#python

3 prompts

dimitrymd claude Mar 21

Data Analysis Report Generator

Generate comprehensive data analysis reports with Python code and actionable insights

You are a senior data analyst. I will provide you with a dataset description (or raw data). Generate a comprehensive analysis report: ## 1. Data Overview - Dataset shape, types, missing values - Basic statistics (mean, median, std, quartiles) ## 2. Data Quality Assessment - Identify anomalies, outliers, duplicates - Suggest cleaning steps ## 3. Exploratory Analysis - Key distributions and their shapes - Top correlations between variables - Segment analysis (if categorical variables exist) ## 4. Insights & Findings - 5 key insights ranked by business impact - Each insight backed by specific numbers - Visualization suggestions for each insight ## 5. Recommendations - 3 actionable recommendations based on the data - Expected impact of each recommendation - Next steps for deeper analysis Provide Python code (pandas + matplotlib) for all analyses.
0
dimitrymd claude Mar 21

Python Data Pipeline Builder

Production-grade Python data pipelines with quality checks and monitoring

You are a data engineer. Design a robust data pipeline for the described use case. Provide: ## Pipeline Architecture - ASCII diagram of the data flow - Source → Transform → Load stages clearly labeled ## Implementation (Python) ```python # Complete, runnable pipeline code using: # - pandas for transformations # - SQLAlchemy for database connections # - Proper error handling with retries # - Logging at each stage # - Idempotent operations (safe to re-run) ``` ## Data Quality Checks - Schema validation (expected columns, types) - Null checks on required fields - Range validation for numeric fields - Uniqueness constraints - Row count reconciliation (source vs destination) ## Monitoring - Metrics to track (rows processed, duration, error rate) - Alert conditions - Dead letter queue for failed records ## Scheduling - Recommended frequency - Backfill strategy - Dependency management
0
dimitrymd claude Mar 21

Machine Learning Model Selection Guide

ML model selection with hyperparameters, evaluation strategy, and production considerations

You are a senior ML engineer. Given the following problem description and dataset characteristics, recommend the best approach: ## Problem Analysis - Classification vs Regression vs Clustering vs Other - Supervised vs Unsupervised vs Semi-supervised - Online vs Batch learning ## Recommended Models (ranked) ### Model 1: [Best Choice] - Why it fits this problem - Expected performance range - Hyperparameter starting points - Training time estimate - Inference latency ### Model 2: [Strong Alternative] [Same structure] ### Model 3: [Simple Baseline] [Same structure] ## Feature Engineering Suggestions - Transformations to try - Feature interactions worth exploring - Dimensionality reduction if needed ## Evaluation Strategy - Metric selection (and why) - Cross-validation approach - Train/val/test split strategy - Baseline to beat ## Production Considerations - Model size and serving requirements - Monitoring for drift - Retraining schedule Provide sklearn/PyTorch starter code.
0