ArtStudies/M2/Clustering In Practice/Encoding.Rmd

```{r}
library(caret)
library(dplyr)
```

# One Hot Encoding

```{r}
df <- data.frame(
  team = c("A", "A", "B", "B", "B", "B", "C", "C"),
  points = c(25, 12, 15, 14, 19, 23, 25, 29)
)

dummies <- dummyVars(~team + points, data = df)
one_hot_data <- predict(dummies, newdata = df)

one_hot_data
```

# Target Encoding

```{r}
train <- data.frame(
  target = c(10, 20, 15),
  cat_col1 = c("city1", "city2", "city1"),
  cat_col2 = c("james", "adam", "charles")
)

global_mean <- mean(train$target)
alpha <- 10

target_encoding <- train |>
  group_by(cat_col1) |>
  summarise(
    n = n(),
    sum_target = sum(target),
    cat_col1_te = (sum_target + (alpha * global_mean)) / (n + alpha),
    .groups = "drop"
  ) |>
  select(cat_col1, cat_col1_te)

train <- train |> left_join(target_encoding, by = "cat_col1")
```

# Frequential Encoding


```{r}
df <- data.frame(
  color = c("blue", "red", "blue", "green"),
  value = c(10, 20, 10, 30)
)
```