# AveragedPerceptronBinaryClassifier
import numpy as np
from nimbusml.datasets import get_dataset
from nimbusml.feature_extraction.categorical import OneHotVectorizer
from nimbusml.linear_model import AveragedPerceptronBinaryClassifier
from sklearn.model_selection import train_test_split
# use the built-in data set 'infert' to create test and train data
# Unnamed: 0 education age parity induced case spontaneous stratum \
# 0 1 0.0 26.0 6.0 1.0 1.0 2.0 1.0
# 1 2 0.0 42.0 1.0 1.0 1.0 0.0 2.0
# pooled.stratum education_str
# 0 3.0 0-5yrs
# 1 1.0 0-5yrs
np.random.seed(0)
df = get_dataset("infert").as_df()
# remove : and ' ' from column names, and encode categorical column
df.columns = [i.replace(': ', '') for i in df.columns]
df = (OneHotVectorizer() << 'education_str').fit_transform(df)
X_train, X_test, y_train, y_test = \
train_test_split(df.loc[:, df.columns != 'case'], df['case'])
lr = AveragedPerceptronBinaryClassifier().fit(X_train, y_train)
scores = lr.predict(X_test)
# Evaluate the model
print('Accuracy:', np.mean(y_test == [i for i in scores]))
def test_syntax_slots_wo_pipeline(self):
# data
df = get_dataset("infert").as_df()
df = df.drop(['row_num', ], axis=1)
X = df.drop('case', axis=1)
y = df['case']
# transform
xf1 = OneHotVectorizer(columns=['age', 'parity', 'education_str'])
X_xf1 = xf1.fit_transform(X, verbose=0)
assert "age.21" in list(X_xf1.columns)
# learner
# (1 .a.)
model = AveragedPerceptronBinaryClassifier()
# (1. b)
try:
model = AveragedPerceptronBinaryClassifier(feature=['age'])
model.fit(X_xf1, y, verbose=0)
cont = True
assert False
except Exception as e:
# does not work
cont = False
print(e)
if cont:
y_pred = model.predict(X_xf1)
assert y_pred.shape == (248, 3)
pipeline = Pipeline([
OneHotVectorizer(columns=['age', 'parity', 'education_str']),
AveragedPerceptronBinaryClassifier(feature='age')
])
pipeline.fit(X, y, verbose=0)
y_pred_withpipeline = pipeline.predict(X)
print(y_pred_withpipeline.head())
assert y_pred_withpipeline.shape == (248, 3)
metrics, scores = pipeline.test(X, y, output_scores=True)
print(metrics)
assert scores.shape == (248, 3)
assert metrics.shape == (1, 11)
# back to X_xf1
print(list(X_xf1.columns))
l1 = list(sorted(set(_.split('.')[-1] for _ in X_xf1.columns)))
levels = [['age', 'education', 'education_str', 'parity',
'pooled', 'spontaneous', 'stratum', 'induced'], [''] + l1]
names = ['columns', 'slots']
labels = [[], []]
ages = []
for _ in X_xf1.columns:
spl = _.split('.')
l1 = levels[0].index(spl[0])
try:
l2 = levels[1].index(spl[1])
except IndexError:
l2 = levels[1].index('')
labels[0].append(l1)
labels[1].append(l2)
if spl[0] == 'age':
ages.append(l2)
X_xf1.columns = pandas.MultiIndex(
levels=levels, labels=labels, names=names)
print(X_xf1.head(n=2).T)
col_ages = [('age', a) for a in ages]
print(col_ages)
try:
model = AveragedPerceptronBinaryClassifier(feature=col_ages)
model.fit(X_xf1, y, verbose=0)
y_pred = model.predict(X_xf1)
assert y_pred.shape == (248, 3)
except Exception as e:
# Does not work, probably confusion between list and tuple in nimbusml
print(e)
try:
model = AveragedPerceptronBinaryClassifier(feature=['age'])
model.fit(X_xf1, y, verbose=0)
y_pred = model.predict(X_xf1)
assert y_pred.shape == (248, 3)
except Exception as e:
# Does not work.
print(e)