diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index cda6a4fe543650d59833a0424085d436a843c59a..27aed8b9fa4d4249225607f77befe62badcc0d48 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -14,6 +14,7 @@ unbutu:17.10:
when: always
untracked: true
paths:
- - build_python
+ - public
+ - build
expire_in: 8d
diff --git a/splearn/hankel.py b/splearn/hankel.py
index e9f0d844a0a09ed3a149c24ea090afe36785ac0f..6e629a265785726d476e2749a40a55088704ddf7 100644
--- a/splearn/hankel.py
+++ b/splearn/hankel.py
@@ -112,24 +112,35 @@ class Hankel(object):
raise ValueError("At least sample_instance or lhankel has to be not None.")
def __eq__(self, other):
- print("Hankel equality check")
+ #print("Hankel equality check")
if self.version != other.version:
- print("different versions")
+ #print("version is different")
return False
if self.partial != other.partial:
+ #print("partial is different")
return False
if self.sparse != other.sparse:
+ #print("sparse is different")
return False
if self.build_from_sample != other.build_from_sample:
+ #print("build_from_sample is different")
return False
if self.nbL != other.nbL:
+ #print("nbL is different")
return False
if self.nbEx != other.nbEx:
+ #print("nbEx is different")
return False
if len(self.lhankel) != len(other.lhankel):
+ #print("lhankel length is different")
return False
for lh1, lh2 in zip(self.lhankel, other.lhankel):
- if (lh1 != lh2).nnz > 0:
+ if self.sparse:
+ if (lh1 != lh2).nnz > 0:
+ #print("{:d} elements oh lhandel are different".format((lh1 != lh2).nnz))
+ return False
+ elif not np.array_equal(lh1, lh2):
+ #print("Different Array")
return False
return True
diff --git a/splearn/serializer.py b/splearn/serializer.py
index f7da0e5769ce24e24c1480099b5a3ea97fca149c..cc22be7ceb428465b79888433c94a46aea8e4b74 100644
--- a/splearn/serializer.py
+++ b/splearn/serializer.py
@@ -153,10 +153,12 @@ class Serializer(object):
if "scipy.dok_matrix" in data_str:
data = data_str["scipy.dok_matrix"]
keys = {"shape", "dtype", "values"}
+ errorMsg = "The input data string (" + str(data_str)
+ errorMsg += ") should contain the following keys : \"" + '\", \"'.join(keys) + "\""
+ if data is None:
+ raise ValueError(errorMsg)
if not keys.issubset(set(data.keys())):
- raise ValueError("The input data string (" + str(data_str) +
- ") should contain the following keys : \"" +
- '\", \"'.join(keys) + "\"")
+ raise ValueError(errorMsg)
values = Serializer.__restore_json(data["values"])
shape = Serializer.__restore_json(data["shape"])
dok = sps.dok_matrix(shape, dtype=data["dtype"])
@@ -168,33 +170,35 @@ class Serializer(object):
if "numpy.ndarray" in data_str:
data = data_str["numpy.ndarray"]
keys = {"values", "dtype"}
+ errorMsg = "The input data string (" + str(data_str)
+ errorMsg += ") should contain the following keys : \"" + '\", \"'.join(keys) + "\""
if data is None:
- raise ValueError("The input data string (" + str(data_str) +
- ") should contain the following keys : \"" +
- '\", \"'.join(keys) + "\"")
+ raise ValueError(errorMsg)
if not keys.issubset(set(data.keys())):
- raise ValueError("The input data string (" + str(data_str) +
- ") should contain the following keys : \"" +
- '\", \"'.join(keys) + "\"")
+ raise ValueError(errorMsg)
return np.array(data["values"], dtype=data["dtype"])
if "automaton" in data_str:
data = Serializer.__restore_yaml(data_str["automaton"])
keys = {"nbL", "nbS", "initial", "final", "transitions", "type"}
+ errorMsg = "The input data string (" + str(data_str)
+ errorMsg += ") should contain the following keys : \"" + '\", \"'.join(keys) + "\""
+ if data is None:
+ raise ValueError(errorMsg)
if not keys.issubset(set(data.keys())):
- raise ValueError("The input data string (" + str(data_str) +
- ") should contain the following keys : \"" +
- '\", \"'.join(keys) + "\"")
+ raise ValueError(errorMsg)
return Automaton(nbL=data["nbL"], nbS=data["nbS"], initial=Serializer.__restore_yaml(data["initial"]),
final=Serializer.__restore_yaml(data["final"]),
transitions=[Serializer.__restore_yaml(k) for k in data["transitions"]],
type=data["type"])
if "hankel" in data_str:
- data = Serializer.__restore_json(data_str["hankel"])
+ data = Serializer.__restore_yaml(data_str["hankel"])
keys = {"nbL", "lhankel", "version", "partial", "sparse", "build_from_sample", "nbEx"}
+ errorMsg = "The input data string (" + str(data_str)
+ errorMsg += ") should contain the following keys : \"" + '\", \"'.join(keys) + "\""
+ if data is None:
+ raise ValueError(errorMsg)
if not keys.issubset(set(data.keys())):
- raise ValueError("The input data string (" + str(data_str) +
- ") should contain the following keys : \"" +
- '\", \"'.join(keys) + "\"")
+ raise ValueError(errorMsg)
H = Hankel(version=data["version"], partial=data["partial"], sparse=data["sparse"],
lhankel = [Serializer.__restore_yaml(k) for k in data["lhankel"]])
if data["build_from_sample"]:
diff --git a/splearn/tests/test_hankel.py b/splearn/tests/test_hankel.py
index 970f16a1a6417c97e51d896b40e66c7f6d8e3fe1..2f2a4bc1cb6d43aa8faf681db67347f50ab6eded 100644
--- a/splearn/tests/test_hankel.py
+++ b/splearn/tests/test_hankel.py
@@ -36,16 +36,17 @@
from __future__ import division, print_function
import unittest
+import numpy as np
+import scipy.sparse as sps
+
from splearn.datasets.base import load_data_sample
from splearn.automaton import Automaton
from splearn.spectral import Spectral
from splearn.hankel import Hankel
from splearn.tests.datasets.get_dataset_path import get_dataset_path
-import numpy as np
-import scipy.sparse as sps
-class UnitaryTest(unittest.TestCase):
+class HankelTest(unittest.TestCase):
def test_CreateHankel_classic(self):
adr = get_dataset_path("essai")
@@ -344,5 +345,48 @@ class UnitaryTest(unittest.TestCase):
with self.assertRaises(TypeError):
h.nbEx = 6.8
+ def testEqualityOperator(self):
+ adr = get_dataset_path("essai")
+ data = load_data_sample(adr=adr)
+ cl = Spectral()
+ cl._polulate_dictionnaries(data.data)
+ h1 = Hankel(sample_instance=data.data, lrows=1, lcolumns=1,
+ version="classic", partial=False, sparse=False)
+ h2 = Hankel(sample_instance=data.data, lrows=1, lcolumns=1,
+ version="prefix", partial=False, sparse=False)
+ self.assertTrue(h1 != h2)
+ h2 = Hankel(sample_instance=data.data, lrows=1, lcolumns=1,
+ version="classic", partial=True, sparse=False)
+ self.assertTrue(h1 != h2)
+ h2 = Hankel(sample_instance=data.data, lrows=1, lcolumns=1,
+ version="classic", partial=False, sparse=True)
+ self.assertTrue(h1 != h2)
+ h2 = Hankel(sample_instance=data.data, lrows=1, lcolumns=1,
+ version="classic", partial=False, sparse=False)
+ h2.lhankel[0][0,0] -= 1.0
+ self.assertTrue(h1 != h2)
+ h2.lhankel = h2.lhankel[1:]
+ self.assertTrue(h1 != h2)
+ h2.nbEx -= 1
+ self.assertTrue(h1 != h2)
+ h2.nbL -= 1
+ self.assertTrue(h1 != h2)
+ l = [(0,), (1,), (0,0), (0,1), (1,0), (1,1)]
+ h2 = h1.to_automaton(2).to_hankel(lrows=l, lcolumns=l)
+ self.assertTrue(h1 != h2)
+
+ adr = get_dataset_path("3.pautomac.train")
+ data = load_data_sample(adr=adr)
+ X = data.data
+ sp1 = Spectral()
+ sp1 = sp1.fit(X)
+ H1 = sp1.hankel
+ sp2 = Spectral()
+ sp2 = sp2.fit(X)
+ H2 = sp2.hankel
+ H2.lhankel[0][(1, 1610)] = 0
+ self.assertTrue(H1 != H2)
+
+
if __name__ == '__main__':
unittest.main()
diff --git a/splearn/tests/test_serializer.py b/splearn/tests/test_serializer.py
index aa80ad1bd0c6b5b8de4d4a7ac589298265d49764..fddafd8002d6e27b7d0716adb2963748b2c7daac 100644
--- a/splearn/tests/test_serializer.py
+++ b/splearn/tests/test_serializer.py
@@ -46,7 +46,7 @@ from splearn.spectral import Spectral
from splearn.tests.datasets.get_dataset_path import get_dataset_path
from splearn.datasets.base import load_data_sample
-class UnitaryTest(unittest.TestCase):
+class SerializerTest(unittest.TestCase):
def setUp(self):
@@ -119,21 +119,24 @@ class UnitaryTest(unittest.TestCase):
Serializer.data_to_json(deque('ghi'))
def testBadDataException(self):
- yamlstr = "- scipy.dok_matrix:\n shape:\n tuple: [1, 1]\n values: {'(0,0)': 1.0}"
- with self.assertRaises(ValueError):
- Serializer.yaml_to_data(yamlstr)
- jsonstr = "{\"scipy.dok_matrix\":{}}"
- with self.assertRaises(ValueError):
- Serializer.json_to_data(jsonstr)
- yamlstr = "- numpy.ndarray:"
- with self.assertRaises(ValueError):
- Serializer.yaml_to_data(yamlstr)
- yamlstr = "- numpy.ndarray:\n dtype: float64"
- with self.assertRaises(ValueError):
- Serializer.yaml_to_data(yamlstr)
- jsonstr = "{\"numpy.ndarray\":{}}"
- with self.assertRaises(ValueError):
- Serializer.json_to_data(jsonstr)
+ yamlstrList = ["- scipy.dok_matrix:",
+ "- scipy.dok_matrix:\n shape:\n tuple: [1, 1]\n values: {'(0,0)': 1.0}",
+ "- numpy.ndarray:",
+ "- numpy.ndarray:\n dtype: float64",
+ "- automaton:",
+ "- automaton:\n nbL: 1",
+ "- hankel:",
+ "- hankel:\n nbL: 1"]
+ jsonstrList = ["{\"scipy.dok_matrix\":{}}",
+ "{\"numpy.ndarray\":{}}",
+ "{\"automaton\":{}}",
+ "{\"hankel\":{}}"]
+ for yamlstr in yamlstrList:
+ with self.assertRaises(ValueError):
+ Serializer.yaml_to_data(yamlstr)
+ for jsonstr in jsonstrList:
+ with self.assertRaises(ValueError):
+ Serializer.json_to_data(jsonstr)
if __name__ == "__main__":
#import sys;sys.argv = ['', 'Test.testName']