examen

.ipynb_checkpoints/08-Test2-checkpoint.ipynb

@@ -59,7 +59,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 105,
+   "execution_count": 133,
    "metadata": {},
    "outputs": [
     {
@@ -180,7 +180,7 @@
        "Documento3       0.0  "
       ]
      },
-     "execution_count": 105,
+     "execution_count": 133,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -193,6 +193,11 @@
     "\n",
     "class MatrizDT:\n",
     "    def __init__(self, listaDocs):\n",
+    "        \"\"\"Constructor de la clase\n",
+    "\n",
+    "        Args:\n",
+    "            listaDocs [(string)]: lista de documentos (Textos a interpretar)\n",
+    "        \"\"\"\n",
     "        self.listaDocs = listaDocs\n",
     "        self.cleanDocs = self.getArrayCleanDocs()\n",
     "        self.totalDocs = len(listaDocs)\n",
@@ -200,11 +205,26 @@
     "        self.listNameDoc = self.getListNameDoc()\n",
     "        \n",
     "    def removerpunt(self, s):\n",
+    "        \"\"\"Funcion que elimina caracteres no alpaheticos\n",
+    "\n",
+    "        Args:\n",
+    "            s (string): palabra a la cual se eliminaran los caracteres\n",
+    "\n",
+    "        Examples:\n",
+    "            >>> self.removerpunt(\"este es un texto con texto que es  repetido y repetido, \")\n",
+    "            este es un texto con texto que es repetido y repetido\n",
+    "        \"\"\"\n",
     "        s = re.sub(r\"[,|\\.|:|?|=|​]\", \"\", s)\n",
     "        s = re.sub(r\"[^\\w\\s]\", '', s)\n",
     "        return s\n",
     "    \n",
     "    def getListNameDoc(self):\n",
+    "        \"\"\"Funcion que devuelve un listado de nombres de documentos tomando de referencia la cantidad de documentos\n",
+    "        \n",
+    "        Examples:\n",
+    "            >>> self.getListNameDoc()\n",
+    "            [\"Documento1\", \"Documento2\", ..., \"DocumentoN\"]\n",
+    "        \"\"\"\n",
     "        aux = []\n",
     "        iCont = 1\n",
     "        for i in self.listaDocs:\n",
@@ -213,6 +233,8 @@
     "        return aux\n",
     "\n",
     "    def getArrayCleanDocs(self):\n",
+    "        \"\"\"Funcion que devueleve el arreglo de documentos al cual se le han eliminado los caracteres no deseados\n",
+    "        \"\"\"\n",
     "        aux = []\n",
     "        for i in self.listaDocs:\n",
     "            texto = self.removerpunt(i)\n",
@@ -221,6 +243,12 @@
     "        return np.array(aux)\n",
     "        \n",
     "    def getTerminos(self):\n",
+    "        \"\"\"Funcion que devueleve el liestado completo de terminos existentes en los documentos\n",
+    "        \n",
+    "        Examples:\n",
+    "            >>> self.getTerminos()\n",
+    "            [\"este\", \"es\", \"un\", \"ejemplo\"]\n",
+    "        \"\"\"\n",
     "        listaDocs = self.listaDocs\n",
     "        texto = ' '.join(listaDocs)\n",
     "        texto = texto.lower()\n",
@@ -228,6 +256,14 @@
     "        return np.array(list(set(arrayTexto)))\n",
     "        \n",
     "    def tf(self):\n",
+    "        \"\"\"Funcion que devueleve una matriz documento-termino en la cual cada celda es la frecuencia del termino\n",
+    "        \n",
+    "        Examples:\n",
+    "            >>> self.getTerminos()\n",
+    "            array([[0., 0., 1., 0., 1.69314718, 1., 0., 0., 0., 1., 0., 1., 0., 1., 0., 0.],\n",
+    "            [1., 0., 0., 1., 1., 1., 0., 0., 0., 0., 1., 0., 0., 1., 0., 1.],\n",
+    "            [0., 1., 0., 0., 1., 1., 1., 0., 1., 0., 0., 0., 0., 0., 1., 0.]])\n",
+    "        \"\"\"\n",
     "        aux = []\n",
     "        iCont = 1\n",
     "        for iDoc in self.cleanDocs:\n",
@@ -236,6 +272,14 @@
     "        return np.array(aux)\n",
     "    \n",
     "    def idf(self):\n",
+    "        \"\"\"Funcion que devueleve el liestado completo de terminos existentes en los documentos\n",
+    "        \n",
+    "        Examples:\n",
+    "            >>> self.getTerminos()\n",
+    "            array([[0., 0., 1., 0., 1.69314718, 1., 0., 0., 0., 1., 0., 1., 0., 1., 0., 0.],\n",
+    "            [1., 0., 0., 1., 1., 1., 0., 0., 0., 0., 1., 0., 0., 1., 0., 1.],\n",
+    "            [0., 1., 0., 0., 1., 1., 1., 0., 1., 0., 0., 0., 0., 0., 1., 0.]])\n",
+    "        \"\"\"\n",
     "        aux = []\n",
     "        data = self.tf()\n",
     "        #print(self.tf())\n",
@@ -280,6 +324,37 @@
     "mdt.getDF(tf)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 134,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[0.        , 0.        , 1.        , 0.        , 1.69314718,\n",
+       "        1.        , 0.        , 0.        , 0.        , 1.        ,\n",
+       "        0.        , 1.        , 0.        , 1.        , 0.        ,\n",
+       "        0.        ],\n",
+       "       [1.        , 0.        , 0.        , 1.        , 1.        ,\n",
+       "        1.        , 0.        , 0.        , 0.        , 0.        ,\n",
+       "        1.        , 0.        , 0.        , 1.        , 0.        ,\n",
+       "        1.        ],\n",
+       "       [0.        , 1.        , 0.        , 0.        , 1.        ,\n",
+       "        1.        , 1.        , 0.        , 1.        , 0.        ,\n",
+       "        0.        , 0.        , 0.        , 0.        , 1.        ,\n",
+       "        0.        ]])"
+      ]
+     },
+     "execution_count": 134,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tf"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 106,