# AI-generated function for data cleaning
clean_data <- function(df) {
  df %>%
    remove_empty(c("rows", "cols")) %>%
    mutate(across(where(is.character), str_trim)) %>%
    mutate(across(where(is.numeric), ~replace_na(., median(., na.rm = TRUE))))
}

# Error message
Error in summarise(grouped_df(df, groups), mean_value = mean(value)) : 
  object 'value' not found

# AI suggestion
# The error suggests that the column 'value' doesn't exist in your dataframe.
# Check your column names and ensure you're using the correct name:
df %>%
  group_by(category) %>%
  summarise(mean_value = mean(correct_column_name, na.rm = TRUE))

# AI-generated code for a complex ggplot visualization
ggplot(mtcars, aes(x = mpg, y = hp, color = factor(cyl), size = wt)) +
  geom_point(alpha = 0.7) +
  geom_smooth(method = "lm", se = FALSE) +
  facet_wrap(~gear) +
  scale_color_viridis_d() +
  theme_minimal() +
  labs(title = "Car Performance Metrics",
       x = "Miles per Gallon",
       y = "Horsepower",
       color = "Cylinders",
       size = "Weight")

# AI recommendation for time series forecasting
"For time series forecasting in R, consider using the 'forecast' package:

install.packages('forecast')
library(forecast)

# Example usage:
data(AirPassengers)
model <- auto.arima(AirPassengers)
forecast(model, h = 12)

# The 'forecast' package offers robust algorithms and is widely used in the R community for time series analysis."

#' Calculate the Weighted Moving Average
#'
#' This function computes the weighted moving average of a given vector.
#'
#' @param x A numeric vector of values.
#' @param weights A numeric vector of weights. Must have the same length as the window size.
#' @param k The size of the moving window.
#'
#' @return A numeric vector of the same length as x, containing the weighted moving averages.
#'
#' @examples
#' data <- c(1, 2, 3, 4, 5)
#' weights <- c(0.1, 0.2, 0.7)
#' weighted_ma(data, weights, 3)
#'
#' @export
weighted_ma <- function(x, weights, k) {
  # Function implementation here
}

# Original code
for(i in 1:length(df$column)) {
  if(df$column[i] < 0) {
    df$column[i] <- 0
  }
}

# AI-suggested refactoring (more idiomatic R)
df %>%
  mutate(column = pmax(column, 0))

"Challenge: Create a function that takes a dataframe and returns a list of summary statistics for each numeric column. Use the purrr package for functional programming.

Hint: Start with something like this:

summarize_numeric <- function(df) {
  df %>%
    select(where(is.numeric)) %>%
    map(~ list(
      mean = mean(.x, na.rm = TRUE),
      median = median(.x, na.rm = TRUE),
      sd = sd(.x, na.rm = TRUE)
    ))
}

Try implementing this function and test it on the mtcars dataset!"

# AI-generated skeleton for a simple Shiny app
library(shiny)

ui <- fluidPage(
  titlePanel("My Shiny App"),
  sidebarLayout(
    sidebarPanel(
      selectInput("variable", "Choose a variable:", 
                  choices = names(mtcars))
    ),
    mainPanel(
      plotOutput("distPlot")
    )
  )
)

server <- function(input, output) {
  output$distPlot <- renderPlot({
    ggplot(mtcars, aes_string(x = input$variable)) +
      geom_histogram(bins = 30) +
      theme_minimal()
  })
}

shinyApp(ui = ui, server = server)

# AI-generated code that needs verification
result <- df[df$column == max(df$column),]

# Human verification and improvement
result <- df %>%
  filter(column == max(column, na.rm = TRUE))

# Always test AI-generated code with your specific data and use cases