Best Jasper prompts for Models

Generate a comprehensive data quality audit report for a dataset containing customer demographic information, including age, income, and geographic location. The report should include an analysis of data completeness, consistency, and accuracy, as well as recommendations for data cleansing and normalization. Assume the dataset is stored in a relational database and contains 100,000 rows. Provide a detailed summary of the findings, including any data quality issues identified and proposed solutions. The report should be written in a formal, technical tone and include visualizations and charts to support the analysis.

Design a feature engineering pipeline for a predictive modeling task, including data ingestion, preprocessing, transformation, and feature selection. The pipeline should take in a raw dataset containing text, categorical, and numerical features, and output a transformed dataset with a specified set of features. Assume the dataset is stored in a cloud-based data warehouse and contains 1 million rows. Provide a detailed description of each step in the pipeline, including any relevant algorithms, parameters, or hyperparameters. The pipeline should be written in a Python-based framework and include example code snippets to illustrate each step.

Generate a model interpretability report for a trained machine learning model, including an analysis of feature importance, partial dependence plots, and SHAP values. The report should provide insights into how the model is making predictions and identify any potential biases or areas for improvement. Assume the model is a neural network trained on a dataset containing customer transaction data, and provide a detailed summary of the findings, including any recommendations for model refinement or retraining. The report should be written in a clear, concise tone and include visualizations and charts to support the analysis.

Develop a model validation framework for evaluating the performance of a predictive modeling task, including metrics, thresholds, and alerting rules. The framework should take in a trained model and a holdout dataset, and output a comprehensive validation report, including metrics such as accuracy, precision, recall, and F1 score. Assume the model is a classification model trained on a dataset containing customer churn data, and provide a detailed description of the framework, including any relevant algorithms, parameters, or hyperparameters. The framework should be written in a Python-based framework and include example code snippets to illustrate each step.