def test_decision_function_binary(self):
from lale.lib.lale import Project
train_X, train_y = self._creditG["X"], self._creditG["y"]
trainable = Project(columns={"type": "number"}) >> LogisticRegression()
trained = trainable.fit(train_X, train_y)
_ = trained.decision_function(train_X)
def test_keep_numbers(self):
from lale.datasets.data_schemas import to_schema
from lale.lib.lale import Project
train_X, train_y = self._creditG["X"], self._creditG["y"]
trainable = Project(columns={"type": "number"})
trained = trainable.fit(train_X)
transformed = trained.transform(train_X)
transformed_schema = to_schema(transformed)
transformed_expected = {
"type": "array",
"minItems": 670,
"maxItems": 670,
"items": {
"type": "array",
"minItems": 7,
"maxItems": 7,
"items": [
{"description": "duration", "type": "number"},
{"description": "credit_amount", "type": "number"},
{"description": "installment_commitment", "type": "number"},
{"description": "residence_since", "type": "number"},
{"description": "age", "type": "number"},
{"description": "existing_credits", "type": "number"},
{"description": "num_dependents", "type": "number"},
],
},
}
self.maxDiff = None
self.assertEqual(transformed_schema, transformed_expected)
def test_keep_non_numbers(self):
from lale.datasets.data_schemas import to_schema
from lale.lib.lale import Project
train_X, train_y = self._creditG['X'], self._creditG['y']
trainable = Project(columns={'not': {'type': 'number'}})
trained = trainable.fit(train_X)
transformed = trained.transform(train_X)
transformed_schema = to_schema(transformed)
transformed_expected = {
'type': 'array', 'minItems': 670, 'maxItems': 670,
'items': {
'type': 'array', 'minItems': 13, 'maxItems': 13,
'items': [
{'description': 'checking_status', 'enum': [
'<0', '0<=X<200', '>=200', 'no checking']},
{'description': 'credit_history', 'enum': [
'no credits/all paid', 'all paid',
'existing paid', 'delayed previously',
'critical/other existing credit']},
{'description': 'purpose', 'enum': [
'new car', 'used car', 'furniture/equipment',
'radio/tv', 'domestic appliance', 'repairs',
'education', 'vacation', 'retraining', 'business',
'other']},
{'description': 'savings_status', 'enum': [
'<100', '100<=X<500', '500<=X<1000', '>=1000',
'no known savings']},
{'description': 'employment', 'enum': [
'unemployed', '<1', '1<=X<4', '4<=X<7', '>=7']},
{'description': 'personal_status', 'enum': [
'male div/sep', 'female div/dep/mar', 'male single',
'male mar/wid', 'female single']},
{'description': 'other_parties', 'enum': [
'none', 'co applicant', 'guarantor']},
{'description': 'property_magnitude', 'enum': [
'real estate', 'life insurance', 'car',
'no known property']},
{'description': 'other_payment_plans', 'enum': [
'bank', 'stores', 'none']},
{'description': 'housing', 'enum': [
'rent', 'own', 'for free']},
{'description': 'job', 'enum': [
'unemp/unskilled non res', 'unskilled resident',
'skilled', 'high qualif/self emp/mgmt']},
{'description': 'own_telephone', 'enum': ['none', 'yes']},
{'description': 'foreign_worker', 'enum': ['yes', 'no']}]}}
self.maxDiff = None
self.assertEqual(transformed_schema, transformed_expected)
def test_keep_numbers(self):
from lale.datasets.data_schemas import to_schema
from lale.lib.lale import Project
train_X, train_y = self._creditG['X'], self._creditG['y']
trainable = Project(columns={'type': 'number'})
trained = trainable.fit(train_X)
transformed = trained.transform(train_X)
transformed_schema = to_schema(transformed)
transformed_expected = {
'type': 'array',
'minItems': 670,
'maxItems': 670,
'items': {
'type':
'array',
'minItems':
7,
'maxItems':
7,
'items': [{
'description': 'duration',
'type': 'number'
}, {
'description': 'credit_amount',
'type': 'number'
}, {
'description': 'installment_commitment',
'type': 'number'
}, {
'description': 'residence_since',
'type': 'number'
}, {
'description': 'age',
'type': 'number'
}, {
'description': 'existing_credits',
'type': 'number'
}, {
'description': 'num_dependents',
'type': 'number'
}]
}
}
self.maxDiff = None
self.assertEqual(transformed_schema, transformed_expected)
def test_keep_non_numbers(self):
from lale.datasets.data_schemas import to_schema
from lale.lib.lale import Project
train_X = self._creditG["X"]
trainable = Project(columns={"not": {"type": "number"}})
trained = trainable.fit(train_X)
transformed = trained.transform(train_X)
transformed_schema = to_schema(transformed)
transformed_expected = {
"type": "array",
"minItems": 670,
"maxItems": 670,
"items": {
"type":
"array",
"minItems":
13,
"maxItems":
13,
"items": [
{
"description": "checking_status",
"enum": ["<0", "0<=X<200", ">=200", "no checking"],
},
{
"description":
"credit_history",
"enum": [
"no credits/all paid",
"all paid",
"existing paid",
"delayed previously",
"critical/other existing credit",
],
},
{
"description":
"purpose",
"enum": [
"new car",
"used car",
"furniture/equipment",
"radio/tv",
"domestic appliance",
"repairs",
"education",
"vacation",
"retraining",
"business",
"other",
],
},
{
"description":
"savings_status",
"enum": [
"<100",
"100<=X<500",
"500<=X<1000",
">=1000",
"no known savings",
],
},
{
"description": "employment",
"enum":
["unemployed", "<1", "1<=X<4", "4<=X<7", ">=7"],
},
{
"description":
"personal_status",
"enum": [
"male div/sep",
"female div/dep/mar",
"male single",
"male mar/wid",
"female single",
],
},
{
"description": "other_parties",
"enum": ["none", "co applicant", "guarantor"],
},
{
"description":
"property_magnitude",
"enum": [
"real estate",
"life insurance",
"car",
"no known property",
],
},
{
"description": "other_payment_plans",
"enum": ["bank", "stores", "none"],
},
{
"description": "housing",
"enum": ["rent", "own", "for free"]
},
{
"description":
"job",
"enum": [
"unemp/unskilled non res",
"unskilled resident",
"skilled",
"high qualif/self emp/mgmt",
],
},
{
"description": "own_telephone",
"enum": ["none", "yes"]
},
{
"description": "foreign_worker",
"enum": ["yes", "no"]
},
],
},
}
self.maxDiff = None
self.assertEqual(transformed_schema, transformed_expected)
def test_decision_function_binary(self):
from lale.lib.lale import Project
train_X, train_y = self._creditG['X'], self._creditG['y']
trainable = Project(columns={'type': 'number'}) >> LogisticRegression()
trained = trainable.fit(train_X, train_y)
decisions = trained.decision_function(train_X)