baatout

from pandas import read_csv
from sklearn.model_selection import train_test_split

url = "https://raw.githubusercontent.com/baatout/ml-in-prod/master/pima-indians-diabetes.csv"
features = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age']
label = 'label'
dataframe = read_csv(url, names=features + [label])
X = dataframe[features]
Y = dataframe[label]
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.33, random_state=42)

baatout

# with X_train, X_test, Y_train, Y_test
from sklearn.linear_model import LogisticRegression

clf = LogisticRegression()
clf.fit(X_train, Y_train)
print(clf.score(X_test, Y_test))

import json
with open('logreg_coefs', 'w') as f:
    json.dump(clf.coef_.tolist(), f)

baatout

# with X_train, X_test, Y_train, Y_test
import numpy as np
from sklearn_pandas import DataFrameMapper
from sklearn2pmml import PMMLPipeline, sklearn2pmml
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import FunctionTransformer

clf = PMMLPipeline([
   ("mapper", DataFrameMapper([
       (['mass'], FunctionTransformer(np.log1p)),

baatout

<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
<PMML xmlns="http://www.dmg.org/PMML-4_3" xmlns:data="http://jpmml.org/jpmml-model/InlineTable" version="4.3">
	<Header>
		<Application name="JPMML-SkLearn" version="1.5.6"/>
		<Timestamp>2018-09-08T11:13:03Z</Timestamp>
	</Header>
	<MiningBuildTask>
		<Extension>PMMLPipeline(steps=[('mapper', DataFrameMapper(default=False, df_out=False,
        features=[(['mass'], FunctionTransformer(accept_sparse=False, func=&lt;ufunc 'log1p'&gt;,
          inv_kw_args=None, inverse_func=None, kw_args=None,

baatout

# with X_train, X_test, Y_train, Y_test
from sklearn_pandas import DataFrameMapper
from sklearn2pmml import PMMLPipeline, sklearn2pmml
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import FunctionTransformer

def is_adult(x): return x > 18

clf = PMMLPipeline([
    ("mapper", DataFrameMapper([

baatout

# with X_train, X_test, Y_train, Y_test
import dill
from sklearn_pandas import DataFrameMapper
from sklearn.pipeline import Pipeline
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import FunctionTransformer

def is_adult(x): return x > 18

clf = Pipeline([

baatout

# run this anywhere and change the pipeline.pk path
import dill
from pandas import read_csv

url = "https://raw.githubusercontent.com/baatout/ml-in-prod/master/pima-indians-diabetes.csv"
features = ['preg', 'plas', 'pres', 'skin', 'test', 'mass', 'pedi', 'age']
label = 'label'
dataframe = read_csv(url, names=features + [label])
X = dataframe[features]
Y = dataframe[label]

baatout

def add(a, b):
	return a + b

baatout

from adder import add

x = add(4, 6)

baatout

def add(a: int, b: int) -> int:
	return a + b