这里会显示出您选择的修订版和当前版本之间的差别。
— |
model:preprocess:group [2020/07/12 12:07] (当前版本) |
||
---|---|---|---|
行 1: | 行 1: | ||
+ | ====== 使用ReplaceTransformer进行连续数据分段 ====== | ||
+ | 离散数据分组,一般可以通过 ReplaceTransformer 来进行,示例如下: | ||
+ | |||
+ | <code python> | ||
+ | # ##################################################### | ||
+ | # File: 02-preprocess-07-ReplaceTransformer | ||
+ | # Author: jinlong.hao | ||
+ | # Date: 2019-12-04 | ||
+ | # ReplaceTransformer: 实现替换方式用于实现离散形变量的合并 | ||
+ | # DESC: | ||
+ | # 1. import | ||
+ | # 2. 加载测试数据 | ||
+ | # 3. 基础使用 | ||
+ | # 4. 与DataFrame整合使用 | ||
+ | # #################################################### | ||
+ | |||
+ | # 1. import | ||
+ | from sklearn.preprocessing import OneHotEncoder, LabelBinarizer, LabelEncoder | ||
+ | from sklearn_pandas import DataFrameMapper | ||
+ | import numpy as np | ||
+ | import pandas as pd | ||
+ | from sklearn2pmml.preprocessing import ReplaceTransformer | ||
+ | |||
+ | # 2. 加载示例数据 | ||
+ | df = pd.DataFrame({ | ||
+ | 'age': [3, 3, 4, 4, 2, 2, 1, 7, 8], | ||
+ | 'name': ['james', 'james河北', 'jessica', 'jessica2', 'steve', 'steve', 'lili', 'lucy', 'stone'] | ||
+ | }) | ||
+ | |||
+ | # 4. 与DataFrameMapper配合使用 | ||
+ | dataFrameMapper = DataFrameMapper([ | ||
+ | ('name', [ | ||
+ | ReplaceTransformer(pattern='^(?!james|jessica|steve).*', replacement='others'), | ||
+ | ReplaceTransformer(pattern='^jessica.*', replacement='jessica'), | ||
+ | ReplaceTransformer(pattern='^james.*', replacement='james'), | ||
+ | LabelBinarizer() | ||
+ | ]) | ||
+ | ], df_out=True) | ||
+ | dataFrameMapper.fit_transform(df) | ||
+ | </code> |