mlcourse 3

# necessary to remove rows with incorrect labels in test dataset
data_test = data_test[
    (data_test["Target"] == " >50K.") | (data_test["Target"] == " <=50K.")
]

# encode target variable as integer
data_train.loc[data_train["Target"] == " <=50K", "Target"] = 0
data_train.loc[data_train["Target"] == " >50K", "Target"] = 1

data_test.loc[data_test["Target"] == " <=50K.", "Target"] = 0
data_test.loc[data_test["Target"] == " >50K.", "Target"] = 1

第一行代码    看似是一句废话，其实是将不同值域的数值弄到一起。(我后来看看，确实有点废话，应该是想抛弃某些值）

data_test.describe(include="all").T

 转置，让表格可能更加美观，格式符合人们一般认知

 将训练集和测试集分开看待

# choose categorical and continuous features from data

categorical_columns = [
    c for c in data_train.columns if data_train[c].dtype.name == "object"
]
numerical_columns = [
    c for c in data_train.columns if data_train[c].dtype.name != "object"
]

print("categorical_columns:", categorical_columns)
print("numerical_columns:", numerical_columns)

将分类变量与数值变量直接分开来看 

# fill missing data

for c in categorical_columns:
    data_train[c].fillna(data_train[c].mode()[0], inplace=True)
    data_test[c].fillna(data_train[c].mode()[0], inplace=True)

for c in numerical_columns:
    data_train[c].fillna(data_train[c].median(), inplace=True)
    data_test[c].fillna(data_train[c].median(), inplace=True)

分类变量的空缺值，用众数填充；数值变量的空缺值用平均数填充

data_train = pd.concat(
    [data_train[numerical_columns], pd.get_dummies(data_train[categorical_columns])],
    axis=1,
)

data_test = pd.concat(
    [data_test[numerical_columns], pd.get_dummies(data_test[categorical_columns])],
    axis=1,
)

异常聪明的哑变量代换   ，之前鼠鼠是个傻逼

 鼠鼠直接全截图下来吧，由于测试集可能不具备训练集的某些特征种类，我们利用集合知识求出两个列表的差集，通过差集找出没有的那一个feature，为测试集创造一个值全为0的特征。

read_html      读取的是表格的集合  ，从中抽取 你想要的

这一部要经过很原始的查数         有趣有趣