## ----include = FALSE----------------------------------------------------------
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  eval = FALSE
)

## ----setup--------------------------------------------------------------------
# library(gooseR)
# library(dplyr)

## -----------------------------------------------------------------------------
# # Save any R object
# my_model <- lm(mpg ~ wt + cyl, data = mtcars)
# 
# goose_save(
#   my_model,
#   category = "models",
#   tags = c("mtcars", "regression", "fuel_efficiency")
# )
# 
# # Save data frames
# clean_data <- mtcars %>%
#   filter(mpg > 20) %>%
#   select(mpg, wt, cyl, hp)
# 
# goose_save(
#   clean_data,
#   category = "datasets",
#   tags = c("filtered", "mtcars", "high_mpg")
# )
# 
# # Save multiple objects at once
# results <- list(
#   model = my_model,
#   data = clean_data,
#   summary = summary(my_model)
# )
# 
# goose_save(
#   results,
#   category = "analysis",
#   tags = c("complete_analysis", "2024_q4")
# )

## -----------------------------------------------------------------------------
# # List what's saved
# goose_list()
# 
# # List by category
# goose_list(category = "models")
# 
# # List by tags
# goose_list(tags = "mtcars")
# 
# # Load an object
# my_saved_model <- goose_load("my_model")
# 
# # Load with full metadata
# obj_with_meta <- goose_load("my_model", include_metadata = TRUE)
# print(obj_with_meta$metadata$created_at)

## -----------------------------------------------------------------------------
# # Categories: Broad classifications
# # - "models", "datasets", "plots", "reports", "temp"
# 
# # Tags: Specific descriptors
# # - "production", "test", "client_a", "2024_q4", "regression"
# 
# # Example: Organizing a project
# goose_save(raw_data, category = "datasets", tags = c("raw", "client_a", "2024"))
# goose_save(clean_data, category = "datasets", tags = c("clean", "client_a", "2024"))
# goose_save(model_v1, category = "models", tags = c("v1", "client_a", "baseline"))
# goose_save(model_v2, category = "models", tags = c("v2", "client_a", "improved"))
# goose_save(final_plot, category = "plots", tags = c("final", "client_a", "presentation"))

## -----------------------------------------------------------------------------
# # Backup everything before major changes
# goose_backup()
# # Creates timestamped backup: backup_20241204_143022
# 
# # Work on your analysis...
# # If something goes wrong:
# 
# # List available backups
# list.files(path = "~/.config/goose/memory/backups")
# 
# # Restore from backup
# goose_restore("backup_20241204_143022")

## -----------------------------------------------------------------------------
# # Remove all test objects
# goose_clear_tags(c("test", "temp"))
# 
# # Remove draft versions
# goose_clear_tags("draft")
# 
# # Clean up after experimentation
# goose_clear_tags(c("experiment", "sandbox"))

## -----------------------------------------------------------------------------
# # Work in a temporary session that auto-cleans
# with_goose_session({
# 
#   # Experimental work
#   test_data <- mtcars %>%
#     mutate(mpg_squared = mpg^2)
# 
#   test_model <- lm(mpg_squared ~ wt + cyl, data = test_data)
# 
#   # Save temporarily
#   goose_save(test_model, category = "session_temp", tags = "experiment")
# 
#   # Do analysis
#   print(summary(test_model))
# 
# }, cleanup = TRUE)  # Everything in session_temp is deleted after
# 
# # For persistent session work
# with_goose_session({
# 
#   # Production work
#   final_model <- lm(mpg ~ wt + cyl + hp, data = mtcars)
#   goose_save(final_model, category = "production", tags = "final")
# 
# }, cleanup = FALSE)  # Keeps everything

## -----------------------------------------------------------------------------
# # Load your data
# my_data <- read.csv("complex_dataset.csv")
# 
# # Share a sample with goose for context
# goose_give_sample(my_data, n = 10)
# 
# # Now goose understands your data structure
# advice <- goose_ask("What's the best way to handle the missing values in this dataset?")

## -----------------------------------------------------------------------------
# # Share your data first
# goose_give_sample(my_data)
# 
# # Get an exploratory analysis plan
# exploratory_plan <- goose_make_a_plan("exploratory")
# cat(exploratory_plan)
# 
# # Output:
# # Based on your data structure, here's an exploratory analysis plan:
# #
# # 1. Data Overview
# #    - Check dimensions: 1000 rows × 15 columns
# #    - Examine variable types
# #    - Missing value analysis
# #
# # 2. Univariate Analysis
# #    - Distribution of continuous variables
# #    - Frequency tables for categorical
# # ...
# 
# # Get a predictive modeling plan
# predictive_plan <- goose_make_a_plan("predictive")
# 
# # Get a diagnostic plan
# diagnostic_plan <- goose_make_a_plan("diagnostic")

## -----------------------------------------------------------------------------
# # After completing analysis
# results <- list(
#   model = final_model,
#   performance = model_metrics,
#   plots = list(residual_plot, prediction_plot)
# )
# 
# # Create comprehensive handoff documentation
# handoff <- goose_handoff()
# 
# # This generates:
# # - Summary of work completed
# # - Key findings
# # - Code snippets for reproduction
# # - List of saved objects
# # - Next steps recommendations
# 
# # Save the handoff
# writeLines(handoff, "project_handoff.md")

## -----------------------------------------------------------------------------
# # At the end of your work session
# goose_continuation_prompt()
# 
# # This creates a prompt you can use tomorrow:
# # "Continue analysis of customer churn model. Last session:
# #  - Completed data cleaning (saved as 'clean_data')
# #  - Built baseline model (saved as 'baseline_model', AUC=0.72)
# #  - Identified class imbalance issue
# #  Next: Try SMOTE for balancing, feature engineering on date fields"
# 
# # Save it
# prompt <- goose_continuation_prompt()
# writeLines(prompt, paste0("continue_", Sys.Date(), ".txt"))

## -----------------------------------------------------------------------------
# # Summarize what you've done
# summary <- goose_summarize_session()
# cat(summary)
# 
# # Output:
# # Session Summary - 2024-12-04
# #
# # Objects Created:
# # - clean_data (datasets): 5000 rows × 12 columns
# # - model_v1 (models): Linear regression, R² = 0.84
# # - model_v2 (models): Random forest, R² = 0.91
# # - comparison_plot (plots): Model comparison visualization
# #
# # Key Activities:
# # - Data cleaning and preprocessing
# # - Feature engineering (3 new features)
# # - Model comparison (linear vs. tree-based)
# #
# # Recommendations:
# # - model_v2 shows better performance
# # - Consider ensemble approach
# # - Validate on holdout set

## -----------------------------------------------------------------------------
# # Morning: Continue from yesterday
# yesterday_prompt <- readLines("continue_2024-12-03.txt")
# cat(yesterday_prompt)
# 
# # Load saved objects
# my_data <- goose_load("clean_data")
# my_model <- goose_load("baseline_model")
# 
# # Work on improvements
# improved_model <- improve_model(my_model, my_data)
# 
# # Get feedback
# goose_honk(severity = "moderate")
# 
# # Save progress
# goose_save(improved_model, category = "models", tags = c("improved", "day2"))
# 
# # End of day
# goose_continuation_prompt()
# goose_summarize_session()

## -----------------------------------------------------------------------------
# # Team member A completes initial analysis
# model_a <- build_model(data)
# goose_save(model_a, category = "models", tags = c("team_a", "initial"))
# 
# # Create handoff for Team member B
# handoff <- goose_handoff()
# writeLines(handoff, "handoff_to_team_b.md")
# 
# # Team member B picks up work
# goose_list(tags = "team_a")
# model_a <- goose_load("model_a")
# 
# # Continue work
# model_b <- enhance_model(model_a)
# goose_save(model_b, category = "models", tags = c("team_b", "enhanced"))

## -----------------------------------------------------------------------------
# # Structure for a complete project
# project_setup <- function(project_name) {
# 
#   # Save raw data
#   goose_save(
#     raw_data,
#     category = "data_raw",
#     tags = c(project_name, "raw", Sys.Date())
#   )
# 
#   # Save cleaned data
#   goose_save(
#     clean_data,
#     category = "data_clean",
#     tags = c(project_name, "clean", Sys.Date())
#   )
# 
#   # Save models with versioning
#   goose_save(
#     model_v1,
#     category = "models",
#     tags = c(project_name, "v1", "baseline")
#   )
# 
#   # Save visualizations
#   goose_save(
#     plots,
#     category = "visualizations",
#     tags = c(project_name, "final")
#   )
# 
#   # Save reports
#   goose_save(
#     report,
#     category = "reports",
#     tags = c(project_name, "final", Sys.Date())
#   )
# }
# 
# # List everything for a project
# goose_list(tags = project_name)

## -----------------------------------------------------------------------------
# # Get memory usage statistics
# stats <- goose_memory_stats()
# print(stats)
# 
# # Output:
# # Memory Statistics:
# # Total objects: 47
# # Total size: 15.3 MB
# # By category:
# #   - models: 12 objects (8.1 MB)
# #   - datasets: 20 objects (5.2 MB)
# #   - plots: 15 objects (2.0 MB)

## -----------------------------------------------------------------------------
# # Delete specific objects
# goose_delete("old_model")
# 
# # Delete by pattern
# objects <- goose_list()
# old_objects <- objects %>%
#   filter(grepl("^test_", name))
# 
# for(obj in old_objects$name) {
#   goose_delete(obj)
# }

## -----------------------------------------------------------------------------
# # Export memory for sharing
# goose_export_memory("project_memory.zip")
# 
# # On another machine
# goose_import_memory("project_memory.zip")

## -----------------------------------------------------------------------------
# # Check if it exists
# all_objects <- goose_list()
# grep("my_object", all_objects$name, value = TRUE)
# 
# # Check with different category
# goose_list(category = "models")
# 
# # Check metadata
# meta <- goose_get_metadata("object_name")

## -----------------------------------------------------------------------------
# # Check what's taking space
# stats <- goose_memory_stats()
# 
# # Clean old backups
# goose_clean_backups(keep_last = 3)
# 
# # Remove by tags
# goose_clear_tags(c("old", "deprecated", "test"))