From a6622ab1d5c3daac93df8e4462ce343e28b044b8 Mon Sep 17 00:00:00 2001
From: faturita <rramele@gmail.com>
Date: Thu, 27 Jun 2024 10:39:53 -0300
Subject: [PATCH] Update due to library version changes.

---
 filter_spatial.py              |  4 +---
 onepassclassifier.py           |  2 +-
 onepassfeatureextraction.py    |  2 +-
 signalfeatureclassification.py | 23 +++++++++++------------
 4 files changed, 14 insertions(+), 17 deletions(-)

diff --git a/filter_spatial.py b/filter_spatial.py
index 1aba3e5..1a68bfe 100644
--- a/filter_spatial.py
+++ b/filter_spatial.py
@@ -29,15 +29,13 @@
 
 # The first plot with all the signals, as it may be in reality.
 plt.figure(1)
-plt.title('Sinusoidal')
 plt.subplot(3,1,1)
 plt.plot(s1, color='red')
-plt.title('Squared')
 plt.subplot(3,1,2)
 plt.plot(s2, color='steelblue')
-plt.title('Sawtooth')
 plt.subplot(3,1,3)
 plt.plot(s3, color='orange')
+plt.show()
 
 
 # Put all the signals together in a multichannel arrangement
diff --git a/onepassclassifier.py b/onepassclassifier.py
index 0656a99..96324c2 100644
--- a/onepassclassifier.py
+++ b/onepassclassifier.py
@@ -53,7 +53,7 @@ def unpickle_keypoints(array):
     keypoints = []
     descriptors = []
     for point in array:
-        temp_feature = cv2.KeyPoint(x=point[0][0],y=point[0][1],_size=point[1], _angle=point[2], _response=point[3], _octave=point[4], _class_id=point[5])
+        temp_feature = cv2.KeyPoint(x=point[0][0],y=point[0][1],size=point[1], angle=point[2], response=point[3], octave=point[4], class_id=point[5])
         temp_descriptor = point[6]
         keypoints.append(temp_feature)
         descriptors.append(temp_descriptor)
diff --git a/onepassfeatureextraction.py b/onepassfeatureextraction.py
index 5eb5314..fa432aa 100644
--- a/onepassfeatureextraction.py
+++ b/onepassfeatureextraction.py
@@ -53,7 +53,7 @@ def unpickle_keypoints(array):
 
 print ("Connecting..")
 
-for i in range(1,20):
+for i in range(1,2000):
     # Capture frame-by-frame
     ret, frame = cap.read()
 
diff --git a/signalfeatureclassification.py b/signalfeatureclassification.py
index 8235395..2c4eeec 100644
--- a/signalfeatureclassification.py
+++ b/signalfeatureclassification.py
@@ -3,8 +3,8 @@
 Signal Feature Classification
 ==========================================
 
-# Run with ann virtual environment
-# EPOC Emotiv file format https://www.researchgate.net/publication/332514530_EPOC_Emotiv_EEG_Basics
+# Run with a virtual environment with keras, sklearn, numpy and tensorflow installed.
+# EPOC Emotiv file format https://arxiv.org/pdf/2206.09051
 
 # OpemMP sometimes raises coredumps, try export KMP_DUPLICATE_LIB_OK=TRUE
 
@@ -38,6 +38,14 @@
 
 from scipy.signal import butter, lfilter
 
+from sklearn.linear_model import LogisticRegression
+
+from keras.models import Sequential
+from keras.layers import Dense
+
+import matplotlib.pyplot as plt
+
+
 def isartifact(window, threshold=80):
     # Window is EEG Matrix
 
@@ -46,10 +54,6 @@ def isartifact(window, threshold=80):
     signalaverage = ameans.tolist()
     athresholds = np.asarray([threshold]*len(signalaverage))
 
-    #print awindow
-    #print ameans
-    #print athresholds
-
     # FIXME
     for t in range(0,len(window)):
         asample = (ameans+athresholds)-awindow[t]
@@ -62,7 +66,7 @@ def isartifact(window, threshold=80):
 
     return False
 
-import matplotlib.pyplot as plt
+
 
 def butter_bandpass(lowcut, highcut, fs, order=5):
     nyq = 0.5 * fs
@@ -296,8 +300,6 @@ def classify(afeatures1, afeatures2, featuresize):
     report = classification_report(testlabels, predlabels, target_names=target_names)
     print(report)
 
-    from sklearn.linear_model import LogisticRegression
-
     # all parameters not specified are set to their defaults
     logisticRegr = LogisticRegression()
     logisticRegr.fit(trainingdata,traininglabels)
@@ -315,9 +317,6 @@ def classify(afeatures1, afeatures2, featuresize):
     report = classification_report(testlabels, predlabels, target_names=target_names)
     print(report)
 
-    from keras.models import Sequential
-    from keras.layers import Dense
-
     model = Sequential([
         Dense(64, activation='tanh', input_shape=(trainingdata.shape[1],)),
         Dense(32, activation='tanh'),