Practica 3 del parcial 2

Test2-3.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 124,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "import re\n",
+    "from operator import itemgetter    \n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "\n",
+    "frequency = {}\n",
+    "open_file = open('data/data_named_entity_recognition_sp_MX_locations.JSON', 'r')\n",
+    "file_to_string = open_file.read()\n",
+    "words = re.findall(r'(b[A-Za-z][a-z]{2,9}b)', file_to_string)\n",
+    "\n",
+    "for word in words:\n",
+    "    count = frequency.get(word,0)\n",
+    "    frequency[word] = count + 1\n",
+    "values=[]    \n",
+    "for key, value in reversed(sorted(frequency.items(), key = itemgetter(1))):\n",
+    "    values= np.append(values,[[key,value]])\n",
+    "\n",
+    "for i in range(len(values)):\n",
+    "    #print(values[i])\n",
+    "    if(i%2!=0):\n",
+    "        x=np.append(values2,[int(values[i])])\n",
+    "        \n",
+    "# the histogram of the data\n",
+    "patches = plt.hist(x, density=True, facecolor='g', alpha=0.75)\n",
+    "\n",
+    "plt.xlabel('X')\n",
+    "plt.ylabel('Y')\n",
+    "plt.title('La ley de Zipf')\n",
+    "\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "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": "3.6.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}