一、FM回归任务
1. 导库
import numpy as np
from sklearn.feature_extraction import DictVectorizer
from pyfm import pylibfm
DictVectorizer：它是可以将非结构化的数据转成array格式，这里将字典数据转成数组，一般情况下使用字典是因为在推荐系统中的矩阵一般是稀疏的，所以采用字典存储数据高效，可以不用存储大量无用的0
它转成数组的原理和OneHot差不多，对于数值型数据，它是保留原值，而对于非数值型则会将其利用OneHot进行编码，形成一个稀疏矩阵，每列表示同个特征不同值的选择门
2. 加载数据
"""加载数据"""
def loadData(filename, path="data/ml-100k/"):
data = []
y= []
users = set()
items = set()
with open(path + filename) as f:
for line in f:
(user, movie, rating, ts) = line.split('\t')
data.append({"user_id":str(user), "movie_id":str(movie)})
y.append(float(rating))
users.add(user)
items.add(movie)
return (data, np.array(y), users, items)
3. 获取数据
"""获取数据"""
(train_data, y_train, train_users, train_items) = loadData("ua.base")
(test_data, y_test, test_users, test_items) = loadData("ua.test")
4. 定义编码器
vec = DictVectorizer() # 将字典数据进行编码
X_train = vec.fit_transform(train_data)
X_test = vec.fit_transform(test_data)
5. 构建模型
fm = pylibfm.FM(num_factors = 10, # 交互特征维度
num_iter = 10, # 迭代次数
verbose = True, # 是否打印日志
task = "regression", # 模式
initial_learning_rate = 0.001, # 学习率
learning_rate_schedule = "optimal")
fm.fit(X_train, y_train)
6. 衡量误差
pred = fm.predict(X_test)
from sklearn.metrics import mean_squared_error
print("FM MSE: %.4f" % mean_squared_error(y_test, pred)) # 均方误差
二、FM分类任务
1. 导库
import numpy as np
from sklearn.feature_extraction import DictVectorizer
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_classification
from pyfm import pylibfm
2. 构造数据
"""加载数据"""
X, y = make_classification(n_samples=1000,n_features=100, n_clusters_per_class=1)
"""将数据转成字典类型"""
data = [ {v: k for k, v in dict(zip(i, range(len(i)))).items()} for i in X]
3. 划分数据集
"""划分数据集"""
X_train, X_test, y_train, y_test = train_test_split(data, y, test_size = 0.1, random_state = 2021)
4. 定义编码器
vec = DictVectorizer()
X_train = vec.fit_transform(X_train)
X_test = vec.fit_transform(X_test)
5. 构建模型
"""构建模型"""
fm = pylibfm.FM(num_factors = 2,
num_iter = 10,
verbose = True,
task = "classification",
initial_learning_rate = 0.0001,
learning_rate_schedule = "optimal")
fm.fit(X_train, y_train)
6. 衡量误差
"""衡量误差"""
from sklearn.metrics import log_loss
print("Validation log loss: %.4f" % log_loss(y_test,fm.predict(X_test)))
