def train_als(trn,tst):
model.fit(trn,show_progress=True)
MAP = mean_average_precision_at_k(model, trn, tst, K=10,
show_progress=True, num_threads=1)
NDCG = ndcg_at_k(model, trn, tst, K=10,
show_progress=True, num_threads=1)
print("MAP is %.4f and NDCG is %.4f: " %(MAP,NDCG))
return model
def train_test_split_recommend(self,model,user_item_csr,user_lookup,user_id):
train, test = train_test_split(user_item_csr)
# train the model on a sparse matrix of item/user/confidence weights
model.fit(train.T.tocsr())
"""Calculate Precision@N & NDCG@N"""
precision = precision_at_k(model, train, test, K=20)
ndcg = ndcg_at_k(model, train, test, K=20)
print('Precision@20: {0}\n NDCG@20: {1}\n'.format(precision, ndcg))
"""Recommend items to every user"""
top_rec_4all = model.recommend_all(test,filter_already_liked_items=True)
top_rec_4all = top_rec_4all.T
# top_rec_4all = pd.DataFrame(top_rec_4all)
top_rec_4all = pd.DataFrame(data=top_rec_4all, columns=user_lookup.index.categories)
print('Recommendations Dataframe:\n{}'.format(top_rec_4all))
top_products = top_rec_4all[user_id]
return top_products
def learningCurve(model, train, test, epochs, outFile=None,
k=5, showProgress=True, numThreads=12):
# if not userIndex:
# userIndex = range(train.shape[0])
prevEpoch = 0
pAtK = []
MAPatK = []
NDCGatK = []
AUCatK = []
headers = ["epochs", f"p@{k}", f"MAP@{k}", f"NDCG@{k}", f"AUC@{k}"]
printLog(headers, header=True, outFile=outFile)
for epoch in epochs:
model.iterations = epoch - prevEpoch
if not hasattr(model, "user_vectors"):
model.fit(train, show_progress=showProgress)
else:
model.fit_partial(train, show_progress=showProgress)
pAtK.append(precision_at_k(model, train.T.tocsr(), test.T.tocsr(),
K=k, show_progress=showProgress,
num_threads=numThreads))
MAPatK.append(mean_average_precision_at_k(model, train.T.tocsr(),
test.T.tocsr(), K=k,
show_progress=showProgress,
num_threads=numThreads))
NDCGatK.append(ndcg_at_k(model, train.T.tocsr(), test.T.tocsr(),
K=k, show_progress=showProgress,
num_threads=numThreads))
AUCatK.append(AUC_at_k(model, train.T.tocsr(), test.T.tocsr(),
K=k, show_progress=showProgress,
num_threads=numThreads))
row = [epoch, pAtK[-1], MAPatK[-1], NDCGatK[-1], AUCatK[-1]]
printLog(row, outFile=outFile)
prevEpoch = epoch
return model, pAtK, MAPatK, NDCGatK, AUCatK
print(f"Computing p@{k} ...", flush=True)
t0 = time()
pAtK = precision_at_k(model, trainTscr, testTscr, K=k,
show_progress=args.progressBar,
num_threads=args.numThreads)
print(f"Δt: {time() - t0:5.1f}s")
print(f"Computing MAP@{k} ...", flush=True)
t0 = time()
MAPatK = mean_average_precision_at_k(model, trainTscr, testTscr, K=k,
show_progress=args.progressBar,
num_threads=args.numThreads)
print(f"Δt: {time() - t0:5.1f}s")
print(f"Computing NDCG@{k} ...", flush=True)
t0 = time()
NDCGatK = ndcg_at_k(model, trainTscr, testTscr, K=k,
show_progress=args.progressBar,
num_threads=args.numThreads)
AUCatK = AUC_at_k(model, trainTscr, testTscr, K=k,
show_progress=args.progressBar,
num_threads=args.numThreads)
print(f"Δt: {time() - t0:5.1f}s")
print(f"p@{k}: {pAtK:6.4f}, MAP@{k}: {MAPatK:6.4f}"
f"NDCG@{k}: {NDCGatK:6.4f}, AUC@{k}: {AUCatK:6.4f}", flush=True)
# thang = [curves[x]["params"] for x in range(len(curves))]
# df0 = pd.DataFrame(thang)
# blah = [curves[x][f"p@{k}"] for x in range(len(curves))]
# df1 = pd.DataFrame(blah)
def run(modelName, datasetName, factorCt, k, λ, α,
maxIters, showProgress, useGPU, threadCt):
if modelName == 'als':
model = getModel(modelName, volubility=2,
params={'factors': factorCt,
'regularization': λ,
'iterations': maxIters,
'use_gpu': useGPU})
else:
model = getModel(modelName, volubility=2,
params={'factors': factorCt,
'regularization': λ,
'alpha': α,
'iterations': maxIters,
'use_gpu': useGPU})
artists, users, plays = fetchDataset(datasetName, volubility=2)
print(artists.shape, users.shape, plays.shape, flush=True)
if issubclass(model.__class__, AlternatingLeastSquares):
# lets weight these models by bm25weight.
print("weighting matrix by bm25_weight")
plays = bm25_weight(plays, K1=100, B=0.8)
# also disable building approximate recommend index
model.approximate_recommend = False
# print(asctime(localtime()))
# t0 = time()
plays = plays.tocsr()
# print(f"Δt: {time() - t0:5.1f}s")
train, test = train_test_split(plays, train_percentage=0.8)
print("Training model")
print(asctime(localtime()), flush=True)
t0 = time()
model.fit(train, show_progress=showProgress)
print(f"Δt: {time() - t0:5.1f}s", flush=True)
trainTscr = train.T.tocsr()
testTscr = test.T.tocsr()
print(f"Computing p@{k} ...", flush=True)
t0 = time()
pAtK = precision_at_k(model, trainTscr, testTscr, K=k,
show_progress=showProgress,
num_threads=threadCt)
ex.log_scalar(f"p@{k}", pAtK)
print(f"Δt: {time() - t0:5.1f}s")
print(f"Computing MAP@{k} ...", flush=True)
t0 = time()
MAPatK = mean_average_precision_at_k(model, trainTscr, testTscr, K=k,
show_progress=showProgress,
num_threads=threadCt)
ex.log_scalar(f"MAP@{k}", MAPatK)
print(f"Δt: {time() - t0:5.1f}s")
print(f"Computing NDCG@{k} ...", flush=True)
t0 = time()
NDCGatK = ndcg_at_k(model, trainTscr, testTscr, K=k,
show_progress=showProgress,
num_threads=threadCt)
ex.log_scalar(f"NDCG@{k}", NDCGatK)
AUCatK = AUC_at_k(model, trainTscr, testTscr, K=k,
show_progress=showProgress,
num_threads=threadCt)
ex.log_scalar(f"AUC@{k}", AUCatK)
print(f"Δt: {time() - t0:5.1f}s")
print(f"p@{k}: {pAtK:6.4f}, MAP@{k}: {MAPatK:6.4f}"
f"NDCG@{k}: {NDCGatK:6.4f}, AUC@{k}: {AUCatK:6.4f}", flush=True)
csr_data, user_lookup, item_lookup = create_sparse_matrix(
data, userkey, itemkey)
#print(csr_data)
csr_data = csr_data.T.tocsr()
print(csr_data)
train, test = train_test_split(csr_data)
print(train, test)
#print(user_lookup,item_lookup)
"""initialize a model --- choose a model"""
#model = implicit.als.AlternatingLeastSquares(factors=20,regularization=0.1,iterations=50)
model = implicit.als.AlternatingLeastSquares(factors=50)
#model = implicit.bpr.BayesianPersonalizedRanking(factors=100)
#model = implicit.lmf.LogisticMatrixFactorization(factors=100)
#model = implicit.approximate_als.AnnoyAlternatingLeastSquares()
print(train.T.tocsr())
"""Train the model on a sparse matrix of item/user/confidence weights"""
model.fit(train.T.tocsr())
"""Evaluation Metrics Calculation"""
precision = precision_at_k(model, train, test, K=20)
ndcg = ndcg_at_k(model, train, test, K=20)
print('Precision@20: {0}\n NDCG@20: {1}\n'.format(precision, ndcg))
"""Recommend N best items for each user"""
top_rec_4all = model.recommend_all(test, N=20)
top_rec_4all = top_rec_4all.T
#top_rec_4all = pd.DataFrame(data=top_rec_4all,columns=user_lookup.index.categories)
top_rec_4all = pd.DataFrame(data=top_rec_4all,
columns=user_lookup.index.values)
print(top_rec_4all)