import requests
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.cluster import KMeans
from collections import defaultdict

# Function to fetch all users from Codeforces API
def fetch_users():
    url = "https://codeforces.me/api/user.ratedList"
    response = requests.get(url)

    if response.status_code == 200:
        data = response.json()
        if data["status"] == "OK":
            return data["result"]
        else:
            print("Error in response: ", data["comment"])
    else:
        print("Error fetching data: ", response.status_code)
    return []

# Function to filter users by max rating
def filter_users_by_rating(users, min_rating):
    return [user for user in users if user.get('maxRating', 0) > min_rating]

# Function to cluster users by the similarity of their names
def cluster_users_by_name(usernames, num_clusters=10):
    # Vectorize the usernames using TF-IDF with character n-grams
    vectorizer = TfidfVectorizer(analyzer='char', ngram_range=(2, 3))
    X = vectorizer.fit_transform(usernames)

    # Perform k-means clustering
    kmeans = KMeans(n_clusters=num_clusters, random_state=42)
    clusters = kmeans.fit_predict(X)

    clustered_users = defaultdict(list)
    user_cluster_map = {}
    for username, cluster_id in zip(usernames, clusters):
        clustered_users[cluster_id].append(username)
        user_cluster_map[username] = cluster_id

    return clustered_users, user_cluster_map

# Main processing function
def process_users(min_rating, num_clusters):
    # Fetch users
    users = fetch_users()

    # Filter users by max rating
    filtered_users = filter_users_by_rating(users, min_rating)
    print(len(filtered_users))
    # Extract usernames
    usernames = [user["handle"] for user in filtered_users]

    # Cluster users by the similarity of their names
    clusters, user_cluster_map = cluster_users_by_name(usernames, num_clusters)

    return clusters, user_cluster_map

# Fetch and process users (run this once)
clusters, user_cluster_map = process_users(min_rating=1599, num_clusters=5000)

from google.colab import files

def save_clusters_to_file(clusters, filename="clusters.txt"):
    with open(filename, "w") as file:
        for cluster_id, user_list in clusters.items():
            cluster_size = len(user_list)
            file.write(f"{cluster_size} {' '.join(user_list)}\n")
    return filename

output_file = save_clusters_to_file(clusters)

# Provide a link to download the file in Google Colab
files.download(output_file)

def get_user_cluster(username):
    cluster_id = user_cluster_map.get(username, None)
    if cluster_id is not None:
        return clusters[cluster_id]
    else:
        return "User not found"

# Example usage
username = "nifeshe"
user_cluster = get_user_cluster(username)
if user_cluster != "User not found":
    print(len(user_cluster))
    print(f"The cluster for user '{username}' is: {user_cluster}")
else:
    print(user_cluster)