Skip to content

Move to minmax scaler #866

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jun 9, 2020
Merged

Move to minmax scaler #866

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 8 additions & 18 deletions autosklearn/metalearning/metalearning/kNearestDatasets/kND.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,6 +2,7 @@
import pandas as pd

from sklearn.neighbors import NearestNeighbors
from sklearn.preprocessing import MinMaxScaler
import sklearn.utils

from ....util.logging_ import get_logger
Expand All @@ -18,6 +19,7 @@ def __init__(self, metric='l1', random_state=None, metric_params=None):
self.runs = None
self.best_configuration_per_dataset = None
self.random_state = sklearn.utils.check_random_state(random_state)
self.scaler = MinMaxScaler()

if self.metric_params is None:
self.metric_params = {}
Expand All @@ -44,6 +46,9 @@ def fit(self, metafeatures, runs):
self.runs = runs
self.num_datasets = runs.shape[1]

# Fit the metafeatures for scaler
self.scaler.fit(self.metafeatures)

# for each dataset, sort the runs according to their result
best_configuration_per_dataset = {}
for dataset_name in runs:
Expand Down Expand Up @@ -102,8 +107,9 @@ def kNearestDatasets(self, x, k=1, return_distance=False):
elif k == -1:
k = self.num_datasets

X_train, x = self._scale(self.metafeatures, x)
X_train = self.scaler.transform(self.metafeatures)
x = x.values.reshape((1, -1))
x = self.scaler.transform(x)
self._nearest_neighbors.fit(X_train)
distances, neighbor_indices = self._nearest_neighbors.kneighbors(
x, n_neighbors=k, return_distance=True)
Expand All @@ -126,6 +132,7 @@ def kBestSuggestions(self, x, k=1, exclude_double_configurations=True):
raise ValueError('Number of neighbors k cannot be zero or negative.')
nearest_datasets, distances = self.kNearestDatasets(x, -1,
return_distance=True)

kbest = []

added_configurations = set()
Expand All @@ -151,20 +158,3 @@ def kBestSuggestions(self, x, k=1, exclude_double_configurations=True):
if k == -1:
k = len(kbest)
return kbest[:k]

def _scale(self, metafeatures, other):
assert isinstance(other, pd.Series), type(other)
assert other.values.dtype == np.float64
scaled_metafeatures = metafeatures.copy(deep=True)
other = other.copy(deep=True)

mins = scaled_metafeatures.min()
maxs = scaled_metafeatures.max()
# I also need to scale the target dataset meta features...
mins = pd.DataFrame(data=[mins, other]).min()
maxs = pd.DataFrame(data=[maxs, other]).max()
divisor = (maxs-mins)
divisor[divisor == 0] = 1
scaled_metafeatures = (scaled_metafeatures - mins) / divisor
other = (other - mins) / divisor
return scaled_metafeatures, other
24 changes: 6 additions & 18 deletions test/test_metalearning/pyMetaLearn/metalearning/test_kND.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,21 +42,21 @@ def test_kNearestDatasets(self):
neighbor, distance = kND.kNearestDatasets(self.anneal, 1,
return_distance=True)
self.assertEqual([233], neighbor)
np.testing.assert_array_almost_equal([1.82298937], distance)
np.testing.assert_array_almost_equal([3.8320802803440586], distance)

neighbors = kND.kNearestDatasets(self.anneal, 2)
self.assertEqual([233, 234], neighbors)
neighbors, distance = kND.kNearestDatasets(self.anneal, 2,
return_distance=True)
self.assertEqual([233, 234], neighbors)
np.testing.assert_array_almost_equal([1.822989, 2.267919], distance)
np.testing.assert_array_almost_equal([3.8320802803440586, 4.367919719655942], distance)

neighbors = kND.kNearestDatasets(self.anneal, -1)
self.assertEqual([233, 234], neighbors)
neighbors, distance = kND.kNearestDatasets(self.anneal, -1,
return_distance=True)
self.assertEqual([233, 234], neighbors)
np.testing.assert_array_almost_equal([1.822989, 2.267919], distance)
np.testing.assert_array_almost_equal([3.8320802803440586, 4.367919719655942], distance)

self.assertRaises(ValueError, kND.kNearestDatasets, self.anneal, 0)
self.assertRaises(ValueError, kND.kNearestDatasets, self.anneal, -2)
Expand All @@ -67,35 +67,23 @@ def test_kBestSuggestions(self):
self.runs.loc[:, [233, 234]])
neighbor = kND.kBestSuggestions(self.anneal, 1)
np.testing.assert_array_almost_equal(
[(233, 1.8229893712531495, 1)],
[(233, 3.8320802803440586, 1)],
neighbor,
)
neighbors = kND.kBestSuggestions(self.anneal, 2)
np.testing.assert_array_almost_equal(
[(233, 1.8229893712531495, 1), (234, 2.2679197196559415, 2)],
[(233, 3.8320802803440586, 1), (234, 4.367919719655942, 2)],
neighbors,
)
neighbors = kND.kBestSuggestions(self.anneal, -1)
np.testing.assert_array_almost_equal(
[(233, 1.8229893712531495, 1), (234, 2.2679197196559415, 2)],
[(233, 3.8320802803440586, 1), (234, 4.367919719655942, 2)],
neighbors,
)

self.assertRaises(ValueError, kND.kBestSuggestions, self.anneal, 0)
self.assertRaises(ValueError, kND.kBestSuggestions, self.anneal, -2)

def test_scale(self):
kND = KNearestDatasets()
metafeatures = pd.DataFrame([self.anneal, self.krvskp])
metafeatures, other = kND._scale(metafeatures, self.labor)
from pandas.util.testing import assert_series_equal
# Series.equal does not work properly with floats...
assert_series_equal(metafeatures.iloc[0],
pd.Series({"number_of_instances": 0.267919719656,
"number_of_classes": 1,
"number_of_features": 1},
name=232))

def test_random_metric(self):
kND = KNearestDatasets(metric=get_random_metric(random_state=1))
kND.fit(pd.DataFrame([self.krvskp, self.labor]),
Expand Down