Adding subwindow approach support

README.md

@@ -34,6 +34,12 @@ Configuration parameters are located at the beginning of CV_script, you MUST cha
 To change or check the algorithms parameters, they all are redefined in custom wrapper classes to avoid errors, if a parameter is not specified in the constructor, it is left as default.
 The representations methods are defined inside utils.representations and the classifications methods inside utils.classifications.
 
+To change the parameter of TS-CHIEF, you can change the values of the following arguments in the ts-chief script:
+```bash
+-trees="300" -s="ee:4,boss:50,rise:50"
+```
+If you want to give more predictive power to this algorithm, increasing the number of trees and the number of random split generated by each method (boss, rise, ...) is the way to go. We used those value to avoid memory errors, the shorter the input time series, the higher those values can be without causing trouble.
+
 ## Usage
 
 Extract the files of the dataset archive located in ~/datasets in the dataset folder
@@ -74,8 +80,6 @@ by
 from sktime.utils.data_container import tabularize, from_3d_numpy_to_nested
 ```
 
-* We also modified InceptionTime to use binary_crossentropy (change loss name and use sigmod layer with 1 neuron as an output) and weighted accuracy for early stopping. This is not mandatory but is more suited to our problem.
-
 ## Contributing
 
 If any bug should occur, please open a issue so we can work on a fix !

ts-chief_script.sh

 #!/bin/bash
 n_cv=9
 n_r=4
-size=1000
+size=1513
 
 for id_r in `seq 1 $n_r`
 do
 	for id_cv in `seq 0 $n_cv`
 	do
-		jdk/jdk-15/bin/java -jar tschief.jar -train="datasets/TSCHIEF/data_Train_"$size"_"$id_cv"_R"$id_r".csv" -test="datasets/TSCHIEF/data_Test_"$size"_"$id_cv"_R"$id_r".csv" -out="results/TSCHIEF/" -repeats="1" -trees="500" -s="ee:10,boss:150,rise:150" -export="1" -verbosity="1" -shuffle="True" -target_column="last"
+		jdk/jdk-15/bin/java -Xms6G -Xmx12G -jar tschief.jar -train="datasets/TSCHIEF/data_Train_"$size"_"$id_cv"_R"$id_r".csv" -test="datasets/TSCHIEF/data_Test_"$size"_"$id_cv"_R"$id_r".csv" -out="results/TSCHIEF/" -repeats="1" -trees="300" -s="ee:4,boss:50,rise:50" -export="1" -verbosity="1" -shuffle="True" -target_column="last" 
 	done
 done
 

utils/classifications.py

@@ -9,7 +9,7 @@ from sklearn.svm import SVC
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.linear_model import RidgeClassifier
 from sktime.classification.interval_based import TimeSeriesForest
-from sktime.utils.data_container import concat_nested_arrays as cna
+from sktime.utils.data_container import _concat_nested_arrays as cna
 from sktime.classification.frequency_based import RandomIntervalSpectralForest
 from sklearn.base import BaseEstimator, ClassifierMixin
 
@@ -58,14 +58,13 @@ class ResNetV2(BaseEstimator, ClassifierMixin):
             classes=1,
             classifier_activation="sigmoid",
         )
-        model.compile(optimizer=self.optimizer, loss=self.loss, weighted_metrics=['accuracy'])
+        model.compile(optimizer=self.optimizer, loss=self.loss, metrics=['accuracy'])
         self.model = model
 
-    def fit(self, X, y, epochs=1000, batch_size=32, return_hist=False, el_patience=70, verbose=0, val_size=0.1):
+    def fit(self, X, y, epochs=1500, batch_size=32, return_hist=False, el_patience=100, verbose=0, val_size=0.1):
         self.init_model((X.shape[1], X.shape[2], X.shape[3]))
         X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=val_size)
-        el = EarlyStopping(monitor='val_accuracy', patience=el_patience, restore_best_weights=True, mode='max')
-        cw = compute_class_weight('balanced', np.unique(y_train), y_train)
+        el = EarlyStopping(monitor='val_loss', patience=el_patience, restore_best_weights=True, mode='min')
 
         self.model.fit(
             X_train, y_train,
@@ -74,8 +73,7 @@ class ResNetV2(BaseEstimator, ClassifierMixin):
             batch_size=batch_size,
             verbose=verbose,
             callbacks=[el],
-            shuffle=True,
-            class_weight={0:cw[0],1:cw[1]}
+            shuffle=True
         )
         return self
 
@@ -85,7 +83,7 @@ class ResNetV2(BaseEstimator, ClassifierMixin):
     def predict_proba(self,X):
         return self.model.predict(X)
 
-    
+#Depending on your sktime_dl version, this might throw import errors, see Readme for a fix.
 from sktime_dl.deeplearning.inceptiontime._classifier import InceptionTimeClassifier
 
 
@@ -100,8 +98,8 @@ class InceptionTime(BaseEstimator, ClassifierMixin):
             el_patience=100, verbose=False, val_size=0.1):
         self.model = InceptionTimeClassifier(verbose=verbose, depth=self.depth,
                                              nb_filters=self.nb_filters, bottleneck_size=self.bottleneck_size,
-                                             callbacks=[EarlyStopping(monitor='val_accuracy', patience=el_patience,
-                                                                      restore_best_weights=True, mode='max')])
+                                             callbacks=[EarlyStopping(monitor='val_loss', patience=el_patience,
+                                                                      restore_best_weights=True, mode='min')])
 
         X_train, X_val, y_train, y_val = train_test_split(X, y, test_size=val_size)
         self.model.fit(X_train, y_train, validation_X=X_val,validation_y=y_val)
@@ -141,7 +139,8 @@ class RISE(BaseEstimator, ClassifierMixin, SktimeEstimator):
 
     def fit(self,X,y):
         X, y = self._sktime_format(X,y)
-        self.estimator = RandomIntervalSpectralForest(n_estimators=self.n_estimators, min_interval=self.min_length)
+        self.estimator = RandomIntervalSpectralForest(n_estimators=self.n_estimators,
+                                                      min_interval=self.min_length)
         self.estimator.fit(X,y)
         return self
 
@@ -155,11 +154,10 @@ class RISE(BaseEstimator, ClassifierMixin, SktimeEstimator):
 
 
 class Random_Forest(BaseEstimator, ClassifierMixin):
-    def __init__(self, n_estimators=300, max_depth=None, max_features=0.75, max_samples=0.75,
+    def __init__(self, n_estimators=300, max_depth=None, max_samples=0.75,
             ccp_alpha=0.0225, class_weight="balanced_subsample"):
         self.n_estimators=n_estimators
         self.max_depth=max_depth
-        self.max_features=max_features
         self.max_samples=max_samples
         self.ccp_alpha=ccp_alpha
         self.class_weight=class_weight
@@ -167,9 +165,11 @@ class Random_Forest(BaseEstimator, ClassifierMixin):
 
     def fit(self, X, y):
         X = np.asarray([x.astype(np.float32) for x in X])
-        self.estimator = RandomForestClassifier(n_estimators=self.n_estimators, max_depth=self.max_depth,
-                                                max_features=self.max_features, max_samples=self.max_samples,
-                                                ccp_alpha=self.ccp_alpha,class_weight=self.class_weight)
+        self.estimator = RandomForestClassifier(n_estimators=self.n_estimators,
+                                                max_depth=self.max_depth,
+                                                max_samples=self.max_samples,
+                                                ccp_alpha=self.ccp_alpha,
+                                                class_weight=self.class_weight)
 
         self.estimator.fit(X,y)
         return self
@@ -183,14 +183,15 @@ class Random_Forest(BaseEstimator, ClassifierMixin):
         return self.estimator.predict_proba(X)
 
 class KNN_classif(BaseEstimator, ClassifierMixin):
-    def __init__(self, n_neighbors=9, weights='distance',p=2):
+    def __init__(self, n_neighbors=7, weights='distance',p=2):
         self.n_neighbors = n_neighbors
         self.weights = weights
         self.p = p
         self.estimator = None
 
     def fit(self,X,y):
-        self.estimator = KNeighborsClassifier(n_neighbors=self.n_neighbors, weights=self.weights, p=self.p)
+        self.estimator = KNeighborsClassifier(n_neighbors=self.n_neighbors,
+                                              weights=self.weights, p=self.p)
         self.estimator.fit(X,y)
         return self
 
@@ -201,7 +202,7 @@ class KNN_classif(BaseEstimator, ClassifierMixin):
         return self.estimator.predict_proba(X)
 
 class TimeSeries_Forest(BaseEstimator, ClassifierMixin, SktimeEstimator):
-    def __init__(self, n_estimators=300,  min_interval=3):
+    def __init__(self, n_estimators=300,  min_interval=5):
         self.n_estimators = n_estimators
         self.min_interval = min_interval
         self.estimator = None
@@ -228,7 +229,7 @@ class SVM_classif(BaseEstimator, ClassifierMixin):
                  cache_size=500, class_weight='balanced'):
             self.C = C
             self.kernel = kernel
-            self.degree = degree
+            self.degree = degree #Not used with RBF
             self.gamma = gamma
             self.cache_size = cache_size
             self.class_weight = class_weight
@@ -275,7 +276,7 @@ class Ridge_classif(BaseEstimator, ClassifierMixin):
         return self.estimator.predict_proba(X)
 
 class KNN_TS_classif(BaseEstimator, ClassifierMixin, PytsEstimator):
-    def __init__(self, n_neighbors=9, weights='distance', p=2):
+    def __init__(self, n_neighbors=7, weights='distance', p=2):
         self.n_neighbors = n_neighbors
         self.weights = weights
         self.p = p
@@ -296,11 +297,10 @@ class KNN_TS_classif(BaseEstimator, ClassifierMixin, PytsEstimator):
         X = self._format_X(X)
         return self.estimator.predict_proba(X)
 
-
 class BOSSVS_classif(BaseEstimator, ClassifierMixin, PytsEstimator):
-    def __init__(self, word_size=9, n_bins=7, window_size=0.2, window_step=1,
+    def __init__(self, word_size=5, n_bins=5, window_size=0.15, window_step=0.01,
                  anova=True, drop_sum=False, norm_mean=False, norm_std=False,
-                 strategy='uniform', alphabet=None):
+                 strategy='quantile', alphabet=None,smooth_idf=True):
         self.word_size = word_size
         self.n_bins = n_bins
         self.window_size = window_size
@@ -311,6 +311,7 @@ class BOSSVS_classif(BaseEstimator, ClassifierMixin, PytsEstimator):
         self.norm_std = norm_std
         self.strategy = strategy
         self.alphabet = alphabet
+        self.smooth_idf = smooth_idf
         self.estimator = None
 
     def fit(self,X,y):
@@ -319,7 +320,8 @@ class BOSSVS_classif(BaseEstimator, ClassifierMixin, PytsEstimator):
                                 window_size=self.window_size, window_step=self.window_step,
                                 anova=self.anova, drop_sum=self.drop_sum,
                                 norm_mean=self.norm_mean, norm_std=self.norm_std,
-                                strategy=self.strategy, alphabet=self.alphabet)
+                                strategy=self.strategy, alphabet=self.alphabet,
+                                smooth_idf=self.smooth_idf)
 
         self.estimator.fit(X,y)
         return self

utils/representations.py

@@ -109,7 +109,7 @@ class PiecewiseApproximation_transform(BaseEstimator, TransformerMixin):
         return self
 
 class SymbolicAggregate_transform(BaseEstimator, TransformerMixin):
-    def __init__(self, n_bins=7, strategy='uniform', alphabet='ordinal'):
+    def __init__(self, n_bins=5, strategy='uniform', alphabet='ordinal'):
         self.n_bins = n_bins
         self.strategy = strategy
         self.alphabet = alphabet
@@ -128,8 +128,8 @@ class SymbolicAggregate_transform(BaseEstimator, TransformerMixin):
         return self
 
 class SymbolicFourrier_transform(BaseEstimator, TransformerMixin):
-    def __init__(self, n_coefs=20, n_bins=7, strategy='uniform', drop_sum=False,
-                 anova=True, norm_mean=True, norm_std=False, alphabet='ordinal'):
+    def __init__(self, n_coefs=10, n_bins=5, strategy='uniform', drop_sum=True,
+                 anova=True, norm_mean=False, norm_std=False, alphabet='ordinal'):
         self.n_coefs = n_coefs
         self.n_bins = n_bins
         self.strategy = strategy
@@ -156,7 +156,7 @@ class SymbolicFourrier_transform(BaseEstimator, TransformerMixin):
 
 
 class MatrixProfile_transform():
-    def __init__(self, window_size=0.075):
+    def __init__(self, window_size=0.15):
         self.window_size = window_size
 
     def transform(self, X, y=None):
@@ -170,7 +170,7 @@ class MatrixProfile_transform():
         return self
 
 class ROCKET_transform(BaseEstimator, TransformerMixin):
-    def __init__(self, n_kernels=15000, kernel_sizes=(5,7,9), flatten=False):
+    def __init__(self, n_kernels=20000, kernel_sizes=(5,7,9,11), flatten=False):
         self.flatten = flatten
         self.n_kernels = n_kernels
         self.kernel_sizes = kernel_sizes