Lab_Week1

Lab1_Week3.ipynb

@@ -0,0 +1,346 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "4e7dda1b-c83b-4286-a2fc-81057cb0890a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from functools import reduce\n",
+    "import numpy\n",
+    "import pandas"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "848e37d7-459c-484e-92b6-4c11b0e8d417",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Número de palabras: 13694\n"
+     ]
+    }
+   ],
+   "source": [
+    "import urllib.request\n",
+    "\n",
+    "url = \"https://www.gutenberg.org/cache/epub/58585/pg58585.txt\"\n",
+    "response = urllib.request.urlopen(url)\n",
+    "prophet = response.read().decode(\"utf8\").split(\" \")\n",
+    "\n",
+    "print(\"Número de palabras:\", len(prophet))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "c55c6688-4e11-442f-a4dc-818c831f7573",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prophet = prophet[568:]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "3c815a30-0959-4d2f-97bc-0bd9b8f67ff5",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['was',\n",
+       " 'to\\r\\nreturn',\n",
+       " 'and',\n",
+       " 'bear',\n",
+       " 'him',\n",
+       " 'back',\n",
+       " 'to',\n",
+       " 'the',\n",
+       " 'isle',\n",
+       " 'of\\r\\nhis']"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prophet[:10]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "66466b48-d2de-44fe-9bc2-6d64e4375f7b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def reference(x):\n",
+    "    '''\n",
+    "    Input: A string\n",
+    "    Output: The string with references removed\n",
+    "    \n",
+    "    Example:\n",
+    "    Input: 'the{7}'\n",
+    "    Output: 'the'\n",
+    "    '''\n",
+    "    parts = x.split('{')\n",
+    "    return parts[0]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "dc2b5a05-960b-417d-b0b0-191ae434a210",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prophet_reference = list(map(reference,prophet))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "5c1f09b5-e94e-486a-baf8-9519ecf5eee0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def line_break(x):\n",
+    "    '''\n",
+    "    Input: A string\n",
+    "    Output: A list of strings split on the line break (\\n) character\n",
+    "        \n",
+    "    Example:\n",
+    "    Input: 'the\\nbeloved'\n",
+    "    Output: ['the', 'beloved']\n",
+    "    '''\n",
+    "    return x.split('\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "09542ab4-5faa-4890-87b8-f5445cc6aecc",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "prophet_line = list(map(line_break, prophet_reference))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "17233c76-fd30-42ba-a857-737775ac030c",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['was',\n",
+       " 'to\\r',\n",
+       " 'return',\n",
+       " 'and',\n",
+       " 'bear',\n",
+       " 'him',\n",
+       " 'back',\n",
+       " 'to',\n",
+       " 'the',\n",
+       " 'isle',\n",
+       " 'of\\r',\n",
+       " 'his',\n",
+       " 'birth.\\r',\n",
+       " '\\r',\n",
+       " 'And',\n",
+       " 'in',\n",
+       " 'the',\n",
+       " 'twelfth',\n",
+       " 'year,',\n",
+       " 'on']"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prophet_flat = [i for sub in prophet_line for i in sub]\n",
+    "prophet_flat[:20]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "e650e1dc-e47d-495d-9d34-a0bbc4110a09",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Exercise 2 \n",
+    "def word_filter(x):\n",
+    "    '''\n",
+    "    Input: A string\n",
+    "    Output: True if the word is not in the specified list \n",
+    "    and False if the word is in the list.\n",
+    "    '''\n",
+    "    \n",
+    "    word_list = ['and', 'the', 'a', 'an']\n",
+    "    \n",
+    "    if x in word_list:\n",
+    "        return False\n",
+    "    else:\n",
+    "        return True\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "72c4649f-be1a-4791-8af0-4805031f76b2",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['was',\n",
+       " 'to\\r',\n",
+       " 'return',\n",
+       " 'bear',\n",
+       " 'him',\n",
+       " 'back',\n",
+       " 'to',\n",
+       " 'isle',\n",
+       " 'of\\r',\n",
+       " 'his',\n",
+       " 'birth.\\r',\n",
+       " '\\r',\n",
+       " 'And',\n",
+       " 'in',\n",
+       " 'twelfth',\n",
+       " 'year,',\n",
+       " 'on',\n",
+       " 'seventh\\r',\n",
+       " 'day',\n",
+       " 'of']"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prophet_filter = list(filter(word_filter, prophet_flat))\n",
+    "\n",
+    "prophet_filter[:20]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "693b6490-51a7-4d9d-b7d3-340d875bf861",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def word_filter_case(x):\n",
+    "    '''\n",
+    "    Same as word_filter, but ignores case.\n",
+    "    '''\n",
+    "    \n",
+    "    word_list = ['and', 'the', 'a', 'an']\n",
+    "    \n",
+    "    if x.lower() in word_list:\n",
+    "        return False\n",
+    "    else:\n",
+    "        return True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "173ccad8-3ad3-4b91-9c5e-f34a50e06d88",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['was',\n",
+       " 'to\\r',\n",
+       " 'return',\n",
+       " 'bear',\n",
+       " 'him',\n",
+       " 'back',\n",
+       " 'to',\n",
+       " 'isle',\n",
+       " 'of\\r',\n",
+       " 'his',\n",
+       " 'birth.\\r',\n",
+       " '\\r',\n",
+       " 'in',\n",
+       " 'twelfth',\n",
+       " 'year,',\n",
+       " 'on',\n",
+       " 'seventh\\r',\n",
+       " 'day',\n",
+       " 'of',\n",
+       " 'Ielool,']"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "prophet_filter_case = list(filter(word_filter_case, prophet_flat))\n",
+    "prophet_filter_case[:20]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4620572b-6a9d-469d-b160-2c9eb2d93884",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def concat_space(a, b):\n",
+    "    '''\n",
+    "    Input: Two strings\n",
+    "    Output: A single string separated by a space\n",
+    "    \n",
+    "    Example:\n",
+    "    Input: 'John', 'Smith'\n",
+    "    Output: 'John Smith'\n",
+    "    '''\n",
+    "    return a + ' ' + b"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.13.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}