def fit(self, trainSamples, trainTargets):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
data = np.array(self.dataModel.getData().todense())
u, s, v = isvd(data)
new_data = np.dot(u, np.dot(s, v))
new_data[new_data < 1] = np.nan
u, s, v = isvd(new_data)
new_data = np.dot(u, np.dot(s, v))
#new_data[new_data < 1] = 0
self.mf_rate = new_data
train_data = pd.DataFrame(trainSamples,
columns=['user', 'item', 'price'])
item_price = dict(
zip(train_data.ix[:, 'item'], train_data.ix[:, 'price']))
data = train_data.groupby('user').mean()
self.personal_item_price = np.empty(
(self.dataModel.getUsersNum(), self.dataModel.getItemsNum()))
for user_ix in xrange(self.dataModel.getUsersNum()):
user_avg_price = data.loc[self.dataModel.getUserByUid(user_ix),
'price']
for item_ix in xrange(self.dataModel.getItemsNum()):
delta_item_price = (
item_price[self.dataModel.getItemByIid(item_ix)] -
user_avg_price) / user_avg_price
self.personal_item_price[user_ix][item_ix] = item_price[
self.dataModel.getItemByIid(item_ix)]
b = {'phones': train_data}
price_df = Construction.get_user_category_buy_price(b)
self.param_mu, self.param_sigm = MyGaussian.gaussian_curve_fit(
price_df)
self.alpha = np.random.rand(self.dataModel.getUsersNum())
self.beta = np.random.rand(self.dataModel.getUsersNum())
self.gamma = np.zeros(self.dataModel.getUsersNum())
origin_lambda_iter = self.lambda_iter
for user_ix in xrange(self.dataModel.getUsersNum()):
samples = self.sample(user_ix, self.max_iter)
self.lambda_iter = origin_lambda_iter
old_target_value = 0
for item_1, item_2 in samples:
new_alpha, new_beta = self.update(user_ix, item_1, item_2)
##if not old_target_value or old_target_value < target_value:
#old_target_value = target_value
self.alpha[user_ix] = new_alpha
self.beta[user_ix] = new_beta
self.lambda_iter = self.lambda_iter * 0.9
#else:
#break
#print user_ix, target_value
#self.gamma[user_ix] = new_gamma
#print user_ix, self.target_value(user_ix)
#print user_ix, self.target_value(user_ix)
self.lambda_iter = origin_lambda_iter
self.beta = np.zeros(self.dataModel.getUsersNum())
def construct_price_feature(df, dataModel):
#category_df = {'phones':df}
price_df = get_user_category_buy_price(df, dataModel)
param_mu, param_sigm = MyGaussian.gaussian_curve_fit(price_df)
result = {}
for user, user_df in df.groupby('user'):
user_sigm = np.sqrt(param_sigm[dataModel.getUidByUser(user)])
origin_user_price_feature = np.zeros((dataModel.getPriceIxNum(), dataModel.getFeaturesNum()))
user_df.apply((lambda x : _construct_mention_feature_apply(dataModel, origin_user_price_feature, x, user_sigm)), axis=1)
result[dataModel.getUidByUser(user)] = origin_user_price_feature
return result
def fit(self, trainSamples, trainTargets):
self.dataModel = MemeryDataModel(trainSamples, trainTargets)
data = np.array(self.dataModel.getData().todense())
u,s,v = isvd(data)
new_data = np.dot(u, np.dot(s, v))
new_data[new_data < 1] = np.nan
u,s,v = isvd(new_data)
new_data = np.dot(u, np.dot(s, v))
#new_data[new_data < 1] = 0
self.mf_rate = new_data
train_data = pd.DataFrame(trainSamples, columns=['user', 'item', 'price'])
item_price = dict(zip(train_data.ix[:,'item'], train_data.ix[:,'price']))
data = train_data.groupby('user').mean()
self.personal_item_price = np.empty((self.dataModel.getUsersNum(), self.dataModel.getItemsNum()))
for user_ix in xrange(self.dataModel.getUsersNum()):
user_avg_price = data.loc[self.dataModel.getUserByUid(user_ix), 'price']
for item_ix in xrange(self.dataModel.getItemsNum()):
delta_item_price = (item_price[self.dataModel.getItemByIid(item_ix)] - user_avg_price) / user_avg_price
self.personal_item_price[user_ix][item_ix] = item_price[self.dataModel.getItemByIid(item_ix)]
b = {'phones':train_data}
price_df = Construction.get_user_category_buy_price(b)
self.param_mu, self.param_sigm = MyGaussian.gaussian_curve_fit(price_df)
self.alpha = np.random.rand(self.dataModel.getUsersNum())
self.beta = np.random.rand(self.dataModel.getUsersNum())
self.gamma = np.zeros(self.dataModel.getUsersNum())
origin_lambda_iter = self.lambda_iter
for user_ix in xrange(self.dataModel.getUsersNum()):
samples = self.sample(user_ix, self.max_iter)
self.lambda_iter = origin_lambda_iter
old_target_value = 0
for item_1, item_2 in samples:
new_alpha, new_beta = self.update(user_ix, item_1, item_2)
##if not old_target_value or old_target_value < target_value:
#old_target_value = target_value
self.alpha[user_ix] = new_alpha
self.beta[user_ix] = new_beta
self.lambda_iter = self.lambda_iter * 0.9
#else:
#break
#print user_ix, target_value
#self.gamma[user_ix] = new_gamma
#print user_ix, self.target_value(user_ix)
#print user_ix, self.target_value(user_ix)
self.lambda_iter = origin_lambda_iter
self.beta = np.zeros(self.dataModel.getUsersNum())
def construct_price_feature(df, dataModel):
#category_df = {'phones':df}
price_df = get_user_category_buy_price(df, dataModel)
param_mu, param_sigm = MyGaussian.gaussian_curve_fit(price_df)
result = {}
for user, user_df in df.groupby('user'):
user_sigm = np.sqrt(param_sigm[dataModel.getUidByUser(user)])
origin_user_price_feature = np.zeros(
(dataModel.getPriceIxNum(), dataModel.getFeaturesNum()))
user_df.apply((lambda x: _construct_mention_feature_apply(
dataModel, origin_user_price_feature, x, user_sigm)),
axis=1)
result[dataModel.getUidByUser(user)] = origin_user_price_feature
return result
def main():
a = pd.read_csv('../../../dataset/workplace/filter_phones_format.csv')
b = {'phones': a}
price_df = Construction.get_user_category_buy_price(b)
param_mu, param_sigm = MyGaussian.gaussian_curve_fit(price_df)
print min(param_sigm['phones']), max(param_sigm['phones'])
def main():
a = pd.read_csv('../../../dataset/workplace/filter_phones_format.csv')
b = {'phones':a}
price_df = Construction.get_user_category_buy_price(b)
param_mu, param_sigm = MyGaussian.gaussian_curve_fit(price_df)
print min(param_sigm['phones']), max(param_sigm['phones'])
