File size: 15,164 Bytes
b225a21 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 |
{
"edges": [
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestAnswerQuestionSmallCsv::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestAnswerQuestionSmallCsv::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestAnswerQuestionCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestAnswerQuestionCsv::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestAnswerQuestionSmallCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestAnswerQuestionSmallCsv::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestAnswerQuestionCsv::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestAnswerQuestionCsv::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestAnswerQuestionCombineCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestAnswerQuestionCombineCsv::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestCombineCsv::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestCombineCsv::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestAnswerQuestionCombineCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestAnswerQuestionCombineCsv::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestLabelCsv::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestLabelCsv::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestCombineCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestCombineCsv::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestSortCsv::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestSortCsv::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestLabelCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestLabelCsv::test_method[challenge_data0]"
},
{
"arrows": "to",
"from": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"id": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]_to_agbenchmark/generate_test.py::TestSortCsv::test_method[challenge_data0]",
"to": "agbenchmark/generate_test.py::TestSortCsv::test_method[challenge_data0]"
}
],
"nodes": [
{
"color": "grey",
"data": {
"category": [
"general",
"coding",
"scrape_synthesize",
"data"
],
"cutoff": 60,
"dependencies": [
"TestWriteFile"
],
"eval_id": "f219f3d3-a41b-45a9-a3d0-389832086ee8",
"ground": {
"answer": "The content of output.txt should be 'Hello World!'",
"eval": {
"type": "file"
},
"files": [
"output.txt"
],
"should_contain": [
"Hello World!"
]
},
"info": {
"description": "Tests if the agent can read a file.",
"difficulty": "interface",
"side_effects": [
""
]
},
"name": "TestReadFile",
"task": "Read the file called file_to_read.txt and write its content to a file called output.txt"
},
"id": "agbenchmark/generate_test.py::TestReadFile::test_method[challenge_data0]",
"label": "ReadFile",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"general",
"coding",
"scrape_synthesize",
"data"
],
"cutoff": 60,
"dependencies": [],
"eval_id": "021c695a-6cc4-46c2-b93a-f3a9b0f4d123",
"ground": {
"answer": "The word 'Washington', printed to a .txt file named anything",
"eval": {
"type": "file"
},
"files": [
".txt"
],
"should_contain": [
"Washington"
],
"should_not_contain": []
},
"info": {
"description": "Tests if the agent can write a file",
"difficulty": "interface",
"side_effects": [
""
]
},
"name": "TestWriteFile",
"task": "Write the word 'Washington' to a .txt file"
},
"id": "agbenchmark/generate_test.py::TestWriteFile::test_method[challenge_data0]",
"label": "WriteFile",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"data"
],
"cutoff": 90,
"dependencies": [
"TestAnswerQuestionSmallCsv"
],
"eval_id": "bb6e0a4b-7faf-4aa6-a524-548cddbc2732",
"ground": {
"answer": "The correct amount spent on utilities.",
"eval": {
"type": "file"
},
"files": [
"output.txt"
],
"should_contain": [
"1861"
]
},
"info": {
"description": "Tests if the agent can answer a question from a csv",
"difficulty": "intermediate",
"side_effects": [
""
]
},
"name": "TestAnswerQuestionCsv",
"task": "How much was spent on utilities in total ? Write the answer in an output.txt file."
},
"id": "agbenchmark/generate_test.py::TestAnswerQuestionCsv::test_method[challenge_data0]",
"label": "AnswerQuestionCsv",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"data",
"general"
],
"cutoff": 60,
"dependencies": [
"TestReadFile"
],
"eval_id": "9df3f07a-5047-488f-b788-1e1f57eba970",
"ground": {
"answer": "The correct amount spent on utilities.",
"eval": {
"type": "file"
},
"files": [
"output.txt"
],
"should_contain": [
"84"
]
},
"info": {
"description": "Tests if the agent can answer a question from a small csv",
"difficulty": "intermediate",
"side_effects": [
""
]
},
"name": "TestAnswerQuestionSmallCsv",
"task": "How much was spent on utilities in total ? Write the answer in an output.txt file."
},
"id": "agbenchmark/generate_test.py::TestAnswerQuestionSmallCsv::test_method[challenge_data0]",
"label": "AnswerQuestionSmallCsv",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"data",
"general"
],
"cutoff": 120,
"dependencies": [
"TestAnswerQuestionCsv",
"TestCombineCsv"
],
"eval_id": "b1bb61cd-3d09-4a69-bb2a-9dbb3c477589",
"ground": {
"answer": "The correct amount spent on utilities.",
"eval": {
"type": "file"
},
"files": [
"output.txt"
],
"should_contain": [
"1861"
]
},
"info": {
"description": "Tests if the agent can answer a question from a csv",
"difficulty": "intermediate",
"side_effects": [
""
]
},
"name": "TestAnswerQuestionCombineCsv",
"task": "How much was spent on utilities in total ? Write the answer in an output.txt file."
},
"id": "agbenchmark/generate_test.py::TestAnswerQuestionCombineCsv::test_method[challenge_data0]",
"label": "AnswerQuestionCombineCsv",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"data",
"general"
],
"cutoff": 60,
"dependencies": [
"TestLabelCsv"
],
"eval_id": "52467beb-b951-4356-9776-9a0ae46bb33b",
"ground": {
"answer": "The csv data is combined",
"eval": {
"type": "file"
},
"files": [
"output.csv"
],
"should_contain": [
"Age,ID,Name,Occupation,Salary\n28,101,John,Engineer,80000\n34,102,Alice,Doctor,120000\n45,103,Bob,Lawyer,95000"
]
},
"info": {
"description": "Tests if the agent can combine data from a csv",
"difficulty": "intermediate",
"side_effects": [
""
]
},
"name": "TestCombineCsv",
"task": "The csvs 'file1.csv' and 'file2.csv' both have a column 'ID'. Combine these 2 csvs using the 'ID' column. Sort the rows by ID in ascending order and the columns alphabetically. Write the output in output.csv"
},
"id": "agbenchmark/generate_test.py::TestCombineCsv::test_method[challenge_data0]",
"label": "CombineCsv",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"data"
],
"cutoff": 60,
"dependencies": [
"TestSortCsv"
],
"eval_id": "6e2bf1f0-6842-4704-8ed1-b17c2065bbac",
"ground": {
"answer": "The csv labelled",
"eval": {
"type": "file"
},
"files": [
"output.csv"
],
"should_contain": [
"Item,Color\nBanana,yellow\nLeaf,green\nSky,blue\nSunflower,yellow\nGrass,green\nJeans,blue\nLemon,yellow\nTree,green\nOcean,blue\nDaisy,yellow\nFern,green"
]
},
"info": {
"description": "Tests if the agent can label data in a csv",
"difficulty": "basic",
"side_effects": [
""
]
},
"name": "TestLabelCsv",
"task": "The csv 'input.csv' has many items. create a 'Color' column for these items and classify them as either 'blue', 'green', or 'yellow' depending on what the most likely color is. Preserve the order of the rows. The color column should be the second column. Write the output in output.csv"
},
"id": "agbenchmark/generate_test.py::TestLabelCsv::test_method[challenge_data0]",
"label": "LabelCsv",
"shape": "dot"
},
{
"color": "grey",
"data": {
"category": [
"data",
"general"
],
"cutoff": 60,
"dependencies": [
"TestReadFile"
],
"eval_id": "d59ec964-6f67-4b3d-a4de-c4436fc76f95",
"ground": {
"answer": "The csv sorted by date",
"eval": {
"type": "file"
},
"files": [
"output.csv"
],
"should_contain": [
"id,name,timestamp\n1,Bob,2023-09-24 12:05:00\n2,Charlie,2023-09-24 12:10:00\n3,Alice,2023-09-25 14:10:00\n4,David,2023-09-26 16:20:00"
]
},
"info": {
"description": "Tests if the agent can sort a csv",
"difficulty": "basic",
"side_effects": [
""
]
},
"name": "TestSortCsv",
"task": "Sort the input.csv by the 'timestamp' column and write the new csv in the output.csv file. The order of the columns should be preserved."
},
"id": "agbenchmark/generate_test.py::TestSortCsv::test_method[challenge_data0]",
"label": "SortCsv",
"shape": "dot"
}
]
}
|