Spaces:
Sleeping
Sleeping
Commit ·
dd5dc61
1
Parent(s): fb67766
Data examples visualization
Browse files- CARSE_00_Cleaning.ipynb +48 -48
CARSE_00_Cleaning.ipynb
CHANGED
|
@@ -1285,7 +1285,7 @@
|
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"cell_type": "code",
|
| 1288 |
-
"execution_count":
|
| 1289 |
"metadata": {},
|
| 1290 |
"outputs": [
|
| 1291 |
{
|
|
@@ -1345,48 +1345,48 @@
|
|
| 1345 |
" <td>...</td>\n",
|
| 1346 |
" </tr>\n",
|
| 1347 |
" <tr>\n",
|
| 1348 |
-
" <th>
|
| 1349 |
-
" <td>
|
| 1350 |
-
" <td>
|
| 1351 |
" </tr>\n",
|
| 1352 |
" <tr>\n",
|
| 1353 |
-
" <th>
|
| 1354 |
-
" <td>
|
| 1355 |
-
" <td>
|
| 1356 |
" </tr>\n",
|
| 1357 |
" <tr>\n",
|
| 1358 |
-
" <th>
|
| 1359 |
-
" <td>
|
| 1360 |
-
" <td>
|
| 1361 |
" </tr>\n",
|
| 1362 |
" <tr>\n",
|
| 1363 |
-
" <th>
|
| 1364 |
-
" <td>
|
| 1365 |
-
" <td>
|
| 1366 |
" </tr>\n",
|
| 1367 |
" <tr>\n",
|
| 1368 |
-
" <th>
|
| 1369 |
-
" <td>
|
| 1370 |
-
" <td>
|
| 1371 |
" </tr>\n",
|
| 1372 |
" </tbody>\n",
|
| 1373 |
"</table>\n",
|
| 1374 |
-
"<p>
|
| 1375 |
"</div>"
|
| 1376 |
],
|
| 1377 |
"text/plain": [
|
| 1378 |
-
"
|
| 1379 |
-
"0
|
| 1380 |
-
"1
|
| 1381 |
-
"2
|
| 1382 |
-
"3
|
| 1383 |
-
"4
|
| 1384 |
-
"..
|
| 1385 |
-
"
|
| 1386 |
-
"
|
| 1387 |
-
"
|
| 1388 |
-
"
|
| 1389 |
-
"
|
| 1390 |
"\n",
|
| 1391 |
" assistant \n",
|
| 1392 |
"0 Ya casi amorcito, solo me falta checar algunos... \n",
|
|
@@ -1395,23 +1395,23 @@
|
|
| 1395 |
"3 Te invito a besarnos escuchando a Dani Flow \n",
|
| 1396 |
"4 Perdóname Carmen Q, me quedé dormido de la nad... \n",
|
| 1397 |
".. ... \n",
|
| 1398 |
-
"
|
| 1399 |
-
"
|
| 1400 |
-
"
|
| 1401 |
-
"
|
| 1402 |
-
"
|
| 1403 |
"\n",
|
| 1404 |
-
"[
|
| 1405 |
]
|
| 1406 |
},
|
| 1407 |
-
"execution_count":
|
| 1408 |
"metadata": {},
|
| 1409 |
"output_type": "execute_result"
|
| 1410 |
}
|
| 1411 |
],
|
| 1412 |
"source": [
|
| 1413 |
"# Ruta de tu archivo JSONL\n",
|
| 1414 |
-
"archivo_jsonl = 'Training_Data/
|
| 1415 |
"\n",
|
| 1416 |
"# Lista para almacenar los datos extraídos\n",
|
| 1417 |
"json_data = []\n",
|
|
@@ -1435,7 +1435,7 @@
|
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"cell_type": "code",
|
| 1438 |
-
"execution_count":
|
| 1439 |
"metadata": {},
|
| 1440 |
"outputs": [
|
| 1441 |
{
|
|
@@ -1443,20 +1443,20 @@
|
|
| 1443 |
"output_type": "stream",
|
| 1444 |
"text": [
|
| 1445 |
"\n",
|
| 1446 |
-
"User:
|
| 1447 |
-
"Assistant:
|
| 1448 |
"\n",
|
| 1449 |
-
"User:
|
| 1450 |
-
"Assistant:
|
| 1451 |
"\n",
|
| 1452 |
-
"User:
|
| 1453 |
-
"Assistant:
|
| 1454 |
"\n",
|
| 1455 |
-
"User:
|
| 1456 |
-
"Assistant:
|
| 1457 |
"\n",
|
| 1458 |
-
"User:
|
| 1459 |
-
"Assistant:
|
| 1460 |
]
|
| 1461 |
}
|
| 1462 |
],
|
|
|
|
| 1285 |
},
|
| 1286 |
{
|
| 1287 |
"cell_type": "code",
|
| 1288 |
+
"execution_count": 196,
|
| 1289 |
"metadata": {},
|
| 1290 |
"outputs": [
|
| 1291 |
{
|
|
|
|
| 1345 |
" <td>...</td>\n",
|
| 1346 |
" </tr>\n",
|
| 1347 |
" <tr>\n",
|
| 1348 |
+
" <th>201</th>\n",
|
| 1349 |
+
" <td>Hoy que hiciste?</td>\n",
|
| 1350 |
+
" <td>Si quieres más tarde en llamada te cuento</td>\n",
|
| 1351 |
" </tr>\n",
|
| 1352 |
" <tr>\n",
|
| 1353 |
+
" <th>202</th>\n",
|
| 1354 |
+
" <td>Te extraño</td>\n",
|
| 1355 |
+
" <td>Igual te extraño, pero mucho</td>\n",
|
| 1356 |
" </tr>\n",
|
| 1357 |
" <tr>\n",
|
| 1358 |
+
" <th>203</th>\n",
|
| 1359 |
+
" <td>Que soñaste?</td>\n",
|
| 1360 |
+
" <td>Ahorita te cuento</td>\n",
|
| 1361 |
" </tr>\n",
|
| 1362 |
" <tr>\n",
|
| 1363 |
+
" <th>204</th>\n",
|
| 1364 |
+
" <td>Si se me antoja</td>\n",
|
| 1365 |
+
" <td>Pues vamos mi amorcito</td>\n",
|
| 1366 |
" </tr>\n",
|
| 1367 |
" <tr>\n",
|
| 1368 |
+
" <th>205</th>\n",
|
| 1369 |
+
" <td>Te amo</td>\n",
|
| 1370 |
+
" <td>Yo mas, solo esta vez déjame ganar Carmen Q, p...</td>\n",
|
| 1371 |
" </tr>\n",
|
| 1372 |
" </tbody>\n",
|
| 1373 |
"</table>\n",
|
| 1374 |
+
"<p>206 rows × 2 columns</p>\n",
|
| 1375 |
"</div>"
|
| 1376 |
],
|
| 1377 |
"text/plain": [
|
| 1378 |
+
" user \\\n",
|
| 1379 |
+
"0 Ya acabaste tus entregas de hoy? \n",
|
| 1380 |
+
"1 Buenos días amorchis \n",
|
| 1381 |
+
"2 Ya no quiero ir al gym \n",
|
| 1382 |
+
"3 Qué me vas a invitar hoy? \n",
|
| 1383 |
+
"4 Hola amor, ten bonito día, te quierooooo \n",
|
| 1384 |
+
".. ... \n",
|
| 1385 |
+
"201 Hoy que hiciste? \n",
|
| 1386 |
+
"202 Te extraño \n",
|
| 1387 |
+
"203 Que soñaste? \n",
|
| 1388 |
+
"204 Si se me antoja \n",
|
| 1389 |
+
"205 Te amo \n",
|
| 1390 |
"\n",
|
| 1391 |
" assistant \n",
|
| 1392 |
"0 Ya casi amorcito, solo me falta checar algunos... \n",
|
|
|
|
| 1395 |
"3 Te invito a besarnos escuchando a Dani Flow \n",
|
| 1396 |
"4 Perdóname Carmen Q, me quedé dormido de la nad... \n",
|
| 1397 |
".. ... \n",
|
| 1398 |
+
"201 Si quieres más tarde en llamada te cuento \n",
|
| 1399 |
+
"202 Igual te extraño, pero mucho \n",
|
| 1400 |
+
"203 Ahorita te cuento \n",
|
| 1401 |
+
"204 Pues vamos mi amorcito \n",
|
| 1402 |
+
"205 Yo mas, solo esta vez déjame ganar Carmen Q, p... \n",
|
| 1403 |
"\n",
|
| 1404 |
+
"[206 rows x 2 columns]"
|
| 1405 |
]
|
| 1406 |
},
|
| 1407 |
+
"execution_count": 196,
|
| 1408 |
"metadata": {},
|
| 1409 |
"output_type": "execute_result"
|
| 1410 |
}
|
| 1411 |
],
|
| 1412 |
"source": [
|
| 1413 |
"# Ruta de tu archivo JSONL\n",
|
| 1414 |
+
"archivo_jsonl = 'Training_Data/Training_Prompts_1.jsonl'\n",
|
| 1415 |
"\n",
|
| 1416 |
"# Lista para almacenar los datos extraídos\n",
|
| 1417 |
"json_data = []\n",
|
|
|
|
| 1435 |
},
|
| 1436 |
{
|
| 1437 |
"cell_type": "code",
|
| 1438 |
+
"execution_count": 210,
|
| 1439 |
"metadata": {},
|
| 1440 |
"outputs": [
|
| 1441 |
{
|
|
|
|
| 1443 |
"output_type": "stream",
|
| 1444 |
"text": [
|
| 1445 |
"\n",
|
| 1446 |
+
"User: Sueña bonito mi amor, hablamos mañana\n",
|
| 1447 |
+
"Assistant: También que sueñes muy bonito. Hablamos mañana, que tengas una linda noche. Besos\n",
|
| 1448 |
"\n",
|
| 1449 |
+
"User: Como vas con tus pendientes?\n",
|
| 1450 |
+
"Assistant: La verdad medio mal. Siento que ya no me va a dar el tiempo para hacer las cosas bien, ya me estresé mucho\n",
|
| 1451 |
"\n",
|
| 1452 |
+
"User: Yo más\n",
|
| 1453 |
+
"Assistant: Está bien, tú me amas más, pero solo poquito\n",
|
| 1454 |
"\n",
|
| 1455 |
+
"User: Soñé bonito contigo\n",
|
| 1456 |
+
"Assistant: Sí amorcito? Soñaste que nos casamos o algo así?\n",
|
| 1457 |
"\n",
|
| 1458 |
+
"User: Ahorita andamos en el McDonald’s\n",
|
| 1459 |
+
"Assistant: Disfruta. Guárdame una papita o algo asi\n"
|
| 1460 |
]
|
| 1461 |
}
|
| 1462 |
],
|