parsnip से मॉडल विनिर्देश

rf_spec <- rand_forest(
  mtry  = tune(),
  trees = 500,
  min_n = tune()
) |>
  set_engine('ranger', importance = 'impurity') |>
  set_mode('classification')

print(rf_spec)

# OLS linear regression
lm_spec <- linear_reg() |>
  set_engine('lm')

# Ridge regression (penalty > 0, mixture = 0)
ridge_spec <- linear_reg(penalty = 0.01, mixture = 0) |>
  set_engine('glmnet')

# Lasso (penalty > 0, mixture = 1)
lasso_spec <- linear_reg(penalty = tune(), mixture = 1) |>
  set_engine('glmnet')

xgb_spec <- boost_tree(
  trees      = 500,
  tree_depth = tune(),
  learn_rate = tune(),
  loss_reduction = tune()
) |>
  set_engine('xgboost') |>
  set_mode('classification')

print(xgb_spec)

lm_spec <- linear_reg() |> set_engine('lm')

# Fit the model on training data
lm_fit <- fit(lm_spec, mpg ~ wt + hp + cyl, data = mtcars)

# The fitted object wraps the engine result
print(lm_fit)

# Access the underlying lm object
extract_fit_engine(lm_fit)

x_train <- train_baked |> select(-price)
y_train <- train_baked$price

lm_spec <- linear_reg() |> set_engine('lm')

# Matrix-style fit
lm_fit_xy <- fit_xy(lm_spec, x = x_train, y = y_train)

print(lm_fit_xy)

rf_spec <- rand_forest(mtry = 3, trees = 500) |>
  set_engine('ranger') |>
  set_mode('classification')

# See what ranger() call will be generated
translate(rf_spec)

# ranger::ranger(formula = ..., data = ...,
#   num.trees = 500, mtry = 3, ...)

log_fit <- fit(logistic_reg() |> set_engine('glm') |> set_mode('classification'),
               species ~ ., data = train_df)

# Predicted classes
predict(log_fit, new_data = test_df, type = 'class')

# Predicted probabilities
predict(log_fit, new_data = test_df, type = 'prob')

log_fit <- fit(
  logistic_reg() |> set_engine('glm') |> set_mode('classification'),
  species ~ ., data = train_df
)

# Get predictions joined to test data
results <- augment(log_fit, new_data = test_df)
head(results[, c('species', '.pred_class', '.pred_setosa')])

specs <- list(
  lm    = linear_reg() |> set_engine('lm'),
  ridge = linear_reg(penalty = 0.01, mixture = 0) |> set_engine('glmnet'),
  rf    = rand_forest(trees = 200) |> set_engine('ranger') |> set_mode('regression')
)

fits <- lapply(specs, fit, mpg ~ ., data = train_mtcars)

preds <- lapply(fits, predict, new_data = test_mtcars)

rmse_vals <- sapply(preds, function(p) {
  sqrt(mean((p$.pred - test_mtcars$mpg)^2))
})
print(rmse_vals)

# Parsnip model comparison template
spec <- rand_forest(trees = 500, mtry = tune()) |>
  set_engine('ranger', importance = 'impurity') |>
  set_mode('classification')

print(translate(spec))

# When mtry is fixed:
spec_fixed <- rand_forest(trees = 500, mtry = 5) |>
  set_engine('ranger') |>
  set_mode('classification')
fit_fixed <- fit(spec_fixed, label ~ ., data = train_df)