def objective_function(x_int):
objective_function.n_iterations += 1
list_score = []
# Parameter to optimise
w_sim, w_rank, w_reg, w_SVM, w_lightfm = x_int
for week_ID in list_week_ID :
for index, user in enumerate(d_user[week_ID]) :
d_blend_pred[week_ID][user] = d_user_pred[week_ID][user]["sim"]*w_sim
d_blend_pred[week_ID][user] += d_user_pred[week_ID][user]["xgb_rank"]*w_rank
d_blend_pred[week_ID][user] += d_user_pred[week_ID][user]["xgb_reg"]*w_reg
d_blend_pred[week_ID][user] += d_user_pred[week_ID][user]["xgb_SVM"]*w_SVM
d_blend_pred[week_ID][user] += d_user_pred[week_ID][user]["lightfm"]*w_lightfm
list_pred = d_blend_pred[week_ID][user]
top_k = np.argsort(-list_pred)[:10]
d_blend_pred[week_ID][user] = d_coupon[week_ID][top_k]
list_user = d_user_purchase[week_ID].keys()
list_actual = [d_user_purchase[week_ID][key] for key in list_user]
list_pred = [d_blend_pred[week_ID][key] for key in list_user]
list_score.append(mapr.mapk(list_actual, list_pred))
list_score = np.array(list_score)
print(objective_function.n_iterations, \
"w_sim, w_rank, w_reg, w_SVM, w_lightfm =", w_sim, w_rank, w_reg, w_SVM, w_lightfm, \
"\nList_score = ", list_score, \
"\nMean of MAP = ", np.mean(list_score), \
"\n Std of MAP = ", np.std(list_score))
return -np.median(list_score)
def objective_function(x_int):
objective_function.n_iterations += 1
list_score = []
# Parameter to optimise
gnr, disc, disp, large, small, val, us_sum, sex = x_int
#Build sparse matrix of weights
Wm = sps.block_diag(
(gnr * np.eye(13), disc * np.eye(1), disp * np.eye(1),
large * np.eye(9), small * np.eye(55), val * np.eye(2),
us_sum * np.eye(1), sex * np.eye(2)))
Wm_sparse = sps.csr_matrix(Wm)
for week_ID in list_week:
WmT = Wm_sparse.dot(d_test[week_ID])
score = 1. / distance.cdist(uchar_sparse.todense(),
WmT.T.todense(), metric)
#Store predictions in a dict
d_user_pred[week_ID] = {}
# Compute score
for i, user in enumerate(d_user_full[week_ID]):
list_pred = np.ravel(score[i, :])
list_index_top10 = list_pred.argsort()[-10:][::-1]
d_user_pred[week_ID][user] = d_coupon[week_ID][
list_index_top10]
for key in d_user_purchase[week_ID].keys():
try:
d_user_pred[week_ID][key]
except KeyError:
d_user_pred[week_ID][key] = []
list_user = d_user_purchase[week_ID].keys()
list_actual = [d_user_purchase[week_ID][key] for key in list_user]
list_pred = [d_user_pred[week_ID][key] for key in list_user]
list_score.append(mapr.mapk(list_actual, list_pred))
list_score = np.array(list_score)
print objective_function.n_iterations, \
"gnr, disc, disp, large, small, val, us_sum, sex =", gnr, disc, disp, large, small, val, us_sum, sex, \
"\nMean of MAP = ", np.mean(list_score), \
"\n Std of MAP = ", np.std(list_score)
return -np.min(list_score)
def score_similarity_predictions():
""" Score cosine similarity predictions
"""
list_score = []
# Loop over validation weeks
for week_ID in ["week51", "week52"]:
script_utils.print_utility("Training until " + week_ID)
#Get predictions
d_user_pred, list_user_full, list_coupon = get_similarity_distance(
week_ID, "1", "cosine")
#Format predictions
for index, user in enumerate(list_user_full):
list_pred = d_user_pred[user]
top_k = np.argsort(-list_pred)[:10]
d_user_pred[user] = list_coupon[top_k]
#Get actual purchase
d_user_purchase = {}
with open(
"../Data/Validation/" + week_ID +
"/dict_purchase_validation_" + week_ID + ".pickle", "r") as fp:
d_user_purchase = pickle.load(fp)
# Take care of users which registered during validation test week
for key in d_user_purchase.keys():
try:
d_user_pred[key]
except KeyError:
d_user_pred[key] = []
list_user = np.array(d_user_purchase.keys())
permut = np.random.permutation(len(list_user))
list_actual = [
d_user_purchase[key]
for key in list_user[permut][:int(len(permut))]
]
list_pred = [
d_user_pred[key] for key in list_user[permut][:int(len(permut))]
]
list_score.append(mapr.mapk(list_actual, list_pred))
list_score = np.array(list_score)
print list_score
print str(np.mean(list_score)) + " +/- " + str(np.std(list_score))
return np.mean(list_score)
def objective_function(x_int):
objective_function.n_iterations += 1
list_score = []
# Parameter to optimise
gnr, disc, disp, large, small, val, us_sum, sex = x_int
#Build sparse matrix of weights
Wm = sps.block_diag((gnr*np.eye(13), disc*np.eye(1), disp*np.eye(1), large*np.eye(9), small*np.eye(55), val*np.eye(2), us_sum*np.eye(1), sex*np.eye(2)))
Wm_sparse = sps.csr_matrix(Wm)
for week_ID in list_week :
WmT = Wm_sparse.dot(d_test[week_ID])
score = 1./distance.cdist(uchar_sparse.todense(), WmT.T.todense(), metric)
#Store predictions in a dict
d_user_pred[week_ID] = {}
# Compute score
for i, user in enumerate(d_user_full[week_ID]) :
list_pred = np.ravel(score[i,:])
list_index_top10 = list_pred.argsort()[-10:][::-1]
d_user_pred[week_ID][user] = d_coupon[week_ID][list_index_top10]
for key in d_user_purchase[week_ID].keys() :
try :
d_user_pred[week_ID][key]
except KeyError :
d_user_pred[week_ID][key] = []
list_user = d_user_purchase[week_ID].keys()
list_actual = [d_user_purchase[week_ID][key] for key in list_user]
list_pred = [d_user_pred[week_ID][key] for key in list_user]
list_score.append(mapr.mapk(list_actual, list_pred))
list_score = np.array(list_score)
print objective_function.n_iterations, \
"gnr, disc, disp, large, small, val, us_sum, sex =", gnr, disc, disp, large, small, val, us_sum, sex, \
"\nMean of MAP = ", np.mean(list_score), \
"\n Std of MAP = ", np.std(list_score)
return -np.min(list_score)
def score_lightFM(no_comp, lr, ep):
"""
Score the lightFM model for mean average precision at k = 10
args = no_comp, lr, ep (int, float, int)
number of components, learning rate, number of epochs for lightFM model
"""
list_score = []
# Loop over validation weeks
for week_ID in ["week51"] :
#Get predictions, manually choose metric and classifier
d_user_pred, list_user_full, list_coupon = fit_model(week_ID, no_comp, lr, ep)
#Format predictions
for index, user in enumerate(list_user_full) :
list_pred = d_user_pred[user]
top_k = np.argsort(-list_pred)[:10]
d_user_pred[user] = list_coupon[top_k]
#Get actual purchase
d_user_purchase = {}
with open("../Data/Validation/" + week_ID + "/dict_purchase_validation_" + week_ID + ".pickle", "r") as fp:
d_user_purchase = pickle.load(fp)
# Take care of users which registered during validation test week
for key in d_user_purchase.keys() :
try :
d_user_pred[key]
except KeyError :
d_user_pred[key] = []
list_user = d_user_purchase.keys()
list_actual = [d_user_purchase[key] for key in list_user]
list_pred = [d_user_pred[key] for key in list_user]
list_score.append(mapr.mapk(list_actual, list_pred))
print(list_score)
list_score = np.array(list_score)
print(list_score)
print(str(np.mean(list_score)) + " +/- " + str(np.std(list_score)))
def score_similarity_predictions():
""" Score cosine similarity predictions
"""
list_score = []
# Loop over validation weeks
for week_ID in ["week51", "week52"] :
script_utils.print_utility("Training until " + week_ID)
#Get predictions
d_user_pred, list_user_full, list_coupon = get_similarity_distance(week_ID, "1", "cosine")
#Format predictions
for index, user in enumerate(list_user_full) :
list_pred = d_user_pred[user]
top_k = np.argsort(-list_pred)[:10]
d_user_pred[user] = list_coupon[top_k]
#Get actual purchase
d_user_purchase = {}
with open("../Data/Validation/" + week_ID + "/dict_purchase_validation_" + week_ID + ".pickle", "r") as fp:
d_user_purchase = pickle.load(fp)
# Take care of users which registered during validation test week
for key in d_user_purchase.keys() :
try :
d_user_pred[key]
except KeyError :
d_user_pred[key] = []
list_user = np.array(d_user_purchase.keys())
permut = np.random.permutation(len(list_user))
list_actual = [d_user_purchase[key] for key in list_user[permut][:int(len(permut))]]
list_pred = [d_user_pred[key] for key in list_user[permut][:int(len(permut))]]
list_score.append(mapr.mapk(list_actual, list_pred))
list_score = np.array(list_score)
print list_score
print str(np.mean(list_score)) + " +/- " + str(np.std(list_score))
return np.mean(list_score)
def score_submission():
""" Score cosine similarity predictions
"""
list_score = []
# Loop over validation weeks
for week_ID in ["week51", "week52"] :
print "Training " + week_ID
#Get predictions, manually choose metric and classifier
d_user_pred, list_user_full, list_coupon = fit_xgboost(week_ID, "reg:linear")
# d_user_pred, list_user_full, list_coupon = fit_SVM(week_ID)
#Format predictions
for index, user in enumerate(list_user_full) :
list_pred = d_user_pred[user]
top_k = np.argsort(-list_pred)[:10]
d_user_pred[user] = list_coupon[top_k]
#Get actual purchase
d_user_purchase = {}
with open("../Data/Validation/" + week_ID + "/dict_purchase_validation_" + week_ID + ".pickle", "r") as fp:
d_user_purchase = pickle.load(fp)
# Take care of users which registered during validation test week
for key in d_user_purchase.keys() :
try :
d_user_pred[key]
except KeyError :
d_user_pred[key] = []
list_user = d_user_purchase.keys()
list_actual = [d_user_purchase[key] for key in list_user]
list_pred = [d_user_pred[key] for key in list_user]
list_score.append(mapr.mapk(list_actual, list_pred))
print list_score
list_score = np.array(list_score)
print list_score
print str(np.mean(list_score)) + " +/- " + str(np.std(list_score))