main.py

import random
import time
import re

# Top 300 most used English words
top_300_words = [
    "the", "be", "to", "of", "and", "a", "in", "that", "have", "I",
    "it", "for", "not", "on", "with", "he", "as", "you", "do", "at",
    "this", "but", "his", "by", "from", "they", "we", "say", "her", "she",
    "or", "an", "will", "my", "one", "all", "would", "there", "their", "what",
    "so", "up", "out", "if", "about", "who", "get", "which", "go", "me",
    "when", "make", "can", "like", "time", "no", "just", "him", "know", "take",
    "person", "into", "year", "your", "good", "some", "could", "them", "see", "other",
    "than", "then", "now", "look", "only", "come", "its", "over", "think", "also",
    "back", "after", "use", "two", "how", "our", "work", "first", "well", "way",
    "even", "new", "want", "because", "any", "these", "give", "day", "most", "us",
    "should", "home", "old", "same", "tell", "too", "show", "try", "hand", "end",
    "put", "read", "low", "must", "high", "off", "leave", "here", "eye", "words",
    "ask", "need", "side", "once", "set", "boy", "came", "along", "next", "kind",
    "went", "open", "run", "don't", "began", "grow", "turn", "seem", "help", "hard",
    "start", "might", "late", "miss", "idea", "food", "stop", "room", "air", "mother",
    "river", "car", "feet", "care", "second", "group", "book", "carry", "took", "science",
    "eat", "room", "friend", "began", "idea", "fish", "mountain", "north", "once", "base",
    "hear", "cut", "sure", "watch", "color", "face", "wood", "main", "enough", "plain",
    "girl", "usual", "young", "ready", "above", "ever", "red", "list", "though", "feel",
    "talk", "bird", "soon", "body", "dog", "family", "direct", "pose", "leave", "song",
    "measure", "door", "product", "black", "short", "numeral", "class", "wind", "question",
    "happen", "complete", "ship", "area", "half", "rock", "order", "fire", "south", "problem",
    "piece", "tell", "knew", "pass", "since", "top", "whole", "king", "size", "stop",
    "river", "space", "remember", "clear", "fact", "power", "tail", "nothing", "local", "course",
    "both", "full", "vowel", "gold", "brother", "wife", "garden", "common", "certain", "kill",
    "final", "ten", "young", "hope", "meet", "rest", "hear", "clear", "show", "list",
    "song", "teach", "page", "door", "low", "fall", "mile", "dead", "sun", "fast",
    "verb", "five", "bring", "sing", "sit", "class", "floor", "either", "correct", "sleep",
    "race", "inch", "thousand", "meet", "behind", "sight", "white", "winter", "game", "strong",
    "close", "talk", "front", "shape", "yes", "late", "help", "mark", "rain", "sentence",
    "hot", "object", "farm", "ten", "king", "draw", "left", "sleep", "hundred", "deal",
    "hour", "rock", "rule", "figure", "certain", "age", "land", "friend", "fit", "join",
    "cry", "prize", "feel", "unit", "begin", "inch", "lot", "today", "usual", "silent",
    "particular", "seat", "star", "watch", "boat", "chart", "summer", "market", "swim", "sister",
    "climb", "sleep", "shop", "race", "the", "ship", "nation", "cool", "oil", "thousand",
    "notice", "cause", "floor", "busy", "leg", "exercise", "sent", "indicate", "radio", "atom",
    "human", "history", "effect", "electric", "expect", "crop", "modern", "element", "hit", "student",
    "corner", "party"
]


# Randomly select a subset of 15 words from the top 300 words in english language
subset = random.sample(top_300_words, 15)

# Remove symbols from target words (not really needed here, just done to make the database clear, and homogeneous)
subset = [re.sub(r'[^\w\s]', '', word) for word in subset]

# Calculate the character error rate within each word (using the levenshtein edit distance dp algo https://www.youtube.com/watch?v=Dd_NgYVOdLk)
def character_error_rate(word1, word2):
    len1 = len(word1)
    len2 = len(word2)
    matrix = [[0] * (len2 + 1) for _ in range(len1 + 1)]

    for i in range(len1 + 1):
        matrix[i][0] = i
    for j in range(len2 + 1):
        matrix[0][j] = j

    for i in range(1, len1 + 1):
        for j in range(1, len2 + 1):
            if word1[i - 1] == word2[j - 1]:
                matrix[i][j] = matrix[i - 1][j - 1]
            else:
                insert = matrix[i][j - 1] + 1
                delete = matrix[i - 1][j] + 1
                substitute = matrix[i - 1][j - 1] + 1
                matrix[i][j] = min(insert, delete, substitute)

    return matrix[len1][len2] / len(word1)

# Calculate the word error rate based on character errors within words
def word_error_rate(subset, typed_para):
    typed_words = typed_para.split()
    subset_words = subset

    error_count = 0
    total_words = max(len(typed_words), len(subset_words))

    if len(typed_words) != len(subset):
        print("you haven't typed the correct number of words!")
        exit()
    
    for typed_word, subset_word in zip(typed_words, subset_words):
        error_rate = character_error_rate(subset_word, typed_word)
        error_count += error_rate

    word_error_rate = (error_count / total_words) * 100
    return word_error_rate

# Print the target words to the user
print("Type the following words:")
print(" ".join(subset))

# Start the timer when the user starts typing
start_time = None
typed_para = ""

# Wait for the user to start typing (the user clicks enter (return) to signal it will start typing)
input("Press Enter when you are ready to start typing.")

start_time = time.time()

# Read user input
typed_para = input()

end_time = time.time()

time_taken = end_time - start_time

# Clear any extra symbols the user might have typed (also remove extra spaces between words, which might mess up our calculations)
# Also by adding lower(), after the re.sub() function, it converts all characters in typed_para to lowercase while removing symbols.
typed_para = re.sub(r'[^\w\s]', '', typed_para).lower()

# Calculate the error percentage, and 100 - error percent would be the typing accuracy
error_percent = word_error_rate(subset, typed_para)

# If the user types nonsense, punish.
if error_percent > 50:
    print(f"Your word error rate {error_percent:.2f}% was quite high, and hence your accurate speed could not be computed.")

# Else, give them their results.
else:
    typed_words = typed_para.split()
    num_typed_words = len(typed_words)
    speed = num_typed_words * 60 / time_taken
    print("******YOUR SCORE REPORT******")
    print(f"Your speed is {speed:.2f} words/min")
    print(f"The word error rate (based on characters within words) is {error_percent:.2f}%")
    print(f"The accuracy is {100-error_percent:.2f}%")