A script I wrote to try and find the best starting word in wordle

get_wordle_probs.py

"""Find the most common letters in five letter English words at each position.

This is to help you play wordle (https://www.powerlanguage.co.uk/wordle/)

"""


import requests

URL = "https://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt"
ALPHABET = "abcdefghijklmnopqrstuvwxyz"
N_SLOTS = 5


def order_letters_and_get_probs(nword_by_letter, number_of_words):
    letters = sorted(nword_by_letter, key=nword_by_letter.get)[::-1]
    probs = [nword_by_letter[letter] / number_of_words for letter in letters]
    return letters, probs


def format_probs(letters_and_probs):
    letters, probs = letters_and_probs
    return " ".join(
        [f"{letter}: {round(prob, 2)}" for letter, prob in zip(letters, probs)]
    )


def main():
    print(f"Fetching a list of words from {URL}...")
    words = [
        word
        for word in requests.get(URL).text.split("\r\n")
        if len(word) == N_SLOTS
    ]
    slots = list(range(N_SLOTS))
    words_by_slot = {
        slot: {
            letter: [word for word in words if word[slot] == letter]
            for letter in ALPHABET
        }
        for slot in slots
    }
    nword_per_letter_by_slot = {
        k: {kk: len(vv) for kk, vv in v.items()}
        for k, v in words_by_slot.items()
    }
    letters_and_probs_by_slot = {
        slot: order_letters_and_get_probs(
            nword_per_letter_by_slot[slot], len(words)
        )
        for slot in slots
    }
    print("\n*******Most common letters at each position**********")
    for slot in slots:
        print(f"{slot + 1}: {''.join(letters_and_probs_by_slot[slot][0])}")
    print("\n*******Probability of each letter at each slot**********")
    for slot in slots:
        print(f"{slot + 1}: {format_probs(letters_and_probs_by_slot[slot])}")


if __name__ == "__main__":
    main()

Output when I ran this script just now:

Fetching a list of words from https://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt...
*******Most common letters at each position**********

1: scabtpmdgfrlhkwenouivjyzqx
2: aoeiurlhntpycmwsdbgkvxfzqj
3: rainoleutsmcdgbpkvwyhfzxjq
4: eaitnlorsudckgmpbhfvywzjxq
5: seyatnrdloihkmcpguxfbwzvqj


*******Probability of each letter at each slot**********

1: s: 0.11 c: 0.08 a: 0.07 b: 0.07 t: 0.06 p: 0.06 m: 0.05 d: 0.05 g: 0.05 f: 0.04 r: 0.04 l: 0.04 h: 0.04 k: 0.03 w: 0.03 e: 0.03 n: 0.03 o: 0.02 u: 0.02 i: 0.02 v: 0.02 j: 0.02 y: 0.01 z: 0.01 q: 0.01 x: 0.0
2: a: 0.18 o: 0.14 e: 0.12 i: 0.1 u: 0.09 r: 0.07 l: 0.05 h: 0.05 n: 0.03 t: 0.02 p: 0.02 y: 0.02 c: 0.02 m: 0.01 w: 0.01 s: 0.01 d: 0.01 b: 0.01 g: 0.01 k: 0.01 v: 0.01 x: 0.0 f: 0.0 z: 0.0 q: 0.0 j: 0.0
3: r: 0.1 a: 0.09 i: 0.08 n: 0.08 o: 0.07 l: 0.07 e: 0.06 u: 0.05 t: 0.05 s: 0.04 m: 0.04 c: 0.03 d: 0.03 g: 0.03 b: 0.03 p: 0.03 k: 0.02 v: 0.02 w: 0.02 y: 0.01 h: 0.01 f: 0.01 z: 0.01 x: 0.01 j: 0.0 q: 0.0
4: e: 0.16 a: 0.1 i: 0.08 t: 0.06 n: 0.06 l: 0.06 o: 0.06 r: 0.05 s: 0.05 u: 0.04 d: 0.03 c: 0.03 k: 0.03 g: 0.03 m: 0.03 p: 0.03 b: 0.02 h: 0.02 f: 0.01 v: 0.01 y: 0.01 w: 0.01 z: 0.01 j: 0.0 x: 0.0 q: 0.0
5: s: 0.2 e: 0.12 y: 0.11 a: 0.08 t: 0.07 n: 0.06 r: 0.06 d: 0.05 l: 0.05 o: 0.03 i: 0.03 h: 0.03 k: 0.02 m: 0.02 c: 0.01 p: 0.01 g: 0.01 u: 0.01 x: 0.01 f: 0.01 b: 0.01 w: 0.01 z: 0.0 v: 0.0 q: 0.0 j: 0.0```