def test_build_features():
users, items = 10, 100
dataset = Dataset(user_identity_features=False, item_identity_features=False)
dataset.fit(
range(users),
range(items),
["user:{}".format(x) for x in range(users)],
["item:{}".format(x) for x in range(items)],
)
# Build from lists
user_features = dataset.build_user_features(
[
(user_id, ["user:{}".format(x) for x in range(users)])
for user_id in range(users)
]
)
assert user_features.getnnz() == users ** 2
item_features = dataset.build_item_features(
[
(item_id, ["item:{}".format(x) for x in range(items)])
for item_id in range(items)
]
)
assert item_features.getnnz() == items ** 2
# Build from dicts
user_features = dataset.build_user_features(
[
(user_id, {"user:{}".format(x): float(x) for x in range(users)})
for user_id in range(users)
],
normalize=False,
)
assert np.all(user_features.todense() == np.array([list(range(users))] * users))
item_features = dataset.build_item_features(
[
(item_id, {"item:{}".format(x): float(x) for x in range(items)})
for item_id in range(items)
],
normalize=False,
)
assert np.all(item_features.todense() == np.array([list(range(items))] * items))
# Test normalization
item_features = dataset.build_item_features(
[
(item_id, {"item:{}".format(x): float(x) for x in range(items)})
for item_id in range(items)
]
)
assert np.all(item_features.sum(1) == 1.0)
def test_build_features():
users, items = 10, 100
dataset = Dataset(user_identity_features=False, item_identity_features=False)
dataset.fit(
range(users),
range(items),
["user:{}".format(x) for x in range(users)],
["item:{}".format(x) for x in range(items)],
)
# Build from lists
user_features = dataset.build_user_features(
[(user_id, ["user:{}".format(x) for x in range(users)]) for user_id in range(users)]
)
assert user_features.getnnz() == users ** 2
item_features = dataset.build_item_features(
[(item_id, ["item:{}".format(x) for x in range(items)]) for item_id in range(items)]
)
assert item_features.getnnz() == items ** 2
# Build from dicts
user_features = dataset.build_user_features(
[
(user_id, {"user:{}".format(x): float(x) for x in range(users)})
for user_id in range(users)
],
normalize=False,
)
assert np.all(user_features.todense() == np.array([list(range(users))] * users))
item_features = dataset.build_item_features(
[
(item_id, {"item:{}".format(x): float(x) for x in range(items)})
for item_id in range(items)
],
normalize=False,
)
assert np.all(item_features.todense() == np.array([list(range(items))] * items))
# Test normalization
item_features = dataset.build_item_features(
[
(item_id, {"item:{}".format(x): float(x) for x in range(items)})
for item_id in range(items)
]
)
assert np.all(item_features.sum(1) == 1.0)
def interactions(df):
movie_genre = [x.split("|") for x in df["genre"]]
all_movie_genre = sorted(
list(set(itertools.chain.from_iterable(movie_genre))))
all_occupations = sorted(list(set(df["occupation"])))
dataset = Dataset()
dataset.fit(
df["userID"],
df["itemID"],
item_features=all_movie_genre,
user_features=all_occupations,
)
item_features = dataset.build_item_features(
(x, y) for x, y in zip(df.itemID, movie_genre))
user_features = dataset.build_user_features(
(x, [y]) for x, y in zip(df.userID, df["occupation"]))
(interactions, _) = dataset.build_interactions(df.iloc[:, 0:3].values)
train_interactions, test_interactions = cross_validation.random_train_test_split(
interactions,
test_percentage=TEST_PERCENTAGE,
random_state=np.random.RandomState(SEEDNO),
)
return train_interactions, test_interactions, item_features, user_features
def prepareData(df, tags):
df = df[df.actionCategory == "WebNei clicked"]
actionByUsers = df.groupby(["userName", "actionName"]).size()
uniqueUsers = df[df.userName.isin(
actionByUsers.index.get_level_values(
0).unique().values)].drop_duplicates('userName')
uniqueUsers['user_features'] = uniqueUsers[[
'title', 'team', 'organization', 'department'
]].values.tolist()
dataset = Dataset()
dataset.fit((list(actionByUsers.index.get_level_values(0))),
(list(actionByUsers.index.get_level_values(1))))
rowM, colM = prepareJson(tags)
rowU, colU = prepareUserFeatures(uniqueUsers)
dataset.fit_partial(items=rowM,
item_features=colM,
users=rowU,
user_features=colU)
(interactions, weights) = dataset.build_interactions(
zip(list(actionByUsers.index.get_level_values(0)),
list(actionByUsers.index.get_level_values(1))))
item_features = dataset.build_item_features(zip(rowM, [colM]))
user_features = dataset.build_user_features(zip(rowU, [colU]))
return interactions, item_features, user_features
def create_dataset(df, item_features, list_item_features):
"""
function to create the dataset based on df which stores all the data including
features (tags) of each products
Args: df(pandas dataframe) -
"""
## create a mapping between the user and item ids from our input data
#to indices that will be used internally by the model
dataset = Dataset(item_identity_features=True)
list_user_names = list(df.index)
list_items = df.columns.values
dataset.fit(
(user_name for user_name in list_user_names),
(item for item in list_items),
item_features=(item_feature for item_feature in list_item_features))
## Build the interaction matrix
# it encodes the interactions betwee users and items.
# need (user, item) pair that has 1's in df
list_pairs = list(df.stack().index)
(interactions, weights) = dataset.build_interactions(
(pair for pair in list_pairs))
item_feature_matrix = dataset.build_item_features(item_features)
return dataset, interactions, weights, item_feature_matrix
class DataFit:
def __init__(self):
self.dataset = None
def fit(self):
book_list = DataPrep.get_book_list()
book_feature_list = DataPrep.get_feature_list()
user_list = DataPrep.get_user_list()
self.dataset = Dataset()
self.dataset.fit(users=user_list,
items=book_list,
item_features=book_feature_list)
rating_list = DataPrep.get_rating_list()
interactions, weights = self.dataset.build_interactions(rating_list)
book_features = DataPrep.create_features()
books_features = self.dataset.build_item_features(book_features)
return interactions, weights, books_features
def create_new_interactions(self, checkpoint):
rating_list = DataPrep.get_rating_list_from_checkpoint(checkpoint)
interactions, weights = self.dataset.build_interactions(rating_list)
return interactions, weights
def get_user_mapping(self):
user_id_map, user_feature_map, item_id_map, item_feature_map = self.dataset.mapping(
)
return user_id_map
def get_book_mapping(self):
user_id_map, user_feature_map, item_id_map, item_feature_map = self.dataset.mapping(
)
return item_id_map
@staticmethod
def fit_evaluate(test_percentage=0.1):
book_list = DataPrep.get_book_list()
book_feature_list = DataPrep.get_feature_list()
user_list = DataPrep.get_user_list()
dataset = Dataset()
dataset.fit(users=user_list,
items=book_list,
item_features=book_feature_list)
rating_list = DataPrep.get_rating_list()
random.shuffle(rating_list)
rating_list_test = rating_list[:int(test_percentage *
len(rating_list))]
rating_list_train = rating_list[int(test_percentage *
len(rating_list)):]
interactions_train, weights_train = dataset.build_interactions(
rating_list_train)
interactions_test, weights_test = dataset.build_interactions(
rating_list_test)
return interactions_train, weights_train, interactions_test, weights_test
def obtener_matrices(self):
"""
Método obtener_matrices. Obtiene las matrices necesarias para la creación de los modelos de LightFM.
Este método solo se utiliza en la interfaz de texto.
"""
global train, test, modelo, item_features, user_features
# Se obtienen los dataframes
Entrada.obtener_datos()
ratings_df = Entrada.ratings_df
users_df = Entrada.users_df
items_df = Entrada.items_df
# Se transforman los dataframes en matrices que puedan ser utilzadas por los modelos
dataset = Dataset()
dataset.fit(users_df[users_df.columns.values[0]],
items_df[items_df.columns.values[0]],
user_features=users_df[users_df.columns.values[1]],
item_features=items_df[items_df.columns.values[1]])
# Si el modelo es colaborativo o híbrido se tienen en cuenta las valoraciones de los usuarios
if self.opcion_modelo == 1 or self.opcion_modelo == 2:
(interacciones, pesos) = dataset.build_interactions(
(row[ratings_df.columns.values[0]],
row[ratings_df.columns.values[1]],
row[ratings_df.columns.values[2]])
for index, row in ratings_df.iterrows())
else:
(interacciones, pesos) = dataset.build_interactions(
(row[ratings_df.columns.values[0]],
row[ratings_df.columns.values[1]])
for index, row in ratings_df.iterrows())
# Se obtienen las matrices de features y se guardan
item_features = dataset.build_item_features(
(row[items_df.columns.values[0]],
[row[items_df.columns.values[1]]])
for index, row in items_df.iterrows())
user_features = dataset.build_user_features(
(row[users_df.columns.values[0]],
[row[users_df.columns.values[1]]])
for index, row in users_df.iterrows())
print("Guarda la matriz de item features")
guardar_datos_pickle(item_features, 'la matriz de item features')
print("Guarda la matriz de user features")
guardar_datos_pickle(user_features, 'la matriz de user feautures')
# Se dividen las interacciones en conjuntos de entrenamiento y test y se guardan
train, test = random_train_test_split(interacciones,
test_percentage=0.2)
print("Guarda la matriz de entrenamiento")
guardar_datos_pickle(train, 'la matriz de entrenamiento')
print("Guarda la matriz de test")
guardar_datos_pickle(test, 'la matriz de test')
def test_fitting():
users, items = 10, 100
dataset = Dataset()
dataset.fit(range(users), range(items))
assert dataset.interactions_shape() == (users, items)
assert dataset.user_features_shape() == (users, users)
assert dataset.item_features_shape() == (items, items)
assert dataset.build_interactions([])[0].shape == (users, items)
assert dataset.build_user_features([]).getnnz() == users
assert dataset.build_item_features([]).getnnz() == items
def test_fitting_no_identity():
users, items = 10, 100
dataset = Dataset(user_identity_features=False, item_identity_features=False)
dataset.fit(range(users), range(items))
assert dataset.interactions_shape() == (users, items)
assert dataset.user_features_shape() == (users, 0)
assert dataset.item_features_shape() == (items, 0)
assert dataset.build_interactions([])[0].shape == (users, items)
assert dataset.build_user_features([], normalize=False).getnnz() == 0
assert dataset.build_item_features([], normalize=False).getnnz() == 0
def test_fitting():
users, items = 10, 100
dataset = Dataset()
dataset.fit(range(users), range(items))
assert dataset.interactions_shape() == (users, items)
assert dataset.user_features_shape() == (users, users)
assert dataset.item_features_shape() == (items, items)
assert dataset.build_interactions([])[0].shape == (users, items)
assert dataset.build_user_features([]).getnnz() == users
assert dataset.build_item_features([]).getnnz() == items
def test_fitting_no_identity():
users, items = 10, 100
dataset = Dataset(user_identity_features=False, item_identity_features=False)
dataset.fit(range(users), range(items))
assert dataset.interactions_shape() == (users, items)
assert dataset.user_features_shape() == (users, 0)
assert dataset.item_features_shape() == (items, 0)
assert dataset.build_interactions([])[0].shape == (users, items)
assert dataset.build_user_features([], normalize=False).getnnz() == 0
assert dataset.build_item_features([], normalize=False).getnnz() == 0
def build_lightfm_dataset(self) -> None:
"""
Builds final datasets for user-variant and variant-variant recommendations.
"""
logging.info("Creating LightFM matrices...")
lightfm_dataset = LFMDataset()
ratings_list = self.interaction_list
logging.info('#'*60)
lightfm_dataset.fit_partial(
(rating['user_id'] for rating in ratings_list),
(rating['product_id'] for rating in ratings_list)
)
item_feature_names = self.item_df.columns
logging.info(f'Logging item_feature_names - with product_id: \n{item_feature_names}')
item_feature_names = item_feature_names[~item_feature_names.isin(['product_id'])]
logging.info(f'Logging item_feature_names - without product_id: \n{item_feature_names}')
for item_feature_name in item_feature_names:
lightfm_dataset.fit_partial(
items=(item['product_id'] for item in self.item_list),
item_features=((item[item_feature_name] for item in self.item_list)),
)
item_features_data = []
for item in self.item_list:
item_features_data.append(
(
item['product_id'],
[
item['product_name'],
item['aisle'],
item['department']
],
)
)
logging.info(f'Logging item_features_data @build_lightfm_dataset: \n{item_features_data}')
self.item_features = lightfm_dataset.build_item_features(item_features_data)
self.interactions, self.weights = lightfm_dataset.build_interactions(
((rating['user_id'], rating['product_id']) for rating in ratings_list)
)
self.n_users, self.n_items = self.interactions.shape
logging.info(f'Logging self.interactions @build_lightfm_dataset: \n{self.interactions}')
logging.info(f'Logging self.weights @build_lightfm_dataset: \n{self.weights}')
logging.info(
f'The shape of self.interactions {self.interactions.shape} '
f'and self.weights {self.weights.shape} represent the user-item matrix.')
def fit_data(self, matrix, user_features=None, item_features=None):
"""
Create datasets for .fit() method.
Args:
matrix: User-item interactions matrix (weighted)
user_features: User-features pandas dataframe which index contains user_ids (crd_no)
item_features: Item-features pandas dataframe which index contains good_ids (plu_id)
Returns:
Model with fitted (mapped) datasets
"""
matrix.sort_index(inplace=True)
matrix.sort_index(inplace=True, axis=1)
dataset = Dataset()
dataset.fit((x for x in matrix.index), (x for x in matrix.columns))
interactions = pd.melt(
matrix.replace(0, np.nan).reset_index(),
id_vars='index',
value_vars=list(matrix.columns[1:]),
var_name='plu_id',
value_name='rating').dropna().sort_values('index')
interactions.columns = ['crd_no', 'plu_id', 'rating']
self.interactions, self.weights = dataset.build_interactions(
[tuple(x) for x in interactions.values])
if user_features is not None:
user_features.sort_index(inplace=True)
dataset.fit_partial(users=user_features.index,
user_features=user_features)
self.user_features = dataset.build_user_features(
((index, dict(row))
for index, row in user_features.iterrows()))
else:
self.user_features = None
if item_features is not None:
item_features.sort_index(inplace=True)
dataset.fit_partial(items=item_features.index,
item_features=item_features)
self.item_features = dataset.build_item_features(
((index, dict(row))
for index, row in item_features.iterrows()))
else:
self.item_features = None
def load_parameter():
ratings = get_ratings()
books = get_books()
users = get_users()
books_pd = convert_pd(books)
id_users_books = StoreValue()
for x in ratings:
id_users_books._user_id.append(x[0])
id_users_books._book_id.append(x[1])
# Được tạo ra theo hướng dẫn tại https://making.lyst.com/lightfm/docs/examples/dataset.html
dataset_explicit = Dataset()
dataset_explicit.fit(id_users_books._user_id,
id_users_books._book_id)
num_users, num_items = dataset_explicit.interactions_shape()
print('Num users: {}, num_items {}.'.format(num_users, num_items))
dataset_explicit.fit_partial(items=(x[0] for x in books),
item_features=(x[7] for x in books))
dataset_explicit.fit_partial(users=(x[0] for x in users))
# create ---> mapping
# interactions: dưới dạng COO_maxtrix, các tương tác sẽ là user_id và book_id
# Trọng số voting
(interactions_explicit, weights_explicit) = dataset_explicit.build_interactions((id_users_books._user_id[i], id_users_books._book_id[i]) for i in range(len(ratings)))
# Đây là đặc trưng trích xuất từ các items (sách) dựa trên tác giả của cuốn sách được cung cấp
item_features = dataset_explicit.build_item_features(((x[0], [x[7]]) for x in books))
# user_features = dataset_explicit.build_user_features(((x[0], [x[1]]) for x in users))
model_explicit_ratings = LightFM_ext(loss='warp')
(train, test) = random_train_test_split(interactions=interactions_explicit, test_percentage=0.02)
model_explicit_ratings.fit(train, item_features=item_features, epochs=2, num_threads=4)
return model_explicit_ratings, dataset_explicit, interactions_explicit, weights_explicit, item_features, books_pd
def create_datasets(cluster_id):
events_list = get_events_from_es(cluster_id)
dataframe_interactions, dataframe_users_features, dataframe_item_features, user_tuple, item_tuple = create_interactions_and_features(events_list, cluster_id)
print(dataframe_interactions, cluster_id, file=sys.stderr)
print(dataframe_users_features, cluster_id, file=sys.stderr)
print(dataframe_item_features, cluster_id, file=sys.stderr)
#print(user_tuple)
# print(item_tuple)
user_features = format_users_features(dataframe_users_features)
#print(user_features)
item_features = format_items_features(dataframe_item_features)
#print(item_features)
dataset = Dataset()
dataset.fit(
dataframe_interactions['user'].unique(), # all the users
dataframe_interactions['item'].unique(), # all the items
user_features = user_features,
item_features = item_features
)
(interactions, weights) = dataset.build_interactions([(x[0], x[1], x[2]) for x in dataframe_interactions.values ])
# print(interactions)
# print(weights)
final_user_features = dataset.build_user_features(user_tuple, normalize= False)
final_item_features = dataset.build_item_features(item_tuple, normalize= False)
return dataset, interactions, weights, final_item_features, final_user_features
def predict(user_id: int) -> str:
model_file = Path(BASE_DIR).joinpath(MODEL_FILE_NAME)
data_file = Path(BASE_DIR).joinpath(DATA_FILE_NAME)
if not model_file.exists():
return None
if not data_file.exists():
return None
model: LightFM = pickle.load(open(model_file, "rb"))
data: pd.DataFrame = pd.read_csv(data_file)
dataset = Dataset()
dataset.fit((cac for cac in data.cac.unique()),
(product for product in data.product_code.unique()))
features = ['product_code', 'country_code', 'cost_bin']
for product_feature in features:
dataset.fit_partial(
users=(cac for cac in data.cac.unique()),
items=(product for product in data.product_code.unique()),
item_features=(feature
for feature in data[product_feature].unique()))
item_features = dataset.build_item_features(((getattr(row, 'product_code'), [getattr(row, product_feature) for product_feature in features if product_feature != 'product_code']) \
for row in data[features].itertuples()))
predicted_products: List[str] = sample_recommendation(
model=model,
dataset=dataset,
raw_data=data,
item_features=item_features,
user_ids=user_id)
return predicted_products
def train_model(
df, user_id_col='user_id', item_id_col='business_id',
item_name_col='name_business', evaluate=True):
""" Train the model using collaborative filtering.
Args:
df: the input dataframe.
user_id_col: user id column.
item_id_col: item id column.
item_name_col: item name column.
evaluate: if evaluate the model performance.
Returns:
model_full: the trained model.
df_interactions: dataframe with user-item interactions.
user_dict: user dictionary containing user_id as key and
interaction_index as value.
item_dict: item dictionary containing item_id as key and
item_name as value.
user_feature_map: the feature map of users
business_feature_map: the feature map of items
"""
if evaluate:
print('Evaluating model...')
evaluate_model(df, user_id_col='user_id', item_id_col='business_id')
print('Training model...')
# build recommendations for known users and known businesses
# with collaborative filtering method
ds_full = Dataset()
# we call fit to supply userid, item id and user/item features
user_cols = ['user_id', 'average_stars']
categories = [c for c in df.columns if c[0].isupper()]
item_cols = ['business_id', 'state']
for i in df.columns[10:]:
item_cols.append(str(i))
user_features = user_cols[1:]
item_features = item_cols[2:]
ds_full.fit(
df[user_id_col].unique(), # all the users
df[item_id_col].unique(), # all the items
user_features=user_features, # additional user features
item_features=item_features
)
df_users = df.drop_duplicates(user_id_col)
# df_users = df[df.duplicated(user_id_col) == False]
users_features = []
for i in range(len(df_users)):
users_features.append(get_users_features_tuple(df_users.values[i]))
users_features = ds_full.build_user_features(
users_features, normalize=False)
items = df.drop_duplicates(item_id_col)
# items = df[df.duplicated(item_id_col) == False]
items_features = []
for i in range(len(items)):
items_features.append(get_items_features_tuple(
items.values[i], categories))
items_features = ds_full.build_item_features(
items_features, normalize=False)
(interactions, weights) = ds_full.build_interactions(
[(x[0], x[1], x[2]) for x in df.values])
# model
model_full = LightFM(
no_components=100, learning_rate=0.05, loss='warp', max_sampled=50)
model_full.fit(
interactions, user_features=users_features,
item_features=items_features, sample_weight=weights,
epochs=10, num_threads=10)
# mapping
user_id_map, user_feature_map, business_id_map, business_feature_map = \
ds_full.mapping()
# data preparation
df_interactions = pd.DataFrame(weights.todense())
df_interactions.index = list(user_id_map.keys())
df_interactions.columns = list(business_id_map.keys())
user_dict = user_id_map
item_dict = df.set_index(item_id_col)[item_name_col].to_dict()
return model_full, df_interactions, user_dict, \
item_dict, user_feature_map, business_feature_map
def lambda_handler(event, context):
try:
## Fetch data from RDS code
connection = pymysql.connect(
host='fitbookdb.crm91a2epcbi.us-east-1.rds.amazonaws.com',
user='******',
passwd='postgres',
db='fitbookdb',
cursorclass=pymysql.cursors.DictCursor)
print("Connection successful")
except:
print("Connection error")
# In[3]:
#Get Food DataFrame
dict_list = []
with connection.cursor() as cur:
cur.execute("select * from food_dataset")
for row in cur:
dict_list.append(row)
food_rds_df = pd.DataFrame(dict_list)
food_df = food_rds_df.copy()
food_df.drop([
'Portion_Default', 'Portion_Amount', 'Factor', 'Increment',
'Multiplier', 'Portion_Display_Name', 'Food_Code', 'Display_Name'
],
axis=1,
inplace=True)
# food_df.head()
print('Food Dataframe imported')
# In[4]:
# # TODO: Perform Binning
# food_30_bins = ['Alcohol', 'Calories', 'Saturated_Fats']
# for each_column in food_30_bins:
# bins = np.linspace(food_df[each_column].min(), food_df[each_column].max(), 30)
# food_df[each_column+'bin'] = pd.cut(food_df[each_column], bins, labels=np.arange(0,len(bins)-1))
# food_df
# In[5]:
# for each_column in food_30_bins:
# print(food_df[each_column].min())
# In[6]:
#Get User Dataframe
# user_df = pd.read_csv('user_db_try.csv')
# user_df.head()
dict_list = []
with connection.cursor() as cur:
cur.execute("select * from tblUserData")
for row in cur:
dict_list.append(row)
user_rds_df = pd.DataFrame(dict_list)
user_df = user_rds_df.copy()
user_df.drop([
'cognitoAccessToken', 'cognitoIDToken', 'cognitoRefreshToken',
'fitbitAccessToken', 'fitbitUserID', 'userName'
],
axis=1,
inplace=True)
# user_df.head()
print('User Dataframe imported')
# In[7]:
#Get userItem DataFrame
# userItem_df = pd.read_csv('userItem_db_try_new.csv')
# userItem_df.head()
dict_list = []
with connection.cursor() as cur:
cur.execute("select * from tblUserRating")
for row in cur:
dict_list.append(row)
userItem_rds_df = pd.DataFrame(dict_list)
userItem_df = userItem_rds_df.copy()
# userItem_df.head()
print('UserItem Dataframe imported')
# In[8]:
#Make all the feature values unique
for column_name in food_df.columns:
if column_name != 'food_ID':
food_df[column_name] = str(
column_name) + ":" + food_df[column_name].astype(str)
# food_df.head()
# In[9]:
#This Dict will be useful while creating tupples
food_features_df = food_df.drop(['food_ID'], axis=1).copy()
food_features_dict = food_features_df.to_dict('split')
# food_features_dict
# In[10]:
food_feature_values = []
for column_name in food_features_df.columns:
food_feature_values.extend(food_features_df[column_name].unique())
# food_feature_values
# In[11]:
for column_name in user_df.columns:
if column_name != 'userID':
user_df[column_name] = str(
column_name) + ":" + user_df[column_name].astype(str)
user_features_df = user_df.drop(['userID'], axis=1).copy()
user_features_dict = user_features_df.to_dict('split')
# user_features_dict
# In[12]:
user_feature_values = []
for column_name in user_features_df.columns:
user_feature_values.extend(user_features_df[column_name].unique())
# user_feature_values
# In[13]:
user_tuples = []
food_tuples = []
for index, row in user_df.iterrows():
user_tuples.append((row['userID'], user_features_dict['data'][index]))
for index, row in food_df.iterrows():
food_tuples.append((row['food_ID'], food_features_dict['data'][index]))
# food_tuples
# In[14]:
print("Creating LightFm dataset")
dataset = Dataset()
dataset.fit(users=(user_id for user_id in user_df['userID']),
items=(food_id for food_id in food_df['food_ID']))
print("Dataset Created")
# In[15]:
num_users, num_items = dataset.interactions_shape()
print('Num users: {}, num_items {}.'.format(num_users, num_items))
# In[16]:
# dataset.fit_partial(items=(food_id for food_id in food_df['Food_Code']),
# item_features=((each_feature for each_feature in food_features)for food_features in food_features_dict['data']))
# In[17]:
# dataset.fit_partial(items=(food_id for food_id in food_df['Food_Code']),
# item_features=((row['Milk'], row['Meats'], row['Alcohol'], row['Calories'])for index,row in food_df.iterrows()))
# In[18]:
print("fittng item partial features")
dataset.fit_partial(items=(food_id for food_id in food_df['food_ID']),
item_features=(each_value
for each_value in food_feature_values))
# In[19]:
# dataset.fit_partial(users=(user_id for user_id in user_df['Id']),
# user_features=((each_feature for each_feature in user_features)for user_features in user_features_dict['data']))
# In[20]:
print("fittng user partial features")
dataset.fit_partial(users=(user_id for user_id in user_df['userID']),
user_features=(each_value
for each_value in user_feature_values))
# In[21]:
# dataset.item_features_shape()
# dataset.user_features_shape()
# In[22]:
print("Building Interactions")
(interactions, weights) = dataset.build_interactions(
((x['userID'], x['food_ID'], x['rating'])
for y, x in userItem_df.iterrows()))
# print(repr(interactions))
# print(weights)
# In[23]:
# interactions.shape
# In[24]:
print("Building item features")
item_features = dataset.build_item_features(each_tuple
for each_tuple in food_tuples)
# print(item_features)
# In[25]:
user_features = dataset.build_user_features(each_tuple
for each_tuple in user_tuples)
# print(user_features)
# In[26]:
print("Fitting Model")
model = LightFM(loss='warp')
model.fit(interactions,
item_features=item_features,
user_features=user_features)
print("Model trained!!")
print("Pickle started!!")
pickle.dump(model, open("/tmp/model.pkl", 'wb'), protocol=2)
bucketName = "fitbook-lambda-packages"
Key = "/tmp/model.pkl"
outPutname = "model.pkl"
print("Uploading to S3")
s3 = boto3.client('s3')
s3.upload_file(Key, bucketName, outPutname)
print("Upload done")
os.remove("/tmp/model.pkl")
print("Pickle file deleted")
print("Successssss!!!!!")
def evaluate_model(
df, user_id_col='user_id',
item_id_col='business_id', stratify=None):
""" Model evaluation.
Args:
df: the input dataframe.
user_id_col: user id column.
item_id_col: item id column.
stratify: if use stratification.
No return value
"""
# create test and train datasets
print('model evaluation')
train, test = train_test_split(df, test_size=0.2, stratify=stratify)
ds = Dataset()
# we call fit to supply userid, item id and user/item features
user_cols = ['user_id', 'average_stars']
categories = [c for c in df.columns if c[0].isupper()]
item_cols = ['business_id', 'state']
for i in df.columns[10:]:
item_cols.append(str(i))
user_features = user_cols[1:]
item_features = item_cols[2:]
ds.fit(
df[user_id_col].unique(), # all the users
df[item_id_col].unique(), # all the items
user_features=user_features, # additional user features
item_features=item_features
)
train_users = train.drop_duplicates('user_id')
# train_users = train[train.duplicated('user_id') == False]
train_user_features = []
for i in range(len(train_users)):
train_user_features.append(get_users_features_tuple(
train_users.values[i]))
train_user_features = ds.build_user_features(
train_user_features, normalize=False)
test_users = test.drop_duplicates('user_id')
# test_users = test[test.duplicated('user_id') == False]
test_user1_features = []
for i in range(len(test_users)):
test_user1_features.append(get_users_features_tuple(
test_users.values[i]))
test_user_features = ds.build_user_features(
test_user1_features, normalize=False)
train_items = train.drop_duplicates('business_id')
# train_items = train[train.duplicated('business_id') == False]
train_item1_features = []
for i in range(len(train_items)):
train_item1_features.append(get_items_features_tuple(
train_items.values[i], categories))
train_item_features = ds.build_item_features(
train_item1_features, normalize=False)
test_items = test.drop_duplicates('business_id')
# test_items = test[test.duplicated('business_id') == False]
test_item_features = []
for i in range(len(test_items)):
test_item_features.append(get_items_features_tuple(
test_items.values[i], categories))
test_item_features = ds.build_item_features(
test_item_features, normalize=False)
# plugging in the interactions and their weights
(train_interactions, train_weights) = ds.build_interactions(
[(x[0], x[1], x[2]) for x in train.values])
(test_interactions, test_weights) = ds.build_interactions(
[(x[0], x[1], x[2]) for x in test.values])
# model
model = LightFM(
no_components=100, learning_rate=0.05, loss='warp', max_sampled=50)
model.fit(
train_interactions, user_features=train_user_features,
item_features=train_item_features, sample_weight=train_weights,
epochs=10, num_threads=10)
# auc-roc
train_auc = auc_score(
model, train_interactions, user_features=train_user_features,
item_features=train_item_features, num_threads=20).mean()
print('Training set AUC: %s' % train_auc)
test_auc = auc_score(
model, test_interactions, user_features=test_user_features,
item_features=test_item_features, num_threads=20).mean()
print('Testing set AUC: %s' % test_auc)
def calc(request):
try :
stores = Store.objects.all();
reviews = Review.objects.all();
stores = pd.DataFrame(list(stores.values('id', 'store_id','store_name', 'category',
'address','latitude','longitude','average_rating')))
reviews = pd.DataFrame(list(reviews.values('id', 'storeid','userid', 'score','reg_time')))
reviews_source = [(reviews['userid'][i], reviews['storeid'][i]) for i in range(reviews.shape[0])]
item_feature_source = [(stores['store_id'][i], [ stores['category'][i],stores['address'][i],stores['latitude'][i],stores['longitude'][i], stores['average_rating'][i]] ) for i in range(stores.shape[0]) ]
dataset = Dataset()
dataset.fit(users=reviews['userid'].unique(),
items=reviews['storeid'].unique(),
item_features=stores[stores.columns[1:]].values.flatten())
interactions, weights = dataset.build_interactions(reviews_source)
item_features = dataset.build_item_features(item_feature_source)
# Split Train, Test data
train, test = random_train_test_split(interactions, test_percentage=0.1)
train, test = train.tocsr().tocoo(), test.tocsr().tocoo()
train_weights = train.multiply(weights).tocoo()
# Define Search Space
trials = Trials()
space = [hp.choice('no_components', range(10, 50, 10)), hp.uniform('learning_rate', 0.01, 0.05)]
# Define Objective Function
def objective(params):
no_components, learning_rate = params
global model
model = LightFM(no_components=no_components,
learning_schedule='adagrad',
loss='warp',
learning_rate=learning_rate,
random_state=0)
model.fit(interactions=train,
item_features=item_features,
sample_weight=train_weights,
epochs=3,
verbose=False)
test_precision = precision_at_k(model, test, k=5, item_features=item_features).mean()
print("no_comp: {}, lrn_rate: {:.5f}, precision: {:.5f}".format(
no_components, learning_rate, test_precision))
# test_auc = auc_score(model, test, item_features=item_features).mean()
output = -test_precision
if np.abs(output+1) < 0.01 or output < -1.0:
output = 0.0
return output
# max_evals가 몇번 반복실행 할껀지.
best_params = fmin(fn=objective, space=space, algo=tpe.suggest, max_evals=10, trials=trials)
# 아이템피쳐 저장
with open('./saved_models/item_features.pickle', 'wb') as fle:
pickle.dump(item_features, fle, protocol=pickle.HIGHEST_PROTOCOL)
# 모델 저장해야 됨
with open('./saved_models/model.pickle', 'wb') as fle:
pickle.dump(model, fle, protocol=pickle.HIGHEST_PROTOCOL)
item_biases, item_embeddings = model.get_item_representations(features=item_features)
# item_embeddings 저장하기
with open('./saved_models/item_embeddings.pickle', 'wb') as fle:
pickle.dump(item_embeddings, fle, protocol=pickle.HIGHEST_PROTOCOL)
return Response({'result': True})
except :
return Response({'result': False})
print('Num users : {}, num_items {}.'.format(num_users, num_items))
# add some item feature mappings, and creates a unique feature for each author
# NOTE: more item ids are fitted than usual, to make sure our mappings are complete
# even if there are items in the features dataset that are not in the interaction set
dataset.fit_partial(items=(x['ISBN'] for x in get_book_features()),
item_features=(x['Book-Author']
for x in get_book_features()))
# build the interaction matrix which is a main input to the LightFM model
# it encodes the interactions between the users and the items
(interactions, weights) = dataset.build_interactions(
((x['User-ID'], x['ISBN']) for x in get_ratings()))
# item_features matrix can also be created
item_features = dataset.build_item_features(
((x['ISBN'], [x['Book-Author']]) for x in get_book_features()))
# split the current dataset into a training and test dataset
train, test = random_train_test_split(interactions,
test_percentage=0.01,
random_state=None)
# build the model using the training dataset, notice the use of item_features as well,
# this is a hybrid model
model = LightFM(loss='warp',
item_alpha=ITEM_ALPHA,
no_components=NUM_COMPONENTS)
# train the hybrid model on the training dataset
model.fit(train, item_features=item_features, epochs=NUM_EPOCHS, num_threads=1)
def run_lightfm(ratings, train, test, k_items, dataset):
def create_interaction_matrix(df,
user_col,
item_col,
rating_col,
norm=False,
threshold=None):
'''
Function to create an interaction matrix dataframe from transactional type interactions
Required Input -
- df = Pandas DataFrame containing user-item interactions
- user_col = column name containing user's identifier
- item_col = column name containing item's identifier
- rating col = column name containing user feedback on interaction with a given item
- norm (optional) = True if a normalization of ratings is needed
- threshold (required if norm = True) = value above which the rating is favorable
Expected output -
- Pandas dataframe with user-item interactions ready to be fed in a recommendation algorithm
'''
interactions = df.groupby([user_col, item_col])[rating_col] \
.sum().unstack().reset_index(). \
fillna(0).set_index(user_col)
if norm:
interactions = interactions.applymap(lambda x: 1
if x > threshold else 0)
return interactions
test_interactions = create_interaction_matrix(df=test,
user_col='userId',
item_col='movieId',
rating_col='rating')
budget_l = dataset.budget.unique().tolist()
gross_l = dataset.gross.unique().tolist()
awards_l = dataset.awards.unique().tolist()
nom_l = dataset.nominations.unique().tolist()
votes_l = dataset.votes.unique().tolist()
item_ids = np.unique(train.movieId.astype(int))
print(f'length dataset: {len(dataset)}')
dataset = dataset[dataset.movieId.isin(item_ids)]
print(f'length dataset: {len(dataset)}')
item_features_list = [f'rating_{f}' for f in range(11)]
gen = [
'Action', 'Adventure', 'Animation', "Children's", 'Comedy', 'Crime',
'Documentary', 'Drama', 'Fantasy', 'Film-Noir', 'Horror', 'IMAX',
'Musical', 'Mystery', 'Romance', 'Sci-Fi', 'Thriller', 'War', 'Western'
] # 'unknown' add unknown for movielens100k
item_features_list += gen
item_features_list += budget_l
item_features_list += gross_l
item_features_list += awards_l
item_features_list += nom_l
item_features_list += votes_l
item_features = []
for y, x in dataset.iterrows():
genres = x['genres']
tmp_row = (int(x['movieId']), [
x['rating'], x['budget'], x['gross'], x['awards'],
x['nominations'], x['votes']
])
for g in genres:
tmp_row[1].append(g)
item_features.append(tmp_row)
#item_features = [(int(x['movieId']), [x['rating'], z, x['budget'], x['gross'], x['awards'], x['votes']]) for y, x in dataset.iterrows() for z in x['genres']] #x['nominations']
user_ids = np.unique(train.userId)
built_dif = Dataset()
built_dif.fit_partial(users=user_ids)
built_dif.fit_partial(items=item_ids)
built_dif.fit_partial(item_features=item_features_list)
dataset_item_features = built_dif.build_item_features(item_features)
(interactions, weights) = built_dif.build_interactions(
((int(x['userId']), int(x['movieId'])) for y, x in train.iterrows()))
modelx = LightFM(no_components=30, loss='bpr', k=15, random_state=1)
modelx.fit(interactions,
epochs=30,
num_threads=4,
item_features=dataset_item_features
) #item_features=dataset_item_features
test = sparse.csr_matrix(test_interactions.values)
test = test.tocoo()
num_users, num_items = built_dif.interactions_shape()
print('Num users: {}, num_items {}.'.format(num_users, num_items))
prec_list = dict()
rec_list = dict()
for num_k in k_items:
trainprecision = precision_at_k(
modelx, test, k=num_k, item_features=dataset_item_features).mean(
) #item_features=dataset_item_features,
print('Hybrid training set precision: %s' % trainprecision)
trainrecall = recall_at_k(modelx,
test,
k=num_k,
item_features=dataset_item_features).mean(
) #item_features=dataset_item_features
print('Hybrid training set recall: %s' % trainrecall)
if num_k in prec_list:
prec_list[num_k].append(trainprecision)
else:
prec_list[num_k] = trainprecision
if num_k in rec_list:
rec_list[num_k].append(trainrecall)
else:
rec_list[num_k] = trainrecall
return prec_list, rec_list
for rid, row in movies.iterrows():
for m in match_lst:
if m.lower() in row[1].lower():
matches.append(row[0])
print(good_ratings.head())
rating_iter = zip(good_ratings['userId'], good_ratings['movieId'])
new_iter = ((new_user, x) for x in matches)
interactions, weights = dataset.build_interactions(chain(
rating_iter, new_iter))
print(repr(interactions))
mov_features = ((row[0], row[2].split('|') + [row[3], row[0]])
for rid, row in movies.iterrows())
# print(mov_features[0])
item_features = dataset.build_item_features(mov_features)
model = LightFM(loss='warp',
no_components=28,
item_alpha=0.0001,
learning_rate=0.05)
model.fit(interactions, item_features=item_features, num_threads=16)
movie2name = {}
for rid, row in movies.iterrows():
movie2name[row[0]] = row[1]
n_users, n_items = dataset.interactions_shape()
# Adjust using base ratings
base_mat = model.predict(0, np.arange(n_items), num_threads=16)
base_mat = (base_mat + np.min(base_mat))
item_features=range(2048))
# Build Train Interactions
(train_interactions, weights) = train.build_interactions(
((row[0], row[1]) for index, row in df_train.iterrows()))
# Build Features
## Call build_user/item_features with iterables of (user/item id, [features]) or (user/item id, {feature: feature weight}) to build feature matrices.
print('Loading Features...')
list_features = {}
for image_index, image_feature in enumerate(features):
list_features[image_index] = []
for feature_index, feature_weight in enumerate(image_feature):
list_features[image_index].append({feature_index: feature_weight})
features_generator = ((item_id, ele) for item_id in list_features.keys()
for ele in list_features[item_id])
item_features = train.build_item_features(features_generator,
normalize=False)
print('End Loading Features.')
### LOAD
print('Load Model...')
with open(weight_directory + '_step{0}_LFM.pickle'.format(args.epoch),
'rb') as dump:
model = pickle.load(dump)
print('End Model')
# # Evaluation
print("Evaluation...")
with open(
result_directory +
'_top{0}_ep{1}_LFM.tsv'.format(args.topk, args.epoch), 'w') as out:
def main():
if request.method == 'POST':
global df_movies
# global top_trending_ids
# print(list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].title) )
print(request.form)
# Get recommendations!
if 'run-mf-model' in request.form:
for i, user_rating in enumerate(session['arr']):
session['arr'][i] = user_rating[:-2]
session['movieIds'] = session['movieIds'][:-2]
rated_movies = min(len(session['arr'][0]), len(session['movieIds']))
for i, user_rating in enumerate(session['arr']):
session['arr'][i] = user_rating[:rated_movies]
session['movieIds'] = session['movieIds'][:rated_movies]
pu = recommendation_mf(session['arr'], session['members'], session['movieIds'])
session.clear()
top_trending_ids = list(df_movies.sort_values(by="trending_score").head(200).sample(15).movie_id_ml)
session['counter'] = 0
session['members'] = 0
session['userAges'] = []
session['userGenders'] = []
session['movieIds'] = list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].movie_id_ml)
session['top15'] = list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].title)
session['top15_posters'] = list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].poster_url)
session['arr'] = None
return(render_template('main.html', settings = {'friendsInfo':False, 'showVote': False, 'people': 0, 'buttonDisable': False,'chooseRecommendation':False, 'recommendation': pu}))
if 'run-siamese-model' in request.form:
# global df
global friends
global ratings
global new_friend_id
new_ratings = []
for mid, movie_real_id in enumerate(session['movieIds']):
avg_mv_rating = np.median(np.array([user_ratings[mid] for user_ratings in session['arr']]))
new_ratings.append({'movie_id_ml':movie_real_id,
'rating': avg_mv_rating,
'friend_id': new_friend_id})
new_friend = {'friend_id': new_friend_id, 'friends_age': np.mean(np.array(session['userAges'])), 'friends_gender': np.mean(np.array(session['userGenders']))}
friends.append(new_friend)
ratings.extend(new_ratings)
dataset = LightFMDataset()
item_str_for_eval = "x['title'],x['release'], x['unknown'], x['action'], x['adventure'],x['animation'], x['childrens'], x['comedy'], x['crime'], x['documentary'], x['drama'], x['fantasy'], x['noir'], x['horror'], x['musical'],x['mystery'], x['romance'], x['scifi'], x['thriller'], x['war'], x['western'], *soup_movie_features[x['soup_id']]"
friend_str_for_eval = "x['friends_age'], x['friends_gender']"
dataset.fit(users=(int(x['friend_id']) for x in friends),
items=(int(x['movie_id_ml']) for x in movies),
item_features=(eval("("+item_str_for_eval+")") for x in movies),
user_features=((eval(friend_str_for_eval)) for x in friends))
num_friends, num_items = dataset.interactions_shape()
print(f'Num friends: {num_friends}, num_items {num_items}. {datetime.datetime.now()}')
(interactions, weights) = dataset.build_interactions(((int(x['friend_id']), int(x['movie_id_ml']))
for x in ratings))
item_features = dataset.build_item_features(((x['movie_id_ml'],
[eval("("+item_str_for_eval+")")]) for x in movies) )
user_features = dataset.build_user_features(((x['friend_id'],
[eval(friend_str_for_eval)]) for x in friends) )
print(f"Item and User features created {datetime.datetime.now()}")
epochs = 50 #150
lr = 0.015
max_sampled = 11
loss_type = "warp" # "bpr"
model = LightFM(learning_rate=lr, loss=loss_type, max_sampled=max_sampled)
model.fit_partial(interactions, epochs=epochs, user_features=user_features, item_features=item_features)
train_precision = precision_at_k(model, interactions, k=10, user_features=user_features, item_features=item_features).mean()
train_auc = auc_score(model, interactions, user_features=user_features, item_features=item_features).mean()
print(f'Precision: {train_precision}, AUC: {train_auc}, {datetime.datetime.now()}')
k = 18
top_movie_ids, scores = predict_top_k_movies(model, new_friend_id, k, num_items, user_features=user_features, item_features=item_features, use_features = False)
top_movies = df_movies[df_movies.movie_id_ml.isin(top_movie_ids)]
pu = recommendation_siamese(top_movies, scores)
return(render_template('main.html', settings = {'friendsInfo':False, 'showVote': False, 'people': 0, 'buttonDisable': False,'chooseRecommendation':False, 'recommendation': pu}))
# Collect friends info
elif 'person-select-gender-0' in request.form:
for i in range(session['members']):
session['userAges'].append(int(request.form.get(f'age-{i}')))
session['userGenders'].append(int(request.form.get(f'person-select-gender-{i}')))
return(render_template('main.html', settings = {'friendsInfo':False, 'showVote': True, 'people': session['members'], 'buttonDisable': True,'chooseRecommendation':False, 'recommendation': None}))
# Choose number of people in the group
elif 'people-select' in request.form:
count = int(request.form.get('people-select'))
session['members'] = count
session['arr'] = [[0 for x in range(15)] for y in range(count)]
return(render_template('main.html', settings = {'friendsInfo':True, 'showVote': False, 'people': count, 'buttonDisable': True,'chooseRecommendation':False, 'recommendation': None}))
# All people voting
elif 'person-select-0' in request.form:
for i in range(session['members']):
session['arr'][i][session['counter']] = int(request.form.get(f'person-select-{i}'))
session['counter'] += 1
if session['counter'] < 15:
return(render_template('main.html', settings = {'friendsInfo':False, 'showVote': True, 'people': len(request.form), 'buttonDisable': True,'chooseRecommendation':False, 'recommendation': None}))
else:
return(render_template('main.html', settings = {'friendsInfo':False, 'showVote': False, 'people': len(request.form), 'buttonDisable': True,'chooseRecommendation':True, 'recommendation': None}))
elif request.method == 'GET':
session.clear()
top_trending_ids = list(df_movies.sort_values(by="trending_score").head(200).sample(15).movie_id_ml)
print(top_trending_ids)
print(list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].title) )
session['counter'] = 0
session['members'] = 0
session['userAges'] = []
session['userGenders'] = []
session['movieIds'] = list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].movie_id_ml)
session['top15'] = list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].title)
session['top15_posters'] = list(df_movies[df_movies.movie_id_ml.isin(top_trending_ids)].poster_url)
session['arr'] = None
return(render_template('main.html', settings = {'showVote': False, 'people': 0, 'buttonDisable': False, 'recommendation': None}))
items = pd.read_csv('items.txt', sep=';', error_bad_lines=False, header=None)
users = pd.read_csv('usersDescription.txt', sep=';', header=None)
ratings = pd.read_csv('ratings.txt', sep=';', header=None)
from lightfm.data import Dataset
dataset = Dataset(user_identity_features=True, item_identity_features=True)
dataset.fit(users=(users[50].unique()),
items=(items[0]),
item_features=list(range(2, 10)),
user_features=list(range(2, 50)))
items_features_raw = list(
(item[1], (np.argwhere(np.array(item[3:]) == 1)[0] + 2).tolist())
for item in items.itertuples())
items_features = dataset.build_item_features(items_features_raw)
users_features_raw = build_user_dict(users)
users_features = dataset.build_user_features(users_features_raw)
num_users, num_items = dataset.interactions_shape()
print('Num users: {}, num_items {}.'.format(num_users, num_items))
ratings2 = ratings[ratings[2] > 0]
ratings2 = ratings2.drop_duplicates(subset=[1, 2, 3])
train, test = train_test_split(ratings2, test_size=0.1)
print(train.shape)
print(test.shape)
(train_interactions,
train_weights) = dataset.build_interactions(train[[3, 1]].values)
(test_interactions, test_weights) = dataset.build_interactions(test[[3, 1
def obtener_matrices_gui(self, ruta_ratings, sep_ratings, encoding_ratings,
ruta_users, sep_users, encoding_users, ruta_items,
sep_items, encoding_items):
"""
Método obtener_matrices_gui. Obtiene las matrices necesarias para la creación de los modelos de LightFM.
Este método solo se utiliza en la interfaz web.
Parameters
----------
ruta_ratings: str
ruta del archivo que contiene las valoraciones.
sep_ratings: str
separador utilizado en el archivo de valoraiones.
encoding_ratings: str
encoding utilizado en el archivo de valoraciones.
ruta_users: str
ruta del archivo que contiene los datos de los usuarios.
sep_users: str
separador utilizado en el archivo de usuarios.
encoding_users: str
encoding utilizado en el archivo de usuarios.
ruta_items: str
ruta del archivo que contiene los datos de los ítems.
sep_items: str
separador utilizado en el archivo de ítems.
encoding_items: str
encoding utilizado en el archivo de ítems.
"""
global train, test, item_features, user_features
# Se obtienen los dataframes
ratings_df = Entrada.leer_csv(ruta_ratings, sep_ratings,
encoding_ratings)
ratings_df.sort_values(
[ratings_df.columns.values[0], ratings_df.columns.values[1]],
inplace=True)
users_df = Entrada.leer_csv(ruta_users, sep_users, encoding_users)
users_df.sort_values([users_df.columns.values[0]], inplace=True)
items_df = Entrada.leer_csv(ruta_items, sep_items, encoding_items)
items_df.sort_values([items_df.columns.values[0]], inplace=True)
# Se transforman los dataframes en matrices que puedan ser utilzadas por los modelos
dataset = Dataset()
dataset.fit(users_df[users_df.columns.values[0]],
items_df[items_df.columns.values[0]],
user_features=users_df[users_df.columns.values[1]],
item_features=items_df[items_df.columns.values[1]])
# Si el modelo es colaborativo o híbrido se tienen en cuenta las valoraciones de los usuarios
if self.opcion_modelo == 1 or self.opcion_modelo == 2:
(interacciones, pesos) = dataset.build_interactions(
(row[ratings_df.columns.values[0]],
row[ratings_df.columns.values[1]],
row[ratings_df.columns.values[2]])
for index, row in ratings_df.iterrows())
else:
(interacciones, pesos) = dataset.build_interactions(
(row[ratings_df.columns.values[0]],
row[ratings_df.columns.values[1]])
for index, row in ratings_df.iterrows())
# Se obtienen las matrices de features y se guardan
item_features = dataset.build_item_features(
(row[items_df.columns.values[0]],
[row[items_df.columns.values[1]]])
for index, row in items_df.iterrows())
user_features = dataset.build_user_features(
(row[users_df.columns.values[0]],
[row[users_df.columns.values[1]]])
for index, row in users_df.iterrows())
print("Guarda la matriz de item features")
guardar_datos_pickle(item_features, 'la matriz de item features')
print("Guarda la matriz de user features")
guardar_datos_pickle(user_features, 'la matriz de user feautures')
# Se dividen las interacciones en conjuntos de entrenamiento y test y se guardan
train, test = random_train_test_split(interacciones,
test_percentage=0.2)
print("Guarda la matriz de entrenamiento")
guardar_datos_pickle(train, 'la matriz de entrenamiento')
print("Guarda la matriz de test")
guardar_datos_pickle(test, 'la matriz de test')
#This will create a feature for every unique author name in the dataset.
#(Note that we fit some more item ids: this is to make sure our mappings are complete even if there are items in the features dataset that are not in the interactions set.)
## Building the interactions matrix
#Having created the mapping, we build the interaction matrix:
(interactions, weights) = dataset.build_interactions(
((x['User-ID'], x['ISBN']) for x in get_ratings()))
print(repr(interactions))
#This is main input into a LightFM model: it encodes the interactions betwee users and items.
#Since we have item features, we can also create the item features matrix:
item_features = dataset.build_item_features(
((x['ISBN'], [x['Book-Author']]) for x in get_book_features()))
print(repr(item_features))
## Building a model
#This is all we need to build a LightFM model:
model = LightFM(loss='bpr')
model.fit(interactions, item_features=item_features)
#trying to put own csv files into lightFM dataset
def get_own_data():
dataset.fit_partial(item_features=(x[str(fields[i])] for x in winefeatures))
num_users, num_items = dataset.interactions_shape()
#building the interaction matrix for training ratings
(interactions, weights) = dataset.build_interactions(((x['taster'],x['title']) for x in trainrankings))
#and the corresponding sparse matrices for CV and Test ratings
(testinteractions, testweights) = dataset.build_interactions(((x['taster'],x['title']) for x in testrankings))
(cvinteractions, cvweights) = dataset.build_interactions(((x['taster'],x['title']) for x in cvrankings))
#here we need to remove title so our next iterator works properly
fields.remove('title')
#double list comprehension to build the item features in a smart way, providing each feature in wine features
#which is >200
item_features = dataset.build_item_features((x['title'],[x[field] for field in fields[1:]]) for x in winefeatures)
#uncomment below to run randomized optimization
#yieldlist = list(randomsearch(interactions, cvinteractions, item_features))
#(score, hyperparams, model) = max(yieldlist, key=lambda x: x[0])
#print("Best score {} at {}".format(score, hyperparams))
#print(yieldlist)
#Below are the results of our random optimiaztion, hardcoded as parameters now.
#Best score 0.9843319654464722 at
bestparams = {'no_components': 59,
'learning_schedule': 'adagrad', 'loss': 'warp', 'learning_rate': 0.08565020895037347,
'item_alpha': 7.345729662383957e-10, 'user_alpha': 4.776609106732949e-09,
'max_sampled': 14, 'random_state':69}
model = LightFM(**bestparams)
user_features=user_feature_names,
item_features=item_feature_names
)
# check shape
num_users, num_items = dataset.interactions_shape()
print('Num users: {}, num_items: {}.'.format(num_users, num_items))
_, num_users_feature = dataset.user_features_shape()
_, num_items_feature = dataset.item_features_shape()
print('Num users feature: {}, num_items feature: {}.'.format(num_users_feature, num_items_feature))
# build user feature matrix
user_feature_matrix = dataset.build_user_features(user_feature_iterable, normalize=True)
# build item feature matrix
item_feature_matrix = dataset.build_item_features(item_feature_iterable, normalize=True)
# build interaction
(train_interactions, weights) = dataset.build_interactions(data=((row['userCode'], row['project_id'], row[interaction_col_name])for index, row in train.iterrows() if row['project_id'] not in ignore_project))
from lightfm import LightFM
model = LightFM(loss='warp', random_state=44, learning_schedule='adagrad')
model.fit(train_interactions,
item_features=item_feature_matrix,
user_features=user_feature_matrix,
)
is_evaluate=0
if is_evaluate:
from lightfm.evaluation import precision_at_k
