featrixsphere 0.2.1235__tar.gz → 0.2.1238__tar.gz

{featrixsphere-0.2.1235/featrixsphere.egg-info → featrixsphere-0.2.1238}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featrixsphere
-Version: 0.2.1235
+Version: 0.2.1238
 Summary: Transform any CSV into a production-ready ML model in minutes, not months.
 Home-page: https://github.com/Featrix/sphere
 Author: Featrix

featrixsphere-0.2.1238/VERSION

@@ -0,0 +1 @@
+0.2.1238

{featrixsphere-0.2.1235 → featrixsphere-0.2.1238}/featrixsphere/__init__.py

@@ -38,7 +38,7 @@ Example:
     ...                                labels=['Experiment A', 'Experiment B'])
 """
 
-__version__ = "0.2.1235"
+__version__ = "0.2.1238"
 __author__ = "Featrix"
 __email__ = "support@featrix.com"
 __license__ = "MIT"

{featrixsphere-0.2.1235 → featrixsphere-0.2.1238}/featrixsphere/client.py

@@ -1727,48 +1727,6 @@ class FeatrixSphereClient:
     # File Upload
     # =========================================================================
     
-    def upload_file(self, file_path: str) -> str:
-        """
-        Upload a file to the server without creating a session.
-        Returns the filename that can be used in training requests.
-        
-        Args:
-            file_path: Path to the file to upload
-            
-        Returns:
-            Filename (relative path) that can be used in training requests
-        """
-        from pathlib import Path as PathLib
-        file_path_obj = PathLib(file_path)
-        if not file_path_obj.exists():
-            raise FileNotFoundError(f"File not found: {file_path}")
-        
-        with open(file_path_obj, 'rb') as f:
-            files = {'file': (file_path_obj.name, f, 'text/csv' if file_path_obj.suffix == '.csv' else 'application/gzip')}
-            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")
-        
-        return filename
-
     def upload_file_and_create_session(self, file_path: Path, session_name_prefix: str = None, name: str = None, webhooks: Dict[str, str] = None) -> SessionInfo:
         """
         Upload a CSV, Parquet, JSON, or JSONL file and create a new session.
@@ -4213,74 +4171,60 @@ class FeatrixSphereClient:
             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)")
-            
-            # Create temporary CSV file
-            temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False)
-            temp_file_path = temp_file.name
-            temp_file.close()
-            
-            # Save DataFrame to temp file
-            df.to_csv(temp_file_path, index=False)
-            
-            if verbose:
-                print(f"📁 Saved to temporary file: {os.path.basename(temp_file_path)}")
-                print(f"📤 Uploading file to server...")
-            
-            # Upload the file
-            uploaded_filename = self.upload_file(temp_file_path)
-            input_filename = uploaded_filename
-            
-            if verbose:
-                print(f"✅ File uploaded: {input_filename}")
-            
-            # Clean up temp file
-            try:
-                os.unlink(temp_file_path)
-            except Exception:
-                pass  # Ignore cleanup errors
-        
+            # Prepare multipart form data (like train_single_predictor_with_file does)
+            files = None
             data = {
                 "foundation_model_id": foundation_model_id,
                 "target_column": target_column,
                 "target_column_type": target_column_type,
-                "epochs": epochs,
+                "epochs": str(epochs),
                 "optimize_for": optimize_for,
             }
             
-            if input_filename:
-                # If absolute path provided, upload the file first
+            # Handle file upload - send file directly in multipart form
+            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)")
+                
+                # Create temporary CSV file
+                temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.csv', delete=False)
+                temp_file_path = temp_file.name
+                temp_file.close()
+                
+                # Save DataFrame to temp file
+                df.to_csv(temp_file_path, index=False)
+                
+                if verbose:
+                    print(f"📁 Saved to temporary file: {os.path.basename(temp_file_path)}")
+                    print(f"📤 Uploading file directly with training request...")
+                
+                # Send file in multipart form
+                files = {'file': (os.path.basename(temp_file_path), open(temp_file_path, 'rb'), 'text/csv')}
+                
+            elif input_filename:
+                # If absolute path provided, send file directly
                 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}")
+                        print(f"📤 Sending file directly 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
+                    # Send file in multipart form
+                    files = {'file': (input_path.name, open(input_path, 'rb'), 'text/csv' if input_path.suffix == '.csv' else 'application/gzip')}
                 else:
                     # Relative filename - assume it's already on the server
                     data["input_filename"] = input_filename
+            
             if name:
                 data["name"] = name
             if session_name_prefix:
@@ -4288,11 +4232,29 @@ class FeatrixSphereClient:
             if rare_label_value:
                 data["rare_label_value"] = rare_label_value
             if class_imbalance:
-                data["class_imbalance"] = class_imbalance
+                import json
+                data["class_imbalance"] = json.dumps(class_imbalance)
             if webhooks:
-                data["webhooks"] = webhooks
+                import json
+                data["webhooks"] = json.dumps(webhooks)
             
-            response_data = self._post_json("/compute/train_on_foundational_model", data)
+            # Send request with file if provided
+            try:
+                if files:
+                    response = self._make_request("POST", "/compute/train_on_foundational_model", files=files, data=data)
+                else:
+                    response = self._make_request("POST", "/compute/train_on_foundational_model", json=data)
+                response_data = response.json()
+            finally:
+                # Close file handles
+                if files and 'file' in files:
+                    files['file'][1].close()
+                    # Clean up temp file if we created one
+                    if df is not None and temp_file_path:
+                        try:
+                            os.unlink(temp_file_path)
+                        except Exception:
+                            pass
             
             new_session_id = response_data.get('session_id')
             print(f"✅ Predictor training session created: {new_session_id}")

{featrixsphere-0.2.1235 → featrixsphere-0.2.1238/featrixsphere.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featrixsphere
-Version: 0.2.1235
+Version: 0.2.1238
 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

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