leetcode-手动labelEncoder

1，按照标签排序

 test ['label'] =  -  1 ##测试集没有标签，可标记为-1 
train = train.sort_values（by ='label'，ascending = False）.reset_index（drop = True）

2，手动编码

for col in obj_cols:
    data[col].fillna('-1', inplace = True)
    data[col] = data[col].map(dict(zip(data[col].unique(),list(range(data[col].nunique())))))
    print(col+' over...')

3，绘制和保存分布

train = data[data.label!=-1]
test = data[data.label==-1]
train = train.dropna()
test = test.dropna()
for i in data.columns:
    try:
        g = sns.kdeplot(train[i], color="Red", shade = True)
        g = sns.kdeplot(test[i], ax =g, color="Blue", shade= True)
        g.set_xlabel(i)
        g.set_ylabel("Frequency")
        g = g.legend(["train","test"])
        tmp = 'train_test_' + i
        plt.savefig('./train_test/%s.jpg'%tmp)
        plt.show()
        print('plot over:%s'%i)
    except:
        print('jump %s'%i)