Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/rainingcomputers/pykitml
Machine Learning library written in Python and NumPy.
https://github.com/rainingcomputers/pykitml
deep-learning machine-learning neural-network numpy python-library random-forest
Last synced: about 2 months ago
JSON representation
Machine Learning library written in Python and NumPy.
- Host: GitHub
- URL: https://github.com/rainingcomputers/pykitml
- Owner: RainingComputers
- License: mit
- Created: 2019-12-04T07:52:45.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2022-12-27T16:39:49.000Z (almost 2 years ago)
- Last Synced: 2024-10-11T11:16:16.021Z (2 months ago)
- Topics: deep-learning, machine-learning, neural-network, numpy, python-library, random-forest
- Language: Python
- Size: 1.04 MB
- Stars: 27
- Watchers: 3
- Forks: 1
- Open Issues: 3
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# pykitml (Python Kit for Machine Learning)
Machine Learning library written in Python and NumPy.
### Installation
```
python3 -m pip install pykitml
```
### Documentation
https://pykitml.readthedocs.io/en/latest/
# Demo (MNIST)
### Training
``` python
import os.path
import numpy as np
import pykitml as pk
from pykitml.datasets import mnist
# Download dataset
if(not os.path.exists('mnist.pkl')): mnist.get()
# Load dataset
training_data, training_targets, testing_data, testing_targets = mnist.load()
# Create a new neural network
digit_classifier = pk.NeuralNetwork([784, 100, 10])
# Train it
digit_classifier.train(
training_data=training_data,
targets=training_targets,
batch_size=50,
epochs=1200,
optimizer=pk.Adam(learning_rate=0.012, decay_rate=0.95),
testing_data=testing_data,
testing_targets=testing_targets,
testing_freq=30,
decay_freq=15
)
# Save it
pk.save(digit_classifier, 'digit_classifier_network.pkl')
# Show performance
accuracy = digit_classifier.accuracy(training_data, training_targets)
print('Train Accuracy:', accuracy)
accuracy = digit_classifier.accuracy(testing_data, testing_targets)
print('Test Accuracy:', accuracy)
# Plot performance graph
digit_classifier.plot_performance()
# Show confusion matrix
digit_classifier.confusion_matrix(training_data, training_targets)
```
### Trying the model
```python
import random
import numpy as np
import matplotlib.pyplot as plt
import pykitml as pk
from pykitml.datasets import mnist
# Load dataset
training_data, training_targets, testing_data, testing_targets = mnist.load()
# Load the trained network
digit_classifier = pk.load('digit_classifier_network.pkl')
# Pick a random example from testing data
index = random.randint(0, 9999)
# Show the test data and the label
plt.imshow(training_data[index].reshape(28, 28))
plt.show()
print('Label: ', training_targets[index])
# Show prediction
digit_classifier.feed(training_data[index])
model_output = digit_classifier.get_output_onehot()
print('Predicted: ', model_output)
```
### Performance Graph
### Confusion Matrix
