Ultimate preprocessing

preprocessing/sports/tracking_data/tracking_class.py

@@ -4,7 +4,7 @@
 
 class Tracking_data:
     soccer_data_provider = ["soccer"]
-    ultimate_data_provider = ["ultimate_track"]
+    ultimate_data_provider = ["UltimateTrack", "UFA"]
     handball_data_provider = []
     rocket_league_data_provider = []
 
@@ -22,64 +22,120 @@ def __new__(cls, data_provider, *args, **kwargs):
 
 
 if __name__ == "__main__":
+    import argparse
     import os
 
-    # Test Soccer tracking data
-    print("Testing Soccer tracking data...")
-    game_id = 0  # Select the index from the list of files in the data_path.
-    data_path = os.getcwd() + "/test/sports/event_data/data/datastadium/"
-
-    try:
-        # Call the function for soccer directly
-        soccer_tracker = Soccer_tracking_data()
-        tracking_home, tracking_away, jerseynum_df = (
-            soccer_tracker.process_datadium_tracking_data(game_id, data_path, test=True)
-        )
-
-        os.makedirs(os.path.dirname(data_path), exist_ok=True)
-        tracking_home.to_csv(
-            os.getcwd()
-            + "/test/sports/event_data/data/datastadium/test_tracking_home.csv",
-            index=False,
-        )
-        tracking_away.to_csv(
-            os.getcwd()
-            + "/test/sports/event_data/data/datastadium/test_tracking_away.csv",
-            index=False,
-        )
-        jerseynum_df.to_csv(
-            os.getcwd() + "/test/sports/event_data/data/datastadium/test_jerseynum.csv",
-            index=False,
-        )
-        print("Soccer test completed successfully!")
-    except Exception as e:
-        print(f"Soccer test failed: {e}")
-
-    # Test Ultimate Track data
-    print("\nTesting Ultimate Track data...")
-    ultimate_game_id = 0  # Select the first CSV file
-    ultimate_data_path = os.getcwd() + "/test/sports/tracking_data/data/ultimatetrack/"
-
-    try:
-        # Call the function for Ultimate Track directly
-        ultimate_tracker = Ultimate_tracking_data()
-        tracking_offense, tracking_defense, team_info_df = (
-            ultimate_tracker.process_ultimatetrack_tracking_data(
-                ultimate_game_id, ultimate_data_path, test=True
+    parser = argparse.ArgumentParser(description="Test tracking data processing")
+    parser.add_argument(
+        "data_provider",
+        type=str,
+        default="soccer",
+        help="Data provider to use (e.g., 'soccer', 'UltimateTrack', 'UFA')",
+    )
+    args = parser.parse_args()
+
+    data_provider = args.data_provider
+
+    if data_provider in Tracking_data.soccer_data_provider:
+        # Test Soccer tracking data
+        print("Testing Soccer tracking data...")
+        game_id = 0  # Select the index from the list of files in the data_path.
+        data_path = os.getcwd() + "/test/sports/event_data/data/datastadium/"
+
+        try:
+            # Call the function for soccer directly
+            soccer_tracker = Soccer_tracking_data()
+            tracking_home, tracking_away, jerseynum_df = (
+                soccer_tracker.process_datadium_tracking_data(
+                    game_id, data_path, test=True
+                )
+            )
+
+            os.makedirs(os.path.dirname(data_path), exist_ok=True)
+            tracking_home.to_csv(
+                os.getcwd()
+                + "/test/sports/event_data/data/datastadium/test_tracking_home.csv",
+                index=False,
+            )
+            tracking_away.to_csv(
+                os.getcwd()
+                + "/test/sports/event_data/data/datastadium/test_tracking_away.csv",
+                index=False,
+            )
+            jerseynum_df.to_csv(
+                os.getcwd()
+                + "/test/sports/event_data/data/datastadium/test_jerseynum.csv",
+                index=False,
+            )
+            print("Soccer test completed successfully!")
+        except Exception as e:
+            print(f"Soccer test failed: {e}")
+
+    elif data_provider in Tracking_data.ultimate_data_provider:
+        if data_provider == "UFA":
+            # Test UFA data
+            print("\nTesting UFA data...")
+            data_path = os.getcwd() + "/test/sports/tracking_data/UFA/2_1.txt"
+
+            try:
+                # Call the function for UFA directly
+                ufa_tracker = Ultimate_tracking_data("UFA", data_path)
+                tracking_offense, tracking_defense, events_df = (
+                    ufa_tracker.preprocessing()
+                )
+
+                # Create output directory if it doesn't exist
+                output_dir = os.getcwd() + "/test/sports/tracking_data/UFA/metrica/"
+                base_name = os.path.splitext(os.path.basename(data_path))[0]
+                os.makedirs(output_dir, exist_ok=True)
+
+                tracking_offense.to_csv(
+                    os.path.join(output_dir, f"{base_name}_home.csv"), index=False
+                )
+                tracking_defense.to_csv(
+                    os.path.join(output_dir, f"{base_name}_away.csv"), index=False
+                )
+                events_df.to_csv(
+                    os.path.join(output_dir, f"{base_name}_events.csv"), index=False
+                )
+                print("UFA test completed successfully!")
+                print(f"UFA data path: {data_path}")
+            except Exception as e:
+                print(f"UFA test failed: {e}")
+
+        elif data_provider == "UltimateTrack":
+            # Test Ultimate Track data
+            print("\nTesting Ultimate Track data...")
+            data_path = (
+                os.getcwd() + "/test/sports/tracking_data/UltimateTrack/1_1_1.csv"
             )
-        )
-
-        # Create output directory if it doesn't exist
-        os.makedirs(ultimate_data_path, exist_ok=True)
-
-        tracking_offense.to_csv(
-            ultimate_data_path + "test_tracking_offense.csv", index=False
-        )
-        tracking_defense.to_csv(
-            ultimate_data_path + "test_tracking_defense.csv", index=False
-        )
-        team_info_df.to_csv(ultimate_data_path + "test_team_info.csv", index=False)
-        print("Ultimate Track test completed successfully!")
-        print(f"Ultimate Track data path: {ultimate_data_path}")
-    except Exception as e:
-        print(f"Ultimate Track test failed: {e}")
+
+            try:
+                # Call the function for Ultimate Track directly
+                ultimatetrack_tracker = Ultimate_tracking_data(
+                    "UltimateTrack", data_path
+                )
+                tracking_offense, tracking_defense, events_df = (
+                    ultimatetrack_tracker.preprocessing()
+                )
+
+                # Create output directory if it doesn't exist
+                output_dir = (
+                    os.getcwd() + "/test/sports/tracking_data/UltimateTrack/metrica/"
+                )
+                base_name = os.path.splitext(os.path.basename(data_path))[0]
+                os.makedirs(output_dir, exist_ok=True)
+
+                tracking_offense.to_csv(
+                    os.path.join(output_dir, f"{base_name}_home.csv"), index=False
+                )
+                tracking_defense.to_csv(
+                    os.path.join(output_dir, f"{base_name}_away.csv"), index=False
+                )
+                events_df.to_csv(
+                    os.path.join(output_dir, f"{base_name}_events.csv"), index=False
+                )
+                print("Ultimate Track test completed successfully!")
+                print(f"Ultimate Track data path: {data_path}")
+            except Exception as e:
+                print(f"Ultimate Track test failed: {e}")

preprocessing/sports/tracking_data/ultimate/README.md

@@ -0,0 +1,77 @@
+# Ultimate Frisbee Tracking Data Preprocessing
+
+This module provides preprocessing functionality for Ultimate Frisbee tracking data from multiple data providers, converting them into a standardized Metrica format for analysis.
+
+## Overview
+
+The Ultimate tracking data preprocessing system supports two main data providers:
+- **UFA (Ultimate Frisbee Analytics)**: Professional Ultimate game data
+- **Ultimate Track**: Research-grade tracking data with detailed motion features
+
+## Data Providers
+
+### UFA Data Provider
+- **Input Format**: CSV/TXT files with player and disc positions
+- **Features**: Player positions, velocities, disc tracking, holder identification
+- **Output**: Metrica format with home/away team separation
+
+### Ultimate Track Data Provider  
+- **Input Format**: CSV files with raw tracking data
+- **Features**: Enhanced motion analysis with velocity/acceleration calculations
+- **Output**: Metrica format with calculated motion features
+
+## Architecture
+
+```
+ultimate/
+├── ultimate_tracking_class.py     # Main interface class
+├── ufa_preprocessing/             # UFA data processing
+│   ├── preprocessing.py           # UFA-specific preprocessing functions
+│   ├── preprocess_config.py       # UFA configuration constants
+│   └── README.md                  # UFA module documentation
+└── ultimatetrack_preprocessing/   # Ultimate Track data processing
+    ├── preprocessing.py           # Ultimate Track preprocessing functions  
+    ├── preprocess_config.py       # Ultimate Track configuration constants
+    └── __init__.py
+```
+
+## Usage
+
+```python
+from preprocessing.sports.tracking_data.ultimate import Ultimate_tracking_data
+
+# For UFA data
+ufa_tracker = Ultimate_tracking_data("UFA", "/path/to/ufa_data.csv")
+home_df, away_df, events_df = ufa_tracker.preprocessing()
+
+# For Ultimate Track data
+ut_tracker = Ultimate_tracking_data("UltimateTrack", "/path/to/ut_data.csv")
+home_df, away_df, events_df = ut_tracker.preprocessing()
+```
+
+## Output Format
+
+All data providers output data in Metrica format with three DataFrames:
+
+### Home/Away DataFrames
+- **MultiIndex columns**: Team, Player ID, Coordinate (X/Y)
+- **Data**: Player positions over time with disc tracking
+- **Frequency**: Configurable based on data provider (10Hz for UFA, 15Hz for Ultimate Track)
+
+### Events DataFrame
+- **Columns**: Team, Type, Subtype, Period, Start Frame, Start Time, End Frame, End Time, From, To, Start X, Start Y, End X, End Y
+- **Data**: Disc possession events and position data per frame
+
+## Configuration
+
+Each data provider has its own configuration file defining:
+- Field dimensions and specifications
+- Players per team (7 for Ultimate Frisbee)
+- Tracking frequency and coordinate scaling
+- Column mappings and processing parameters
+
+## Dependencies
+
+- pandas: Data manipulation and analysis
+- numpy: Numerical computations
+- Standard Python libraries (os, argparse for CLI usage)

preprocessing/sports/tracking_data/ultimate/ufa_preprocessing/__init__.py

@@ -0,0 +1,6 @@
+# UFA preprocessing module
+from .preprocessing import preprocessing_for_ufa
+
+__all__ = [
+    "preprocessing_for_ufa",
+]

preprocessing/sports/tracking_data/ultimate/ufa_preprocessing/preprocess_config.py

@@ -0,0 +1,66 @@
+# -*- coding: utf-8 -*-
+"""Configuration for UFA data processing.
+
+Attributes
+----------
+field_length : float
+    The length of a Ultimate field (109.73 meters).
+field_width : float
+    The width of a Ultimate field (37 meters).
+players_per_team : int
+    Number of players per team in Ultimate (7).
+tracking_herz : int
+    Frequency of tracking data (10 frames per second).
+coordinate_scale : float
+    Scale factor for coordinate conversion.
+"""
+
+# Ultimate field specifications (in meters for UFA data)
+FIELD_LENGTH: float = 109.73  # 109.73 meters total field length
+FIELD_WIDTH: float = 48.77  # 48.77 meters width
+PLAYING_FIELD_LENGTH: float = 73.15  # 73.15 meters playing field (without end zones)
+END_ZONE_LENGTH: float = 18.29  # 18.29 meters each end zone
+
+# Player configuration
+PLAYERS_PER_TEAM: int = 7  # Standard Ultimate has 7 players per team
+MAX_SUBSTITUTIONS: int = 0  # Unlimited substitutions in Ultimate
+
+# Data processing configuration
+TRACKING_HERZ: int = 10  # UFA data frame rate (10 fps)
+COORDINATE_SCALE: float = 1.0  # UFA data is in meters
+
+# Team identifiers
+OFFENSE_TEAM: str = "offense"
+DEFENSE_TEAM: str = "defense"
+DISC_ENTITY: str = "disc"
+
+# Data columns mapping for UFA
+UFA_COLUMNS = {
+    "frame": "frame",
+    "id": "id",
+    "x": "x",
+    "y": "y",
+    "vx": "vx",
+    "vy": "vy",
+    "ax": "ax",
+    "ay": "ay",
+    "v_mag": "v_mag",
+    "a_mag": "a_mag",
+    "v_angle": "v_angle",
+    "a_angle": "a_angle",
+    "diff_v_a_angle": "diff_v_a_angle",
+    "diff_v_angle": "diff_v_angle",
+    "diff_a_angle": "diff_a_angle",
+    "class": "class",
+    "holder": "holder",
+    "closest": "closest",
+    "selected": "selected",
+    "prev_holder": "prev_holder",
+    "def_selected": "def_selected",
+}
+
+# Columns to remove from UFA data
+COLUMNS_TO_REMOVE = ["selected", "prev_holder", "def_selected"]
+
+# File name patterns
+DEFAULT_FILE_PATTERN = r"(\d+)_(\d+)\.txt"  # quarter_possession.txt