train test split

app.py

@@ -1,11 +1,18 @@
 import pandas as pd
-from datasets import load_dataset
+from datasets import load_dataset, DatasetDict
 
 # Load the dataset from Huggingface
-dataset = load_dataset('thankrandomness/spam-detection-sample')
+dataset = load_dataset("thankrandomness/spam-detection-sample")
+
+# Split the dataset into train and validation sets
+split_dataset = dataset['train'].train_test_split(test_size=0.3, seed=42)
+dataset = DatasetDict({
+    'train': split_dataset['train'],
+    'validation': split_dataset['test']
+})
 
 # Convert to a pandas DataFrame
-df = pd.DataFrame(dataset)
+df = pd.DataFrame(dataset['train'])
 
 # Display the first few rows of the dataframe to verify
 print(df.head())