import logging
import numpy as np
import scipy.sparse as sp
import sys
from pprint import pformat
from lightfm import LightFM
import experiments
from experiments.cf_model import CFModel
from experiments.lsiup_model import LsiUpModel
from experiments.modelutils import fit_model
from experiments.stackexchange.data import read_post_features, read_interactions, read_user_features
logger = experiments.getLogger("experiments.stackexchange.model")
def read_data(tags, post_ids, post_text, about, sampled_negatives_ratio):
logger.debug("Reading features")
features = read_post_features(tags, post_ids, post_text)
item_features_matrix = features.mat.tocoo().tocsr()
logger.debug("Reading interactions")
interactions = read_interactions(features.item_ids)
interactions.fit(min_positives=1, sampled_negatives_ratio=sampled_negatives_ratio)
user_features = read_user_features(about=about, user_ids=True, user_id_mapping=interactions.user_ids)
logger.debug(
import codecs
from HTMLParser import HTMLParser
from lxml import etree
import os
import re
import experiments
from experiments.data import Features, Interactions
# Data description here: http://meta.stackexchange.com/questions/2677/database-schema-documentation-for-the-public-data-dump-and-sede
logger = experiments.getLogger('experiments.stackexchange.model')
DATA_DIR = os.path.dirname(__file__)
QUESTION_POST_TYPE_ID = 1
QUESTION_POST_TYPE_ANSWER = 2
class MLStripper(HTMLParser):
def __init__(self):
self.reset()
self.fed = []
def handle_data(self, d):
self.fed.append(d)
def get_data(self):
return ''.join(self.fed)
def strip_tags(html):
import logging
import numpy as np
from pprint import pformat
import scipy.sparse as sp
import sys
from lightfm import LightFM
import experiments
from experiments.cf_model import CFModel
from experiments.lsiup_model import LsiUpModel
from experiments.modelutils import fit_model
from experiments.movielens.data import read_movie_features, read_interaction_data
logger = experiments.getLogger('experiments.movielens.model')
def read_data(titles, genres,
genome_tag_threshold,
positive_threshold):
logger.debug('Reading features')
features = read_movie_features(titles=titles, genres=genres, genome_tag_threshold=genome_tag_threshold)
item_features_matrix = features.mat.tocoo().tocsr()
logger.debug('Reading interactions')
interactions = read_interaction_data(features.item_ids,
positive_threshold=positive_threshold)
interactions.fit(min_positives=1, sampled_negatives_ratio=0, use_observed_negatives=True)
