preprocessing.LabelEncoder()使用

preprocessing.LabelEncoder()使用
e.g. 1：

from sklearn import preprocessing
le = preprocessing.LabelEncoder()

arr_gf = [1,2,3,'wom','wom','中文','中文']
le.fit(arr_gf)
one_hot_gf = le.transform(arr_gf)
print(one_hot_gf)

输出：[0 1 2 3 3 4 4]

e.g. 2:

csv_path = './all_xx.csv'
all_xx_df = pandas.read_csv(csv_path, error_bad_lines=False)
all_xx_df = all_xx_df.dropna()
np.save('./all_xx.npy', all_xx_df)
all_xx = np.load('./all_xx.npy', allow_pickle=True)

# numpy格式
arr_xf = all_xx[:, 6]
arr_hw = all_xx[:, 12]

# 编码：fit 与transform
le.fit(arr_xf)
one_hot_xf = le.transform(arr_xf)
np.save('/root/whq/data/input/one_hot_xf', one_hot_xf)

另：在用字典统计交易记录时，注意两种格式的不同(pd与numpy)：

for key, value in tqdm(zip(all_xx['column名称'], all_xx['关联column名称'])):
    ...

for i in tqdm(range(all_xx.shape[0])):
    dic_xf[one_hot_xf[i]] = all_xx[i, 6]
    dic_hw[one_hot_hw[i]] = all_xx[i, 12]
    ...