its an implimentation of Perceptron
Project description
-1NeuronPerceptron_Pypi
1Neuron|Perceptron|_Pypi
""" author: Nazmul email: md.nazmul.islam0087@gmail.com """
How to use this
First install the library using below command by using latest version-
pip install 1NeuronPerceptron-Pypi-mdnazmulislam0087==0.0.4
Run the below code to see the training and plot file for or Gate, similarly you can use AND, NAND and XOR GATE to see the difference-
from oneNeuronPerceptron.perceptron import Perceptron
from oneNeuronPerceptron.all_utils import prepare_data, save_model, save_plot
import pandas as pd
import numpy as np
import logging
import os
logging_str = "[%(asctime)s: %(levelname)s: %(module)s] %(message)s"
logging.basicConfig(level=logging.INFO, format=logging_str)
def main(data, eta, epochs, modelfilename,plotfilename):
df = pd.DataFrame(data)
logging.info(f"The dataframe is : {df}")
X,y = prepare_data(df)
model = Perceptron(eta=eta, epochs=epochs)
model.fit(X, y)
_ = model.total_loss()
save_model(model, filename=modelfilename)
save_plot(df, file_name=plotfilename, model=model)
if __name__=="__main__": # << entry point <<
OR = {
"x1": [0,0,1,1],
"x2": [0,1,0,1],
"y": [0,1,1,1],
}
ETA = 0.3 # 0 and 1
EPOCHS = 10
try:
logging.info(">>>>> starting training >>>>>")
main(data=OR, eta=ETA, epochs=EPOCHS, modelfilename="or.model", plotfilename="or.png")
logging.info("<<<<< training done successfully<<<<<\n")
except Exception as e:
logging.exception(e)
raise e
Packages required-
- matplotlib
- numpy
- pandas
- joblib
- tqdm
Limitation
Using one Neuron Perceptron, We cant make decision boundary for XOR GATe, In summary XOR Gate classification is not possible using one Neuron Perceptron
Reference -
github docs for github actions
more details can be found
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Close
Hashes for 1NeuronPerceptron_Pypi-mdnazmulislam0087-0.0.4.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | abbeac044c7a117a8eb7dd1c4d63807ff31da8266c20e1caddc2bf988c40eb50 |
|
MD5 | feb6c08367c7f4a3b7b306874355544f |
|
BLAKE2b-256 | 7089f8243cf67565709463190ead7c539b0ebc81b7da0356136f422e64e027a4 |
Close
Hashes for 1NeuronPerceptron_Pypi_mdnazmulislam0087-0.0.4-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 4fb0b851c4dfb9b2caad0c296d50bccb2bc6e116f4ec2a61f0ec95ac31573388 |
|
MD5 | 34890a7b6a30fc4fd85f72e3eec15ef4 |
|
BLAKE2b-256 | 3e15bb76e5177bccda0f6208d8787476054545d41864747141f32cceeef82a44 |