Add ignore_patterns in ModelTrainer to ignore specific files/folders

src/sagemaker/modules/configs.py

@@ -21,7 +21,7 @@
 
 from __future__ import absolute_import
 
-from typing import Optional, Union
+from typing import Optional, Union, List
 from pydantic import BaseModel, model_validator, ConfigDict
 
 import sagemaker_core.shapes as shapes
@@ -96,12 +96,16 @@ class SourceCode(BaseConfig):
         command (Optional[str]):
             The command(s) to execute in the training job container. Example: "python my_script.py".
             If not specified, entry_script must be provided.
+        ignore_patterns: (Optional[List[str]]) :
+            The ignore patterns to ignore specific files/folders when uploading to S3. Example:
+            ['.env', '.git', 'data', '__pycache__'].
     """
 
     source_dir: Optional[str] = None
     requirements: Optional[str] = None
     entry_script: Optional[str] = None
     command: Optional[str] = None
+    ignore_patterns: Optional[List[str]] = None
 
 
 class Compute(shapes.ResourceConfig):

src/sagemaker/modules/train/model_trainer.py

@@ -119,7 +119,8 @@ class ModelTrainer(BaseModel):
         from sagemaker.modules.train import ModelTrainer
         from sagemaker.modules.configs import SourceCode, Compute, InputData
 
-        source_code = SourceCode(source_dir="source", entry_script="train.py")
+        ignore_patterns = ['.env', '.git', 'data', '__pycache__']
+        source_code = SourceCode(source_dir="source", entry_script="train.py", ignore_patterns=ignore_patterns)
         training_image = "123456789012.dkr.ecr.us-west-2.amazonaws.com/my-training-image"
         model_trainer = ModelTrainer(
             training_image=training_image,
@@ -654,6 +655,7 @@ def train(
                     channel_name=SM_CODE,
                     data_source=self.source_code.source_dir,
                     key_prefix=input_data_key_prefix,
+                    ignore_patterns=self.source_code.ignore_patterns,
                 )
                 final_input_data_config.append(source_code_channel)
 
@@ -755,7 +757,11 @@ def train(
             local_container.train(wait)
 
     def create_input_data_channel(
-        self, channel_name: str, data_source: DataSourceType, key_prefix: Optional[str] = None
+        self,
+        channel_name: str,
+        data_source: DataSourceType,
+        key_prefix: Optional[str] = None,
+        ignore_patterns: Optional[List[str]] = None,
     ) -> Channel:
         """Create an input data channel for the training job.
 
@@ -771,6 +777,9 @@ def create_input_data_channel(
 
                 If specified, local data will be uploaded to:
                 ``s3://<default_bucket_path>/<key_prefix>/<channel_name>/``
+            ignore_patterns: (Optional[List[str]]) :
+                The ignore patterns to ignore specific files/folders when uploading to S3.
+                Example: ['.env', '.git', 'data', '__pycache__'].
         """
         channel = None
         if isinstance(data_source, str):
@@ -810,11 +819,25 @@ def create_input_data_channel(
                     )
                     if self.sagemaker_session.default_bucket_prefix:
                         key_prefix = f"{self.sagemaker_session.default_bucket_prefix}/{key_prefix}"
-                    s3_uri = self.sagemaker_session.upload_data(
-                        path=data_source,
-                        bucket=self.sagemaker_session.default_bucket(),
-                        key_prefix=key_prefix,
-                    )
+                    if ignore_patterns:
+                        tmp_dir = TemporaryDirectory()
+                        shutil.copytree(
+                            data_source,
+                            os.path.join(tmp_dir.name, os.path.basename(data_source)),
+                            dirs_exist_ok=True,
+                            ignore=shutil.ignore_patterns(*ignore_patterns),
+                        )
+                        s3_uri = self.sagemaker_session.upload_data(
+                            path=tmp_dir.name,
+                            bucket=self.sagemaker_session.default_bucket(),
+                            key_prefix=key_prefix,
+                        )
+                    else:
+                        s3_uri = self.sagemaker_session.upload_data(
+                            path=data_source,
+                            bucket=self.sagemaker_session.default_bucket(),
+                            key_prefix=key_prefix,
+                        )
                     channel = Channel(
                         channel_name=channel_name,
                         data_source=DataSource(