#!/usr/bin/env python
# coding: utf-8
from sklearn.datasets import load_iris
from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn2pmml import PMMLPipeline
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(iris.data, iris.target, test_size = 0.25)
y_train
pipe_l = PMMLPipeline([('minmax', MinMaxScaler()), ('lr', LogisticRegression())])
model = pipe_l.fit(X_train,y_train)
pipe_l.score(X_test, y_test)
X_test[1]
y_test[1]
pipe_l.predict([[6.7, 3. , 5.2, 2.3]])
import pandas as pd
irisd = pd.DataFrame(iris.data, columns=iris.feature_names)
irisd.columns
from nyoka import skl_to_pmml
skl_to_pmml(pipe_l, irisd.columns, 'Target', "iris_nyoka_pipeline.pmml")
from sklearn2pmml import sklearn2pmml
sklearn2pmml(pipe_l, "iris_pipeline.pmml", with_repr = True, debug = True)
# nn
nn = PMMLPipeline([("classifier",
sk_nn.MLPClassifier(activation='tanh',
solver='adam',
alpha=0.0001,
learning_rate='adaptive',
learning_rate_init=0.001,
max_iter=1000))])
# 模型拟合
nn.fit(data, label)
# 模型预测
nn_predict = nn.predict(X_test)
# 模型评估
# 基础打分
nn_score = nn.score(X_test, y_test)
print(nn_score)
# 交叉验证
nn_cross1 = cross_val_score(nn,
X_train,
y_train,
scoring='accuracy',
cv=10,
n_jobs=-1)
nn_cross2 = cross_val_score(nn,
X_test,
y_test,
scoring='accuracy',
cv=10,
n_jobs=-1)
print(nn_cross1)
