Update data_preprocessing_notebook_v1.ipynb

data_preprocessing_notebook_v1.ipynb

@@ -340,9 +340,12 @@
     "num_test_samples = len(test_sequences_by_family)\n",
     "num_train_samples = len(train_sequences_by_family)\n",
     "\n",
-    "# Generate random indices representing 50% of each dataset\n",
-    "random_test_indices = random.sample(range(num_test_samples), num_test_samples // 26.66)\n",
-    "random_train_indices = random.sample(range(num_train_samples), num_train_samples // 26.66)\n",
+    "# Define the percentage of data you want to keep",
+    "percentage_to_keep = 3.64  # for keeping 3.64% of the data",
+    "\n",
+    "# Generate random indices representing a percentage of each dataset",
+    "random_test_indices = random.sample(range(num_test_samples), int(num_test_samples * (percentage_to_keep / 100)))",
+    "random_train_indices = random.sample(range(num_train_samples), int(num_train_samples * (percentage_to_keep / 100)))",
     "\n",
     "# Create smaller datasets using the random indices\n",
     "test_sequences_small = [test_sequences_by_family[i] for i in random_test_indices]\n",