使用 PyMC3 的分层贝叶斯线性回归非常慢

Question

我正在尝试编写一些代码，以便在逻辑回归的情况下使用 UCI 存储库中的成人数据集实现 HBM。

我已经编写了代码，但采样速度非常慢，每个样本大约 107 秒，即使是 64 个维度或特征。我做错了什么吗？

我附上代码以供参考。由于建议加快速度，我还重新调整了数据，但无济于事。

我感谢任何反馈。

代码是这里和这里所写内容的混合体。

#re loading the dataset this time without converting the country into one-hot vector rather for hierarchical modeling
adult_df = pd.read_csv('adult.data', header=None, sep=', ', )
adult_df.columns = ["Age", "WorkClass", "fnlwgt", "Education", "EducationNum",
    "MaritalStatus", "Occupation", "Relationship", "Race", "Gender",
    "CapitalGain", "CapitalLoss", "HoursPerWeek", "NativeCountry", "Income"]

adult_df["Income"] = adult_df["Income"].map({ "<=50K": 0, ">50K": 1 })
adult_df.drop("CapitalGain", axis=1, inplace=True,)
adult_df.drop("CapitalLoss", axis=1, inplace=True,)
adult_df.Age = adult_df.Age.astype(float)
adult_df.fnlwgt = adult_df.fnlwgt.astype(float)
adult_df.EducationNum = adult_df.EducationNum.astype(float)
adult_df.HoursPerWeek = adult_df.HoursPerWeek.astype(float)

# dropping native country here!!
adult_df = pd.get_dummies(adult_df, columns=[
    "WorkClass", "Education", "MaritalStatus", "Occupation", "Relationship",
    "Race", "Gender",
])
standard_scaler_cols = ["Age", "fnlwgt", "EducationNum", "HoursPerWeek",]
other_cols = list(set(adult_df.columns) - set(standard_scaler_cols))
mapper = DataFrameMapper(
    [([col,], StandardScaler(),) for col in standard_scaler_cols] +
    [(col, None,) for col in other_cols]
)

le = preprocessing.LabelEncoder()
country_idx = le.fit_transform(adult_df['NativeCountry'])
pd.value_counts(pd.Series(y_all))
y_all = adult_df["Income"].values
adult_df.drop("Income", axis=1, inplace=True,)
adult_df.drop("NativeCountry", axis=1, inplace=True,)
n_countries = len(set(country_idx))
n_features = len(adult_df.columns) 
min_max_scaler = preprocessing.MinMaxScaler()
adult_df = min_max_scaler.fit_transform(adult_df)
X_train, X_test, y_train, y_test, country_idx_train, country_idx_test = train_test_split(adult_df, y_all, country_idx, train_size=0.1, test_size=0.25, stratify=y_all, random_state=rs)
with pm.Model() as multilevel_model:
    # Hyperiors for intercept      
    mu_theta = pm.MvNormal(name='mu_a', mu=np.zeros(n_features), cov=np.eye(n_features), shape=n_features)
   packed_L_theta = pm.LKJCholeskyCov('packed_L', n=n_features,
                                 eta=2., sd_dist=pm.HalfCauchy.dist(2.5))
    L_theta = pm.expand_packed_triangular(n_features, packed_L_theta)
    theta = pm.MvNormal(mu=mu_theta, name='mu_theta', chol=L_theta, shape=[n_countries, n_features])

    # Hyperiors for intercept (Comment 1)
    mu_b = pm.StudentT('mu_b', nu=3, mu=0., sd=1.0)
    sigma_b = pm.HalfNormal('sigma_b', sd=1.0)
    b = pm.Normal('b', mu=mu_b, sd=sigma_b, shape=[n_countries, 1])
    # Calculate predictions given values
    # for intercept and slope 
    yhat = pm.invlogit(b[country_idx_train] +  pm.math.dot(theta[country_idx_train], np.asarray(X_train).T))
    #Make predictions fit reality
    y = pm.Binomial('y', n=np.ones(y_train.shape[0]), p=yhat, observed=y_train)

Answer 1

您可能会在我们的

pymc3 问题讨论中取得更大的成功： https://discourse.pymc.io/我邀请您将问题移到那里。

我要检查的第一件事是你的Theano是否针对MKL库进行编译，或者甚至可能使用Python模式。如果你通过 conda 安装东西，那应该给你 MKL，如果你使用 pip，这可能会更困难。http://deeplearning.net/software/theano/troubleshooting.html#test-blas