add notebook and files for homework with regex

hw5/.ipynb_checkpoints/regex-checkpoint.ipynb

@@ -0,0 +1,215 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import re\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 1. Find all ftp links and write them to **ftp** file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('references', 'r') as f_in:\n",
+    "    lines = f_in.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "text = ''.join(lines)\n",
+    "pattern = re.compile(r'ftp\\.[^;\\t\\n]+')\n",
+    "ftp_links = pattern.findall(text)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('ftps', 'w') as f_out:\n",
+    "    for ftp_link in ftp_links:\n",
+    "        f_out.write(f'{ftp_link}\\n')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 2. Extract all numbers from **2430 A.D.** story"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "with open('2430AD', 'r') as f_in:\n",
+    "    lines = f_in.readlines()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "2430 1969 2430 2430 57 57 1970 3 68 35 460 2430\n"
+     ]
+    }
+   ],
+   "source": [
+    "text = ''.join(lines)\n",
+    "pattern = re.compile(r'[0-9]+')\n",
+    "all_numbers = pattern.findall(text)\n",
+    "print(*all_numbers)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 3. Extract all words starting with **A** or **a**."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "and and are all and an Alvarez An adjustment along as and Alvarez and athletic and almost an and avoided and and apartment Alvarez All And at against and almost And another as about an and And at all always all and asked and and Alvarez ask as as are and always all and asking accede Alvarez amount and Alvarez and and are all and And and all Alvarez as as amount And asked All All Alvarez against against are and and abandoned all are Alvarez and and Alvarez and and and at and all and as and advances are and art and and advance and animal animal all all animal Alvarez amphibians at all and animals And and are are are adjusted are all an and and after attempt and Alvarez and animals all another already and and are All at all and all acted act And Alvarez Alvarez audible against are and and and And And and amused and and and and and and and And and and and and and and And all as and all and and animals appropriate and and and and also and after all all and all at and ASSET again and at and agree and about about ashamed and as added as and and animal above\n"
+     ]
+    }
+   ],
+   "source": [
+    "pattern = re.compile(r'\\s([Aa]\\w+)\\s')\n",
+    "words = pattern.findall(text)\n",
+    "print(*words)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 3. Extract all proposals ending with **!**"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Yes!\n",
+      "Literally!\n",
+      "There was once a time!\n",
+      "Centuries ago!\n",
+      "Think, Cranwitz!\n",
+      "If we succeed!\n"
+     ]
+    }
+   ],
+   "source": [
+    "pattern = re.compile('[A-Z][^\\n.!?]+[!]')\n",
+    "proposals = pattern.findall(text)\n",
+    "for proposal in proposals:\n",
+    "    print(proposal)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "#### 4. Draw length distribution of unique words with length more than 1 (register does not matter)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "pattern = re.compile('\\s([A-Za-z]+)')\n",
+    "all_words = pattern.findall(text)\n",
+    "all_words_capitalized = [word.lower() for word in all_words]\n",
+    "unique_words= set(all_words_capitalized)\n",
+    "length_ls = [len(word) for word in unique_words]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 864x720 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12, 10));\n",
+    "plt.hist(length_ls, color='red', alpha=.5);\n",
+    "plt.xlabel('word length', fontsize=16);\n",
+    "plt.ylabel('frequency', fontsize=16);\n",
+    "plt.grid();"
+   ]
+  }
+ ],
+ "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": "3.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}