自有预测问题: 内存使用极高,有什么解决办法吗?

from collections import defaultdict from surprise import Dataset, Reader from surprise.similarities import cosine, msd, pearson, pearson_baseline from surprise.prediction_algorithms.knns import KNNBasic, KNNWithMeans, KNNWithZScore, KNNBaseline from surprise.model_selection import train_test_split, GridSearchCV, cross_validate from surprise import accuracy, SVD from surprise.model_selection import KFold from sklearn.metrics.pairwise import cosine_similarity import pandas as pd import numpy as np import csv from surprise import accuracy from datetime import datetime start_time = datetime.now()

def get_top_n(predictions, n=10): """Return the top-N recommendation for each user from a set of predictions. Args: predictions(list of Prediction objects): The list of predictions, as returned by the test method of an algorithm. n(int): The number of recommendation to output for each user. Default is 10. Returns: A dict where keys are user (raw) ids and values are lists of tuples: [(raw item id, rating estimation), ...] of size n. """

# First map the predictions to each user.
top_n = defaultdict(list)
for uid, iid, true_r, est, _ in predictions:
    top_n[uid].append((iid, est))

# Then sort the predictions for each user and retrieve the k highest ones.
for uid, user_ratings in top_n.items():
    user_ratings.sort(key=lambda x: x[1], reverse=False)
    top_n[uid] = user_ratings[:n]

return top_n

First train an SVD algorithm

postulaciones = 'c1_postulaciones.csv' reader = Reader(rating_scale = (1,12)) data = Dataset.load_from_df(data[["mrun", "rbd", "preferencia_postulante"]], reader) trainset = data.build_full_trainset() algo = SVD() algo.fit(trainset)

Than predict ratings for all pairs (u, i) that are NOT in the training set.

testset = trainset.build_anti_testset() predictions = algo.test(testset)

top_n = get_top_n(predictions, n=1)

##Dataframe con recomendaciones## columnas = ["mrun", "rbd"] recomendaciones