Datasets
Models
Downloads: 1
Diff of
/synthetics/05_compare_associations.ipynb
[000000]
..
[befbfc]
Switch to unified view
| a | b/synthetics/05_compare_associations.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "markdown", |
||
| 5 | "id": "3a93d4c0", |
||
| 6 | "metadata": {}, |
||
| 7 | "source": [ |
||
| 8 | "# Compare Associations\n", |
||
| 9 | "* This notebook compares the final GWAS p-values for the full synthetic genome/phenome datasets to those in the original genome/phenome datasets and computes the precision, recall and F1 values." |
||
| 10 | ] |
||
| 11 | }, |
||
| 12 | { |
||
| 13 | "cell_type": "code", |
||
| 14 | "execution_count": 1, |
||
| 15 | "id": "97ac91d7", |
||
| 16 | "metadata": {}, |
||
| 17 | "outputs": [], |
||
| 18 | "source": [ |
||
| 19 | "import os\n", |
||
| 20 | "import pathlib\n", |
||
| 21 | "import pandas as pd\n", |
||
| 22 | "\n", |
||
| 23 | "base_path = pathlib.Path(os.getcwd().replace(\"/synthetics\", \"\"))\n", |
||
| 24 | "data_path = base_path / 'mice_data_set' / 'data' \n", |
||
| 25 | "real_gwas_path = base_path / 'mice_data_set' / 'out' \n", |
||
| 26 | "synthetic_gwas_path = base_path / 'mice_data_set' / 'out_synth'\n" |
||
| 27 | ] |
||
| 28 | }, |
||
| 29 | { |
||
| 30 | "cell_type": "code", |
||
| 31 | "execution_count": 6, |
||
| 32 | "id": "0198fdaf", |
||
| 33 | "metadata": {}, |
||
| 34 | "outputs": [ |
||
| 35 | { |
||
| 36 | "data": { |
||
| 37 | "text/html": [ |
||
| 38 | "<div>\n", |
||
| 39 | "<style scoped>\n", |
||
| 40 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 41 | " vertical-align: middle;\n", |
||
| 42 | " }\n", |
||
| 43 | "\n", |
||
| 44 | " .dataframe tbody tr th {\n", |
||
| 45 | " vertical-align: top;\n", |
||
| 46 | " }\n", |
||
| 47 | "\n", |
||
| 48 | " .dataframe thead th {\n", |
||
| 49 | " text-align: right;\n", |
||
| 50 | " }\n", |
||
| 51 | "</style>\n", |
||
| 52 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 53 | " <thead>\n", |
||
| 54 | " <tr style=\"text-align: right;\">\n", |
||
| 55 | " <th></th>\n", |
||
| 56 | " <th>index</th>\n", |
||
| 57 | " <th>snp</th>\n", |
||
| 58 | " <th>p</th>\n", |
||
| 59 | " <th>interest</th>\n", |
||
| 60 | " </tr>\n", |
||
| 61 | " </thead>\n", |
||
| 62 | " <tbody>\n", |
||
| 63 | " <tr>\n", |
||
| 64 | " <th>0</th>\n", |
||
| 65 | " <td>1</td>\n", |
||
| 66 | " <td>rs29477109</td>\n", |
||
| 67 | " <td>5.052317e-14</td>\n", |
||
| 68 | " <td>True</td>\n", |
||
| 69 | " </tr>\n", |
||
| 70 | " <tr>\n", |
||
| 71 | " <th>1</th>\n", |
||
| 72 | " <td>2</td>\n", |
||
| 73 | " <td>rs27071351</td>\n", |
||
| 74 | " <td>7.074181e-14</td>\n", |
||
| 75 | " <td>True</td>\n", |
||
| 76 | " </tr>\n", |
||
| 77 | " <tr>\n", |
||
| 78 | " <th>2</th>\n", |
||
| 79 | " <td>3</td>\n", |
||
| 80 | " <td>rs27024162</td>\n", |
||
| 81 | " <td>7.170582e-14</td>\n", |
||
| 82 | " <td>True</td>\n", |
||
| 83 | " </tr>\n", |
||
| 84 | " <tr>\n", |
||
| 85 | " <th>3</th>\n", |
||
| 86 | " <td>4</td>\n", |
||
| 87 | " <td>rs49423067</td>\n", |
||
| 88 | " <td>7.198661e-14</td>\n", |
||
| 89 | " <td>True</td>\n", |
||
| 90 | " </tr>\n", |
||
| 91 | " <tr>\n", |
||
| 92 | " <th>4</th>\n", |
||
| 93 | " <td>5</td>\n", |
||
| 94 | " <td>rs29470802</td>\n", |
||
| 95 | " <td>8.049849e-14</td>\n", |
||
| 96 | " <td>True</td>\n", |
||
| 97 | " </tr>\n", |
||
| 98 | " <tr>\n", |
||
| 99 | " <th>...</th>\n", |
||
| 100 | " <td>...</td>\n", |
||
| 101 | " <td>...</td>\n", |
||
| 102 | " <td>...</td>\n", |
||
| 103 | " <td>...</td>\n", |
||
| 104 | " </tr>\n", |
||
| 105 | " <tr>\n", |
||
| 106 | " <th>79640</th>\n", |
||
| 107 | " <td>79641</td>\n", |
||
| 108 | " <td>rs3162358</td>\n", |
||
| 109 | " <td>9.998911e-01</td>\n", |
||
| 110 | " <td>False</td>\n", |
||
| 111 | " </tr>\n", |
||
| 112 | " <tr>\n", |
||
| 113 | " <th>79641</th>\n", |
||
| 114 | " <td>79642</td>\n", |
||
| 115 | " <td>rs50509099</td>\n", |
||
| 116 | " <td>9.999012e-01</td>\n", |
||
| 117 | " <td>False</td>\n", |
||
| 118 | " </tr>\n", |
||
| 119 | " <tr>\n", |
||
| 120 | " <th>79642</th>\n", |
||
| 121 | " <td>79643</td>\n", |
||
| 122 | " <td>rs47505090</td>\n", |
||
| 123 | " <td>9.999041e-01</td>\n", |
||
| 124 | " <td>False</td>\n", |
||
| 125 | " </tr>\n", |
||
| 126 | " <tr>\n", |
||
| 127 | " <th>79643</th>\n", |
||
| 128 | " <td>79644</td>\n", |
||
| 129 | " <td>rs232293770</td>\n", |
||
| 130 | " <td>9.999351e-01</td>\n", |
||
| 131 | " <td>False</td>\n", |
||
| 132 | " </tr>\n", |
||
| 133 | " <tr>\n", |
||
| 134 | " <th>79644</th>\n", |
||
| 135 | " <td>79645</td>\n", |
||
| 136 | " <td>rs247449322</td>\n", |
||
| 137 | " <td>9.999861e-01</td>\n", |
||
| 138 | " <td>False</td>\n", |
||
| 139 | " </tr>\n", |
||
| 140 | " </tbody>\n", |
||
| 141 | "</table>\n", |
||
| 142 | "<p>79645 rows × 4 columns</p>\n", |
||
| 143 | "</div>" |
||
| 144 | ], |
||
| 145 | "text/plain": [ |
||
| 146 | " index snp p interest\n", |
||
| 147 | "0 1 rs29477109 5.052317e-14 True\n", |
||
| 148 | "1 2 rs27071351 7.074181e-14 True\n", |
||
| 149 | "2 3 rs27024162 7.170582e-14 True\n", |
||
| 150 | "3 4 rs49423067 7.198661e-14 True\n", |
||
| 151 | "4 5 rs29470802 8.049849e-14 True\n", |
||
| 152 | "... ... ... ... ...\n", |
||
| 153 | "79640 79641 rs3162358 9.998911e-01 False\n", |
||
| 154 | "79641 79642 rs50509099 9.999012e-01 False\n", |
||
| 155 | "79642 79643 rs47505090 9.999041e-01 False\n", |
||
| 156 | "79643 79644 rs232293770 9.999351e-01 False\n", |
||
| 157 | "79644 79645 rs247449322 9.999861e-01 False\n", |
||
| 158 | "\n", |
||
| 159 | "[79645 rows x 4 columns]" |
||
| 160 | ] |
||
| 161 | }, |
||
| 162 | "execution_count": 6, |
||
| 163 | "metadata": {}, |
||
| 164 | "output_type": "execute_result" |
||
| 165 | } |
||
| 166 | ], |
||
| 167 | "source": [ |
||
| 168 | "PHENOTYPE = 'abBMD'\n", |
||
| 169 | "\n", |
||
| 170 | "real_snps = pd.read_csv(real_gwas_path / f'lm_{PHENOTYPE}_1_79646.csv')\n", |
||
| 171 | "real_snps = real_snps.rename(columns={real_snps.columns[0]: 'index'})\n", |
||
| 172 | "real_snps = real_snps[['index', 'snp', 'p']]\n", |
||
| 173 | "real_snps['interest'] = real_snps['p'].apply(lambda x: True if x <= 1e-8 else False)\n", |
||
| 174 | "real_snps" |
||
| 175 | ] |
||
| 176 | }, |
||
| 177 | { |
||
| 178 | "cell_type": "code", |
||
| 179 | "execution_count": 7, |
||
| 180 | "id": "34958109", |
||
| 181 | "metadata": {}, |
||
| 182 | "outputs": [ |
||
| 183 | { |
||
| 184 | "data": { |
||
| 185 | "text/html": [ |
||
| 186 | "<div>\n", |
||
| 187 | "<style scoped>\n", |
||
| 188 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 189 | " vertical-align: middle;\n", |
||
| 190 | " }\n", |
||
| 191 | "\n", |
||
| 192 | " .dataframe tbody tr th {\n", |
||
| 193 | " vertical-align: top;\n", |
||
| 194 | " }\n", |
||
| 195 | "\n", |
||
| 196 | " .dataframe thead th {\n", |
||
| 197 | " text-align: right;\n", |
||
| 198 | " }\n", |
||
| 199 | "</style>\n", |
||
| 200 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 201 | " <thead>\n", |
||
| 202 | " <tr style=\"text-align: right;\">\n", |
||
| 203 | " <th></th>\n", |
||
| 204 | " <th>index</th>\n", |
||
| 205 | " <th>snp</th>\n", |
||
| 206 | " <th>p</th>\n", |
||
| 207 | " <th>interest</th>\n", |
||
| 208 | " </tr>\n", |
||
| 209 | " </thead>\n", |
||
| 210 | " <tbody>\n", |
||
| 211 | " <tr>\n", |
||
| 212 | " <th>0</th>\n", |
||
| 213 | " <td>1</td>\n", |
||
| 214 | " <td>rs36353660</td>\n", |
||
| 215 | " <td>0.000000e+00</td>\n", |
||
| 216 | " <td>True</td>\n", |
||
| 217 | " </tr>\n", |
||
| 218 | " <tr>\n", |
||
| 219 | " <th>1</th>\n", |
||
| 220 | " <td>2</td>\n", |
||
| 221 | " <td>rs29220747</td>\n", |
||
| 222 | " <td>1.398388e-86</td>\n", |
||
| 223 | " <td>True</td>\n", |
||
| 224 | " </tr>\n", |
||
| 225 | " <tr>\n", |
||
| 226 | " <th>2</th>\n", |
||
| 227 | " <td>3</td>\n", |
||
| 228 | " <td>rs29470086</td>\n", |
||
| 229 | " <td>5.929727e-86</td>\n", |
||
| 230 | " <td>True</td>\n", |
||
| 231 | " </tr>\n", |
||
| 232 | " <tr>\n", |
||
| 233 | " <th>3</th>\n", |
||
| 234 | " <td>4</td>\n", |
||
| 235 | " <td>rs33102275</td>\n", |
||
| 236 | " <td>2.838852e-85</td>\n", |
||
| 237 | " <td>True</td>\n", |
||
| 238 | " </tr>\n", |
||
| 239 | " <tr>\n", |
||
| 240 | " <th>4</th>\n", |
||
| 241 | " <td>5</td>\n", |
||
| 242 | " <td>rs252502314</td>\n", |
||
| 243 | " <td>9.043721e-85</td>\n", |
||
| 244 | " <td>True</td>\n", |
||
| 245 | " </tr>\n", |
||
| 246 | " <tr>\n", |
||
| 247 | " <th>...</th>\n", |
||
| 248 | " <td>...</td>\n", |
||
| 249 | " <td>...</td>\n", |
||
| 250 | " <td>...</td>\n", |
||
| 251 | " <td>...</td>\n", |
||
| 252 | " </tr>\n", |
||
| 253 | " <tr>\n", |
||
| 254 | " <th>71310</th>\n", |
||
| 255 | " <td>71311</td>\n", |
||
| 256 | " <td>cfw-17-49864534</td>\n", |
||
| 257 | " <td>9.999609e-01</td>\n", |
||
| 258 | " <td>False</td>\n", |
||
| 259 | " </tr>\n", |
||
| 260 | " <tr>\n", |
||
| 261 | " <th>71311</th>\n", |
||
| 262 | " <td>71312</td>\n", |
||
| 263 | " <td>rs30856414</td>\n", |
||
| 264 | " <td>9.999711e-01</td>\n", |
||
| 265 | " <td>False</td>\n", |
||
| 266 | " </tr>\n", |
||
| 267 | " <tr>\n", |
||
| 268 | " <th>71312</th>\n", |
||
| 269 | " <td>71313</td>\n", |
||
| 270 | " <td>rs108433568</td>\n", |
||
| 271 | " <td>9.999735e-01</td>\n", |
||
| 272 | " <td>False</td>\n", |
||
| 273 | " </tr>\n", |
||
| 274 | " <tr>\n", |
||
| 275 | " <th>71313</th>\n", |
||
| 276 | " <td>71314</td>\n", |
||
| 277 | " <td>rs237834328</td>\n", |
||
| 278 | " <td>9.999895e-01</td>\n", |
||
| 279 | " <td>False</td>\n", |
||
| 280 | " </tr>\n", |
||
| 281 | " <tr>\n", |
||
| 282 | " <th>71314</th>\n", |
||
| 283 | " <td>71315</td>\n", |
||
| 284 | " <td>rs52090420</td>\n", |
||
| 285 | " <td>9.999899e-01</td>\n", |
||
| 286 | " <td>False</td>\n", |
||
| 287 | " </tr>\n", |
||
| 288 | " </tbody>\n", |
||
| 289 | "</table>\n", |
||
| 290 | "<p>71315 rows × 4 columns</p>\n", |
||
| 291 | "</div>" |
||
| 292 | ], |
||
| 293 | "text/plain": [ |
||
| 294 | " index snp p interest\n", |
||
| 295 | "0 1 rs36353660 0.000000e+00 True\n", |
||
| 296 | "1 2 rs29220747 1.398388e-86 True\n", |
||
| 297 | "2 3 rs29470086 5.929727e-86 True\n", |
||
| 298 | "3 4 rs33102275 2.838852e-85 True\n", |
||
| 299 | "4 5 rs252502314 9.043721e-85 True\n", |
||
| 300 | "... ... ... ... ...\n", |
||
| 301 | "71310 71311 cfw-17-49864534 9.999609e-01 False\n", |
||
| 302 | "71311 71312 rs30856414 9.999711e-01 False\n", |
||
| 303 | "71312 71313 rs108433568 9.999735e-01 False\n", |
||
| 304 | "71313 71314 rs237834328 9.999895e-01 False\n", |
||
| 305 | "71314 71315 rs52090420 9.999899e-01 False\n", |
||
| 306 | "\n", |
||
| 307 | "[71315 rows x 4 columns]" |
||
| 308 | ] |
||
| 309 | }, |
||
| 310 | "execution_count": 7, |
||
| 311 | "metadata": {}, |
||
| 312 | "output_type": "execute_result" |
||
| 313 | } |
||
| 314 | ], |
||
| 315 | "source": [ |
||
| 316 | "# Be sure to update the name of your lm file appropriately\n", |
||
| 317 | "\n", |
||
| 318 | "synthetic_snps = pd.read_csv(synthetic_gwas_path / 'lm_batchall_abBMD_1_71316.csv') \n", |
||
| 319 | "synthetic_snps = synthetic_snps.rename(columns={synthetic_snps.columns[0]: 'index'})\n", |
||
| 320 | "synthetic_snps = synthetic_snps[['index', 'snp', 'p']]\n", |
||
| 321 | "synthetic_snps['interest'] = synthetic_snps['p'].apply(lambda x: True if x <= 1e-8 else False)\n", |
||
| 322 | "synthetic_snps" |
||
| 323 | ] |
||
| 324 | }, |
||
| 325 | { |
||
| 326 | "cell_type": "code", |
||
| 327 | "execution_count": 8, |
||
| 328 | "id": "e1514a22", |
||
| 329 | "metadata": {}, |
||
| 330 | "outputs": [ |
||
| 331 | { |
||
| 332 | "data": { |
||
| 333 | "text/html": [ |
||
| 334 | "<div>\n", |
||
| 335 | "<style scoped>\n", |
||
| 336 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 337 | " vertical-align: middle;\n", |
||
| 338 | " }\n", |
||
| 339 | "\n", |
||
| 340 | " .dataframe tbody tr th {\n", |
||
| 341 | " vertical-align: top;\n", |
||
| 342 | " }\n", |
||
| 343 | "\n", |
||
| 344 | " .dataframe thead th {\n", |
||
| 345 | " text-align: right;\n", |
||
| 346 | " }\n", |
||
| 347 | "</style>\n", |
||
| 348 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 349 | " <thead>\n", |
||
| 350 | " <tr style=\"text-align: right;\">\n", |
||
| 351 | " <th></th>\n", |
||
| 352 | " <th>index_synthetic</th>\n", |
||
| 353 | " <th>snp</th>\n", |
||
| 354 | " <th>p_synthetic</th>\n", |
||
| 355 | " <th>interest_synthetic</th>\n", |
||
| 356 | " <th>index_real</th>\n", |
||
| 357 | " <th>p_real</th>\n", |
||
| 358 | " <th>interest_real</th>\n", |
||
| 359 | " </tr>\n", |
||
| 360 | " </thead>\n", |
||
| 361 | " <tbody>\n", |
||
| 362 | " <tr>\n", |
||
| 363 | " <th>0</th>\n", |
||
| 364 | " <td>1</td>\n", |
||
| 365 | " <td>rs36353660</td>\n", |
||
| 366 | " <td>0.000000e+00</td>\n", |
||
| 367 | " <td>True</td>\n", |
||
| 368 | " <td>77608</td>\n", |
||
| 369 | " <td>9.734443e-01</td>\n", |
||
| 370 | " <td>False</td>\n", |
||
| 371 | " </tr>\n", |
||
| 372 | " <tr>\n", |
||
| 373 | " <th>1</th>\n", |
||
| 374 | " <td>2</td>\n", |
||
| 375 | " <td>rs29220747</td>\n", |
||
| 376 | " <td>1.398388e-86</td>\n", |
||
| 377 | " <td>True</td>\n", |
||
| 378 | " <td>75217</td>\n", |
||
| 379 | " <td>9.426825e-01</td>\n", |
||
| 380 | " <td>False</td>\n", |
||
| 381 | " </tr>\n", |
||
| 382 | " <tr>\n", |
||
| 383 | " <th>2</th>\n", |
||
| 384 | " <td>3</td>\n", |
||
| 385 | " <td>rs29470086</td>\n", |
||
| 386 | " <td>5.929727e-86</td>\n", |
||
| 387 | " <td>True</td>\n", |
||
| 388 | " <td>77</td>\n", |
||
| 389 | " <td>1.346918e-12</td>\n", |
||
| 390 | " <td>True</td>\n", |
||
| 391 | " </tr>\n", |
||
| 392 | " <tr>\n", |
||
| 393 | " <th>3</th>\n", |
||
| 394 | " <td>4</td>\n", |
||
| 395 | " <td>rs33102275</td>\n", |
||
| 396 | " <td>2.838852e-85</td>\n", |
||
| 397 | " <td>True</td>\n", |
||
| 398 | " <td>70949</td>\n", |
||
| 399 | " <td>8.872558e-01</td>\n", |
||
| 400 | " <td>False</td>\n", |
||
| 401 | " </tr>\n", |
||
| 402 | " <tr>\n", |
||
| 403 | " <th>4</th>\n", |
||
| 404 | " <td>5</td>\n", |
||
| 405 | " <td>rs252502314</td>\n", |
||
| 406 | " <td>9.043721e-85</td>\n", |
||
| 407 | " <td>True</td>\n", |
||
| 408 | " <td>74884</td>\n", |
||
| 409 | " <td>9.383166e-01</td>\n", |
||
| 410 | " <td>False</td>\n", |
||
| 411 | " </tr>\n", |
||
| 412 | " <tr>\n", |
||
| 413 | " <th>...</th>\n", |
||
| 414 | " <td>...</td>\n", |
||
| 415 | " <td>...</td>\n", |
||
| 416 | " <td>...</td>\n", |
||
| 417 | " <td>...</td>\n", |
||
| 418 | " <td>...</td>\n", |
||
| 419 | " <td>...</td>\n", |
||
| 420 | " <td>...</td>\n", |
||
| 421 | " </tr>\n", |
||
| 422 | " <tr>\n", |
||
| 423 | " <th>71310</th>\n", |
||
| 424 | " <td>71311</td>\n", |
||
| 425 | " <td>cfw-17-49864534</td>\n", |
||
| 426 | " <td>9.999609e-01</td>\n", |
||
| 427 | " <td>False</td>\n", |
||
| 428 | " <td>58306</td>\n", |
||
| 429 | " <td>7.228062e-01</td>\n", |
||
| 430 | " <td>False</td>\n", |
||
| 431 | " </tr>\n", |
||
| 432 | " <tr>\n", |
||
| 433 | " <th>71311</th>\n", |
||
| 434 | " <td>71312</td>\n", |
||
| 435 | " <td>rs30856414</td>\n", |
||
| 436 | " <td>9.999711e-01</td>\n", |
||
| 437 | " <td>False</td>\n", |
||
| 438 | " <td>31335</td>\n", |
||
| 439 | " <td>3.776636e-01</td>\n", |
||
| 440 | " <td>False</td>\n", |
||
| 441 | " </tr>\n", |
||
| 442 | " <tr>\n", |
||
| 443 | " <th>71312</th>\n", |
||
| 444 | " <td>71313</td>\n", |
||
| 445 | " <td>rs108433568</td>\n", |
||
| 446 | " <td>9.999735e-01</td>\n", |
||
| 447 | " <td>False</td>\n", |
||
| 448 | " <td>21151</td>\n", |
||
| 449 | " <td>2.508090e-01</td>\n", |
||
| 450 | " <td>False</td>\n", |
||
| 451 | " </tr>\n", |
||
| 452 | " <tr>\n", |
||
| 453 | " <th>71313</th>\n", |
||
| 454 | " <td>71314</td>\n", |
||
| 455 | " <td>rs237834328</td>\n", |
||
| 456 | " <td>9.999895e-01</td>\n", |
||
| 457 | " <td>False</td>\n", |
||
| 458 | " <td>13645</td>\n", |
||
| 459 | " <td>1.552650e-01</td>\n", |
||
| 460 | " <td>False</td>\n", |
||
| 461 | " </tr>\n", |
||
| 462 | " <tr>\n", |
||
| 463 | " <th>71314</th>\n", |
||
| 464 | " <td>71315</td>\n", |
||
| 465 | " <td>rs52090420</td>\n", |
||
| 466 | " <td>9.999899e-01</td>\n", |
||
| 467 | " <td>False</td>\n", |
||
| 468 | " <td>66119</td>\n", |
||
| 469 | " <td>8.233664e-01</td>\n", |
||
| 470 | " <td>False</td>\n", |
||
| 471 | " </tr>\n", |
||
| 472 | " </tbody>\n", |
||
| 473 | "</table>\n", |
||
| 474 | "<p>71315 rows × 7 columns</p>\n", |
||
| 475 | "</div>" |
||
| 476 | ], |
||
| 477 | "text/plain": [ |
||
| 478 | " index_synthetic snp p_synthetic interest_synthetic \\\n", |
||
| 479 | "0 1 rs36353660 0.000000e+00 True \n", |
||
| 480 | "1 2 rs29220747 1.398388e-86 True \n", |
||
| 481 | "2 3 rs29470086 5.929727e-86 True \n", |
||
| 482 | "3 4 rs33102275 2.838852e-85 True \n", |
||
| 483 | "4 5 rs252502314 9.043721e-85 True \n", |
||
| 484 | "... ... ... ... ... \n", |
||
| 485 | "71310 71311 cfw-17-49864534 9.999609e-01 False \n", |
||
| 486 | "71311 71312 rs30856414 9.999711e-01 False \n", |
||
| 487 | "71312 71313 rs108433568 9.999735e-01 False \n", |
||
| 488 | "71313 71314 rs237834328 9.999895e-01 False \n", |
||
| 489 | "71314 71315 rs52090420 9.999899e-01 False \n", |
||
| 490 | "\n", |
||
| 491 | " index_real p_real interest_real \n", |
||
| 492 | "0 77608 9.734443e-01 False \n", |
||
| 493 | "1 75217 9.426825e-01 False \n", |
||
| 494 | "2 77 1.346918e-12 True \n", |
||
| 495 | "3 70949 8.872558e-01 False \n", |
||
| 496 | "4 74884 9.383166e-01 False \n", |
||
| 497 | "... ... ... ... \n", |
||
| 498 | "71310 58306 7.228062e-01 False \n", |
||
| 499 | "71311 31335 3.776636e-01 False \n", |
||
| 500 | "71312 21151 2.508090e-01 False \n", |
||
| 501 | "71313 13645 1.552650e-01 False \n", |
||
| 502 | "71314 66119 8.233664e-01 False \n", |
||
| 503 | "\n", |
||
| 504 | "[71315 rows x 7 columns]" |
||
| 505 | ] |
||
| 506 | }, |
||
| 507 | "execution_count": 8, |
||
| 508 | "metadata": {}, |
||
| 509 | "output_type": "execute_result" |
||
| 510 | } |
||
| 511 | ], |
||
| 512 | "source": [ |
||
| 513 | "combined = pd.merge(synthetic_snps, \n", |
||
| 514 | " real_snps, \n", |
||
| 515 | " how='inner', \n", |
||
| 516 | " on=['snp'],\n", |
||
| 517 | " suffixes=['_synthetic', '_real'])\n", |
||
| 518 | "combined" |
||
| 519 | ] |
||
| 520 | }, |
||
| 521 | { |
||
| 522 | "cell_type": "code", |
||
| 523 | "execution_count": 9, |
||
| 524 | "id": "86ba40f3", |
||
| 525 | "metadata": {}, |
||
| 526 | "outputs": [ |
||
| 527 | { |
||
| 528 | "name": "stdout", |
||
| 529 | "output_type": "stream", |
||
| 530 | "text": [ |
||
| 531 | " precision recall f1-score support\n", |
||
| 532 | "\n", |
||
| 533 | " False 1.00 0.99 1.00 71122\n", |
||
| 534 | " True 0.32 0.92 0.47 193\n", |
||
| 535 | "\n", |
||
| 536 | " accuracy 0.99 71315\n", |
||
| 537 | " macro avg 0.66 0.96 0.74 71315\n", |
||
| 538 | "weighted avg 1.00 0.99 1.00 71315\n" |
||
| 539 | ] |
||
| 540 | } |
||
| 541 | ], |
||
| 542 | "source": [ |
||
| 543 | "from sklearn.metrics import f1_score, classification_report, confusion_matrix\n", |
||
| 544 | "\n", |
||
| 545 | "print(classification_report(combined['interest_real'], combined['interest_synthetic']))\n" |
||
| 546 | ] |
||
| 547 | }, |
||
| 548 | { |
||
| 549 | "cell_type": "code", |
||
| 550 | "execution_count": null, |
||
| 551 | "id": "b50257ac", |
||
| 552 | "metadata": {}, |
||
| 553 | "outputs": [], |
||
| 554 | "source": [] |
||
| 555 | } |
||
| 556 | ], |
||
| 557 | "metadata": { |
||
| 558 | "kernelspec": { |
||
| 559 | "display_name": "Python 3 (ipykernel)", |
||
| 560 | "language": "python", |
||
| 561 | "name": "python3" |
||
| 562 | }, |
||
| 563 | "language_info": { |
||
| 564 | "codemirror_mode": { |
||
| 565 | "name": "ipython", |
||
| 566 | "version": 3 |
||
| 567 | }, |
||
| 568 | "file_extension": ".py", |
||
| 569 | "mimetype": "text/x-python", |
||
| 570 | "name": "python", |
||
| 571 | "nbconvert_exporter": "python", |
||
| 572 | "pygments_lexer": "ipython3", |
||
| 573 | "version": "3.7.5" |
||
| 574 | } |
||
| 575 | }, |
||
| 576 | "nbformat": 4, |
||
| 577 | "nbformat_minor": 5 |
||
| 578 | } |