Creating Training File

CARSE_00_Cleaning.ipynb

@@ -21,7 +21,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -64,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -115,7 +115,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -152,7 +152,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -209,7 +209,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 6,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -230,7 +230,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -288,7 +288,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -345,7 +345,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -461,7 +461,7 @@
        "10  Vale mi amor, disfruta tu baño\\nSabes que me e...  "
       ]
      },
-     "execution_count": 10,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -505,7 +505,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -529,7 +529,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -648,7 +648,7 @@
        "[670 rows x 2 columns]"
       ]
      },
-     "execution_count": 13,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -667,7 +667,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -683,7 +683,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -827,7 +827,7 @@
        "[670 rows x 3 columns]"
       ]
      },
-     "execution_count": 15,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -840,7 +840,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -853,7 +853,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
@@ -997,7 +997,7 @@
        "[670 rows x 3 columns]"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 15,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1010,7 +1010,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -1154,7 +1154,7 @@
        "[670 rows x 3 columns]"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 16,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -1174,7 +1174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1198,7 +1198,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1207,16 +1207,9 @@
     "crear_json(chat_df,nombre_json)\n"
    ]
   },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Separación del File de entrenamiento en partes iguales"
-   ]
-  },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -1240,42 +1233,6 @@
     "    print(\"Archivo no encontrado. Por favor verifica la ruta.\")"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "def dividir_jsonl(ruta_archivo, num_partes):\n",
-    "    # Leer todas las líneas del archivo\n",
-    "    with open(ruta_archivo, 'r', encoding='utf-8') as file:\n",
-    "        lineas = file.readlines()\n",
-    "\n",
-    "    # Calcular el tamaño de cada parte\n",
-    "    tamano_parte = len(lineas) // num_partes\n",
-    "\n",
-    "    for i in range(num_partes):\n",
-    "        # Calcular el inicio y el fin de cada parte\n",
-    "        inicio = i * tamano_parte\n",
-    "        fin = (i + 1) * tamano_parte if i != num_partes - 1 else len(lineas)\n",
-    "\n",
-    "        # Nombre del nuevo archivo\n",
-    "        nombre_nuevo_archivo = ruta_archivo.replace('.jsonl', f'_{i + 1}.jsonl')\n",
-    "\n",
-    "        # Escribir las líneas en el nuevo archivo\n",
-    "        with open(nombre_nuevo_archivo, 'w', encoding='utf-8') as nuevo_archivo:\n",
-    "            nuevo_archivo.writelines(lineas[inicio:fin])"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "dividir_jsonl('Training_Data/Training_Prompts.jsonl', 3)"
-   ]
-  },
   {
    "cell_type": "code",
    "execution_count": null,