def extract_features(deep_feautures='resnet_152_lstm_128.dct'):
LOW_LEVEL_FEATURES = load_features('low_level_dict.bin')
arr = np.array([x[1] for x in LOW_LEVEL_FEATURES.iteritems()])
scaler = preprocessing.StandardScaler().fit(arr)
std = scaler.transform(arr)
LOW_LEVEL_FEATURES = {
k: v
for k, v in it.izip(LOW_LEVEL_FEATURES.keys(), std)
}
DEEP_FEATURES = load_features(deep_feautures)
# DEEP_FEATURES = load_features('bof_128.bin')
arr = np.array([x[1] for x in DEEP_FEATURES.iteritems()])
scaler = preprocessing.StandardScaler().fit(arr)
std = scaler.transform(arr)
DEEP_FEATURES = {k: v for k, v in it.izip(DEEP_FEATURES.keys(), std)}
HYBRID_FEATURES = {}
for k in DEEP_FEATURES.iterkeys():
try:
HYBRID_FEATURES[k] = np.append(DEEP_FEATURES[k],
LOW_LEVEL_FEATURES[k])
except KeyError:
continue
# arr = np.array([x[1] for x in HYBRID_FEATURES.iteritems()])
# scaler = preprocessing.StandardScaler().fit(arr)
# std = scaler.transform(arr)
# HYBRID_FEATURES = {k: v for k, v in it.izip(HYBRID_FEATURES.keys(), std)}
return LOW_LEVEL_FEATURES, DEEP_FEATURES, HYBRID_FEATURES
def get_similarity_matrices():
similarities_low_level = load_features(
'movie_cosine_similarities_low_level.bin')
similarities_deep = load_features('movie_cosine_similarities_deep.bin')
similarities_hybrid = load_features('movie_cosine_similarities_hybrid.bin')
return [similarities_low_level, similarities_deep, similarities_hybrid]
def extract_features(deep_feautures='resnet_152_lstm_128.dct'):
_deep_features = load_features(deep_feautures)
arr = np.array([x[1] for x in _deep_features.iteritems()])
scaler = preprocessing.StandardScaler().fit(arr)
std = scaler.transform(arr)
_deep_features = {k: v for k, v in it.izip(_deep_features.keys(), std)}
return _deep_features
from scipy.spatial.distance import cosine
from opening_feat import load_features
import sqlite3
import scipy
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity, euclidean_distances
from scipy.stats import pearsonr
from scipy.spatial.distance import minkowski
from sklearn import preprocessing
import itertools as it
import opening_feat as of
user_features = of.load_features('users_tfidf_profile.bin')
movie_features = of.load_features('movies_tfidf_profile.bin')
conn = sqlite3.connect('database.db')
# trailerid = 2216 # Jurassic World
movielensid = 4993 # the lord of the rings
# movielensid = 2571 # Matrix
# trailerid = 5632 # ToyStory
# trailerid = 2
# trailerid = 3341
# movie = low_level_features[trailerid]
# movie = features[trailerid]
# movie = features[3412] # Se7en
# movie = features[5612] #Django Unchained
# movie = low_level_features[4484] # Matrix
movie = movie_features[movielensid]
for c in columns:
columnList.append(c)
return columnList
conn = sqlite3.connect('database.db')
SEPARATOR = ","
PREDICTION_LIST_SIZE = 20
LIMIT_ITEMS_TO_PREDICT = 10
NUM_USERS = 1
MIN_FEATURE_VALUE = -1
MAX_FEATURE_VALUE = 1
FEATURES = load_features('res_neurons_places_gru_32_feat_1024_scenes_350.bin') #dictionary
COLUMNS = [
"CAST(imdbrating AS REAL)",
"CAST(tomatorating AS REAL)",
#"movielensrating",
# "CAST(imdbvotes AS NUMERIC)",
# "CAST(year AS NUMERIC)",
"CAST(metascore AS REAL)",
"CAST(tomatouserrating AS REAL)"
]
COLUMNS_NOMINAL = [
"genre",
"actors",
"director",
from opening_feat import load_features
import numpy as np
from sklearn import preprocessing
low_level_features = load_features('low_level_dict.bin') # normalize
arr = np.array([x[1] for x in low_level_features.iteritems()])
normalized_ll_features = preprocessing.normalize(arr)[0]
mid = time()
print mid - start, "seconds"
count = 0
for movie in all_movies:
subsims = {}
for movie_j in all_movies:
count += 1
try:
cos = float(recommender.cosine(movie, movie_j,
HYBRID_FEATURES_BOF))
subsims[movie_j[0]] = cos
except KeyError:
print movie, movie_j, "error"
continue
similarities[movie[0]] = subsims
print similarities[2]
mid = time()
print mid - start, "seconds"
with open('movie_cosine_similarities_hybrid.bin', 'wb') as fp:
pickle.dump(similarities, fp, protocol=2)
similarities = of.load_features('movie_cosine_similarities_hybrid.bin')
print similarities[2]
def get_similarity_matrices():
similarities_deep = load_features('movie_cosine_similarities_deep.bin')
return similarities_deep
def extract_tfidf_features():
user_features = load_features('users_tfidf_profile.bin')
movie_features = load_features('movies_tfidf_profile.bin')
return user_features, movie_features
# import constants
from utils import isValid
# import scipy
# from scipy.spatial.distance import cosine
from math import sqrt
from sklearn.metrics.pairwise import cosine_similarity
from scipy.stats import pearsonr
import numpy as np
from opening_feat import load_features
DEEP_FEATURES = load_features('resnet_152_lstm_128.dct') #dictionary
def computePearson(i, j):
a = np.array(i)
b = np.array(j)
if (a.size == 0 and b.size == 0):
return 0
else:
pearson = pearsonr(a, b)
# print pearson
return pearson[0]
def computeCosine(i, j):
a = np.array(i)
b = np.array(j)
if (a.size == 0 and b.size == 0):
return 0
else:
a = a.reshape(1, -1)
import scipy
import numpy as np
from sklearn.metrics.pairwise import cosine_similarity, euclidean_distances
from scipy.stats import pearsonr
from scipy.spatial.distance import minkowski
from sklearn import preprocessing
import itertools as it
conn = sqlite3.connect('database.db')
# features = load_features('res_neurons_32_feat_1024_scenes_350.bin') #dictionary
# features = load_features('res_neurons_places_gru_32_feat_1024_scenes_350.bin')
# features = load_features('resnet_152_lstm_128.dct')
# features = load_features('bof_128.bin')
# low_level_features = load_features('low_level_dict.bin') # normalize
DEEP_FEATURES = load_features('bof_128.bin')
arr = np.array([x[1] for x in DEEP_FEATURES.iteritems()])
scaler = preprocessing.StandardScaler().fit(arr)
std = scaler.transform(arr)
DEEP_FEATURES = {k: v for k, v in it.izip(DEEP_FEATURES.keys(), std)}
LOW_LEVEL_FEATURES = load_features('low_level_dict.bin')
arr = np.array([x[1] for x in LOW_LEVEL_FEATURES.iteritems()])
scaler = preprocessing.StandardScaler().fit(arr)
std = scaler.transform(arr)
LOW_LEVEL_FEATURES = {k: v for k, v in it.izip(LOW_LEVEL_FEATURES.keys(), std)}
HYBRID_FEATURES = {}
for k in DEEP_FEATURES.iterkeys():
try: