featrixsphere 0.2.1232__tar.gz → 0.2.1235__tar.gz

{featrixsphere-0.2.1232/featrixsphere.egg-info → featrixsphere-0.2.1235}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featrixsphere
-Version: 0.2.1232
+Version: 0.2.1235
 Summary: Transform any CSV into a production-ready ML model in minutes, not months.
 Home-page: https://github.com/Featrix/sphere
 Author: Featrix

featrixsphere-0.2.1235/VERSION

@@ -0,0 +1 @@
+0.2.1235

{featrixsphere-0.2.1232 → featrixsphere-0.2.1235}/featrixsphere/__init__.py

@@ -38,7 +38,7 @@ Example:
     ...                                labels=['Experiment A', 'Experiment B'])
 """
 
-__version__ = "0.2.1232"
+__version__ = "0.2.1235"
 __author__ = "Featrix"
 __email__ = "support@featrix.com"
 __license__ = "MIT"

{featrixsphere-0.2.1232 → featrixsphere-0.2.1235}/featrixsphere/client.py

@@ -1748,6 +1748,21 @@ class FeatrixSphereClient:
             response = self._make_request("POST", "/compute/upload_file", files=files)
         
         response_data = response.json()
+        
+        # Handle S3 upload response (returns s3_url and filename)
+        if 's3_url' in response_data:
+            # S3 upload - extract filename from key or use returned filename
+            filename = response_data.get('filename')
+            if not filename:
+                # Extract from S3 key if filename not provided
+                s3_key = response_data.get('key', '')
+                if s3_key:
+                    filename = PathLib(s3_key).name
+            if not filename:
+                raise ValueError("Server did not return filename in S3 upload response")
+            return filename
+        
+        # Handle local file upload response (returns filename)
         filename = response_data.get('filename')
         if not filename:
             raise ValueError("Server did not return filename in upload response")
@@ -4179,19 +4194,34 @@ class FeatrixSphereClient:
         print(f"Training predictor on foundation model {foundation_model_id}...")
         print(f"  Target: {target_column} ({target_column_type})")
         
-        # Validate that only one data source is provided
-        if input_filename and df is not None:
-            raise ValueError("Provide either input_filename or df, not both")
+        # Get the compute cluster from the foundation model session
+        # This ensures we upload files to the same node where the foundation model lives
+        foundation_session = self.get_session_status(foundation_model_id)
+        foundation_compute_cluster = self.get_last_server_metadata()
+        foundation_compute_cluster = foundation_compute_cluster.get('compute_cluster') if foundation_compute_cluster else None
+        
+        # Temporarily set compute cluster for file uploads if we found one
+        original_compute_cluster = self.compute_cluster
+        original_headers = self.session.headers.copy()
+        if foundation_compute_cluster:
+            self.set_compute_cluster(foundation_compute_cluster)
+            if verbose:
+                print(f"  Using compute cluster: {foundation_compute_cluster}")
         
-        # If DataFrame provided, save to temp file and upload it
-        temp_file = None
-        if df is not None:
-            import pandas as pd
-            import tempfile
-            import os
-            
-            if not isinstance(df, pd.DataFrame):
-                raise ValueError("df must be a pandas DataFrame")
+        try:
+            # Validate that only one data source is provided
+            if input_filename and df is not None:
+                raise ValueError("Provide either input_filename or df, not both")
+            
+            # If DataFrame provided, save to temp file and upload it
+            temp_file = None
+            if df is not None:
+                import pandas as pd
+                import tempfile
+                import os
+                
+                if not isinstance(df, pd.DataFrame):
+                    raise ValueError("df must be a pandas DataFrame")
             
             if verbose:
                 print(f"📊 Using provided DataFrame ({len(df)} rows, {len(df.columns)} columns)")
@@ -4221,51 +4251,65 @@ class FeatrixSphereClient:
             except Exception:
                 pass  # Ignore cleanup errors
         
-        data = {
-            "foundation_model_id": foundation_model_id,
-            "target_column": target_column,
-            "target_column_type": target_column_type,
-            "epochs": epochs,
-            "optimize_for": optimize_for,
-        }
-        
-        if input_filename:
-            # If absolute path provided, upload the file first
-            from pathlib import Path
-            input_path = Path(input_filename)
-            if input_path.is_absolute():
-                # Upload the file first, then use the uploaded filename
-                if not input_path.exists():
-                    raise FileNotFoundError(f"Input file not found: {input_filename}")
-                
-                if verbose:
-                    print(f"📤 Uploading file from absolute path: {input_filename}")
-                
-                # Upload the file
-                uploaded_filename = self.upload_file(str(input_path))
-                
-                if verbose:
-                    print(f"✅ File uploaded as: {uploaded_filename}")
-                
-                data["input_filename"] = uploaded_filename
-            else:
-                # Relative filename - assume it's already on the server
-                data["input_filename"] = input_filename
-        if name:
-            data["name"] = name
-        if session_name_prefix:
-            data["session_name_prefix"] = session_name_prefix
-        if rare_label_value:
-            data["rare_label_value"] = rare_label_value
-        if class_imbalance:
-            data["class_imbalance"] = class_imbalance
-        if webhooks:
-            data["webhooks"] = webhooks
-        
-        response_data = self._post_json("/compute/train_on_foundational_model", data)
-        
-        new_session_id = response_data.get('session_id')
-        print(f"✅ Predictor training session created: {new_session_id}")
+            data = {
+                "foundation_model_id": foundation_model_id,
+                "target_column": target_column,
+                "target_column_type": target_column_type,
+                "epochs": epochs,
+                "optimize_for": optimize_for,
+            }
+            
+            if input_filename:
+                # If absolute path provided, upload the file first
+                from pathlib import Path
+                input_path = Path(input_filename)
+                if input_path.is_absolute():
+                    # Upload the file first, then use the uploaded filename
+                    if not input_path.exists():
+                        raise FileNotFoundError(f"Input file not found: {input_filename}")
+                    
+                    if verbose:
+                        print(f"📤 Uploading file from absolute path: {input_filename}")
+                    
+                    # Upload the file
+                    uploaded_filename = self.upload_file(str(input_path))
+                    
+                    if verbose:
+                        print(f"✅ File uploaded as: {uploaded_filename}")
+                    
+                    data["input_filename"] = uploaded_filename
+                else:
+                    # Relative filename - assume it's already on the server
+                    data["input_filename"] = input_filename
+            if name:
+                data["name"] = name
+            if session_name_prefix:
+                data["session_name_prefix"] = session_name_prefix
+            if rare_label_value:
+                data["rare_label_value"] = rare_label_value
+            if class_imbalance:
+                data["class_imbalance"] = class_imbalance
+            if webhooks:
+                data["webhooks"] = webhooks
+            
+            response_data = self._post_json("/compute/train_on_foundational_model", data)
+            
+            new_session_id = response_data.get('session_id')
+            print(f"✅ Predictor training session created: {new_session_id}")
+            
+            # Restore original compute cluster setting
+            if original_compute_cluster != self.compute_cluster:
+                if original_compute_cluster:
+                    self.set_compute_cluster(original_compute_cluster)
+                else:
+                    self.session.headers = original_headers
+        finally:
+            # Ensure we restore headers even if there's an error
+            if original_compute_cluster != self.compute_cluster:
+                if original_compute_cluster:
+                    self.set_compute_cluster(original_compute_cluster)
+                else:
+                    self.session.headers = original_headers
         
         if verbose:
             print(f"⏳ Waiting for training to complete...")

{featrixsphere-0.2.1232 → featrixsphere-0.2.1235/featrixsphere.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featrixsphere
-Version: 0.2.1232
+Version: 0.2.1235
 Summary: Transform any CSV into a production-ready ML model in minutes, not months.
 Home-page: https://github.com/Featrix/sphere
 Author: Featrix

featrixsphere-0.2.1232/VERSION

@@ -1 +0,0 @@
-0.2.1232