String subclass for phonetic Levenshtein distance - python

I'm trying to create a string subclass, in order to represent Arpabet symbols as single characters. Here is what I got so far:
import Levenshtein
class ArpabetChar(str):
"""
Class that turn string into an Arpabet character.
http://www.speech.cs.cmu.edu/cgi-bin/cmudict
"""
def __init__(self, chars: list):
self._chars = chars
def __repr__(self):
return "".join(char for char in self._chars)
def __str__(self):
return "".join(char for char in self._chars)
def __eq__(self, other):
if self._chars == other._chars:
return True
else:
return False
def __len__(self):
return len(self._chars)
def __getitem__(self, item):
return self._chars[item]
def __iter__(self):
for char in self._chars:
yield ArpabetChar([char])
def __add__(self, other):
added_char = [char for char in self._chars]
for char in other._chars:
added_char.append(char)
return ArpabetChar(added_char)
char1 = ArpabetChar(["AH0"])
char2 = ArpabetChar(["AH1"])
char3 = ArpabetChar(["AE1"])
print("Indexing:", char1[0])
print(f"Length of {char1}: {len(char1)}")
print(f"Length of {char2}: {len(char2)}")
print(f"Levenshtein distance {char1} and {char2}:{Levenshtein.distance(char1, char2)}")
print(f"Levenshtein distance {char1} and {char3}:{Levenshtein.distance(char1, char3)}")
The output that I expect for both calculations is a Levenshtein distance of 1. Any hints or suggestions?

Related

CS50's Introduction to Artificial Intelligence with Python - Knowledge

I'm studyng Harvard's Introduction to Artificial Intelligence with Python course. I'm enjoying a lot. However I downloaded logic file to use Boolean algebra and Knowledge, that simple operations (OR,AND,NOT...) Before I show my doubt I will share the Knowledge class from harvard source code, I hope there isn't issues on it:
link to this class:
Harvard class
logic.py
import itertools
class Sentence():
def evaluate(self, model):
"""Evaluates the logical sentence."""
raise Exception("nothing to evaluate")
def formula(self):
"""Returns string formula representing logical sentence."""
return ""
def symbols(self):
"""Returns a set of all symbols in the logical sentence."""
return set()
#classmethod
def validate(cls, sentence):
if not isinstance(sentence, Sentence):
raise TypeError("must be a logical sentence")
#classmethod
def parenthesize(cls, s):
"""Parenthesizes an expression if not already parenthesized."""
def balanced(s):
"""Checks if a string has balanced parentheses."""
count = 0
for c in s:
if c == "(":
count += 1
elif c == ")":
if count <= 0:
return False
count -= 1
return count == 0
if not len(s) or s.isalpha() or (
s[0] == "(" and s[-1] == ")" and balanced(s[1:-1])
):
return s
else:
return f"({s})"
class Symbol(Sentence):
def __init__(self, name):
self.name = name
def __eq__(self, other):
return isinstance(other, Symbol) and self.name == other.name
def __hash__(self):
return hash(("symbol", self.name))
def __repr__(self):
return self.name
def evaluate(self, model):
try:
return bool(model[self.name])
except KeyError:
raise Exception(f"variable {self.name} not in model")
def formula(self):
return self.name
def symbols(self):
return {self.name}
class Not(Sentence):
def __init__(self, operand):
Sentence.validate(operand)
self.operand = operand
def __eq__(self, other):
return isinstance(other, Not) and self.operand == other.operand
def __hash__(self):
return hash(("not", hash(self.operand)))
def __repr__(self):
return f"Not({self.operand})"
def evaluate(self, model):
return not self.operand.evaluate(model)
def formula(self):
return "¬" + Sentence.parenthesize(self.operand.formula())
def symbols(self):
return self.operand.symbols()
class And(Sentence):
def __init__(self, *conjuncts):
for conjunct in conjuncts:
Sentence.validate(conjunct)
self.conjuncts = list(conjuncts)
def __eq__(self, other):
return isinstance(other, And) and self.conjuncts == other.conjuncts
def __hash__(self):
return hash(
("and", tuple(hash(conjunct) for conjunct in self.conjuncts))
)
def __repr__(self):
conjunctions = ", ".join(
[str(conjunct) for conjunct in self.conjuncts]
)
return f"And({conjunctions})"
def add(self, conjunct):
Sentence.validate(conjunct)
self.conjuncts.append(conjunct)
def evaluate(self, model):
return all(conjunct.evaluate(model) for conjunct in self.conjuncts)
def formula(self):
if len(self.conjuncts) == 1:
return self.conjuncts[0].formula()
return " ∧ ".join([Sentence.parenthesize(conjunct.formula())
for conjunct in self.conjuncts])
def symbols(self):
return set.union(*[conjunct.symbols() for conjunct in self.conjuncts])
class Or(Sentence):
def __init__(self, *disjuncts):
for disjunct in disjuncts:
Sentence.validate(disjunct)
self.disjuncts = list(disjuncts)
def __eq__(self, other):
return isinstance(other, Or) and self.disjuncts == other.disjuncts
def __hash__(self):
return hash(
("or", tuple(hash(disjunct) for disjunct in self.disjuncts))
)
def __repr__(self):
disjuncts = ", ".join([str(disjunct) for disjunct in self.disjuncts])
return f"Or({disjuncts})"
def evaluate(self, model):
return any(disjunct.evaluate(model) for disjunct in self.disjuncts)
def formula(self):
if len(self.disjuncts) == 1:
return self.disjuncts[0].formula()
return " ∨ ".join([Sentence.parenthesize(disjunct.formula())
for disjunct in self.disjuncts])
def symbols(self):
return set.union(*[disjunct.symbols() for disjunct in self.disjuncts])
class Implication(Sentence):
def __init__(self, antecedent, consequent):
Sentence.validate(antecedent)
Sentence.validate(consequent)
self.antecedent = antecedent
self.consequent = consequent
def __eq__(self, other):
return (isinstance(other, Implication)
and self.antecedent == other.antecedent
and self.consequent == other.consequent)
def __hash__(self):
return hash(("implies", hash(self.antecedent), hash(self.consequent)))
def __repr__(self):
return f"Implication({self.antecedent}, {self.consequent})"
def evaluate(self, model):
return ((not self.antecedent.evaluate(model))
or self.consequent.evaluate(model))
def formula(self):
antecedent = Sentence.parenthesize(self.antecedent.formula())
consequent = Sentence.parenthesize(self.consequent.formula())
return f"{antecedent} => {consequent}"
def symbols(self):
return set.union(self.antecedent.symbols(), self.consequent.symbols())
class Biconditional(Sentence):
def __init__(self, left, right):
Sentence.validate(left)
Sentence.validate(right)
self.left = left
self.right = right
def __eq__(self, other):
return (isinstance(other, Biconditional)
and self.left == other.left
and self.right == other.right)
def __hash__(self):
return hash(("biconditional", hash(self.left), hash(self.right)))
def __repr__(self):
return f"Biconditional({self.left}, {self.right})"
def evaluate(self, model):
return ((self.left.evaluate(model)
and self.right.evaluate(model))
or (not self.left.evaluate(model)
and not self.right.evaluate(model)))
def formula(self):
left = Sentence.parenthesize(str(self.left))
right = Sentence.parenthesize(str(self.right))
return f"{left} <=> {right}"
def symbols(self):
return set.union(self.left.symbols(), self.right.symbols())
def model_check(knowledge, query):
"""Checks if knowledge base entails query."""
def check_all(knowledge, query, symbols, model):
"""Checks if knowledge base entails query, given a particular model."""
# If model has an assignment for each symbol
if not symbols:
# If knowledge base is true in model, then query must also be true
if knowledge.evaluate(model):
return query.evaluate(model)
return True
else:
# Choose one of the remaining unused symbols
remaining = symbols.copy()
p = remaining.pop()
# Create a model where the symbol is true
model_true = model.copy()
model_true[p] = True
# Create a model where the symbol is false
model_false = model.copy()
model_false[p] = False
# Ensure entailment holds in both models
return (check_all(knowledge, query, remaining, model_true) and
check_all(knowledge, query, remaining, model_false))
# Get all symbols in both knowledge and query
symbols = set.union(knowledge.symbols(), query.symbols())
# Check that knowledge entails query
return check_all(knowledge, query, symbols, dict())
I know it's too much code, but my doubt is very simple, I tested basic Knowledge Boolean algebra operations such as NOT, AND, and OR. The problem is only at OR fucntion, it always should return TRUE if at least one is true. But it's returning false.
from logic import *
a = Symbol("a")
b = Symbol("b")
# OR
# Error here
orSentence = Or(a, b)
valueOrSentence = model_check(orSentence, a)
print(orSentence.formula() + f" ({valueOrSentence})")
valueOrSentence = model_check(orSentence, Not(a))
print(orSentence.formula() + f" ({valueOrSentence})")
print('---/---/---/')
It should return "true" when check the model, but instead of it it's returning "false"
I prefer to belive there is no error on Harvard logic.py file, what should I do to fix this "OR" logic?
For one specific case of model your knowledge entails but query doesn't, hence it is returning False. There is nothing wrong with it.
When model = {'a': False, 'b': True} then orSentence.evaluate(model) would return True but a.evaluate(model) would return False making the overall result of model_check as False.
If you use andSentence = And(a, b) and then run model_check(andSentence, a), it would return True because for every value of model either andSentence (knowledge) and a (query) both are True or both are False.

Leetcode Python 208. Implement Trie (Prefix Tree)

Can someone say what is wrong with my code, it is passing all the test cases except the last one when I downloaded the specific test case both the expected and actual output seems same, the question is https://leetcode.com/problems/implement-trie-prefix-tree/description/
Edit 1:
Here is the code:
class Trie:
def __init__(self):
"""
Initialize your data structure here.
"""
self.data = None
self.children = {}
self.isWord = False
def insert(self, word):
"""
Inserts a word into the trie.
:type word: str
:rtype: void
"""
if len(word) == 0:
return
if word[0] not in self.children:
self.children[word[0]] = Trie()
self.insertHelper(word[1:], self.children[word[0]])
else:
self.insertHelper(word[1:], self.children[word[0]])
if len(word) == 1:
self.isWord = True
def insertHelper(self, word, trie):
if len(word) == 0:
return
if word[0] not in trie.children:
trie.children[word[0]] = Trie()
trie.insertHelper(word[1:], trie.children[word[0]])
else:
trie.insertHelper(word[1:], trie.children[word[0]])
if len(word) == 1:
trie.isWord = True
def search(self, word):
"""
Returns if the word is in the trie.
:type word: str
:rtype: bool
"""
if len(word) == 1 and word[0] in self.children and self.isWord:
return True
elif len(word) == 0:
return False
if word[0] in self.children:
return self.searchHelper(word[1:], self.children[word[0]])
else:
return False
def searchHelper(self, word, trie):
if len(word) == 1 and word[0] in trie.children and trie.isWord:
return True
elif len(word) == 0:
return False
if word[0] in trie.children:
return self.searchHelper(word[1:], trie.children[word[0]])
else:
return False
def startsWith(self, prefix):
"""
Returns if there is any word in the trie that starts with the given prefix.
:type prefix: str
:rtype: bool
"""
if len(prefix) == 0:
return False
if prefix[0] in self.children:
return self.startsWithHelper(prefix[1:], self.children[prefix[0]])
else:
return False
def startsWithHelper(self, prefix, trie):
if len(prefix) == 0:
return True
if prefix[0] in trie.children:
return trie.startsWithHelper(prefix[1:], trie.children[prefix[0]])
else:
return False
Thanks in advance.
One quirk I noticed is passing an empty prefix into startsWith(). If this method is modeled on the Python str method startswith(), then we expect True:
>>> "apple".startswith("")
True
>>>
But your Trie returns False in this situation:
>>> t = Trie()
>>> t.insert("apple")
>>> t.startsWith("")
False
>>>
Below is my rework of your code that I did primarily to understand it but I also found you had redundancies, particularly your Helper functions. This code fixes the quirk mentioned above and is Python 3 specific:
class Trie:
def __init__(self):
self.children = {}
self.isWord = False
def insert(self, word):
"""
Inserts a word into the trie.
:type word: str (or list internally upon recursion)
:rtype: None
"""
if not word:
return
head, *tail = word
if head not in self.children:
self.children[head] = Trie()
trie = self.children[head]
if tail:
trie.insert(tail)
else:
self.isWord = True
def search(self, word):
"""
Returns True if the word is in the trie.
:type word: str (or list internally upon recursion)
:rtype: bool
"""
if not word:
return False
head, *tail = word
if head in self.children:
if not tail and self.isWord:
return True
return self.children[head].search(word[1:])
return False
def startsWith(self, prefix):
"""
Returns if there is any word in the trie that starts with the given prefix.
:type prefix: str (or list internally upon recursion)
:rtype: bool
"""
if not prefix:
return True
head, *tail = prefix
if head in self.children:
return self.children[head].startsWith(tail)
return False
Here's another solution using the 'defaultdictionary' from the collections module to utilize recursion in the 'insert' function too.
Credit: https://leetcode.com/problems/implement-trie-prefix-tree/discuss/631957/python-elegant-solution-no-nested-dictionaries
class Trie:
def __init__(self):
"""
Initialize your data structure here.
"""
self.nodes = collections.defaultdict(Trie)
self.is_word = False
def insert(self, word: str) -> None:
"""
Inserts a word into the trie.
"""
if not word:
self.is_word = True
else:
self.nodes[word[0]].insert(word[1:])
def search(self, word: str) -> bool:
"""
Returns if the word is in the trie.
"""
if not word:
return self.is_word
if word[0] in self.nodes:
return self.nodes[word[0]].search(word[1:])
return False
def startsWith(self, prefix: str) -> bool:
"""
Returns if there is any word in the trie that starts with the given prefix.
"""
if not prefix:
return True
if prefix[0] in self.nodes:
return self.nodes[prefix[0]].startsWith(prefix[1:])
return False
Your Trie object will be instantiated and called as such:
obj = Trie()
obj.insert(word)
param_2 = obj.search(word)
param_3 = obj.startsWith(prefix)
class TrieNode:
def __init__(self):
# each key is a TrieNode
self.keys = {}
self.end = False
class Trie:
def __init__(self):
self.root = TrieNode()
# node=this.root gives error "this" is not defined
def insert(self, word: str, node=None) -> None:
if node == None:
node = self.root
# insertion is a recursive operation
if len(word) == 0:
node.end = True
return
elif word[0] not in node.keys:
node.keys[word[0]] = TrieNode()
self.insert(word[1:], node.keys[word[0]])
# that means key exists
else:
self.insert(word[1:], node.keys[word[0]])
def search(self, word: str, node=None) -> bool:
if node == None:
node = self.root
# node.end=True means we have inserted the word before
if len(word) == 0 and node.end == True:
return True
# if we inserted apple and then search for app we get false becase we never inserted app so a-p-p last_p.end is not True
# But startsWith(app) would return True
elif len(word) == 0:
return False
elif word[0] not in node.keys:
return False
else:
# we have to return becasue api expects us to return bool
return self.search(word[1:], node.keys[word[0]])
def startsWith(self, prefix: str, node=None) -> bool:
if node == None:
node = self.root
if len(prefix) == 0:
return True
elif prefix[0] not in node.keys:
return False
else:
return self.startsWith(prefix[1:], node.keys[prefix[0]])

How can i implement Vector addition for the form [1,2,3,4] + v where v is vector and [1,2,3,4] is a list in python?

Here is the code for the program:
I tried to implement a vector class as i learned about operator overloading in python. I was able to make a vector class which can be used much like a list with operations like len(vector) , vector1 + vector2 (addition operator overloading) and subtraction . But i found a problem. Here is the code of the program and i have stated the problem below :
class vector:
"""Initialize Vector"""
def __init__(self,d):
self.coords = [0]*d
def __len__(self):
return len(self.coords)
def __getitem__(self, item): #Getting an item from a vector
return self.coords[item]
def __setitem__(self, key, value):
self.coords[key] = value
def __add__(self, other):
if(len(self)!= len(other)):
print("Don't add these too ! they are not same types :P")
else:
result = vector(len(self))
for i in range(0,len(result)):
result[i] = self[i] + other[i]
return result
def __sub__(self, other):
if(len(self) != len(other)):
print("Dont subtract these two!")
else:
result = vector(len(self))
for i in range(0,len(result)):
result[i] = self[i] - other[i]
return result
def __eq__(self, other):
return self.coords == other.coords
def __ne__(self, other):
return self.coords != other.coords
def __str__(self):
return '<'+ str(self.coords)[1:-1] +'>'
print("Input for vector 1")
x = vector(2)
for i in range(0,len(x)):
x[i] = int(input('Enter a number\n'))
print("Input for vector 2")
y = vector(2)
for i in range(0,len(y)):
y[i] = int(input('Enter a number\n'))
z = x-y
print(str(x))
print(" + ")
print(str(y))
print(" = ")
print(str(z))
It works if i add a vector + list but list + vector gives an error. How can i implement the other .
You want to implement __radd__. Since it should do the same thing as __add__ here, you can just assign __add__ to it:
class vector:
...
def __add__(self, other):
if(len(self)!= len(other)):
print("Don't add these too ! they are not same types :P")
else:
result = vector(len(self))
for i in range(0,len(result)):
result[i] = self[i] + other[i]
return result
__radd__ = __add__
...

generic Number class refactoring?

I just made a generic number class.
this class is so simple, descriptions are below
from any ordered character list, make number class representing that ordered character list.
create_number_class("01") returns binary number class
create_number_class("0123456789") returns decimal number class
create_number_class("abcdefghij") return decimal number class but representing each digit as a alphabet.
belows is generic number class definition.
I think it is well-made class definition.
are there something needed improvement in that class definition?
thank you all. always.
ex)
ABC_Class = create_number_class("abc")
x = ABC_Class("baa")
y = ABC_Class("bbb")
print(x+y)
#output digits: abc, v: cbb, decimal_v: 22
below is class definition
def create_number_class(alphabet):
class temp(object):
digits = alphabet
def __init__(self, v):
self.v = v
self.decimal_v = self.to_decimal(self)
#staticmethod
def to_decimal(self):
r = 0
for i in range(0, len(self.v)):
r += len(temp.digits)**(len(self.v)-i-1)*(temp.digits.index(self.v[i]))
return r
#classmethod
def from_decimal(cls, decimal_v):
r = []
mod = len(temp.digits)
if decimal_v < mod:
return cls(temp.digits[decimal_v])
while True:
remainder = decimal_v % mod
r.append(remainder)
decimal_v = int((decimal_v - remainder)/ mod)
if decimal_v < mod:
r.append(decimal_v)
break
r = "".join(list(reversed([temp.digits[x] for x in r])))
#r = "".join(list(reversed([str(temp.digits.index(str(x))) for x in r])))
return cls(r)
def __add__(self, other):
return temp.from_decimal(self.decimal_v+other.decimal_v)
def __sub__(self, other):
return temp.from_decimal(self.decimal_v-other.decimal_v)
def __mul__(self, other):
return temp.from_decimal(self.decimal_v*other.decimal_v)
def __floordiv__(self, other):
return temp.from_decimal(self.decimal_v//other.decimal_v)
def __str__(self):
return "digits: {}, v: {}, decimal_v: {}".format(temp.digits, self.v, self.decimal_v)
def convert_to(self, new_class):
return new_class.from_decimal(self.decimal_v)
return temp
below are example
BinClass = create_number_class("01")
DecimalClass = create_number_class("0123456789")
x = BinClass("111")
x = BinClass("1000")
y = BinClass("10")
HexClass = create_number_class('0123456789ABCDEF')
x = HexClass('1')
y = HexClass('AA')
print(x+y)
print(x-y)
print(x*y)
print(x//y)
print(x.convert_to(DecimalClass))
isinstance(x, BinClass)

Reverse Class Method Not Working

So I created a simple class method to reverse a string and yet it returns to me the original? The Method that I created works outside of the class but for some reason it does not when I try to implement it.
See my code below:
class Stack:
def __init__(self):
self.__items = []
def push(self, item):
self.__items.append(item)
def pop(self):
return self.__items.pop()
def peek(self):
return self.__items[len(self.__items)-1]
def is_empty(self):
return len(self.__items) == 0
def size(self):
return len(self.__items)
def reverse(self):
if len(self.__items) <= 1:
return self.__items
return self.__items.reverse(self.__items[1:]) + self.__items[0]
s=Stack()
rev=input("Enter string to reverse; ")
s.push(rev)
print(s.reverse())
You need to reverse each string in self.__items not self.__items itself:
def reverse(self):
if not self.__items: # if items is empty return empty string
return ""
return " ".join(s[::-1] for s in self.__items)
self.__items[::-1] will reverse the list items not the string/strings inside.
If you wanted to do it without slicing:
def reverse(self):
if not self.__items:
return ""
out = ""
for item in self.__items:
temp = ""
for i in range(len(item)-1, -1, -1):
temp += item[i]
out += temp
return out
Or recursively:
def reverse(self):
if not self.__items:
return ""
def recur(s):
if not s:
return ""
return s[-1] + recur(s[:-1])
return " ".join(recur(w) for w in self.__items)

Categories

Resources