text segunda parte editado

09-TextProcessing.ipynb

@@ -205,7 +205,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -215,7 +215,7 @@
        "\twith 18 stored elements in Compressed Sparse Row format>"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -235,7 +235,43 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 6,
+   "metadata": {
+    "scrolled": true
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  (0, 1)\t1\n",
+      "  (0, 6)\t1\n",
+      "  (0, 2)\t1\n",
+      "  (0, 4)\t1\n",
+      "  (0, 5)\t1\n",
+      "  (1, 7)\t1\n",
+      "  (1, 1)\t1\n",
+      "  (1, 2)\t1\n",
+      "  (1, 4)\t1\n",
+      "  (1, 5)\t1\n",
+      "  (2, 8)\t1\n",
+      "  (2, 2)\t1\n",
+      "  (3, 3)\t1\n",
+      "  (3, 0)\t1\n",
+      "  (3, 6)\t1\n",
+      "  (3, 2)\t1\n",
+      "  (3, 4)\t1\n",
+      "  (3, 5)\t1\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(X)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
    "metadata": {},
    "outputs": [
     {
@@ -244,7 +280,7 @@
        "['este', 'es', 'un', 'documento', 'analizar']"
       ]
      },
-     "execution_count": 9,
+     "execution_count": 7,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -256,7 +292,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
@@ -273,7 +309,7 @@
        " 'tercero']"
       ]
      },
-     "execution_count": 10,
+     "execution_count": 8,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -284,7 +320,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [
     {
@@ -293,7 +329,7 @@
        "1"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 9,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -304,7 +340,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [
     {
@@ -324,13 +360,13 @@
        " 'son muy chidos']"
       ]
      },
-     "execution_count": 16,
+     "execution_count": 12,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "bigram_vectorizer = CountVectorizer(ngram_range=(1, 3), min_df=1)\n",
+    "bigram_vectorizer = CountVectorizer(ngram_range=(1, 3), min_df=4)\n",
     "analyze = bigram_vectorizer.build_analyzer()\n",
     "analyze('Los ngramas son muy chidos')"
    ]
@@ -344,7 +380,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -354,7 +390,7 @@
        "         use_idf=True)"
       ]
      },
-     "execution_count": 17,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -375,7 +411,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [
     {
@@ -389,7 +425,7 @@
        "       [0.58149261, 0.        , 0.81355169]])"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 14,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -413,31 +449,53 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "<4x9 sparse matrix of type '<class 'numpy.float64'>'\n",
-       "\twith 18 stored elements in Compressed Sparse Row format>"
-      ]
-     },
-     "execution_count": 20,
+   "execution_count": 16,
    "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "# Como tf-idf es muy común para representar documentos, existe la clase \n",
     "# TfidfVectorizer que tiene CountVectorizer y TfidfTransformer \n",
     "\n",
     "from sklearn.feature_extraction.text import TfidfVectorizer\n",
     "vectorizer = TfidfVectorizer()\n",
-    "vectorizer.fit_transform(corpus)\n",
+    "Xprima = vectorizer.fit_transform(corpus)\n",
     "                               "
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "  (0, 5)\t0.4181266243877562\n",
+      "  (0, 4)\t0.4181266243877562\n",
+      "  (0, 2)\t0.3418459132932508\n",
+      "  (0, 6)\t0.5164695651831305\n",
+      "  (0, 1)\t0.5164695651831305\n",
+      "  (1, 5)\t0.3878225151467608\n",
+      "  (1, 4)\t0.3878225151467608\n",
+      "  (1, 2)\t0.3170703183040649\n",
+      "  (1, 1)\t0.4790379614294201\n",
+      "  (1, 7)\t0.6075989123184679\n",
+      "  (2, 2)\t0.46263733109032296\n",
+      "  (2, 8)\t0.8865476297873808\n",
+      "  (3, 5)\t0.3314387711719163\n",
+      "  (3, 4)\t0.3314387711719163\n",
+      "  (3, 2)\t0.2709729130450805\n",
+      "  (3, 6)\t0.4093928203750212\n",
+      "  (3, 0)\t0.519262881857229\n",
+      "  (3, 3)\t0.519262881857229\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(Xprima)"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},