def get_results(setNum, reg_term):
reader = Reader(rating_scale = (0,10))
train = pd.read_csv('../data/train_'+str(setNum)+'.csv', sep = ';')
# test = pd.read_csv('../data/test_update.csv', sep = ';')
train_set = Dataset.load_from_df(train[['User-ID', 'ISBN', 'Book-Rating']], reader=reader)
# test_set = Dataset.load_from_df(test[['User-ID', 'ISBN', 'Book-Rating']], reader=reader)
data = train_set.build_full_trainset()
num_factors = 50
if setNum==10:
num_factors_b=200
if setNum==15:
num_factors_b=400
if setNum==30:
num_factors_b=600
svd = SVD(n_factors = num_factors, reg_all=reg_term)
svd_bias = SVD(n_factors = num_factors_b, biased=True, reg_all=reg_term)
baseline = DumbBaseline()
cv_svd = cross_validate(svd, train_set, n_jobs = -2, return_train_measures=True)
cv_svd_bias = cross_validate(svd_bias, train_set, n_jobs = -2, return_train_measures=True)
cv_baseline = cross_validate(baseline, train_set, n_jobs = -2, return_train_measures=True)
# getting the results ready to plot
val_res = [np.mean(cv_svd['test_rmse']), np.mean(cv_svd_bias['test_rmse']),np.mean(cv_baseline['test_rmse'])]
train_res = [np.mean(cv_svd['train_rmse']), np.mean(cv_svd_bias['train_rmse']),np.mean(cv_baseline['train_rmse'])]
val_err = [np.std(cv_svd['test_rmse']), np.std(cv_svd_bias['test_rmse']),np.std(cv_baseline['test_rmse'])]
train_err = [np.std(cv_svd['train_rmse']), np.std(cv_svd_bias['train_rmse']),np.std(cv_baseline['train_rmse'])]
algs = ['MF (k='+str(num_factors)+')', 'MF With Bias (k='+str(num_factors_b)+')', 'Baseline']
return val_res,train_res,val_err,train_err,algs
def svd_ratings_predicate(observed_ratings_df,
truth_ratings_df,
fold='0',
phase='eval'):
"""
pmf_ratings Predicates
"""
print("SVD predicates")
svd_model = SVD()
reader = Reader(rating_scale=(0.2, 1))
train_dataset = Dataset.load_from_df(df=observed_ratings_df.reset_index(
).loc[:, ['userId', 'movieId', 'rating']],
reader=reader)
svd_model.fit(train_dataset.build_full_trainset())
# make predictions
predictions = pd.DataFrame(index=truth_ratings_df.index,
columns=['rating'])
for row in truth_ratings_df.loc[:, ['rating']].iterrows():
uid = row[0][0]
iid = row[0][1]
predictions.loc[(uid, iid), 'rating'] = svd_model.predict(uid, iid).est
write(predictions, 'svd_rating_obs', fold, phase)
def mfb_compute_high_var_trim_rmse(k):
mfb = SVD(n_factors=k, random_state=42)
rmse = []
for trainset, testset in KFold(n_splits=10, random_state=42).split(R):
mfb.fit(trainset)
testset_trimmed = high_variance_trimming(testset, frequency, variance)
pred = mfb.test(testset_trimmed)
rmse.append(accuracy.rmse(pred, verbose=False))
print('k: %s | RMSE: %f' % (k, np.mean(rmse)))
return np.mean(rmse)
def svd_algorithm() -> SVD:
user_input = input(
'Do you want to continue with the default parameters? Y/N')
if user_input.lower() == 'y':
return SVD()
else:
n_factors = int(input('Enter total number of factors: '))
n_epochs = int(input('Enter number of epochs: '))
lr_all = float(
input('Enter the learning rate for all the paramaters: '))
return SVD(n_factors, n_epochs, lr_all)
def mfb_compute_prec_rec(t):
precision, recall = [], []
for trainset, testset in KFold(n_splits=10, random_state=42).split(R):
mfb = SVD(n_factors=mfb_best_k, random_state=42)
mfb.fit(trainset)
trimmed_testset = trim_unpopular_user(testset, t, threshold)
pred = mfb.test(trimmed_testset)
precision_dict, recall_dict = calculate_precision_recall(
pred, t, threshold)
precision.append(np.mean([prec for prec in precision_dict.values()]))
recall.append(np.mean([rec for rec in recall_dict.values()]))
return np.mean(precision), np.mean(recall)
def MF_trim_filter(ratings, dims, func, mv_dict):
reader = Reader(rating_scale=(0.0, 5.0))
data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']],
reader)
RMSE = np.empty([len(dims)])
MAE = np.empty([len(dims)])
min_RMSE = False
min_MAE = False
fac_num_RMSE = 0
fac_num_MAE = 0
kf = KFold(n_splits=10, random_state=42)
for k in range(len(dims)):
svd = SVD(n_factors=dims[k], random_state=42)
test_rmse = np.array([])
test_mae = np.array([])
for trainset, testset in kf.split(data):
svd.fit(trainset)
full_data = trainset.build_testset() + testset
func(mv_dict, testset)
pred = svd.test(testset)
test_rmse = np.append(test_rmse, accuracy.rmse(pred,
verbose=False))
test_mae = np.append(test_mae, accuracy.mae(pred, verbose=False))
RMSE[k] = np.mean(test_rmse)
if ((not min_RMSE) or RMSE[k] < min_RMSE):
min_RMSE = RMSE[k]
fac_num_RMSE = dims[k]
MAE[k] = np.mean(test_mae)
if ((not min_MAE) or MAE[k] < min_MAE):
min_MAE = MAE[k]
fac_num_MAE = dims[k]
print('For k = %i :' % dims[k])
print('RMSE: ', RMSE[k])
print('MAE: ', MAE[k])
plt.plot(dims, RMSE)
plt.plot(dims, MAE)
plt.legend(['RMSE', 'MAE'])
plt.show()
print('Finishing Plotting...')
print('For RMSE:')
print('\t---Optimal number of latent factors is ', fac_num_RMSE)
print('\t---Minumun Average RMSE is ', min_RMSE)
print('\nFor MAE:')
print('\t---Optimal number of latent factors is ', fac_num_MAE)
print('\t---Minumun Average MAE is ', min_MAE)
def Q15and22and29(qNum, bestK, thres=[2.5, 3, 3.5, 4]):
range = 5.0
sim_options = {
'name': 'pearson_baseline',
'shrinkage': 0 # no shrinkage
}
data = load_data()
trainset, testset = train_test_split(data, test_size=0.1)
if qNum == 15:
model = KNNWithMeans(bestK, sim_options=sim_options)
elif qNum == 22:
model = NMF(n_factors=bestK)
else:
model = SVD(n_factors=bestK)
model.fit(trainset)
pred = model.test(testset)
for thrs in thres:
np_true = np.array([])
np_score = np.array([])
for u, i, t, p, d in pred:
if t >= thrs:
t = 1
else:
t = 0
np_true = np.append(np_true, t)
np_score = np.append(np_score, p / range)
title = 'Threshold ' + str(thrs)
plot_ROC(np_true, np_score, title=title)
def slot_select_algo_combobox(self):
self.algo_change_flag=True
self.algo_trained_flag=False
algo_name=self.select_algo_comboBox.currentText()
if algo_name=='SVD':
self.algo=SVD()
self.display_process_label.append('加载SVD模型...')
elif algo_name=='SVD++':
self.algo = SVDpp()
self.display_process_label.append('加载SVD++模型...')
elif algo_name == 'NMF':
self.algo = NMF()
self.display_process_label.append('加载NMF模型...')
elif algo_name == 'Slope One':
self.algo = SlopeOne()
self.display_process_label.append('加载Slope One模型...')
elif algo_name == 'k-NN':
self.algo = KNNBasic()
self.display_process_label.append('加载k-NN模型...')
elif algo_name == 'Centered k-NN':
self.algo = KNNWithMeans()
self.display_process_label.append('加载Centered k-NN模型...')
elif algo_name == 'k-NN Baseline':
self.algo = KNNBaseline()
self.display_process_label.append('加载k-NN Baseline模型...')
elif algo_name == 'Co-Clustering':
self.algo = CoClustering()
self.display_process_label.append('加载Co-Clustering模型...')
elif algo_name == 'Baseline':
self.algo = BaselineOnly()
self.display_process_label.append('加载Baseline模型...')
elif algo_name == 'Random':
self.algo = NormalPredictor()
self.display_process_label.append('加载Random模型...')
def recommand(self):
sim_options = {
'name': 'pearson_baseline',
'shrinkage': 0 # no shrinkage
}
best_model = knns.KNNWithMeans(k=20, sim_options=sim_options)
t_values, precisions_knn, recall_knn = self.test_with_t_and_k(
best_model, msg='KNN')
best_model = matrix_factorization.NMF(n_factors=20, biased=False)
t_values, precisions_nmf, recall_nmf = self.test_with_t_and_k(
best_model, msg='NMF')
best_model = SVD(20)
t_values, precisions_svd, recall_svd = self.test_with_t_and_k(
best_model, msg='SVD')
plt.plot(t_values, precisions_knn, label='precisions_knn')
plt.plot(t_values, precisions_nmf, label='precisions_nmf')
plt.plot(t_values, precisions_svd, label='precisions_svd')
plt.plot(t_values, recall_knn, label='recall_knn')
plt.plot(t_values, recall_nmf, label='recall_nmf')
plt.plot(t_values, recall_svd, label='recall_svd')
plt.xlabel('t_value')
plt.ylabel('percent')
plt.legend(loc="best")
plt.show()
def Question24(data):
ks = range(2, 51, 2)
RMSE = []
MAE = []
for k in ks:
model = SVD(n_factors=k)
pred = cross_validate(model, data, cv=10)
RMSE.append(np.mean(pred['test_rmse']))
MAE.append(np.mean(pred['test_mae']))
# Plot
plt.plot(ks, RMSE)
plt.xlabel('k')
plt.ylabel('Average RMSE')
plt.savefig('Q24_RMSE.png')
plt.figure()
plt.plot(ks, MAE)
plt.xlabel('k')
plt.ylabel('Average MAE')
plt.savefig('Q24_MAE.png')
index = np.argmin(RMSE)
print("Best k: %i" % ks[index])
print("Lowest RMSE: %f" % RMSE[index])
print("Lowest MAE: %f" % np.min(MAE))
def build_model(train,method ='svd'):
"""Builds model and makes predictions for user-book rating.
Args:
train(surprise trainset): training set for the model to train on
method (string): Method to use. Either 'knn' or 'svd'. Deafault is 'svd'.
Returns: list of Prediction objects.
"""
if method == 'knn':
surprise_sim_opt = {'name':'cosine','user_based':False}
model = KNNBasic(k=100, min_k=20,sim_options = surprise_sim_opt)
else:
model = SVD(n_epochs=50)
model.fit(train)
test = train.build_anti_testset()
pred = model.test(testset)
return pred
def run_and_test_all_models(self):
step_size = 2
# KNN
sim_options = {
'name': 'pearson_baseline',
'shrinkage': 0 # no shrinkage
}
algo = knns.KNNWithMeans
args = {'sim_options': sim_options}
best_model = knns.KNNWithMeans(k=20, sim_options=sim_options)
roc_auc_KNN = self.run_and_test_model(algo, args, best_model,
(2, 101, step_size), 'KNN')
# # NMF
algo = matrix_factorization.NMF
args = {'biased': False}
best_model = matrix_factorization.NMF(n_factors=20, biased=False)
roc_auc_NMF = self.run_and_test_model(algo, args, best_model,
(2, 51, step_size), 'NMF')
# SVD
algo = matrix_factorization.SVD
args = {}
best_model = SVD(20)
roc_auc_SVD = self.run_and_test_model(algo, args, best_model,
(2, 51, step_size), 'SVD')
# all
for i in range(len(roc_auc_KNN)):
plt.plot(roc_auc_KNN[i][0],
roc_auc_KNN[i][1],
color='blue',
linewidth=2.0,
label='KNN')
plt.plot(roc_auc_NMF[i][0],
roc_auc_NMF[i][1],
color='blue',
linewidth=2.0,
label='NMF')
plt.plot(roc_auc_SVD[i][0],
roc_auc_SVD[i][1],
color='blue',
linewidth=2.0,
label='SVD')
plt.plot([0, 1], [0, 1], color='yellow', linewidth=2.0)
plt.xlabel('FPR')
plt.ylabel('TPR')
plt.legend(loc="lower right")
plt.show()
# NaiveFilter
self.run_naive_filter(msg='normal')
self.run_naive_filter(test_filter=trimPopular, msg='trimPopular')
self.run_naive_filter(test_filter=trimUnpopular, msg='trimUnpopular')
self.run_naive_filter(test_filter=trimHighVariance,
msg='trimHighVariance')
def rank_predictions(model_name):
k_KNN = 22
k_NNMF = 20
k_MF = 26
if model_name == 'KNN':
sim_options = {
'name': 'pearson_baseline',
'shrinkage': 0
}
model = KNNWithMeans(k_KNN, sim_options=sim_options)
elif model_name == 'NNMF':
model = NMF(n_factors= k_NNMF)
else:
model = SVD(n_factors = k_MF)
precision_arr = []
recall_arr = []
for t in range (1,26):
kf = KFold(n_splits=10)
print(t)
p = []
r = []
for trainSet, testSet in kf.split(data):
model.fit(trainSet)
predictions = model.test(testSet)
precisions, recalls = precision_recall (predictions, t)
p.append(sum(prec for prec in precisions.values()) / len(precisions))
r.append(sum(rec for rec in recalls.values()) / len(recalls))
precision_arr.append(np.mean(np.array(p)))
recall_arr.append(np.mean(np.array(r)))
# precision vs t
plt.plot(list(range (1,26)), precision_arr)
plt.xlabel("Size")
plt.ylabel("Precision")
plt.title("The average precision plot using " + model_name)
plt.show()
# recall vs t
plt.plot(list(range (1,26)), recall_arr)
plt.xlabel("Size")
plt.ylabel("Recall")
plt.title("The average recall plot using MF " + model_name)
plt.show()
# precision vs recall
plt.plot(recall_arr, precision_arr)
plt.xlabel("Recall")
plt.ylabel("Precision")
plt.title("The average precision and recall plot using " + model_name)
plt.show()
return precision_arr, recall_arr
def train_svd(data):
rmse = []
mae = []
sim_options = {'name': 'pearson'}
for k in range(2, 52, 2):
print("using k = %d" % k)
nmf = SVD(n_factors=k)
temp = cross_validate(nmf, data, measures=['RMSE', 'MAE'], cv=10)
rmse.append(np.mean(temp['test_rmse']))
mae.append(np.mean(temp['test_mae']))
print("k-fold validation finished!")
return (rmse, mae)
def train_trim_svd(data, R):
kfold = KFold(n_splits=10)
rmse_list = [[], [], []]
for k in range(2, 52, 2):
print("using k = %d" % k)
p_rmse = []
u_rmse = []
hv_rmse = []
svd = SVD(n_factors=k)
for trainset, testset in kfold.split(data):
svd.fit(trainset)
(p_testset, u_testset, hv_testset) = trim(testset, R)
p_pred = svd.test(p_testset)
u_pred = svd.test(u_testset)
hv_pred = svd.test(hv_testset)
p_rmse.append(accuracy.rmse(p_pred))
u_rmse.append(accuracy.rmse(u_pred))
hv_rmse.append(accuracy.rmse(hv_pred))
rmse_list[0].append(np.mean(p_rmse))
rmse_list[1].append(np.mean(u_rmse))
rmse_list[2].append(np.mean(hv_rmse))
print("SVD with trim is finished!!")
return rmse_list
def Q34():
rang = 5.0
sim_options = {
'name': 'pearson_baseline',
'shrinkage': 0 # no shrinkage
}
data = load_data()
trainset, testset = train_test_split(data, test_size=0.1)
knn = KNNWithMeans(22, sim_options=sim_options)
nmf = NMF(n_factors=18)
svd = SVD(n_factors=8)
fp = {}
tp = {}
area = np.array([])
for model, key in zip([knn, nmf, svd], ['KNN', 'NNMF', 'SVD']):
model.fit(trainset)
pred = model.test(testset)
np_true = np.array([])
np_score = np.array([])
for _, _, t, p, _ in pred:
if t >= 3:
t = 1
else:
t = 0
np_true = np.append(np_true, t)
np_score = np.append(np_score, p / rang)
fpr, tpr, thresholds = roc_curve(np_true, np_score)
print(fpr.shape, tpr.shape)
roc_auc = auc(fpr, tpr)
fp[key] = fpr
tp[key] = tpr
area = np.append(area, roc_auc)
plt.figure()
lw = 2
for mod, f, t, roc_auc in zip(['KNN', 'NNMF', 'SVD'], fp, tp, area):
fpr = fp[f]
tpr = tp[t]
# label = mod+'ROC curve (area = '+str(roc_auc)+'0.2f)'
plt.plot(fpr,
tpr,
lw=lw,
label='%s ROC curve (area = %0.2f)' % (mod, roc_auc))
plt.plot([0, 1], [0, 1], color='navy', lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curves')
plt.legend(loc="lower right")
plt.show()
plt.close()
def MF_bin_pre(ratings, ts, nmf_fac, thrd):
reader = Reader(rating_scale=(0.0, 5.0))
data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']],
reader)
trainset, testset = train_test_split(data, test_size=ts)
algo = SVD(n_factors=nmf_fac, random_state=42)
algo.fit(trainset)
pre = algo.test(testset)
true_rating = np.empty(len(pre))
pred_rating = np.empty(len(pre))
for i in range(len(pre)):
true_rating[i] = pre[i][2]
pred_rating[i] = pre[i][3]
bi_rating = np.empty(len(pre))
one_idx = true_rating >= thrd
zero_idx = true_rating < thrd
bi_rating[one_idx] = 1.0
bi_rating[zero_idx] = 0.0
return bi_rating, pred_rating
def trimmed_test_MF(data, choice=0):
ks = range(2, 51, 2)
avg_RMSEs = []
for k in ks:
kf = KFold(n_splits=10)
rmse_total = 0
for trainset, testset in kf.split(data):
trimmed_testset = trim(data, testset, choice)
model = SVD(n_factors=k).fit(trainset)
pred = model.test(trimmed_testset)
rmse_total += rmse(pred, verbose=False)
rmse_total = rmse_total / 10.0
avg_RMSEs.append(rmse_total)
# Plot
plt.plot(ks, avg_RMSEs)
plt.xlabel('k')
plt.ylabel('Average RMSE')
plt.savefig('RMSE_' + str(choice) + '.png')
index = np.argmin(avg_RMSEs)
print("Best k: %i" % ks[index])
print("Lowest RMSE: %f" % avg_RMSEs[index])
def vary_factors(setNum, n_factors):
reader = Reader(rating_scale = (0,10))
train = pd.read_csv('../data/train_'+str(setNum)+'.csv', sep = ';')
train_set = Dataset.load_from_df(train[['User-ID', 'ISBN', 'Book-Rating']], reader=reader)
data = train_set.build_full_trainset()
train_errors = []
val_errors = []
for f in n_factors:
svd = SVD(n_factors = f)
cv = cross_validate(svd, train_set, return_train_measures=True, n_jobs = -2, verbose=True)
train_errors += [np.mean(cv['train_rmse'])]
val_errors += [np.mean(cv['test_rmse'])]
return train_errors, val_errors
def __init__(self):
super(Window,self).__init__()
self.setupUi(self)
self.connect_slot_function()
self.current_path = os.getcwd()
self.dataset_path='./dataset/data.csv'
self.result_path = './result/pre_result.txt'
self.help_file_path='./help/help.txt'
self.max_totalnum=10000
self.cut_num=0
self.algo = SVD()
self.display_process_label.append('初始化加载SVD模型.')
self.algo_change_flag = False
self.algo_trained_flag=False
self.init_dir()
def Q26To28(qNum, n_splits=10):
data = load_data()
kf = KFold(n_splits=10)
trimFun = {26: popularTrim, 27: unpopularTrim, 28: highVarTrim}
RMSE = []
for k in range(2, 52, 2):
MF_svd = SVD(n_factors=k)
subRMSE = []
for trainSet, testSet in kf.split(data):
subsubRMSE = 0
MF_svd.fit(trainSet)
testSet = trimFun[qNum](testSet)
nTest = len(testSet)
print("test set size after trimming: %d", nTest)
for (r, c, rating) in testSet:
predictedRating = MF_svd.predict(str(r), str(c))
subsubRMSE += (pow(rating - predictedRating.est, 2))
# calculate RMSE of this train-test split
subRMSE.append(np.sqrt(subsubRMSE / nTest))
# average of all train-test splits of k-NN
RMSE.append(np.mean(subRMSE))
return RMSE
def run_svd(data, params, svdpp=False):
'''Returns trained SVD model based on matrix factorization'''
if svdpp:
alg = SVDpp(n_factors=utils.get_param(params, 'n_factors'),
n_epochs=utils.get_param(params, 'n_epochs'),
lr_all=utils.get_param(params, 'learning_rate'),
reg_all=utils.get_param(params, 'reg'),
verbose=True)
else:
alg = SVD(biased=utils.get_param(params, 'biased'),
n_factors=utils.get_param(params, 'n_factors'),
n_epochs=utils.get_param(params, 'n_epochs'),
lr_all=utils.get_param(params, 'learning_rate'),
reg_all=utils.get_param(params, 'reg'),
verbose=True)
alg.fit(data)
return alg
def plot_all_ROC():
rang = 5.0
sim_options = {
'name': 'pearson_baseline',
'shrinkage': 0 # no shrinkage
}
trainset, testset = train_test_split(data, test_size=0.1)
knn = KNNWithMeans(22, sim_options=sim_options)
nmf = NMF(n_factors=18)
svd = SVD(n_factors=8)
fp = {}
tp = {}
area = np.array([])
for model, key in zip([knn, nmf, svd], ['KNN','NNMF','SVD']):
model.fit(trainset)
pred = model.test(testset)
np_true = np.array([])
np_score = np.array([])
for _, _, t, p, _ in pred:
if t >= 3:
t = 1
else:
t = 0
np_true = np.append(np_true, t)
np_score = np.append(np_score, p/rang)
fpr, tpr, thresholds = metrics.roc_curve(np_true, np_score)
print(fpr.shape, tpr.shape)
roc_auc = metrics.auc(fpr, tpr)
fp[key] = fpr
tp[key] = tpr
area = np.append(area, roc_auc)
plt.figure()
lw = 2
for mod, f, t, roc_auc in zip(['k-NN','NNMF','MF'], fp, tp, area):
fpr = fp[f]
tpr = tp[t]
plt.plot(fpr, tpr, lw=lw, label='%s'%mod)
plt.plot([0, 1], [0, 1], lw=lw, linestyle='--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('ROC Curves')
plt.legend()
plt.show()
def grid_search(surprise_model):
if type(surprise_model()) == type(SVDpp()):
param_grid = {'n_factors':[20] , 'n_epochs':[20], 'lr_all':[0.005, 0.007, 0.05, 0.07, 0.5, 0.7, 1.0], 'reg_all':[0.02, 0.05, 0.2, 0.5]}
gs = GridSearchCV(surprise_model, param_grid, measures=['rmse', 'mae'], cv=3,n_jobs=-1,joblib_verbose=1,refit=True)
elif type(surprise_model()) == type(SVD()):
param_grid = {'n_epochs':[20], 'lr_all':[0.005, 0.007, 0.05, 0.07, 0.5, 0.7, 1.0], 'reg_all':[0.02, 0.05, 0.2, 0.5]}
gs = GridSearchCV(surprise_model, param_grid, measures=['rmse', 'mae'], cv=3,n_jobs=-1,joblib_verbose=1,refit=True)
elif type(surprise_model()) == type(NMF()):
param_grid = {'n_epochs':[20], 'reg_pu':[0.02, 0.04, 0.06, 0.08, 0.2], 'reg_qi':[0.02, 0.04, 0.06, 0.08, 0.2]}
gs = GridSearchCV(surprise_model, param_grid, measures=['rmse', 'mae'], cv=3,n_jobs=-1,joblib_verbose=1,refit=True)
elif type(surprise_model()) == type(BaselineOnly()):
param_grid = {'bsl_options': {'method': ['als', 'sgd'], 'reg': [1, 2], 'learning_rate': [0.005, 0.05, 0.5, 1.0]}}
gs = GridSearchCV(surprise_model, param_grid, measures=['rmse', 'mae'], cv=3,n_jobs=-1,joblib_verbose=1,refit=True)
return gs
def MF_bias_filter(ratings, dims):
reader = Reader(rating_scale=(0.0, 5.0))
data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']],
reader)
RMSE = np.empty([len(dims)])
MAE = np.empty([len(dims)])
min_RMSE = False
min_MAE = False
fac_num_RMSE = 0
fac_num_MAE = 0
for k in range(len(dims)):
svd = SVD(n_factors=dims[k], random_state=42)
cv = cross_validate(algo=svd,
data=data,
measures=['RMSE', 'MAE'],
cv=10,
verbose=True)
RMSE[k] = np.mean(cv['test_rmse'])
if ((not min_RMSE) or RMSE[k] < min_RMSE):
min_RMSE = RMSE[k]
fac_num_RMSE = dims[k]
MAE[k] = np.mean(cv['test_mae'])
if ((not min_MAE) or MAE[k] < min_MAE):
min_MAE = MAE[k]
fac_num_MAE = dims[k]
plt.plot(dims, RMSE)
plt.plot(dims, MAE)
plt.legend(['RMSE', 'MAE'])
plt.show()
print('Finishing Plotting...')
print('For RMSE:')
print('\t---Optimal number of latent factors is ', fac_num_RMSE)
print('\t---Minumun Average RMSE is ', min_RMSE)
print('\nFor MAE:')
print('\t---Optimal number of latent factors is ', fac_num_MAE)
print('\t---Minumun Average MAE is ', min_MAE)
def Q24():
# so far using same code as Q10, Q12-14 for Q24, Q26-28, can combine code later
# only using SVD for Q24 for now, but the RMSE and MAE don't change much with latent factor
data = load_data()
meanRMSE, meanMAE = [], []
start = time.time()
for k in range(2, 52, 2):
MF_svd = SVD(n_factors=k)
out = cross_validate(MF_svd, data, measures=['RMSE', 'MAE'], cv=10)
meanRMSE.append(np.mean(out['test_rmse']))
meanMAE.append(np.mean(out['test_mae']))
cv_time = str(datetime.timedelta(seconds=int(time.time() - start)))
print("Total time used for cross validation: " + cv_time)
k = list(range(2, 52, 2))
ys = [[meanRMSE, 'mean RMSE'], [meanMAE, 'mean MAE']]
#currently plot meanRMSE and meanMAE separately because it's hard to see the trend when they are plotted in same graph
make_plot(k, [[meanRMSE, 'mean RMSE']], 'Number of Neighbors', 'Error')
make_plot(k, [[meanMAE, 'mean MAE']], 'Number of Neighbors', 'Error')
return meanRMSE, meanMAE
import matplotlib.pyplot as plt
import numpy as np
file_path = os.path.expanduser('ml-latest-small/ratings_new.csv')
reader = Reader(sep=',')
data = Dataset.load_from_file(file_path, reader=reader)
avg_rmse = []
avg_mae = []
all_k = []
for i in range(2,52,2):
print('k = ',i)
all_k.append(i)
mf = SVD(n_factors=i)
output = cross_validate(mf, data, measures=['RMSE', 'MAE'], cv=10, verbose=True)
avg_rmse.append(np.mean(output['test_rmse']))
avg_mae.append(np.mean(output['test_mae']))
print("min rmse k:", avg_rmse.index(min(avg_rmse)))
print("min mae k:", avg_mae.index(min(avg_mae)))
plt.plot(all_k,avg_rmse)
plt.savefig('plot/mf_rmse_k.png')
plt.clf()
plt.plot(all_k,avg_mae)
plt.savefig('plot/mf_mae_k.png')
plt.clf()
from surprise import Dataset, evaluate, Reader, KNNBasic
from surprise.model_selection import cross_validate
from surprise.prediction_algorithms.matrix_factorization import SVD
from DataProcessing.dataprocessing import ratings
print("Training SVD Algorithm")
reader = Reader()
data = Dataset.load_from_df(ratings[['userId', 'movieId', 'rating']], reader)
data.split(n_folds=5)
svd = SVD()
# print(cross_validate(svd, data, measures=['RMSE', 'MAE'], cv=5, verbose=True))
trainset = data.build_full_trainset()
svd.fit(trainset)
def recColl(userid, movieid, gt=None):
return svd.predict(userid, movieid, gt)
# print(recColl(1,862,3))
sim_options = {'name': 'pearson',
'user_based': True
}
trainset, testset = train_test_split(data, test_size=0.1)
algo = KNNWithMeans(k=34, sim_options=sim_options)
algo.fit(trainset)
predictions1 = algo.test(testset)
algo = NMF(n_factors=16)
algo.fit(trainset)
predictions2 = algo.test(testset)
algo = SVD(n_factors=14)
algo.fit(trainset)
predictions3 = algo.test(testset)
y_true = []
y_estimate1 = []
y_estimate2 = []
y_estimate3 = []
for row in predictions1:
if row[2] >= threshold:
y_true.append(1)
else:
y_true.append(0)
for row in predictions1:
algo.fit(trainset)
# print testset
predictions = algo.test(testset)
Prec, Reca = metrics(predictions, t)
pr = pr + Prec
re = re + Reca
return pr / 10.0, re / 10.0
if __name__ == '__main__':
data = retrieve_data()
G_max = ret_mod_user_dict(data)
algo_NMF = NMF(NMF_no_of_LF, verbose=False)
algo_SVD = SVD(n_factors=MF_no_of_LF)
algo_KNN = KNNWithMeans(k=KNN_no_of_LF,
sim_options=sim_options,
verbose=False)
# Q36
Pr1 = []
Re1 = []
t = list(range(1, 26))
for l in t:
Precision, Recall = cross_val_(data, G_max, l, algo_KNN)
Pr1.append(Precision)
Re1.append(Recall)
plotgraphs(t, Pr1, "Number of Suggestions", "Precision",
"Precision Curve for KNN")
