-
提取数据类型特征列名
numerical_cols = Train_data.select_dtypes(exclude = \'object\').columns
print(numerical_cols)
categorical_cols = Train_data.select_dtypes(include = \'object\').columns
print(categorical_cols)
-
构建训练和测试样本
##选择特征列
feature_cols = [col for col in numerical_cols if col not in [\'SaleID\',\'name\',\'regDate\',\'creatDate\',\'price\',\'model\',\'brand\',\'regionCode\',\'seller\']]
feature_cols = [col for col in feature_cols if \'Type\' not in col]
## 提前特征列，标签列构造训练样本和测试样本
X_data = Train_data[feature_cols]
Y_data = Train_data[\'price\']
X_test = TestA_data[feature_cols]
print(\'X train shape:\',X_data.shape)
print(\'X test shape:\',X_test.shape)
## 定义了一个统计函数，方便后续信息统计
def Sta_inf(data):
print(\'_min\',np.min(data))
print(\'_max:\',np.max(data))
print(\'_mean\',np.mean(data))
print(\'_ptp\',np.ptp(data))
print(\'_std\',np.std(data))
print(\'_var\',np.var(data))
-
统计标签的基本分布信息
print(\'Sta of label:\')
Sta_inf(Y_data)
## 绘制标签的统计图，查看标签分布
plt.hist(Y_data)
plt.show()
plt.close()
- 缺省值用-1填补
X_data = X_data.fillna(-1)
X_test = X_test.fillna(-1)