parameters()))
total_loss = data_loss + reg_loss
# also get accuracy
accuracy = [((yi).__gt__(0)) == ((scorei.data).__gt__(0)) for yi, scorei in zip(yb, scores)]
return total_loss, sum(accuracy) / len(accuracy)
total_loss, acc = loss()
print((total_loss, acc))
#cell
# optimization
for k in range(20): #was 100
# forward
total_loss, acc = loss()
# backward
model.zero_grad()
total_loss.backward()
# update (sgd)
learning_rate = 1.0 - 0.9*k/100
for p in model.parameters():
p.data -= learning_rate * p.grad
if k % 1 == 0:
# print(f"step {k} loss {total_loss.data}, accuracy {acc*100}%")
print_div(f"step {k} loss {total_loss.data}, accuracy {acc*100}%")
#cell
h = 0.25
x_min, x_max = X[:, 0].min() - 1, X[:, 0].max() + 1
y_min, y_max = X[:, 1].min() - 1, X[:, 1].max() + 1
xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
np.arange(y_min, y_max, h))
Xmesh = np.c_[xx.ravel(), yy.ravel()]
inputs = [list(map(Value, xrow)) for xrow in Xmesh]
scores = list(map(model, inputs))
Z = np.array([(s.data).__gt__(0) for s in scores])
Z = Z.reshape(xx.shape)
fig = plt.figure()
plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral, alpha=0.8)
plt.scatter(X[:, 0], X[:, 1], c=y, s=40, cmap=plt.cm.Spectral)
plt.xlim(xx.min(), xx.max())
plt.ylim(yy.min(), yy.max())
finish = datetime.datetime.now()
# print(f"It took {(finish-start).seconds} seconds to run this code.")
print_div(f"It took {(finish-start).seconds} seconds to run this code.")
plt
return plt