Proyecto final

.ipynb_checkpoints/Untitled-checkpoint.ipynb

+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

Untitled.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 89,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sklearn import datasets\n",
+    "from sklearn.feature_extraction.text import CountVectorizer\n",
+    "from sklearn.feature_extraction.text import TfidfVectorizer\n",
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "import pickle\n",
+    "from sklearn import metrics\n",
+    "\n",
+    "categories = [\n",
+    "        'cine',\n",
+    "        'deportes'\n",
+    "    ]\n",
+    "with open(\"data/datatrain.json\") as f:\n",
+    "    for line in f:\n",
+    "        data_train = json.loads(line)\n",
+    "\n",
+    "documentos_train = []\n",
+    "target_train = []\n",
+    "for j in data_train:\n",
+    "    documentos_train.append(j[\"text\"])\n",
+    "    target_train.append(j[\"iclass\"])\n",
+    "\n",
+    "vectorizer = TfidfVectorizer()\n",
+    "\n",
+    "X_train = vectorizer.fit_transform(documentos_train)\n",
+    "y_train = target_train;\n",
+    "features_names = vectorizer.get_feature_names()\n",
+    "\n",
+    "clf, name = (KNeighborsClassifier(n_neighbors=3), \"kNN\")\n",
+    "clf.fit(X_train, y_train)\n",
+    "\n",
+    "with open(\"data/datatest.json\") as f:\n",
+    "    for line in f:\n",
+    "        data_test = json.loads(line)\n",
+    "\n",
+    "documentos_test = []\n",
+    "target_test = []\n",
+    "for j in data_test:\n",
+    "    documentos_test.append(j[\"text\"])\n",
+    "    target_test.append(j[\"iclass\"])\n",
+    "\n",
+    "X_test = vectorizer.transform(documentos_test)\n",
+    "y_test = target_test\n",
+    "\n",
+    "pred = clf.predict(X_test)\n",
+    "features_names = vectorizer.get_feature_names()\n",
+    "#print(pred)\n",
+    "\n",
+    "\n",
+    "\n",
+    "conti = 0\n",
+    "for i in data_test:\n",
+    "    #print(categories[ int(pred[int(conti)]) ] )\n",
+    "    i[\"class\"] = categories[ int(pred[int(conti)]) ]\n",
+    "    conti = conti + 1\n",
+    "with open(\"data/data.json\", 'w') as outfile:\n",
+    "    json.dump(datatest, outfile)\n",
+    "    \n",
+    "#print(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "\n",
+    "extension = '.json'\n",
+    "file_path = 'timeline'\n",
+    "\n",
+    "datatrain = []\n",
+    "datatest = []\n",
+    "with open(\"D:\\descargas\\cine\\data.json\") as f:\n",
+    "    for line in f:\n",
+    "        j_content = json.loads(line)\n",
+    "        icont = 0\n",
+    "        for i in j_content:\n",
+    "            if icont < 20:\n",
+    "                i[\"class\"] = \"cine\"\n",
+    "                i[\"iclass\"] = \"0\"\n",
+    "                datatrain.append(i)\n",
+    "            if icont > 19:\n",
+    "                i[\"class\"] = \"cine\"\n",
+    "                i[\"iclass\"] = \"0\"\n",
+    "                datatest.append(i)\n",
+    "            if icont > 40:\n",
+    "                break\n",
+    "            icont += 1\n",
+    "\n",
+    "with open(\"D:\\descargas\\deportes\\data.json\") as f:\n",
+    "    for line in f:\n",
+    "        j_content = json.loads(line)\n",
+    "        icont = 0\n",
+    "        for i in j_content:\n",
+    "            if icont < 20:\n",
+    "                i[\"class\"] = \"deportes\"\n",
+    "                i[\"iclass\"] = \"1\"\n",
+    "                datatrain.append(i)\n",
+    "            if icont > 19:\n",
+    "                i[\"class\"] = \"deportes\"\n",
+    "                i[\"iclass\"] = \"1\"\n",
+    "                datatest.append(i)\n",
+    "            if icont > 40:\n",
+    "                break\n",
+    "            icont += 1\n",
+    "with open(\"data/datatrain.json\", 'w') as outfile:\n",
+    "    json.dump(datatrain, outfile)\n",
+    "    \n",
+    "with open(\"data/datatest.json\", 'w') as outfile:\n",
+    "    json.dump(datatest, outfile)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<a href=\"http://example.com\">link</a>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "execution_count": 42,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from IPython.core.display import HTML\n",
+    "HTML('<a href=\"http://example.com\">link</a>')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}