avg_item_embedding.py

from github import Github
import itertools
import numpy as np

user_id='BalazsHoranyi'  # hardcoded for demo purposes

def get_github_events(user_name):
    github_token = "superdupersecret"
    urls = [f'https://api.github.com/users/{user_name}/events?page={i}&access_token={github_token}' for i in range(11)]
    headers = {}
    headers['Authorization'] = f'token {github_token}'
    with FuturesSession(max_workers=4) as session:
        futures = [session.get(u, headers=headers) for u in urls]
    rs = [f.result() for f in futures]
    if rs[0].status_code == 404:
        return None
    rs = [r.json() for r in rs]
    rs = [item for sublist in rs for item in sublist]
    repo_names = [repo['repo']['name'] for repo in rs]
    return repo_names

repos = get_github_events(user_id)
total_item_embeddings = np.zeros(32)
count = 0
for repo_name in repos:
    item_id = name_id_norm.get(repo_name, -1) + 1
    item_embedding = item_embedding_map.get(item_id, np.zeros(32))
    if item_id > 0:
        count += 1
        seq_to_predict.append(item_id)
        repo_names.append(repo_name)
        total_item_embeddings += item_embedding

avg_item_embeddings = total_item_embeddings / count

seq_to_predict = seq_to_predict[::-1]
repo_names = repo_names[::-1]
print(f'user interacted with {repo_names}')
        
        
seq_to_predict = seq_to_predict[::-1]  # oldest first
repo_names = repo_names[::-1] . # what the user has already interacted with

# Generate Candidates
candidate_ind = np.array(t.get_nns_by_vector(avg_item_embeddings, 1000))