Token estimators, prompt analyzers, confusion matrices, ML evaluation, learning rate schedules, and neural network calculators.
Estimate token counts for AI prompts across GPT-4, Claude, Llama 3, DeepSeek, and BPE tokenizers with cost previews.
Analyze AI prompt length, word count, token estimates, section structure, template variables, and instructions.
Generate interactive 2x2 confusion matrix visualizations with precision, recall, specificity, accuracy, and F1-scores.
Calculate MAE, MSE, RMSE, R² score, and MAPE metrics to evaluate regression model performance.
Calculate dataset row allocations and percentage splits for training, validation, and testing sets in ML pipelines.
Compare learning rate schedules including Constant, Step Decay, Exponential Decay, and Linear Decay across training epochs.
Calculate trainable parameters (weights and biases) and memory footprint for Dense and Convolutional neural network layers.
Compute convolutional and pooling layer output spatial dimensions based on input size, kernel size, stride, and padding.
Analyze class distributions, calculate class percentages, majority/minority ratios, and assess dataset class imbalance.
Convert categorical variable lists into one-hot binary matrices and export to CSV, JSON, or Python Pandas code.