File size: 7,706 Bytes
9a46619 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 |
"""
Test script for Dynamic Highscores application.
This script tests the key functionality of the Dynamic Highscores application
to ensure everything works as expected before deployment.
"""
import os
import unittest
import tempfile
import sqlite3
from unittest.mock import MagicMock, patch
# Import components to test
from database_schema import DynamicHighscoresDB
from auth import HuggingFaceAuth
from benchmark_selection import BenchmarkSelector
from evaluation_queue import EvaluationQueue
from leaderboard import Leaderboard
class TestDynamicHighscores(unittest.TestCase):
"""Test cases for Dynamic Highscores application."""
def setUp(self):
"""Set up test environment."""
# Create temporary database
self.db_fd, self.db_path = tempfile.mkstemp()
self.db = DynamicHighscoresDB(self.db_path)
# Mock auth manager
self.auth_manager = HuggingFaceAuth(self.db)
# Mock components
self.benchmark_selector = BenchmarkSelector(self.db, self.auth_manager)
self.evaluation_queue = EvaluationQueue(self.db, self.auth_manager)
self.leaderboard = Leaderboard(self.db)
def tearDown(self):
"""Clean up test environment."""
os.close(self.db_fd)
os.unlink(self.db_path)
def test_database_schema(self):
"""Test database schema creation."""
# Check if tables were created
conn = sqlite3.connect(self.db_path)
cursor = conn.cursor()
# Get list of tables
cursor.execute("SELECT name FROM sqlite_master WHERE type='table';")
tables = cursor.fetchall()
table_names = [table[0] for table in tables]
# Check if all expected tables exist
expected_tables = ['users', 'benchmarks', 'models', 'evaluations', 'queue']
for table in expected_tables:
self.assertIn(table, table_names)
conn.close()
def test_user_management(self):
"""Test user management functionality."""
# Add a test user
user_id = self.db.add_user("test_user", "test_hf_id", False)
self.assertIsNotNone(user_id)
# Add an admin user
admin_id = self.db.add_user("admin_user", "admin_hf_id", True)
self.assertIsNotNone(admin_id)
# Test submission limits
self.assertTrue(self.db.can_submit_today(user_id))
self.db.update_submission_date(user_id)
self.assertFalse(self.db.can_submit_today(user_id))
# Admin should always be able to submit
self.assertTrue(self.db.can_submit_today(admin_id))
def test_benchmark_management(self):
"""Test benchmark management functionality."""
# Add a test benchmark
benchmark_id = self.db.add_benchmark(
name="Test Benchmark",
dataset_id="test/dataset",
description="Test description",
metrics={"accuracy": 1.0}
)
self.assertIsNotNone(benchmark_id)
# Get benchmarks
benchmarks = self.db.get_benchmarks()
self.assertEqual(len(benchmarks), 1)
self.assertEqual(benchmarks[0]["name"], "Test Benchmark")
def test_model_management(self):
"""Test model management functionality."""
# Add a test user
user_id = self.db.add_user("test_user", "test_hf_id", False)
# Add a test model
model_id = self.db.add_model(
name="Test Model",
hf_model_id="test/model",
user_id=user_id,
tag="Reasoning",
parameters="7B",
description="Test model description"
)
self.assertIsNotNone(model_id)
# Get models
models = self.db.get_models()
self.assertEqual(len(models), 1)
self.assertEqual(models[0]["name"], "Test Model")
# Get models by tag
models = self.db.get_models(tag="Reasoning")
self.assertEqual(len(models), 1)
self.assertEqual(models[0]["tag"], "Reasoning")
def test_evaluation_management(self):
"""Test evaluation management functionality."""
# Add a test user
user_id = self.db.add_user("test_user", "test_hf_id", False)
# Add a test model
model_id = self.db.add_model(
name="Test Model",
hf_model_id="test/model",
user_id=user_id,
tag="Reasoning"
)
# Add a test benchmark
benchmark_id = self.db.add_benchmark(
name="Test Benchmark",
dataset_id="test/dataset"
)
# Add a test evaluation
evaluation_id = self.db.add_evaluation(
model_id=model_id,
benchmark_id=benchmark_id
)
self.assertIsNotNone(evaluation_id)
# Update evaluation status
self.db.update_evaluation_status(
evaluation_id=evaluation_id,
status="running"
)
# Get next in queue
next_eval = self.db.get_next_in_queue()
self.assertIsNotNone(next_eval)
self.assertEqual(next_eval["evaluation_id"], evaluation_id)
# Complete evaluation
self.db.update_evaluation_status(
evaluation_id=evaluation_id,
status="completed",
results={"accuracy": 0.85},
score=85.0
)
# Get evaluation results
results = self.db.get_evaluation_results()
self.assertEqual(len(results), 1)
self.assertEqual(results[0]["score"], 85.0)
def test_leaderboard(self):
"""Test leaderboard functionality."""
# Add test data
user_id = self.db.add_user("test_user", "test_hf_id", False)
# Add models with different tags
model1_id = self.db.add_model(
name="Model 1",
hf_model_id="test/model1",
user_id=user_id,
tag="Reasoning"
)
model2_id = self.db.add_model(
name="Model 2",
hf_model_id="test/model2",
user_id=user_id,
tag="Coding"
)
# Add a benchmark
benchmark_id = self.db.add_benchmark(
name="Test Benchmark",
dataset_id="test/dataset"
)
# Add evaluations
eval1_id = self.db.add_evaluation(
model_id=model1_id,
benchmark_id=benchmark_id
)
eval2_id = self.db.add_evaluation(
model_id=model2_id,
benchmark_id=benchmark_id
)
# Complete evaluations
self.db.update_evaluation_status(
evaluation_id=eval1_id,
status="completed",
results={"accuracy": 0.9},
score=90.0
)
self.db.update_evaluation_status(
evaluation_id=eval2_id,
status="completed",
results={"accuracy": 0.8},
score=80.0
)
# Get leaderboard data
df = self.leaderboard.get_leaderboard_data()
self.assertEqual(len(df), 2)
# Test filtering by tag
df_reasoning = self.leaderboard.get_leaderboard_data(tag="Reasoning")
self.assertEqual(len(df_reasoning), 1)
self.assertEqual(df_reasoning.iloc[0]["score"], 90.0)
df_coding = self.leaderboard.get_leaderboard_data(tag="Coding")
self.assertEqual(len(df_coding), 1)
self.assertEqual(df_coding.iloc[0]["score"], 80.0)
if __name__ == "__main__":
unittest.main()
|