{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Handling text with Python"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Get started"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text1 = 'In this world nothing can be said to be certain except death and taxes'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"len(text1)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text2 = text1.split(' ')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"len(text2)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text2"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 1. Finding Specific Words"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Words that are more than 5 letters long"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"[w for w in text2 if len(w) > 5]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Words that end with 'd'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"[w for w in text2 if w.endswith('d')]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Words that start with 'd'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"[w for w in text2 if w.startswith('d')]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"[w for w in text2 if w.startswith(('d','n'))]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 2. Using set()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Finding unique words from a list"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text3 = 'to be or not to be'\n",
"text4 = text3.split(' ')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text4"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text5 = set(text4)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"len(text5)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"text5"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### set vs list performance"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import time\n",
"import random\n",
"\n",
"NUMBER_OF_ELEMENTS = 10000\n",
"\n",
"# Create a list\n",
"lst = list(range(NUMBER_OF_ELEMENTS))\n",
"random.shuffle(lst)\n",
"\n",
"# Crt=eate a set from the list\n",
"s = set(lst)\n",
"\n",
"# Test if an element is in the set\n",
"start = time.time()\n",
"for i in range(NUMBER_OF_ELEMENTS):\n",
" i in s\n",
"end = time.time()\n",
"print(f'To test if {NUMBER_OF_ELEMENTS} elements are in the set, runtime is {end-start} seconds')\n",
"\n",
"# Test if an element is in the list\n",
"start = time.time()\n",
"for i in range(NUMBER_OF_ELEMENTS):\n",
" i in lst\n",
"end = time.time()\n",
"print(f'To test if {NUMBER_OF_ELEMENTS} elements are in the list, runtime is {end-start} seconds')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 3. More String Operations"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### t in s - To check whether a substring exists in a given string"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Python' in 'Python is good'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.isupper() - To check whether all the characters of the string are uppercase"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'PYTHON IS GOOD'.isupper()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Python is good'.isupper()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.islower() - To check whether all the characters of the string are lowercase"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'python is good'.islower()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Python is good'.islower()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.istitle() - To check whether each word in the string starts with an uppercase letter"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Python Is Good'.istitle()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Python is good'.istitle()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.isdigit() - To check whether the string contains digits only"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'000002'.isdigit()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'SZ000002'.isdigit()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.isalpha() - To check whether the string contains alphabetic characters only"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Textmining'.isalpha()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'Text mining1'.isalpha()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.isalnum() - To check whether the string contains alphanumeric characters only"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'SZ000002'.isalnum()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'SZ_000002#'.isalnum()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Conversion between uppercase and lowercase"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s1 = 'python is good'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.upper() - Returns a string in which all characters are uppercased"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s2 = s1.upper()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s2"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.lower() - Returns a string in which all characters are lowercased"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s2.lower()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.capitalize() - Returns a string with only its first character capitalized"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s1.capitalize()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.title() - Returns a string in which first characters of all the words are capitalized"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s1.title()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.split()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s3 = 'cattcatt'\n",
"s4 = s3.split('a')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s4"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### join()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'a'.join(s4)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Get all the characters of s3 "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"list(s3)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"[c for c in s3]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### String formatting"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'{} {}'.format('hello', 'world')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"'{} {}'.format(24, 'seconds')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"24 + 'seconds' "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### f-string "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"name = 'Eric'\n",
"age = 74"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"f'Hello, {name}. You are {age}.'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.strip() – Removes whitespaces at the beginning and at the end of the string"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s5 = ' a quick brown fox jumped over the lazy dog '\n",
"s6 = s5.strip()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s6"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### sring.replace(old, new) - Returns a string where all occurrences of the old substring are replaced with the new substring"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s6.replace('o', 'O')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s6.replace('o', 'O', 2)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### string.translate(table) - The translate() method returns a string where each character is mapped to its corresponding character in the translation table. The translation table is created by the static method maketrans()."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"intab = 'aeiou'\n",
"outtab = '12345'\n",
"table = str.maketrans(intab, outtab)\n",
"s7 = 'aeiou-xmppp'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s7.translate(table)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"table_1 = str.maketrans(intab, outtab, 'xm')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s7.translate(table_1)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 4. Index and Slice String"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Accessing characters by positive index number"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s = 'Hello World!'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[4]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Accessing characters by negative index number"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[-3]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Slicing strings"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[1:5]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[:5]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[-4:-1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[-2:]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Specifying stride while slicing strings"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[:5]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[:5:1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[:5:2]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[::-1]"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s[-1:-7:-2]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### String.find() - Return the index of the first occurrence of the substring"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s.find('o')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"s.find('or')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## 5. Writing to and Reading from CSV File"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"import csv"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Writing to a csv file"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('test.csv', 'w', encoding='utf8', newline='') as wf:\n",
" writer = csv.writer(wf)\n",
" writer.writerow(('张三','北京'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Reading from a csv file"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"with open('test.csv', 'r', encoding='utf8') as rf:\n",
" r = csv.reader(rf)\n",
" for row in r:\n",
" print(f'姓名:{row[0]}, 住址:{row[1]}')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Exercise1\n",
"## Write a Python program to get a string from a given string where all occurrences of its first char have been changed to '@' except the first char itself.\n",
"### Sample String : 'restart'\n",
"### Expected Result : 'resta@t'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def change_char(str1):\n",
" ### START CODE HERE ###\n",
"\n",
" ### END CODE HERE ###\n",
" return str1"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check your function\n",
"print(change_char('restart'))\n",
"print(change_char('text'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Expected output\n",
"```\n",
"resta@t\n",
"tex@\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Exercise2\n",
"## Given an input string with the combination of the lower and upper case, arrange characters in such a way that all lowercase letters should come first.\n",
"### Sample String : 'PyNaTive'\n",
"### Expected Result : 'yaivePNT'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def arrange_chars(str1):\n",
" \n",
" ### START CODE HERE ###\n",
"\n",
" ### END CODE HERE ###\n",
" return str1"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check your function\n",
"print(arrange_chars('PyNaTive'))\n",
"print(arrange_chars('OpTYabi'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Expected output\n",
"```\n",
"yaivePNT\n",
"pabiOTY\n",
"```"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Exercise3\n",
"## Write a Python function that takes a list of words and returns the word with the largest length.\n",
"### Sample List : [\"Python\", \"Text\", \"Analysis\"]\n",
"### Expected Result : 'Analysis'"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def find_longest_word(words_list):\n",
" longest_word = ''\n",
" max_len = 0\n",
" ### START CODE HERE ###\n",
"\n",
" ### END CODE HERE ###\n",
" return longest_word"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Check your function\n",
"print(find_longest_word([\"Python\", \"Text\", \"Analysis\"]))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Expected output\n",
"```\n",
"Analysis\n",
"```"
]
},
{
"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": "3.7.4"
}
},
"nbformat": 4,
"nbformat_minor": 2
}