Spaces:
Paused
Paused
File size: 8,139 Bytes
729628a | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 | """Comparative Analytics Dashboard - Core Engine"""
import pandas as pd
import numpy as np
from typing import Dict, List, Optional, Tuple, Any
from dataclasses import dataclass, field, asdict
from enum import Enum
import json
from datetime import datetime
class MetricType(Enum):
"""Metric categories"""
ACCURACY = "accuracy"
F1_SCORE = "f1_score"
AUC = "auc"
INFERENCE_TIME = "inference_time"
MEMORY_USAGE = "memory_usage"
@dataclass
class Configuration:
"""Configuration parameters"""
config_id: str
name: str
technique: str
parameters: Dict[str, Any]
def __hash__(self):
return hash(self.config_id)
@dataclass
class PerformanceMetrics:
"""Evaluation metrics"""
accuracy: Optional[float] = None
precision: Optional[float] = None
recall: Optional[float] = None
f1_score: Optional[float] = None
auc: Optional[float] = None
inference_time: Optional[float] = None
memory_usage: Optional[float] = None
training_time: Optional[float] = None
throughput: Optional[float] = None
latency: Optional[float] = None
def to_dict(self) -> Dict[str, Optional[float]]:
return {k: v for k, v in asdict(self).items() if v is not None}
def get_metric(self, metric_name: str) -> Optional[float]:
return getattr(self, metric_name, None)
@dataclass
class Perception3DMetrics(PerformanceMetrics):
"""3D perception and temporal tracking metrics."""
map_3d: Optional[float] = None
mar_3d: Optional[float] = None
mean_iou_3d: Optional[float] = None
orientation_error_deg: Optional[float] = None
position_error_m: Optional[float] = None
id_swap_rate: Optional[float] = None
track_fragmentation_rate: Optional[float] = None
process_units: Optional[int] = None
compute_cycles: Optional[int] = None
@classmethod
def from_metric_card(cls, card: Dict[str, Any]) -> "Perception3DMetrics":
return cls(
map_3d=card.get("map_3d"),
mar_3d=card.get("mar_3d"),
mean_iou_3d=card.get("mean_iou_3d"),
orientation_error_deg=card.get("orientation_error_deg"),
position_error_m=card.get("position_error_m"),
id_swap_rate=card.get("id_swap_rate"),
track_fragmentation_rate=card.get("track_fragmentation_rate"),
process_units=card.get("process_units"),
compute_cycles=card.get("compute_cycles"),
)
@dataclass
class ExperimentResult:
"""Single experiment result"""
dataset: str
model: str
configuration: Configuration
metrics: PerformanceMetrics
timestamp: str = field(default_factory=lambda: datetime.now().isoformat())
notes: str = ""
def __hash__(self):
return hash((self.dataset, self.model, self.configuration.config_id))
class ComparativeAnalytics:
"""Analytics engine for comparing results"""
def __init__(self):
self.results: List[ExperimentResult] = []
self.datasets: set = set()
self.models: set = set()
self.techniques: set = set()
self.configurations: Dict[str, Configuration] = {}
def add_result(self, result: ExperimentResult) -> None:
self.results.append(result)
self.datasets.add(result.dataset)
self.models.add(result.model)
self.techniques.add(result.configuration.technique)
self.configurations[result.configuration.config_id] = result.configuration
def add_results_batch(self, results: List[ExperimentResult]) -> None:
for result in results:
self.add_result(result)
def filter_results(self, datasets: Optional[List[str]] = None, models: Optional[List[str]] = None,
techniques: Optional[List[str]] = None, configurations: Optional[List[str]] = None) -> List[ExperimentResult]:
filtered = self.results
if datasets:
filtered = [r for r in filtered if r.dataset in datasets]
if models:
filtered = [r for r in filtered if r.model in models]
if techniques:
filtered = [r for r in filtered if r.configuration.technique in techniques]
if configurations:
filtered = [r for r in filtered if r.configuration.config_id in configurations]
return filtered
def to_dataframe(self, datasets: Optional[List[str]] = None, models: Optional[List[str]] = None,
techniques: Optional[List[str]] = None, configurations: Optional[List[str]] = None) -> pd.DataFrame:
filtered = self.filter_results(datasets, models, techniques, configurations)
rows = []
for result in filtered:
row = {
'dataset': result.dataset,
'model': result.model,
'technique': result.configuration.technique,
'configuration': result.configuration.name,
'config_id': result.configuration.config_id,
'timestamp': result.timestamp,
}
row.update(result.metrics.to_dict())
rows.append(row)
return pd.DataFrame(rows)
def get_best_configurations(self, metric: str = 'f1_score', dataset: Optional[str] = None,
model: Optional[str] = None, top_n: int = 5) -> pd.DataFrame:
filters = {'datasets': [dataset] if dataset else None, 'models': [model] if model else None}
df = self.to_dataframe(**filters)
if df.empty or metric not in df.columns:
return pd.DataFrame()
df = df.dropna(subset=[metric])
df = df.sort_values(metric, ascending=False).head(top_n)
return df
def compare_techniques(self, metric: str = 'f1_score', dataset: Optional[str] = None,
model: Optional[str] = None) -> pd.DataFrame:
filters = {'datasets': [dataset] if dataset else None, 'models': [model] if model else None}
df = self.to_dataframe(**filters)
if df.empty or metric not in df.columns:
return pd.DataFrame()
comparison = df.groupby('technique')[metric].agg([('mean', 'mean'), ('std', 'std'),
('min', 'min'), ('max', 'max'), ('count', 'count')]).round(4)
return comparison.sort_values('mean', ascending=False)
def get_summary_statistics(self, metric: str = 'f1_score', groupby: str = 'technique') -> Dict:
df = self.to_dataframe()
if df.empty or metric not in df.columns:
return {}
stats = {}
for group_name, group_df in df.groupby(groupby):
group_data = group_df[metric].dropna()
stats[str(group_name)] = {
'mean': float(group_data.mean()),
'std': float(group_data.std()),
'min': float(group_data.min()),
'max': float(group_data.max()),
'median': float(group_data.median()),
'count': int(len(group_data))
}
return stats
def get_dataset_model_matrix(self, metric: str = 'f1_score') -> pd.DataFrame:
df = self.to_dataframe()
if df.empty or metric not in df.columns:
return pd.DataFrame()
matrix = df.groupby(['dataset', 'model'])[metric].mean().unstack(fill_value=None)
return matrix
class DashboardBuilder:
"""Build dashboard components"""
def __init__(self, analytics: ComparativeAnalytics):
self.analytics = analytics
def get_summary_report(self) -> Dict[str, Any]:
df = self.analytics.to_dataframe()
if df.empty:
return {}
return {
'overview': {
'total_experiments': len(self.analytics.results),
'num_datasets': len(self.analytics.datasets),
'num_models': len(self.analytics.models),
'num_techniques': len(self.analytics.techniques),
},
'datasets': sorted(list(self.analytics.datasets)),
'models': sorted(list(self.analytics.models)),
'techniques': sorted(list(self.analytics.techniques)),
}
|