codesnips
python 
import pandas as pd
import torch
from PIL import Image
from torch.utils.data import Dataset, DataLoader

class ProductImageDataset(Dataset):

Custom Datasets and DataLoaders for robust training input pipelines

pytorch dataloader dataset
by Dr. Elena Vasquez 1 tab
python 
import torch.nn as nn
from torchvision.models import resnet50, ResNet50_Weights

model = resnet50(weights=ResNet50_Weights.IMAGENET1K_V2)

for parameter in model.parameters():

Transfer learning with pretrained torchvision backbones

pytorch transfer-learning torchvision
by Dr. Elena Vasquez 1 tab
python 
import torch.nn as nn

class SmallCNN(nn.Module):
    def __init__(self, num_classes: int) -> None:
        super().__init__()
        self.features = nn.Sequential(

Convolutional neural networks for image classification in PyTorch

pytorch cnn computer-vision
by Dr. Elena Vasquez 1 tab
python 
import torch

best_val_loss = float('inf')

for epoch in range(1, num_epochs + 1):
    model.train()

A clean PyTorch training loop with validation and checkpoints

pytorch training-loop checkpoints
by Dr. Elena Vasquez 1 tab
python 
import torch

device = 'cuda' if torch.cuda.is_available() else 'cpu'
features = torch.tensor([[1.0, 2.0], [3.0, 4.0]], requires_grad=True, device=device)
weights = torch.tensor([[0.2], [0.8]], requires_grad=True, device=device)

PyTorch tensor basics and automatic differentiation

pytorch tensors autograd
by Dr. Elena Vasquez 1 tab
python 
from gensim.models import Word2Vec

sentences = [
    ['customer', 'refund', 'payment', 'issue'],
    ['login', 'authentication', 'password', 'reset'],
    ['delivery', 'shipment', 'tracking', 'delay'],

Word embeddings with gensim for semantic similarity tasks

word-embeddings gensim nlp
by Dr. Elena Vasquez 1 tab
python 
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LogisticRegression
from sklearn.pipeline import Pipeline
from sklearn.metrics import classification_report

pipeline = Pipeline([

Text vectorization with TF-IDF for strong classical baselines

tf-idf nlp text-classification
by Dr. Elena Vasquez 1 tab
python 
import spacy
from spacy.matcher import Matcher

nlp = spacy.load('en_core_web_sm')
matcher = Matcher(nlp.vocab)
matcher.add('INCIDENT_ID', [[{'TEXT': {'REGEX': '^INC-[0-9]{6}$'}}]])

Natural language processing with spaCy pipelines and custom rules

spacy nlp entity-extraction
by Dr. Elena Vasquez 1 tab
python 
from sklearn.decomposition import PCA
from sklearn.manifold import TSNE
from sklearn.preprocessing import StandardScaler

X_scaled = StandardScaler().fit_transform(X)

PCA and t-SNE for dimensionality reduction and inspection

pca tsne dimensionality-reduction
by Dr. Elena Vasquez 1 tab
python 
import numpy as np
from sklearn.metrics import confusion_matrix

probabilities = model.predict_proba(X_valid)[:, 1]
thresholds = np.linspace(0.1, 0.9, 9)

Confusion matrix diagnostics for threshold selection

confusion-matrix thresholding evaluation
by Dr. Elena Vasquez 1 tab
python 
from sklearn.metrics import (
    average_precision_score,
    classification_report,
    precision_recall_curve,
    roc_auc_score,
)

Classification metrics beyond accuracy for imbalanced problems

classification-metrics imbalanced-data evaluation
by Dr. Elena Vasquez 1 tab
python 
import optuna
from sklearn.ensemble import HistGradientBoostingClassifier
from sklearn.model_selection import cross_val_score

def objective(trial):
    model = HistGradientBoostingClassifier(

Bayesian optimization with Optuna for efficient model tuning

optuna hyperparameter-tuning optimization
by Dr. Elena Vasquez 1 tab