Python编程学习：深度剖析shap.datasets.adult()源码中的X,y和X_display,y_display输出数区别

目录

深度剖析shap.datasets.adult()源码中的X,y和X_display,y_display

读取源码

理解源代码

data与raw_data对比结果

X.shape 

X_display.shape 

深度剖析shap.datasets.adult()源码中的X,y和X_display,y_display

X,y = shap.datasets.adult()
X_display,y_display = shap.datasets.adult(display=True)

读取源码

def adult(display=False):
    """ Return the Adult census data in a nice package. """
    dtypes = [
        ("Age", "float32"), ("Workclass", "category"), ("fnlwgt", "float32"),
        ("Education", "category"), ("Education-Num", "float32"), ("Marital Status", "category"),
        ("Occupation", "category"), ("Relationship", "category"), ("Race", "category"),
        ("Sex", "category"), ("Capital Gain", "float32"), ("Capital Loss", "float32"),
        ("Hours per week", "float32"), ("Country", "category"), ("Target", "category")
    ]
    raw_data = pd.read_csv(
        cache(github_data_url + "adult.data"),
        names=[d[0] for d in dtypes],
        na_values="?",
        dtype=dict(dtypes)
    )
    data = raw_data.drop(["Education"], axis=1)   redundant with Education-Num
    filt_dtypes = list(filter(lambda x: not (x[0] in ["Target", "Education"]), dtypes))
    data["Target"] = data["Target"] == " >50K"
    rcode = {
        "Not-in-family": 0,
        "Unmarried": 1,
        "Other-relative": 2,
        "Own-child": 3,
        "Husband": 4,
        "Wife": 5
    }
    for k, dtype in filt_dtypes:
        if dtype == "category":
            if k == "Relationship":
                data[k] = np.array([rcode[v.strip()] for v in data[k]])
            else:
                data[k] = data[k].cat.codes
 
    if display:
        return raw_data.drop(["Education", "Target", "fnlwgt"], axis=1), data["Target"].values
    return data.drop(["Target", "fnlwgt"], axis=1), data["Target"].values

理解源代码

data与raw_data对比结果

结论：
data：是基于raw_data读入的csv文件数据，为新定义的新数据，共计drop了3列(第1个红色矩形框)，又进行了目标特征的二分类(第2个红色矩形框)，最后进行了类别特征进行了数值化/编码化(第3个红色矩形框)；经过处理后的数据均为数字列且目标特征为二分类的dataframe。
raw_data：为原始数据，从csv读入，仅经过drop了3列，其余原封不同输出数据。

X.shape 

(32561, 12) X.shape 
        age         workclass  ...  hours-per-week native-country
0       39         State-gov  ...              40  United-States
1       50  Self-emp-not-inc  ...              13  United-States
2       38           Private  ...              40  United-States
3       53           Private  ...              40  United-States
4       28           Private  ...              40           Cuba
-meta">...    ...               ...  ...             ...            ...
32556   27           Private  ...              38  United-States
32557   40           Private  ...              40  United-States
32558   58           Private  ...              40  United-States
32559   22           Private  ...              20  United-States
32560   52      Self-emp-inc  ...              40  United-States
 
[32561 rows x 12 columns]

X_display.shape 

(32561, 12) X_display.shape 
        age         workclass  ...  hours-per-week native-country
0       39         State-gov  ...              40  United-States
1       50  Self-emp-not-inc  ...              13  United-States
2       38           Private  ...              40  United-States
3       53           Private  ...              40  United-States
4       28           Private  ...              40           Cuba
-meta">...    ...               ...  ...             ...            ...
32556   27           Private  ...              38  United-States
32557   40           Private  ...              40  United-States
32558   58           Private  ...              40  United-States
32559   22           Private  ...              20  United-States
32560   52      Self-emp-inc  ...              40  United-States
 
[32561 rows x 12 columns]