Skip to content

Installation Guide

Machine Gnostics is distributed as a standard Python package and is designed for easy installation and integration into your data science workflow. The library has been tested on macOS with Python 3.11 and is fully compatible with standard data science libraries.

1. Create a Python Virtual Environment

It is best practice to use a virtual environment to manage your project dependencies and avoid conflicts with other Python packages.

# Create a new virtual environment named 'mg-env'     
python3 -m venv mg-env

# Activate the environment     
source mg-env/bin/activate    

# Create a new virtual environment named 'mg-env'     
python -m venv mg-env     

# Activate the environment     
mg-env\Scripts\activate

2. Install Machine Gnostics

Install the Machine Gnostics library using pip:

pip install machinegnostics     

pip install machinegnostics

This command will install Machine Gnostics and automatically resolve its dependencies.

3. Verify Installation

You can verify that Machine Gnostics and its dependencies are installed correctly by importing them in a Python session:

# check import
import machinegnostics
print("imported successfully!")

You can also check the installation with pip:

pip show machinegnostics     

pip show machinegnostics

4. Quick Usage Example

Machine Gnostics is designed to be as simple to use as other machine learning libraries. You can call its functions and classes directly after installation.

Gnostic Distribution Function

import numpy as np
from machinegnostics.magcal import EGDF

data = np.array([ -13.5, 0, 1., 2., 3., 4., 5., 6., 7., 8., 9., 10.])
egdf = EGDF()
egdf.fit(data)
egdf.plot()
print(egdf.params)

Polynomial Regression

import numpy as np
from machinegnostics.models.regression import PolynomialRegressor

# Example data
X = np.array([0., 0.4, 0.8, 1.2, 1.6, 2. ])
y = np.array([17.89408548, 69.61586934, -7.19890572, 9.37670866, -10.55673099, 16.57855348])

# Create and fit a robust polynomial regression model
model = PolynomialRegressor(degree=2)
model.fit(X, y)

model_lr = LinearRegressor()
model_lr.fit(X, y)

# Make predictions
y_pred = model.predict(X)
y_pred_lr = model_lr.predict(X)

print("Predictions:", y_pred)

# coefficients
print("Coefficients:", model.coefficients)

# x vs y, y_pred plot
import matplotlib.pyplot as plt
plt.scatter(X, y, color='blue', label='Data')
plt.plot(X, y_pred, color='red', label='Polynomial Prediction')
plt.plot(X, y_pred_lr, color='green', label='Linear Prediction')
plt.xlabel('X')
plt.ylabel('y')
plt.title('Polynomial and Linear Regression')
plt.legend()
plt.grid(True, alpha=0.3)
plt.show()

Please find step by step tutorial here.

5. Platform and Environment

  • Operating System: Tested on macOS and Windows 11
  • Python Version: 3.11 recommended
  • Dependencies: Compatible with NumPy, pandas, SciPy, and other standard data science libraries

6. Troubleshooting

  • Activate Your Environment: Always activate your virtual environment before installing or running Machine Gnostics.
mg-env\Scripts\activate     
# or for conda     
conda activate myenv     

source mg-env/bin/activate     
# or for conda     
conda activate myenv
  • Check Your Python Version: Ensure you are using Python 3.8 or newer.
python --version     

python3 --version
  • Upgrade pip: An outdated pip can cause installation errors. Upgrade pip before installing:
pip install --upgrade pip     

pip install --upgrade pip
  • Install from a Clean Environment:If you encounter conflicts, try creating a fresh virtual environment and reinstalling.
  • Check Your Internet Connection:Download errors often result from network issues. Make sure you are connected.
  • Permission Issues:If you see permission errors, avoid using sudo pip install. Instead, use a virtual environment.

  • Still Stuck?

  • Double-check the installation instructions.

  • Contact us or open an issue on GitHub.

Machine Gnostics is designed for simplicity and reliability, making robust machine learning accessible for all Python users.