def active_learning(simClass, start, end, simItem_k, topUser_k, itemsFrame,
ratingsFrame, users_rating):
#### Split training set and test set ####
ratings_train = ratingsFrame.to_records(index=False).tolist()
ratings_test = []
for ratingNum in range(ratingsFrame.shape[0]):
if (ratings_train[ratingNum][1] == start):
test_start = ratingNum
while (ratingNum in range(len(ratings_train))
and ratings_train[ratingNum][1] <= end):
ratings_test.append(ratings_train[ratingNum])
ratingNum += 1
test_end = ratingNum
break
ratings_train = ratings_train[0:test_start] + ratings_train[test_end:]
print("pre-split DONE")
#### find k similar items for each new item ####
print("test interval: [" + str(start) + ":" + str(end) + "]")
sims = simClass.generate_topk_item_similarity(
range(start, end), simItem_k, itemsFrame.loc[:, "asin"].tolist())
print("Sims calculation DONE")
#### Calculate Propability for each new item ####
ratings_set = ratingsFrame.loc[:, ["userID", "itemID"]].to_records(
index=False).tolist()
ratings_origin = ratingsFrame.to_records(index=False).tolist()
item_groups = ratingsFrame.groupby("itemID")
for item in sims:
# first, find the set of users who have rated items within sim set.
users_rated_sims = []
for item_sim in sims[item]:
users_rated_sims += item_groups.get_group(
item_sim)["userID"].tolist()
users_rated_sims = list(set(users_rated_sims))
user_score = Score(users_rated_sims, users_rating, sims[item])
user_score = sorted(user_score.items(),
key=lambda d: d[1],
reverse=True)
for top in range(topUser_k):
t = (user_score[top][0], item)
if t in ratings_set:
index = ratings_set.index(t)
ratings_test.remove(ratings_origin[index])
ratings_train.append(ratings_origin[index])
print("active learning ALL DONE")
##### Caculate RMSE for each iteration2 #####
mf = MatrixFactorization()
return mf.matrix_factorization(ratings_train, ratings_test)
def run_matrix_factorization():
""" Executes the Matrix Factorization model on the ratings dataset. """
ratings = pd.read_csv('../data/ratings2.csv', sep='\t')
num_users = len(ratings.buyer_id.unique())
num_items = ratings.product_id.max() + 1
train, val = train_test_split(ratings)
model = MatrixFactorization(train,
num_users,
num_items,
num_latent_factors=20)
model.train(max_iter=20,
learning_rate=0.01,
regularize=0.5,
val=val,
lr_scheduler=True)
def test_matrix_factorization():
print('mf test.............')
since = time.time()
# 潜在因子数
K = 2
# m x n のレーティング行列
R = np.array([[5, 3, 0, 1], [4, 0, 0, 1], [1, 1, 0, 5], [1, 0, 0, 4],
[0, 1, 5, 4]])
m, n = R.shape
# m x K のユーザ行列P
P = np.random.rand(m, K)
# n x K のアイテム行列Q
Q = np.random.rand(n, K)
P_new, Q_new = mf.run(R,
P,
Q,
K,
steps=5000,
alpha=0.0002,
beta=0.2,
threshold=0.001)
evaluate(P, Q, R, P_new, Q_new)
assert False
def test_movielens(load_dataset):
print('mf test.............')
# Load dataset
df_rating = load_dataset
# print(df_rating.head())
m = max(np.unique(df_rating.userId))
n = max(np.unique(df_rating.movieId))
# m = len(np.unique(df_rating.userId))
# n = len(np.unique(df_rating.movieId))
print('m x n: {} x {}'.format(m, n))
R = np.zeros([m, n])
print(type(df_rating.userId[0]))
print(type(df_rating.movieId[0]))
print(R[df_rating.userId[0]][df_rating.movieId[0]])
print(np.unique(df_rating.rating))
print(sum(df_rating.rating.isnull()))
for i, s in df_rating.iterrows():
if s.rating == 0: continue
u_id = int(s.userId)
m_id = int(s.movieId)
R[u_id - 1][m_id - 1] = s.rating
print(R)
# 潜在因子数
K = 2
# m x n のレーティング行列
m, n = df_rating[['userId', 'movieId']].shape
print(m, n)
R = np.array([[5, 3, 0, 1], [4, 0, 0, 1], [1, 1, 0, 5], [1, 0, 0, 4],
[0, 1, 5, 4]])
m, n = R.shape
# m x K のユーザ行列P
P = np.random.rand(m, K)
# n x K のアイテム行列Q
Q = np.random.rand(n, K)
P_new, Q_new = mf.run(R,
P,
Q,
K,
steps=5000,
alpha=0.0002,
beta=0.2,
threshold=0.001)
evaluate(P, Q, R, P_new, Q_new)
assert False
def generate_prediction_model(lr_bound, tree, rI, sMatrix, plambda_candidates,
validation_set):
''' lr_bound: dict {
level 0: [[left_bound, right_bound]], users' bound for one level, each ele in dictionary represents one node
level 1: [[left_bound, right_bound], [left_bound, right_bound], [left_bound, right_bound]], 3
level 2: ..., 9
} (bound means index)
plambda_candidates: {
level 0: [clambda1, clambda2, clambda3, ...]
level 1: [clambda1, clambda2, clambda3, ...]
level 2: [clambda1, clambda2, clambda3, ...]
}
prediction_model: dict {
level 0: { 'best_lambda': x, 'user_profile': ..., 'item_profile': ...}
level 1: { 'best_lambda': x, 'user_profile': ..., 'item_profile': ...}
level 2: { 'best_lambda': x, 'user_profile': ..., 'item_profile': ...}
}
'''
MF = MatrixFactorization()
prediction_model = {}
val_item_list = find(validation_set)[0]
val_user_list = find(validation_set)[1]
user_node_ind = np.zeros(
sMatrix.shape[1]) #### notice that index is not id
for level in lr_bound:
prediction_model.setdefault(level, {})
train_lst = []
for pseudo_user_bound, userid in zip(lr_bound[level],
range(len(lr_bound[level]))):
if pseudo_user_bound[0] > pseudo_user_bound[1]:
continue
pseudo_user_lst = tree[pseudo_user_bound[0]:(pseudo_user_bound[1] +
1)]
pseudo_user_for_item = calculate_avg_rating_for_pesudo_user(
pseudo_user_lst, sMatrix)
train_lst += [(userid, int(itemid),
float(pseudo_user_for_item[itemid]))
for itemid in range(pseudo_user_for_item.shape[0])
if pseudo_user_for_item[itemid]]
#### find node index for each validation user ####
user_node_ind[pseudo_user_lst] = userid
#### Train MF and Do validation ####
min_RMSE = -1
for plambda in plambda_candidates[level]:
MF.change_parameter(plambda)
user_profile, item_profile = MF.matrix_factorization(train_lst)
RMSE = pred_RMSE_for_validate_user(user_node_ind, user_profile,
item_profile, val_user_list,
val_item_list, sMatrix)
if min_RMSE is -1 or RMSE < min_RMSE:
min_RMSE = RMSE
min_user_profile, min_item_profile, min_lambda = user_profile, item_profile, plambda
prediction_model[level]['upro'], prediction_model[level]['ipro'], prediction_model[level]['plambda'] \
= min_user_profile, min_item_profile, min_lambda
MF.end() #### close MF spark session
return prediction_model
def main():
"""
main function for test
"""
# For command line arguments
psr = argparse.ArgumentParser()
psr.add_argument("--data_dir", default="ml-100k/")
psr.add_argument("--base", default="u1.base")
psr.add_argument("--test", default="u1.test")
psr.add_argument("--a", default=0.01, type=float)
psr.add_argument("--b", default=0.2, type=float)
psr.add_argument("--K", default=50, type=int)
psr.add_argument("--tol", default=3.e-2, type=float)
args = psr.parse_args()
# Get rating matrix
R, R_test, user_size, item_size = get_rating(data_dir=args.data_dir,
base=args.base,
test=args.test,
debug=True)
# Training
mf = MatrixFactorization(R=R,
R_test=R_test,
user_size=user_size,
item_size=item_size,
K=args.K,
a=args.a,
b=args.b)
print("training...")
mf.train(tol=args.tol, debug=True)
print("The number of test data is {}.".format(R_test.shape[0]))
icor = 0
for r in R_test:
iu = int(r[0]) - 1
ii = int(r[1]) - 1
Rhatui = mf.rating(iu=iu, ii=ii)
if np.round(Rhatui) == r[2]: icor = icor + 1
print("The number of correct predictions is {}.".format(icor))
def __init__(self, data_path=None):
mf = MatrixFactorization(data_path)
#TODO: Correct?
self._context_data = {str(i): mf.Q[i] for i in range(len(mf.Q))}
#!/usr/bin/env python3
from matrix_factorization import MatrixFactorization
DATA = {
"DATA_DIR": "./ml-latest-small",
"RATING_FILE": "ratings.csv",
"MOVIE_FILE": "movies.csv",
"TAG_FILE": "tags.csv"
}
if __name__ == "__main__":
mf_cf = MatrixFactorization(DATA)
mf_cf.train()
mf_cf.predict_single(1, 110)
# load MovieLens data
num_user, num_item, ratings = load_ml_1m()
np.random.shuffle(ratings)
# set feature numbers
num_feature = 10
# set max_iterations
max_iter = 20
# split data to training & testing
train_pct = 0.9
train_size = int(train_pct * len(ratings))
train = ratings[:train_size]
validation = ratings[train_size:]
# models
rec = MatrixFactorization(num_user, num_item, num_feature, train, validation, max_rating=5, min_rating=1)
# fitting
rec.estimate(max_iter)
# results
train_preds = rec.predict(train)
train_rmse = RMSE(train_preds, np.float16(train[:, 2]))
validation_preds = rec.predict(validation)
validation_rmse = RMSE(validation_preds, np.float16(validation[:, 2]))
print "train RMSE: %.6f, validation RMSE: %.6f " % (train_rmse, validation_rmse)
data = proprocess()
num_data = data.shape[0]
num_training = math.ceil(num_data * 0.8)
idx = np.arange(num_data)
np.random.shuffle(idx)
training = data[idx[:num_training], :]
testing = data[idx[num_training:], :]
best_score = math.inf
for _ in range(NUM_TEST):
dmf = DeepMatrixFactorization(NUM_USER, NUM_MOVIE, EMBEDDING_DIM,
HIDDEN_DIM)
dmf.learn(training[:, 0], training[:, 1], training[:, 2], 2000, 500)
score = dmf.test(testing[:, 0], testing[:, 1], testing[:, 2])
if best_score > score:
best_score = score
print("Best score for deep matrix factorization is %f" % best_score)
best_score = math.inf
for _ in range(NUM_TEST):
mf = MatrixFactorization(NUM_USER, NUM_MOVIE, EMBEDDING_DIM)
mf.learn(training[:, 0], training[:, 1], training[:, 2], 2000, 500)
score = mf.test(testing[:, 0], testing[:, 1], testing[:, 2])
if best_score > score:
best_score = score
print("Best score for matrix factorization is %f" % best_score)
def __init__(self, sMatrix, depth_threshold=6, plambda=7, MSP_item=200):
'''
sMatrix: I*U matrix
depth_threshold: terminate depth
plambda: regularization parameter
self.rI: dict {
itemid1: [ [uid11, rating11], [uid12, rating12], ... ] rating for item 1
itemid2: [ [uid21, rating21], [uid22, rating22], ... ] rating for item 2
itemid3: ...
}
self.rU: dict {
userid1: { itemid11: rating11, itemid12: rating12, ... } rating of user 1
userid2: { itemid21: rating21, itemid22: rating22, ... } rating of user 2
userid3: ...
}
self.lr_bound: dict {
level 0: [[left_bound, right_bound]], users' bound for one level, each ele in dictionary represents one node
level 1: [[left_bound, right_bound], [left_bound, right_bound], [left_bound, right_bound]], 3
level 2: ..., 9
} (bound means index)
self.tree: [] all of userid
self.split_item: list [
level 0: []
level 1: []
level 2: []
]
self.sum_cur_t: dict {
itemid1: {'rating': sum of ratings for item 1, 'cnt': sum of users rated item 1}
itemid2: {'rating': sum of ratings for item 2, 'cnt': sum of users rated item 2}
...
}
self.sum_2_cur_t: dict {
itemid1: sum of square ratings for item 1
itemid2: sum of square ratings for item 2
...
}
self.biasU: dict {
userid1: bias1
userid2: bias2
...
}
self.user_profile: dict {
level 0: {pseudo_user1: [k1, k2, k3, ... , kt]}
level 1: {pseudo_user1: [k1, k2, k3, ... , kt], pseudo_user2: [k1, k2, k3, ... , kt], pseudo_user3: [k1, k2, k3, ... , kt]}
...
} profile for each level's node
self.item_profile: dict {
level 0: {itemid1: [k1, k2, k3, ... , kt], itemid2: [k1, k2, k3, ... , kt], itemid3: [k1, k2, k3, ... , kt], ...} for each item
level 1: {itemid1: [k1, k2, k3, ... , kt], itemid2: [k1, k2, k3, ... , kt], itemid3: [k1, k2, k3, ... , kt], ...} for each item
...
} profile for each item
every element represents ratings for one item, its order decide the users in tree nodes
'''
self.depth_threshold = depth_threshold
self.plambda = plambda
self.cur_depth = 0
self.MSP_item = MSP_item
self.real_item_num = sMatrix.shape[0]
x = find(sMatrix)
itemset = x[0]
userset = x[1]
# self.rI = {}
self.rU = {}
self.sum_cur_t = {}
self.sum_2_cur_t = {}
# self.rI[itemset[0]] = [[userset[0], sMatrix[itemset[0], userset[0]]]]
# self.rU[userset[0]] = {itemset[0]: sMatrix[itemset[0], userset[0]]}
self.global_mean = 0 # global average of ratings
#### Calculate rate of progress ####
self.node_num = 0
self.cur_node = 0
for i in range(self.depth_threshold):
self.node_num += 3**i
#### Generate rI, rU ####
self.rI = list(set(sMatrix.nonzero()[0]))
for itemid, userid in zip(itemset, userset):
self.rU.setdefault(userid, {})[itemid] = sMatrix[itemid, userid]
# self.rI.setdefault(itemid, []).append([userid, sMatrix[itemid, userid]])
self.global_mean += sMatrix[itemid, userid]
self.global_mean /= len(itemset)
self.item_size = len(self.rI)
self.user_size = len(self.rU)
#### Initiate Tree, lr_bound ####
self.tree = list(self.rU.keys())
self.split_item = []
self.lr_bound = {'0': [[0, len(self.tree) - 1]]}
#### Generate bias, sum_cur_t, sum_2_cur_t ####
self.biasU = {}
self.sum_cur_t = np.zeros(self.real_item_num)
self.sum_2_cur_t = np.zeros(self.real_item_num)
self.sum_cntt = np.zeros(self.real_item_num)
# self.sum_cur_t[itemset[0]] = {'rating': sMatrix[itemset[0], userset[0]]-self.biasU[userset[0]], 'cnt': 1}
# self.sum_2_cur_t[itemset[0]] = (sMatrix[itemset[0], userset[0]]-self.biasU[userset[0]])**2
for userid in self.rU:
self.biasU[userid] = (sum(list(self.rU[userid].values())) +
self.plambda * self.global_mean) / (
self.plambda + len(self.rU[userid]))
user_all_rating_id = np.array(list(self.rU[userid].keys()))
# print('user_all_rating_id ', user_all_rating_id[:])
user_all_rating = np.array(list(self.rU[userid].values()))
self.sum_cur_t[
user_all_rating_id[:]] += user_all_rating[:] - self.biasU[
userid]
self.sum_2_cur_t[user_all_rating_id[:]] += (user_all_rating[:] -
self.biasU[userid])**2
self.sum_cntt[user_all_rating_id[:]] += 1
# for itemid, userid, ind in zip(itemset[1:],userset[1:],range(1, len(itemset))):
# if itemid == itemset[ind-1]:
# self.sum_cur_t[itemid]['rating'] += sMatrix[itemid, userid]-self.biasU[userid]
# self.sum_cur_t[itemid]['cnt'] += 1
# self.sum_2_cur_t[itemid] += (sMatrix[itemid, userid]-self.biasU[userid])**2
# else:
# self.sum_cur_t[itemid] = {'rating': sMatrix[itemid, userid]-self.biasU[userid], 'cnt': 1}
# self.sum_2_cur_t[itemid] = (sMatrix[itemid, userid]-self.biasU[userid])**2
#### Prediction Model ####
self.user_profile = {}
self.item_profile = {}
self.MF = MatrixFactorization()
print("Initiation DONE!")
class DecisionTreeModel:
def __init__(self, sMatrix, depth_threshold=6, plambda=7, MSP_item=200):
'''
sMatrix: I*U matrix
depth_threshold: terminate depth
plambda: regularization parameter
self.rI: dict {
itemid1: [ [uid11, rating11], [uid12, rating12], ... ] rating for item 1
itemid2: [ [uid21, rating21], [uid22, rating22], ... ] rating for item 2
itemid3: ...
}
self.rU: dict {
userid1: { itemid11: rating11, itemid12: rating12, ... } rating of user 1
userid2: { itemid21: rating21, itemid22: rating22, ... } rating of user 2
userid3: ...
}
self.lr_bound: dict {
level 0: [[left_bound, right_bound]], users' bound for one level, each ele in dictionary represents one node
level 1: [[left_bound, right_bound], [left_bound, right_bound], [left_bound, right_bound]], 3
level 2: ..., 9
} (bound means index)
self.tree: [] all of userid
self.split_item: list [
level 0: []
level 1: []
level 2: []
]
self.sum_cur_t: dict {
itemid1: {'rating': sum of ratings for item 1, 'cnt': sum of users rated item 1}
itemid2: {'rating': sum of ratings for item 2, 'cnt': sum of users rated item 2}
...
}
self.sum_2_cur_t: dict {
itemid1: sum of square ratings for item 1
itemid2: sum of square ratings for item 2
...
}
self.biasU: dict {
userid1: bias1
userid2: bias2
...
}
self.user_profile: dict {
level 0: {pseudo_user1: [k1, k2, k3, ... , kt]}
level 1: {pseudo_user1: [k1, k2, k3, ... , kt], pseudo_user2: [k1, k2, k3, ... , kt], pseudo_user3: [k1, k2, k3, ... , kt]}
...
} profile for each level's node
self.item_profile: dict {
level 0: {itemid1: [k1, k2, k3, ... , kt], itemid2: [k1, k2, k3, ... , kt], itemid3: [k1, k2, k3, ... , kt], ...} for each item
level 1: {itemid1: [k1, k2, k3, ... , kt], itemid2: [k1, k2, k3, ... , kt], itemid3: [k1, k2, k3, ... , kt], ...} for each item
...
} profile for each item
every element represents ratings for one item, its order decide the users in tree nodes
'''
self.depth_threshold = depth_threshold
self.plambda = plambda
self.cur_depth = 0
self.MSP_item = MSP_item
self.real_item_num = sMatrix.shape[0]
x = find(sMatrix)
itemset = x[0]
userset = x[1]
# self.rI = {}
self.rU = {}
self.sum_cur_t = {}
self.sum_2_cur_t = {}
# self.rI[itemset[0]] = [[userset[0], sMatrix[itemset[0], userset[0]]]]
# self.rU[userset[0]] = {itemset[0]: sMatrix[itemset[0], userset[0]]}
self.global_mean = 0 # global average of ratings
#### Calculate rate of progress ####
self.node_num = 0
self.cur_node = 0
for i in range(self.depth_threshold):
self.node_num += 3**i
#### Generate rI, rU ####
self.rI = list(set(sMatrix.nonzero()[0]))
for itemid, userid in zip(itemset, userset):
self.rU.setdefault(userid, {})[itemid] = sMatrix[itemid, userid]
# self.rI.setdefault(itemid, []).append([userid, sMatrix[itemid, userid]])
self.global_mean += sMatrix[itemid, userid]
self.global_mean /= len(itemset)
self.item_size = len(self.rI)
self.user_size = len(self.rU)
#### Initiate Tree, lr_bound ####
self.tree = list(self.rU.keys())
self.split_item = []
self.lr_bound = {'0': [[0, len(self.tree) - 1]]}
#### Generate bias, sum_cur_t, sum_2_cur_t ####
self.biasU = {}
self.sum_cur_t = np.zeros(self.real_item_num)
self.sum_2_cur_t = np.zeros(self.real_item_num)
self.sum_cntt = np.zeros(self.real_item_num)
# self.sum_cur_t[itemset[0]] = {'rating': sMatrix[itemset[0], userset[0]]-self.biasU[userset[0]], 'cnt': 1}
# self.sum_2_cur_t[itemset[0]] = (sMatrix[itemset[0], userset[0]]-self.biasU[userset[0]])**2
for userid in self.rU:
self.biasU[userid] = (sum(list(self.rU[userid].values())) +
self.plambda * self.global_mean) / (
self.plambda + len(self.rU[userid]))
user_all_rating_id = np.array(list(self.rU[userid].keys()))
# print('user_all_rating_id ', user_all_rating_id[:])
user_all_rating = np.array(list(self.rU[userid].values()))
self.sum_cur_t[
user_all_rating_id[:]] += user_all_rating[:] - self.biasU[
userid]
self.sum_2_cur_t[user_all_rating_id[:]] += (user_all_rating[:] -
self.biasU[userid])**2
self.sum_cntt[user_all_rating_id[:]] += 1
# for itemid, userid, ind in zip(itemset[1:],userset[1:],range(1, len(itemset))):
# if itemid == itemset[ind-1]:
# self.sum_cur_t[itemid]['rating'] += sMatrix[itemid, userid]-self.biasU[userid]
# self.sum_cur_t[itemid]['cnt'] += 1
# self.sum_2_cur_t[itemid] += (sMatrix[itemid, userid]-self.biasU[userid])**2
# else:
# self.sum_cur_t[itemid] = {'rating': sMatrix[itemid, userid]-self.biasU[userid], 'cnt': 1}
# self.sum_2_cur_t[itemid] = (sMatrix[itemid, userid]-self.biasU[userid])**2
#### Prediction Model ####
self.user_profile = {}
self.item_profile = {}
self.MF = MatrixFactorization()
print("Initiation DONE!")
def calculate_error(self, sumt, sumt_2, cntt):
''' Calculate error for one item-split in one node '''
Error_i = np.sum(sumt_2 - (sumt**2) / (cntt + 1e-9))
# for itemid in sumtL:
# Error_i += sumtL_2[itemid] - (sumtL[itemid]['rating']**2)/(sumtL[itemid]['cnt']+1e-9) \
# + sumtD_2[itemid] - (sumtD[itemid]['rating']**2)/(sumtD[itemid]['cnt']+1e-9) \
# + sumtU_2[itemid] - (sumtU[itemid]['rating']**2)/(sumtU[itemid]['cnt']+1e-9)
return Error_i
def generate_decision_tree(self, lr_bound_for_node, chosen_id):
'''
sumtL: dict {
itemid1: {'rating': sum of ratings for item 1, 'cnt': sum of users rated item 1}
itemid2: {'rating': sum of ratings for item 2, 'cnt': sum of users rated item 2}
...
}
sumtL_2: dict {
itemid1: sum of square ratings for item 1
itemid2: sum of square ratings for item 2
...
}
lr_bound_for_node: list [leftind, rightind] for one node
'''
#### Terminate ####
self.cur_depth += 1
if self.cur_depth > self.depth_threshold or len(
chosen_id) == self.item_size:
return
#### Choose Most Popular Items of This Node ####
num_rec = np.zeros(self.real_item_num)
for userid in self.tree[lr_bound_for_node[0]:(lr_bound_for_node[1] +
1)]:
user_all_rating_id = np.array(list(self.rU[userid].keys()))
num_rec[user_all_rating_id[:]] += 1
sub_item_id = np.argsort(num_rec)[:self.MSP_item]
#### Find optimum item to split ####
min_sumtL, min_sumtD, min_sumtL_2, min_sumtD_2, min_sumtU, min_sumtU_2, Error = {}, {}, {}, {}, {}, {}, {}
min_Error = "None"
for itemid in sub_item_id:
if itemid in chosen_id:
continue
'''
user_rating_item_in_nodet: [ [uid01, rating01], [uid02, rating02], ... ]
to find all users in node t who rates item i
'''
user_rating_item_in_nodet = ([
userid, self.rU[userid][itemid]
] for userid in self.tree[lr_bound_for_node[0]:(
lr_bound_for_node[1] + 1)] if itemid in self.rU[userid])
sumt = np.zeros((self.real_item_num, 3))
sumt_2 = np.zeros((self.real_item_num, 3))
cntt = np.zeros((self.real_item_num, 3))
for user in user_rating_item_in_nodet:
''' user_all_rating: array [ [itemid11, rating11], [itemid12, rating12], ... ] '''
user_all_rating_id = np.array(list(self.rU[user[0]].keys()))
user_all_rating = np.array(list(self.rU[user[0]].values()))
#### calculate sumtL for node LIKE ####
if user[1] >= 4:
sumt[user_all_rating_id[:],
0] += user_all_rating[:] - self.biasU[user[0]]
sumt_2[user_all_rating_id[:],
0] += (user_all_rating[:] - self.biasU[user[0]])**2
cntt[user_all_rating_id[:], 0] += 1
#### calculate sumtD for node DISLIKE ####
elif user[1] <= 3:
sumt[user_all_rating_id[:],
1] += user_all_rating[:] - self.biasU[user[0]]
sumt_2[user_all_rating_id[:],
1] += (user_all_rating[:] - self.biasU[user[0]])**2
cntt[user_all_rating_id[:], 1] += 1
#### calculate sumtU for node UNKNOWN ####
sumt[:, 2] = self.sum_cur_t[:] - sumt[:, 0] - sumt[:, 1]
sumt_2[:, 2] = self.sum_2_cur_t[:] - sumt_2[:, 0] - sumt_2[:, 1]
cntt[:, 2] = self.sum_cntt[:] - cntt[:, 0] - cntt[:, 1]
Error[itemid] = self.calculate_error(sumt, sumt_2, cntt)
# sumtL, sumtD, sumtL_2, sumtD_2, sumtU, sumtU_2 = {}, {}, {}, {}, {}, {}
# sumtL = {k:{'rating': 0, 'cnt': 0} for k in self.rI.keys()}
# sumtL_2 = sumtL_2.fromkeys(self.rI.keys(), 0)
# sumtD = {k:{'rating': 0, 'cnt': 0} for k in self.rI.keys()}
# sumtD_2 = sumtD_2.fromkeys(self.rI.keys(), 0)
# for user in user_rating_item_in_nodet:
# ''' user_all_rating: [ [itemid11, rating11], [itemid12, rating12], ... ] '''
# user_all_rating = self.rU[user[0]]
# #### calculate sumtL for node LIKE ####
# if user[1] >= 4:
# for uritem, rating in user_all_rating.items():
# sumtL[uritem]['rating'] += rating
# sumtL_2[uritem] += (rating-self.biasU[user[0]])**2
# sumtL[uritem]['rating'] -= self.biasU[user[0]]
# sumtL[uritem]['cnt'] += 1
# #### calculate sumtD for node DISLIKE ####
# elif user[1] <= 3:
# for uritem, rating in user_all_rating.items():
# sumtD[uritem]['rating'] += rating
# sumtD_2[uritem] += (rating-self.biasU[user[0]])**2
# sumtD[uritem]['rating'] -= self.biasU[user[0]]
# sumtD[uritem]['cnt'] += 1
# #### calculate sumtU for node UNKNOWN ####
# for iid in self.rI:
# sumtU[iid] = {}
# sumtU[iid]['rating'] = self.sum_cur_t[iid]['rating'] - sumtL[iid]['rating'] - sumtD[iid]['rating']
# sumtU[iid]['cnt'] = self.sum_cur_t[iid]['cnt'] - sumtL[iid]['cnt'] - sumtD[iid]['cnt']
# sumtU_2[iid] = self.sum_2_cur_t[iid] - sumtL_2[iid] - sumtD_2[iid]
# #### calculate error by (eL + eD + eU) ####
# Error[itemid] = self.calculate_error(sumtL, sumtL_2, sumtD, sumtD_2, sumtU, sumtU_2)
if min_Error == "None" or Error[itemid] < min_Error:
min_sumt = sumt
min_sumt_2 = sumt_2
min_cntt = cntt
min_Error = Error[itemid]
#### Find optimum split-item ####
optimum_itemid = min(Error, key=Error.get)
if len(self.split_item) == self.cur_depth - 1:
self.split_item.append([optimum_itemid])
else:
self.split_item[self.cur_depth - 1].append(optimum_itemid)
# self.split_item.setdefault(str(self.cur_depth-1), []).append(optimum_itemid)
chosen_id.append(optimum_itemid)
#### sort tree ####
self.lr_bound.setdefault(str(self.cur_depth),
[]).append([]) # for LIKE
self.lr_bound[str(self.cur_depth)].append([]) # for DISLIKE
self.lr_bound[str(self.cur_depth)].append([]) # for UNKNOWN
listU, listL, listD = [], [], []
for userid in self.tree[lr_bound_for_node[0]:(lr_bound_for_node[1] +
1)]:
if optimum_itemid not in self.rU[userid]:
listU.append(userid)
elif self.rU[userid][optimum_itemid] >= 4:
listL.append(userid)
elif self.rU[userid][optimum_itemid] <= 3:
listD.append(userid)
self.tree[lr_bound_for_node[0]:(lr_bound_for_node[1] +
1)] = listL + listD + listU
self.lr_bound[str(self.cur_depth)][-3] = [
lr_bound_for_node[0], lr_bound_for_node[0] + len(listL) - 1
] # for LIKE
self.lr_bound[str(self.cur_depth)][-2] = [
lr_bound_for_node[0] + len(listL),
lr_bound_for_node[0] + len(listL) + len(listD) - 1
] # for DISLIKE
self.lr_bound[str(self.cur_depth)][-1] = [
lr_bound_for_node[0] + len(listL) + len(listD),
lr_bound_for_node[0] + len(listL) + len(listD) + len(listU) - 1
] # for UNKNOWN
#### Generate Subtree of Node LIKE ####
self.sum_cur_t = min_sumt[:, 0]
self.sum_2_cur_t = min_sumt_2[:, 0]
self.sum_cntt = min_cntt[:, 0]
self.generate_decision_tree(self.lr_bound[str(self.cur_depth)][-3],
chosen_id[:])
self.cur_depth -= 1
#### Generate Subtree of Node DISLIKE ####
self.sum_cur_t = min_sumt[:, 1]
self.sum_2_cur_t = min_sumt_2[:, 1]
self.sum_cntt = min_cntt[:, 1]
self.generate_decision_tree(self.lr_bound[str(self.cur_depth)][-2],
chosen_id[:])
self.cur_depth -= 1
#### Generate Subtree of Node UNKNOWN ####
self.sum_cur_t = min_sumt[:, 2]
self.sum_2_cur_t = min_sumt_2[:, 2]
self.sum_cntt = min_cntt[:, 2]
self.generate_decision_tree(self.lr_bound[str(self.cur_depth)][-1],
chosen_id[:])
self.cur_depth -= 1
#### Show Rating Progress ####
for i in range(self.cur_depth - 1):
print("┃", end="")
print("┏", end="")
self.cur_node += 1
print("Current depth: " + str(self.cur_depth) + " %.2f%%" %
(100 * self.cur_node / self.node_num))
def calculate_avg_rating_for_pesudo_user(self, pseudo_user_lst):
'''ret_dict: dict {
itemid0: rating0
itemid1: rating1
...
}'''
cal_dict = {key: {'rating': 0, 'cnt': 0} for key in self.rI}
ret_dict = {}
for userid in pseudo_user_lst:
for itemid, rating in self.rU[userid].items():
cal_dict[itemid]['rating'] += rating
cal_dict[itemid]['cnt'] += 1
for itemid in cal_dict:
if cal_dict[itemid]['cnt'] == 0:
continue
ret_dict[
itemid] = cal_dict[itemid]['rating'] / cal_dict[itemid]['cnt']
return ret_dict
def generate_prediction_model(self):
'''self.lr_bound: dict {
level 0: [[left_bound, right_bound]], users' bound for one level, each ele in dictionary represents one node
level 1: [[left_bound, right_bound], [left_bound, right_bound], [left_bound, right_bound]], 3
level 2: ..., 9
} (bound means index)
'''
for level in self.lr_bound:
self.user_profile.setdefault(level)
train_lst = []
for pseudo_user_bound, userid in zip(
self.lr_bound[level], range(len(self.lr_bound[level]))):
if pseudo_user_bound[0] > pseudo_user_bound[1]:
continue
pseudo_user_lst = self.tree[pseudo_user_bound[0]:(
pseudo_user_bound[1] + 1)]
pseudo_user_for_item = self.calculate_avg_rating_for_pesudo_user(
pseudo_user_lst)
train_lst += [(userid, int(key), float(value))
for key, value in pseudo_user_for_item.items()]
self.user_profile[level], self.item_profile[
level] = self.MF.matrix_factorization(train_lst)
def build_model(self):
#### Construct the tree & get the prediction model ####
self.generate_decision_tree(self.lr_bound['0'][0], [])
self.generate_prediction_model()
def predict(self, new_user_ratings, pred_index):
''' new_user_ratings: list [
[itemid1, rating1],
[itemid2, rating2],
[itemid3, rating3],
[itemid4, rating4],
... ]
pred_rating: array: (I,)
new user's rating for each item
'''
#### Find user profile for new user ####
new_user_profile = np.array(self.user_profile[str(
len(new_user_ratings))][pred_index]) # shape: (k,)
new_item_profile = np.array(
list(self.item_profile[str(
len(new_user_ratings))].values())) # shape: (I, k)
#### Calculate predict rating ####
pred_rating = {itemid: np.dot(new_item_profile[i], new_user_profile) \
for itemid,i in zip(self.item_profile[str(len(new_user_ratings))], range(new_item_profile.shape[0]))}
return pred_rating