ML engineering pipelines

from zenml import pipeline, step


@step
def load_data() -> dict:
    """Simulate loading data from a source."""
    return {"accuracy": 0.0, "loss": 1.0}


@step
def train_model(data: dict) -> dict:
    """Simulate training a model."""
    data["accuracy"] = 0.95
    data["loss"] = 0.1
    return data


@step
def eva…

How to Save and Load PyTorch Model State Dict in Python

This code demonstrates how to save a PyTorch model's state dict to a file and load it back into a new model instance, verifying weights match.

pytorch state-dict model

import torch
import torch.nn as nn

class SimpleNet(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(4, 8)
        self.fc2 = nn.Linear(8, 2)

    def forward(self, x):
        x = torch.relu(self.fc1(x))
        return self.fc2(x)

if __name__ == "__main__":
    model = Simp…

ordinal-encoding sklearn categorical-data

How to ordinal encode categorical data in Python with sklearn

Convert job title categories into ordinal numeric labels using sklearn's OrdinalEncoder with explicit ordering.

from sklearn.preprocessing import OrdinalEncoder
import numpy as np

# Mock data: small job title categories with known ordering
data = np.array([
    ["intern"],
    ["junior"],
    ["mid"],
    ["senior"],
    ["lead"]
])

# Define the ordinal order (lowest to highest)
categories = [["intern", "junior", "mid", "seni…

15 0 Open

csv data-loading standard-library

Load CSV Training Data Without Pandas in Python

This code loads a CSV file into a list of dictionaries using only the standard library, ideal for small ML training data without heavy dependencies.

import csv
from pathlib import Path

def load_csv(path):
    """Load CSV file into list of dicts without pandas."""
    rows = []
    with open(path, newline='', encoding='utf-8') as f:
        reader = csv.DictReader(f)
        for row in reader:
            rows.append(dict(row))
    return rows

if __name__ == "__m…

one-hot encoding categorical numpy

One Hot Encode Categories in Python

Convert a list of categorical strings into one-hot encoded numeric vectors using pure Python and NumPy.

import numpy as np

categories = ["red", "green", "blue", "red", "blue", "green", "red"]

unique = sorted(set(categories))
lookup = {cat: i for i, cat in enumerate(unique)}

one_hot = []
for cat in categories:
    row = [0] * len(unique)
    row[lookup[cat]] = 1
    one_hot.append(row)

print("Categories:", categories…