Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/jakeroggenbuck/game-design-scoring
https://github.com/jakeroggenbuck/game-design-scoring
Last synced: 5 days ago
JSON representation
- Host: GitHub
- URL: https://github.com/jakeroggenbuck/game-design-scoring
- Owner: JakeRoggenbuck
- License: mit
- Created: 2021-02-06T00:33:38.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2024-07-31T06:21:57.000Z (4 months ago)
- Last Synced: 2024-07-31T07:46:27.243Z (4 months ago)
- Language: Python
- Size: 15.6 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Game Design Scoring Regression Model
### Data
The data that this model used to train is the csv `./point-weighting-combined-new.csv` and was made in a spreedsheet
### Building the model
Run the script `./generate_model.py` to build the model
### Usage
To run the model that you built, this is all the code needed
```py
from tensorflow import keras
import numpy as np
import csv
from generate_model import get_data_Y, get_data_X
# Import the model made by ./generate_model.py
model = keras.models.load_model('neural_network.model')
# Gets the data from the model generator file "./generate_model.py"
X = get_data_X()
Y = get_data_Y()
def test_each_match():
# Get the result actual win value, and the one predicted by the model
for x, y in zip(X, Y):
# Predicts the Y value from a given X
result = model.predict(np.array([x]))
# Prints the values in the (actual, predict) format
print(y[0], result[0][0])
```