feat: calc hit_rate for random_select_start_indices();

WenjieDu · Jun 3, 2024 · 2fe87b2 · 2fe87b2
1 parent 9b6f505
commit 2fe87b2
Show file tree

Hide file tree

Showing 2 changed files with 12 additions and 8 deletions.
diff --git a/pygrinder/block_missing/block_missing.py b/pygrinder/block_missing/block_missing.py
@@ -16,7 +16,7 @@ def random_select_start_indices(
  block_width,
  feature_idx,
  step_idx,
- p,
+ hit_rate,
  n_samples,
  n_steps,
  n_features,
@@ -27,7 +27,7 @@ def random_select_start_indices(
  all_feature_start_indices = [i * n_steps for i in all_feature_indices]
  selected_feature_start_indices = np.random.choice(
  all_feature_start_indices,
- math.ceil(len(all_feature_start_indices) * p),
+ math.ceil(len(all_feature_start_indices) * hit_rate),
  replace=False,
  )
  selected_feature_start_indices = np.asarray(selected_feature_start_indices)
@@ -57,8 +57,9 @@ def _block_missing_numpy(
  X = np.copy(X)
 
  n_samples, n_steps, n_features = X.shape
+ hit_rate = p * n_steps * n_features / (block_len * block_width)
  start_indices = random_select_start_indices(
- block_width, feature_idx, step_idx, p, n_samples, n_steps, n_features
+ block_width, feature_idx, step_idx, hit_rate, n_samples, n_steps, n_features
  )
 
  X = X.transpose(0, 2, 1)
@@ -83,8 +84,9 @@ def _block_missing_torch(
  X = torch.clone(X)
 
  n_samples, n_steps, n_features = X.shape
+ hit_rate = p * n_steps * n_features / (block_len * block_width)
  start_indices = random_select_start_indices(
- block_width, feature_idx, step_idx, p, n_samples, n_steps, n_features
+ block_width, feature_idx, step_idx, hit_rate, n_samples, n_steps, n_features
  )
 
  X = X.transpose(1, 2)

diff --git a/pygrinder/sequential_missing/seq_missing.py b/pygrinder/sequential_missing/seq_missing.py
@@ -15,7 +15,7 @@
 def random_select_start_indices(
  feature_idx,
  step_idx,
- p,
+ hit_rate,
  n_samples,
  n_steps,
  n_features,
@@ -31,7 +31,7 @@ def random_select_start_indices(
 
  selected_feature_start_indices = np.random.choice(
  all_feature_start_indices,
- math.ceil(len(all_feature_start_indices) * p),
+ math.ceil(len(all_feature_start_indices) * hit_rate),
  replace=False,
  )
  selected_feature_start_indices = np.asarray(selected_feature_start_indices)
@@ -57,8 +57,9 @@ def _seq_missing_numpy(
  X = np.copy(X)
 
  n_samples, n_steps, n_features = X.shape
+ hit_rate = p * n_steps / seq_len
  start_indices = random_select_start_indices(
- feature_idx, step_idx, p, n_samples, n_steps, n_features
+ feature_idx, step_idx, hit_rate, n_samples, n_steps, n_features
  )
 
  X = X.transpose(0, 2, 1)
@@ -82,8 +83,9 @@ def _seq_missing_torch(
  X = torch.clone(X)
 
  n_samples, n_steps, n_features = X.shape
+ hit_rate = p * n_steps / seq_len
  start_indices = random_select_start_indices(
- feature_idx, step_idx, p, n_samples, n_steps, n_features
+ feature_idx, step_idx, hit_rate, n_samples, n_steps, n_features
  )
 
  X = X.transpose(1, 2)