featrixsphere 0.2.1141__tar.gz → 0.2.1206__tar.gz

{featrixsphere-0.2.1141/featrixsphere.egg-info → featrixsphere-0.2.1206}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featrixsphere
-Version: 0.2.1141
+Version: 0.2.1206
 Summary: Transform any CSV into a production-ready ML model in minutes, not months.
 Home-page: https://github.com/Featrix/sphere
 Author: Featrix

featrixsphere-0.2.1206/VERSION

@@ -0,0 +1 @@
+0.2.1206

{featrixsphere-0.2.1141 → featrixsphere-0.2.1206}/featrixsphere/__init__.py

@@ -38,7 +38,7 @@ Example:
     ...                                labels=['Experiment A', 'Experiment B'])
 """
 
-__version__ = "0.2.1141"
+__version__ = "0.2.1206"
 __author__ = "Featrix"
 __email__ = "support@featrix.com"
 __license__ = "MIT"

{featrixsphere-0.2.1141 → featrixsphere-0.2.1206}/featrixsphere/client.py

@@ -660,6 +660,77 @@ class FeatrixSphereClient:
         )
         return response.json()
     
+    def publish_session(self, session_id: str) -> Dict[str, Any]:
+        """
+        Publish a session by moving it to /sphere/published/<sessionId>.
+        Moves both the session file and output directory.
+        
+        Args:
+            session_id: Session ID to publish
+            
+        Returns:
+            Response with published_path, output_path, and status
+            
+        Example:
+            ```python
+            result = client.publish_session("abc123")
+            print(f"Published to: {result['published_path']}")
+            ```
+        """
+        response_data = self._post_json(f"/compute/session/{session_id}/publish", {})
+        return response_data
+
+    def deprecate_session(self, session_id: str, warning_message: str, expiration_date: str) -> Dict[str, Any]:
+        """
+        Deprecate a published session with a warning message and expiration date.
+        The session remains available until the expiration date.
+        
+        Args:
+            session_id: Session ID to deprecate
+            warning_message: Warning message to display about deprecation
+            expiration_date: ISO format date string when session will be removed (e.g., "2025-12-31T23:59:59Z")
+            
+        Returns:
+            Response with deprecation status
+            
+        Example:
+            ```python
+            from datetime import datetime, timedelta
+            
+            expiration = (datetime.now() + timedelta(days=90)).isoformat() + "Z"
+            result = client.deprecate_session(
+                session_id="abc123",
+                warning_message="This session will be removed on 2025-12-31",
+                expiration_date=expiration
+            )
+            ```
+        """
+        data = {
+            "warning_message": warning_message,
+            "expiration_date": expiration_date
+        }
+        response_data = self._post_json(f"/compute/session/{session_id}/deprecate", data)
+        return response_data
+
+    def unpublish_session(self, session_id: str) -> Dict[str, Any]:
+        """
+        Unpublish a session by moving it back from /sphere/published/<sessionId>.
+        
+        Args:
+            session_id: Session ID to unpublish
+            
+        Returns:
+            Response with unpublish status
+            
+        Example:
+            ```python
+            result = client.unpublish_session("abc123")
+            print(f"Status: {result['status']}")
+            ```
+        """
+        response_data = self._post_json(f"/compute/session/{session_id}/unpublish", {})
+        return response_data
+
     def get_sessions_for_org(self, name_prefix: str, max_retries: int = None) -> Dict[str, Any]:
         """
         Get all sessions matching a name prefix across all compute nodes.
@@ -1555,10 +1626,10 @@ class FeatrixSphereClient:
     
     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 file and create a new session.
+        Upload a CSV, Parquet, JSON, or JSONL file and create a new session.
         
         Args:
-            file_path: Path to the CSV file to upload
+            file_path: Path to the CSV, Parquet, JSON, or JSONL file to upload
             session_name_prefix: Optional prefix for the session ID. Session will be named <prefix>-<full-uuid>
             name: Optional name for the embedding space/model (for identification and metadata)
             webhooks: Optional dict with webhook configuration keys (webhook_callback_secret, s3_backup_url, model_id_update_url)
@@ -1622,7 +1693,7 @@ class FeatrixSphereClient:
                                     webhooks: Dict[str, str] = None,
                                     epochs: int = None) -> SessionInfo:
         """
-        Upload a pandas DataFrame or CSV file and create a new session.
+        Upload a pandas DataFrame, CSV file, Parquet file, JSON file, or JSONL file and create a new session.
         
         Special Column: __featrix_train_predictor
         ------------------------------------------
@@ -1630,7 +1701,7 @@ class FeatrixSphereClient:
         which rows are used for single predictor training.
         
         How it works:
-        - Add a boolean column "__featrix_train_predictor" to your DataFrame/CSV before upload
+        - Add a boolean column "__featrix_train_predictor" to your DataFrame/CSV/Parquet/JSON/JSONL before upload
         - Set it to True for rows you want to use for predictor training
         - Set it to False (or any other value) for rows to exclude from predictor training
         - Embedding space training uses ALL rows (ignores this column)
@@ -1664,7 +1735,7 @@ class FeatrixSphereClient:
         Args:
             df: pandas DataFrame to upload (optional if file_path is provided)
             filename: Name to give the uploaded file (default: "data.csv")
-            file_path: Path to CSV file to upload (optional if df is provided)
+            file_path: Path to CSV, Parquet, JSON, or JSONL file to upload (optional if df is provided)
             column_overrides: Dict mapping column names to types ("scalar", "set", "free_string", "free_string_list")
             column_types: Alias for column_overrides (for backward compatibility)
             string_list_delimiter: Delimiter for free_string_list columns (default: "|")
@@ -1705,21 +1776,90 @@ class FeatrixSphereClient:
             if not os.path.exists(file_path):
                 raise FileNotFoundError(f"File not found: {file_path}")
             
-            # Check if it's a CSV file
-            if not file_path.lower().endswith(('.csv', '.csv.gz')):
-                raise ValueError("File must be a CSV file (with .csv or .csv.gz extension)")
+            # Check if it's a supported file type
+            file_ext = file_path.lower()
+            if not file_ext.endswith(('.csv', '.csv.gz', '.parquet', '.json', '.jsonl')):
+                raise ValueError("File must be a CSV, Parquet, JSON, or JSONL file (with .csv, .csv.gz, .parquet, .json, or .jsonl extension)")
             
             print(f"Uploading file: {file_path}")
             
             # Read the file content
             if file_path.endswith('.gz'):
-                # Already gzipped
+                # Already gzipped CSV
                 with gzip.open(file_path, 'rb') as f:
                     file_content = f.read()
                 upload_filename = os.path.basename(file_path)
                 content_type = 'application/gzip'
+            elif file_path.lower().endswith(('.json', '.jsonl')):
+                # JSON/JSONL file - read as DataFrame, convert to CSV, then compress
+                print(f"Reading {'JSONL' if file_path.lower().endswith('.jsonl') else 'JSON'} file...")
+                try:
+                    from featrix.neural.input_data_file import featrix_wrap_read_json_file
+                    json_df = featrix_wrap_read_json_file(file_path)
+                    if json_df is None:
+                        raise ValueError(f"Failed to parse {'JSONL' if file_path.lower().endswith('.jsonl') else 'JSON'} file")
+                except ImportError:
+                    # Fallback to pandas if featrix wrapper not available
+                    if file_path.lower().endswith('.jsonl'):
+                        # JSONL: one JSON object per line
+                        import json
+                        records = []
+                        with open(file_path, 'r', encoding='utf-8') as f:
+                            for line in f:
+                                if line.strip():
+                                    records.append(json.loads(line))
+                        json_df = pd.DataFrame(records)
+                    else:
+                        # Regular JSON
+                        json_df = pd.read_json(file_path)
+                
+                # Clean NaN values before CSV conversion
+                cleaned_df = json_df.where(pd.notna(json_df), None)
+                
+                # Convert to CSV and compress
+                csv_buffer = io.StringIO()
+                cleaned_df.to_csv(csv_buffer, index=False)
+                csv_data = csv_buffer.getvalue().encode('utf-8')
+                
+                print(f"Compressing {'JSONL' if file_path.lower().endswith('.jsonl') else 'JSON'} (converted to CSV)...")
+                compressed_buffer = io.BytesIO()
+                with gzip.GzipFile(fileobj=compressed_buffer, mode='wb') as gz:
+                    gz.write(csv_data)
+                file_content = compressed_buffer.getvalue()
+                upload_filename = os.path.basename(file_path).replace('.jsonl', '.csv.gz').replace('.json', '.csv.gz')
+                content_type = 'application/gzip'
+                
+                original_size = len(csv_data)
+                compressed_size = len(file_content)
+                compression_ratio = (1 - compressed_size / original_size) * 100
+                print(f"Converted {'JSONL' if file_path.lower().endswith('.jsonl') else 'JSON'} to CSV and compressed from {original_size:,} to {compressed_size:,} bytes ({compression_ratio:.1f}% reduction)")
+            elif file_path.lower().endswith('.parquet'):
+                # Parquet file - read as DataFrame, convert to CSV, then compress
+                print("Reading Parquet file...")
+                parquet_df = pd.read_parquet(file_path)
+                
+                # Clean NaN values before CSV conversion
+                cleaned_df = parquet_df.where(pd.notna(parquet_df), None)
+                
+                # Convert to CSV and compress
+                csv_buffer = io.StringIO()
+                cleaned_df.to_csv(csv_buffer, index=False)
+                csv_data = csv_buffer.getvalue().encode('utf-8')
+                
+                print("Compressing Parquet (converted to CSV)...")
+                compressed_buffer = io.BytesIO()
+                with gzip.GzipFile(fileobj=compressed_buffer, mode='wb') as gz:
+                    gz.write(csv_data)
+                file_content = compressed_buffer.getvalue()
+                upload_filename = os.path.basename(file_path).replace('.parquet', '.csv.gz')
+                content_type = 'application/gzip'
+                
+                original_size = len(csv_data)
+                compressed_size = len(file_content)
+                compression_ratio = (1 - compressed_size / original_size) * 100
+                print(f"Converted Parquet to CSV and compressed from {original_size:,} to {compressed_size:,} bytes ({compression_ratio:.1f}% reduction)")
             else:
-                # Read CSV and compress it
+                # Regular CSV file - read and compress it
                 with open(file_path, 'rb') as f:
                     csv_content = f.read()
                 
@@ -4753,7 +4893,7 @@ class FeatrixSphereClient:
                             predictor_id: str = None, target_column: str = None,
                             batch_size: int = 0, learning_rate: float = None,
                             poll_interval: int = 30, max_poll_time: int = 3600,
-                            verbose: bool = True) -> Dict[str, Any]:
+                            verbose: bool = True, webhooks: Dict[str, str] = None) -> Dict[str, Any]:
         """
         Continue training an existing single predictor for more epochs.
         Loads the existing predictor and resumes training from where it left off.
@@ -4768,6 +4908,7 @@ class FeatrixSphereClient:
             poll_interval: Seconds between status checks (default: 30)
             max_poll_time: Maximum time to poll in seconds (default: 3600 = 1 hour)
             verbose: Whether to print status updates (default: True)
+            webhooks: Optional dict with webhook configuration keys (webhook_callback_secret, s3_backup_url, model_id_update_url)
             
         Returns:
             Response with continuation start confirmation or completion status
@@ -4799,6 +4940,8 @@ class FeatrixSphereClient:
             data["target_column"] = target_column
         if learning_rate is not None:
             data["learning_rate"] = learning_rate
+        if webhooks:
+            data["webhooks"] = webhooks
         
         if verbose:
             print(f"🔄 Continuing training for predictor on session {session_id}")
@@ -4888,6 +5031,139 @@ class FeatrixSphereClient:
                 print(f"❌ Error starting predictor continuation: {e}")
             raise
 
+    def foundation_model_train_more(self, session_id: str, es_id: str = None, data_passes: int = None,
+                                   epochs: int = None, poll_interval: int = 30, max_poll_time: int = 3600,
+                                   verbose: bool = True, webhooks: Dict[str, str] = None) -> Dict[str, Any]:
+        """
+        Continue training an existing foundation model (embedding space) for more epochs.
+        Loads the existing embedding space and resumes training from where it left off.
+        
+        Args:
+            session_id: Session ID containing the trained foundation model
+            es_id: Embedding space ID (optional, uses session's ES if not provided)
+            data_passes: Additional epochs to train (preferred, default: 50)
+            epochs: Additional epochs to train (deprecated, use data_passes instead, for compatibility)
+            poll_interval: Seconds between status checks (default: 30)
+            max_poll_time: Maximum time to poll in seconds (default: 3600 = 1 hour)
+            verbose: Whether to print status updates (default: True)
+            webhooks: Optional dict with webhook configuration keys (webhook_callback_secret, s3_backup_url, model_id_update_url)
+            
+        Returns:
+            Response with continuation start confirmation or completion status
+            
+        Example:
+            ```python
+            # Continue training for 50 more epochs
+            result = client.foundation_model_train_more(
+                session_id="abc123",
+                data_passes=50
+            )
+            ```
+        """
+        # Support both data_passes and epochs for compatibility
+        if data_passes is None and epochs is None:
+            data_passes = 50  # Default
+        elif data_passes is None:
+            data_passes = epochs  # Use epochs if data_passes not provided
+        # If both provided, data_passes takes precedence
+        
+        if data_passes <= 0:
+            raise ValueError("data_passes (or epochs) must be > 0 (specify additional epochs to train)")
+        
+        data = {
+            "data_passes": data_passes,
+        }
+        
+        if es_id:
+            data["es_id"] = es_id
+        if webhooks:
+            data["webhooks"] = webhooks
+        
+        if verbose:
+            print(f"🔄 Continuing training for foundation model on session {session_id}")
+            print(f"   Additional epochs: {data_passes}")
+            if es_id:
+                print(f"   ES ID: {es_id}")
+        
+        try:
+            response_data = self._post_json(f"/compute/session/{session_id}/train_foundation_model_more", data)
+            
+            if verbose:
+                print(f"✅ Foundation model continuation started: {response_data.get('message')}")
+            
+            # Poll for completion if requested
+            if poll_interval > 0 and max_poll_time > 0:
+                import time
+                start_time = time.time()
+                last_status = ""
+                
+                while time.time() - start_time < max_poll_time:
+                    try:
+                        session_info = self.get_session_status(session_id)
+                        jobs = session_info.jobs if hasattr(session_info, 'jobs') else {}
+                        
+                        # Find continuation jobs
+                        es_jobs = {j_id: j for j_id, j in jobs.items() 
+                                 if j.get('type') == 'train_es'}
+                        
+                        if not es_jobs:
+                            if verbose:
+                                print("✅ No continuation jobs found - training may have completed")
+                            break
+                        
+                        # Check job statuses
+                        running_jobs = [j_id for j_id, j in es_jobs.items() if j.get('status') == 'running']
+                        completed_jobs = [j_id for j_id, j in es_jobs.items() if j.get('status') == 'done']
+                        failed_jobs = [j_id for j_id, j in es_jobs.items() if j.get('status') == 'failed']
+                        
+                        current_status = f"Running: {len(running_jobs)}, Done: {len(completed_jobs)}, Failed: {len(failed_jobs)}"
+                        if current_status != last_status and verbose:
+                            print(f"📊 Status: {current_status}")
+                            last_status = current_status
+                        
+                        if not running_jobs and (completed_jobs or failed_jobs):
+                            if completed_jobs:
+                                if verbose:
+                                    print(f"✅ Foundation model continuation completed successfully!")
+                                return {
+                                    "message": "Foundation model continuation completed successfully",
+                                    "session_id": session_id,
+                                    "status": "completed",
+                                    "additional_epochs": data_passes
+                                }
+                            else:
+                                if verbose:
+                                    print(f"❌ Foundation model continuation failed")
+                                return {
+                                    "message": "Foundation model continuation failed",
+                                    "session_id": session_id,
+                                    "status": "failed",
+                                    "failed_jobs": failed_jobs
+                                }
+                        
+                        time.sleep(poll_interval)
+                    except Exception as poll_error:
+                        if verbose:
+                            print(f"⚠️ Error during polling: {poll_error}")
+                        time.sleep(poll_interval)
+                
+                # Timeout
+                if verbose:
+                    print(f"⏱️ Polling timeout reached ({max_poll_time}s)")
+                return {
+                    "message": "Polling timeout",
+                    "session_id": session_id,
+                    "status": "timeout",
+                    "additional_epochs": data_passes
+                }
+            
+            return response_data
+            
+        except Exception as e:
+            if verbose:
+                print(f"❌ Error starting foundation model continuation: {e}")
+            raise
+
     def _train_single_predictor_with_file(
         self,
         session_id: str,
@@ -5965,7 +6241,24 @@ class FeatrixSphereClient:
         if not file_path.exists():
             raise FileNotFoundError(f"File not found: {file_path}")
         
-        df = pd.read_csv(file_path)
+        # Support CSV, Parquet, JSON, and JSONL files
+        file_path_str = str(file_path).lower()
+        if file_path_str.endswith('.parquet'):
+            df = pd.read_parquet(file_path)
+        elif file_path_str.endswith('.jsonl'):
+            # JSONL: one JSON object per line
+            import json
+            records = []
+            with open(file_path, 'r', encoding='utf-8') as f:
+                for line in f:
+                    if line.strip():
+                        records.append(json.loads(line))
+            df = pd.DataFrame(records)
+        elif file_path_str.endswith('.json'):
+            # Regular JSON
+            df = pd.read_json(file_path)
+        else:
+            df = pd.read_csv(file_path)
         
         # Convert to JSON Tables format and clean NaNs
         table_data = JSONTablesEncoder.from_dataframe(df)
@@ -6119,11 +6412,11 @@ class FeatrixSphereClient:
     def run_csv_predictions(self, session_id: str, csv_file: str, target_column: str = None,
                            sample_size: int = None, remove_target: bool = True) -> Dict[str, Any]:
         """
-        Run predictions on a CSV file with automatic accuracy calculation.
+        Run predictions on a CSV, Parquet, JSON, or JSONL file with automatic accuracy calculation.
         
         Args:
             session_id: ID of session with trained predictor
-            csv_file: Path to CSV file
+            csv_file: Path to CSV, Parquet, JSON, or JSONL file
             target_column: Name of target column (for accuracy calculation)
             sample_size: Number of records to test (None = all records)
             remove_target: Whether to remove target column from prediction input
@@ -6133,8 +6426,24 @@ class FeatrixSphereClient:
         """
         import pandas as pd
         
-        # Load CSV
-        df = pd.read_csv(csv_file)
+        # Load CSV, Parquet, JSON, or JSONL
+        csv_file_lower = csv_file.lower()
+        if csv_file_lower.endswith('.parquet'):
+            df = pd.read_parquet(csv_file)
+        elif csv_file_lower.endswith('.jsonl'):
+            # JSONL: one JSON object per line
+            import json
+            records = []
+            with open(csv_file, 'r', encoding='utf-8') as f:
+                for line in f:
+                    if line.strip():
+                        records.append(json.loads(line))
+            df = pd.DataFrame(records)
+        elif csv_file_lower.endswith('.json'):
+            # Regular JSON
+            df = pd.read_json(csv_file)
+        else:
+            df = pd.read_csv(csv_file)
         
         # Handle target column
         actual_values = None

{featrixsphere-0.2.1141 → featrixsphere-0.2.1206/featrixsphere.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: featrixsphere
-Version: 0.2.1141
+Version: 0.2.1206
 Summary: Transform any CSV into a production-ready ML model in minutes, not months.
 Home-page: https://github.com/Featrix/sphere
 Author: Featrix

featrixsphere-0.2.1141/VERSION

@@ -1 +0,0 @@
-0.2.1140