From 074f3dae0b970c2bbfa9ca093930786d6886f8d8 Mon Sep 17 00:00:00 2001
From: Luc Giffon <luc.giffon@lis-lab.fr>
Date: Tue, 30 Oct 2018 09:23:52 +0100
Subject: [PATCH] fix problem normalization in Dataset class + Test
---
skluc/main/data/mldatasets/Dataset.py | 19 +++++++------------
.../test_data/test_mldatasets/TestDataset.py | 7 ++++++-
2 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/skluc/main/data/mldatasets/Dataset.py b/skluc/main/data/mldatasets/Dataset.py
index f211bb7..325f577 100644
--- a/skluc/main/data/mldatasets/Dataset.py
+++ b/skluc/main/data/mldatasets/Dataset.py
@@ -34,14 +34,6 @@ class Dataset(object):
self.permuted_index_validation = None
self.validation_size = validation_size
- @property
- def min(self):
- return np.min(self.train.data)
-
- @property
- def max(self):
- return np.max(self.train.data)
-
def reduce_data_size(self, new_size):
logger.info("Reducing datasize of dataset {} to .".format(self.s_name, new_size))
kept_indices = self.get_uniform_class_rand_indices_train(new_size)
@@ -220,16 +212,19 @@ class Dataset(object):
:return:
"""
logger.info("Apply normalization to data from dataset {}.".format(self.s_name))
+ _min = np.min(self.train.data)
+ _max = np.max(self.train.data)
+ logger.debug(f"Minimum value of train set is {_min}; max is {_max}")
+
for kw in self.data_groups_private:
+ logger.debug("Apply normalization to {} data of {} dataset.".format(kw, self.s_name))
datlab = getattr(self, kw)
if len(datlab.labels) == 0:
continue
data = datlab.data
- _min = self.min
- _max = self.max
- logger.debug(f"Minimum value of train set is {_min}; max is {_max}")
+ logger.debug(f"Minimum value of {kw} set before normalization is {np.min(data)}; max is {np.max(data)}")
data = (data - _min) / (_max - _min)
- logger.debug("Apply normalization to {} data of {} dataset.".format(kw, self.s_name))
+ logger.debug(f"Minimum value of {kw} set after normalization is {np.min(data)}; max is {np.max(data)}")
setattr(self, kw, LabeledData(data, datlab.labels))
def data_astype(self, _type):
diff --git a/skluc/test/test_data/test_mldatasets/TestDataset.py b/skluc/test/test_data/test_mldatasets/TestDataset.py
index a9c9e2e..2d97f22 100644
--- a/skluc/test/test_data/test_mldatasets/TestDataset.py
+++ b/skluc/test/test_data/test_mldatasets/TestDataset.py
@@ -2,6 +2,7 @@ import unittest
import numpy as np
+from skluc.main.data.mldatasets import Cifar100FineDataset, Cifar10Dataset, MnistDataset, SVHNDataset
from skluc.main.data.mldatasets.Dataset import Dataset
from skluc.main.utils import LabeledData
@@ -22,7 +23,11 @@ class FooDataset(Dataset):
class TestDataset(unittest.TestCase):
def setUp(self):
- self.dataset_classes = [FooDataset]
+ self.dataset_classes = [FooDataset,
+ Cifar100FineDataset,
+ Cifar10Dataset,
+ MnistDataset,
+ SVHNDataset]
def test_min_max(self):
for d_class in self.dataset_classes:
--
GitLab