# ############################################################
# File: 02-preprocess-04-OneHotEncoder
# Author: jinlong.hao
# Date: 2019-12-04
# OneHotEncoder: 将数据进行离散化处理，形成哑变量
#     sklearn-19及以前仅支持integer数据，20以后支持string数据了
# Desc: 
#    1. import语句
#    2. 构造数据
#    3. 使用DataFrameMapper进行转化
#    4. 使用DataFrameMapper结合OneHotEncoder进行转化
# ############################################################
 
# 1. import语句
from sklearn.preprocessing import OneHotEncoder, LabelBinarizer
from sklearn_pandas import DataFrameMapper
import numpy as np
import pandas as pd
from sklearn2pmml.preprocessing import CutTransformer
 
# 2. 加载示例数据
df = pd.DataFrame({
    'age': [3, 3, 7, 4, 2, 4],
    'salary': [36, 39, 17, 82, 42, 10],
    'name': ['james', 'jucy', 'jessica', 'tony', 'steve', 'jam']
})
 
# 3. 配合DataFrameMapper使用
dataFrameMapper = DataFrameMapper([
    (['age'], OneHotEncoder(handle_unknown='ignore')),
    (['age'], LabelBinarizer()),
    (['name'], OneHotEncoder(handle_unknown='ignore'))
], df_out=True)
dataFrameMapper.fit_transform(df)
 
# 4 OneHotEncoder 不能在DataRameMapper中连接使用，会报错
dataFrameMapper2 = DataFrameMapper([
    (['age'], [
        CutTransformer(bins=[0, 3, 5, 200], labels=['1', '2', '3']), 
        OneHotEncoder()]
    )  #报错，需要用LabelBinarizer()
], df_out=True)
 
dataFrameMapper2.fit_transform(df)

/usr/local/lib/python3.7/dist-packages/sklearn/utils/validation.py in check_array
(array, accept_sparse, accept_large_sparse, dtype, order, copy, force_all_finite, 
ensure_2d, allow_nd, ensure_min_samples, ensure_min_features, warn_on_dtype, estimator)
    519  "Reshape your data either using array.reshape(-1, 1) if "
    520  "your data has a single feature or array.reshape(1, -1) "
--> 521  "if it contains a single sample.".format(array))
    522 
    523  # in the future np.flexible dtypes will be handled like object dtypes

ValueError: ['age']: Expected 2D array, got 1D array instead:
array=['1' '1' '3' '2' '1' '2' '2' '3' '1'].
Reshape your data either using array.reshape(-1, 1) if your data has a single 
feature or array.reshape(1, -1) if it contains a single sample.

在DataFrameMapper多重处理中，不使用OneHotEncoder，该用LabelBinarizer，修改后的代码如下：

# 4. OneHotEncoder 不能在DataRameMapper中连接使用，改用LabelBinarizer
dataFrameMapper2 = DataFrameMapper([
    #(['age'], [
    #    CutTransformer(bins=[0, 3, 5, 200], labels=['1', '2', '3']), 
    #    OneHotEncoder()]
    #),  #报错，需要用LabelBinarizer()
    ('age', [
        CutTransformer(bins=[0, 3, 5, 200], labels=['1', '2', '3']), 
        LabelBinarizer()]
    ) 
], df_out=True)
 
dataFrameMapper2.fit_transform(df)

# #########################################
# file: 09-sample-02-basic-01
# author: jinlong.hao
# date: 2019-12-06
# desc: sklearn2pmml基础验证代码
# content: 
# ########################################
 
# 1. import
import sklearn
import sklearn.impute
import sklearn.ensemble
import sklearn.linear_model
import sklearn2pmml
import sklearn2pmml.preprocessing
from sklearn2pmml.preprocessing import ReplaceTransformer
import sklearn_pandas
import pandas as pd
import numpy as np
 
# 2. 加载数据
# 2.1 加载特征数据
train_x = pd.DataFrame({
    'phone_brand': ['Huawei', 'Huawei', 'Apple', 'Apple', '360', '8848', np.NaN],
    'phone_price': [2403, 1123,  4823, 2223, np.NaN, 1583, 2222]
})
train_x = pd.DataFrame(data=train_x.values, columns=train_x.columns)
 
# 2.2 train_y
train_y = pd.DataFrame({
    'result': [0, 1, 0, 1, 0, 0, 1]
})
train_y=pd.DataFrame(data=train_y.values, columns=train_y.columns)
 
# 3. 构建DataFrameMapper预处理程序
dataFrameMapper = sklearn_pandas.DataFrameMapper([
    (['phone_brand'], [
        sklearn.impute.SimpleImputer(strategy='constant', fill_value='others')
        ,ReplaceTransformer(pattern='^(?!Huawei|Apple).*', replacement='others')
        ,sklearn.preprocessing.LabelEncoder()
        ,sklearn.preprocessing.LabelBinarizer()
    ]),
    (['phone_price'], [
        sklearn.impute.SimpleImputer(strategy='constant', fill_value=0)
        ,sklearn2pmml.preprocessing.CutTransformer([-1, 1000, 10000])
        ,sklearn.preprocessing.LabelEncoder()
        ,sklearn.preprocessing.LabelBinarizer()
    ])
])
dataFrameMapper.fit_transform(train_x)
 
# 4. 模型训练
# 4.1 构建逻辑回归分类器
logistic_classifier = sklearn.linear_model.LogisticRegression()
 
# 4.2 构建逻辑回归的pipeline
logistic_pipeline = sklearn2pmml.PMMLPipeline([
    ('mapper', dataFrameMapper),
    ('classifier', logistic_classifier)
]) 
# 4.3 执行训练
logistic_pipeline.fit(train_x, train_y)
 
# 5. 模型输出pmml
sklearn2pmml.sklearn2pmml(logistic_pipeline, '02-basic-01.pmml')

Standard output is empty
Standard error:
十二月 09, 2019 5:32:59 下午 org.jpmml.sklearn.Main run
信息: Parsing PKL..
十二月 09, 2019 5:32:59 下午 org.jpmml.sklearn.Main run
严重: Failed to parse PKL
net.razorvine.pickle.PickleException: expected zero arguments for construction 
of ClassDict (for pandas._libs.interval.Interval)
	at net.razorvine.pickle.objects.ClassDictConstructor.construct(ClassDictConstructor.java:23)
	at net.razorvine.pickle.Unpickler.load_reduce(Unpickler.java:773)
	at net.razorvine.pickle.Unpickler.dispatch(Unpickler.java:213)
	at net.razorvine.pickle.Unpickler.load(Unpickler.java:123)
	at numpy.core.NDArrayUtil.readObject(NDArrayUtil.java:378)
	at numpy.core.TypeDescriptor.read(TypeDescriptor.java:163)
	at numpy.core.NDArrayUtil.parseArray(NDArrayUtil.java:214)
	at numpy.core.NDArrayUtil.parseData(NDArrayUtil.java:189)
	at joblib.NumpyArrayWrapper.toArray(NumpyArrayWrapper.java:43)
	at org.jpmml.sklearn.PickleUtil$1.dispatch(PickleUtil.java:88)
	at net.razorvine.pickle.Unpickler.load(Unpickler.java:123)
	at org.jpmml.sklearn.PickleUtil.unpickle(PickleUtil.java:98)
	at org.jpmml.sklearn.Main.run(Main.java:104)
	at org.jpmml.sklearn.Main.main(Main.java:94)

在使用CutTransformer时，指定labels参数，修改如下：

# 3. 构建DataFrameMapper预处理程序
dataFrameMapper = sklearn_pandas.DataFrameMapper([
    (['phone_brand'], [
        sklearn.impute.SimpleImputer(strategy='constant', fill_value='others')
        ,ReplaceTransformer(pattern='^(?!Huawei|Apple).*', replacement='others')
        ,sklearn.preprocessing.LabelEncoder()
        ,sklearn.preprocessing.LabelBinarizer()
    ]),
    (['phone_price'], [
        sklearn.impute.SimpleImputer(strategy='constant', fill_value=0)
        ,sklearn2pmml.preprocessing.CutTransformer(bins=[-1, 1000, 10000],
                                                   labels=['1', '2'])
        # ,sklearn.preprocessing.LabelEncoder()  # 指定labels后不需要在使用LabelEncoder
        ,sklearn.preprocessing.LabelBinarizer()
    ])
])
dataFrameMapper.fit_transform(train_x)