"""
import matplotlib.pyplot as plt
plt.figure(1,figsize=(20,5))
plt.plot(signals[10,0,:])
plt.plot(signals[150,0,:])
plt.plot(signals[240,0,:])
plt.show()
"""
################## TRAIN TEST SPLIT #################
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(signals_ffts, labels, test_size=0.4)
clf = classificator.SignalClassificator("medium_difference")
clf.fit(x_train, y_train, verbose=True)
y_pred = clf.predict(x_test, 11, verbose=False)
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))
"""
plt.figure(1,figsize=(20,5))
plt.plot(clf.master_dict["0"][0,:], color="yellow")
plt.plot(clf.master_dict["1"][0,:], color="green")
plt.plot(clf.master_dict["2"][0,:], color="red")
plt.show()
"""
signals = []
for file in X_FILES:
s = np.array(read_signals("../test/test/" + file))
signals.append(s)
signals = np.transpose(np.array(signals), (1, 0, 2))
labels = np.array(
pd.read_csv("../test/test/" + Y_FILE, header=None, index_col=None))
labels = np.squeeze(labels)
t = transform.FFTGenerator(T, N, fs)
v_ffts = t.doFFT(signals, delete_offset=True)
print(v_ffts.shape)
################## TRAIN TEST SPLIT #################
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(v_ffts[:, :, :, 1],
labels,
test_size=0.4)
cls = classificator.SignalClassificator()
cls.fit(x_train, y_train)
y_pred = cls.predict(x_test, 4.5, verbose=True)
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))
print(signals_ffts.shape)
import matplotlib.pyplot as plt
plt.figure(1, figsize=(20, 5))
plt.plot(signals_filtered[10, 0, :])
plt.plot(signals_filtered[150, 0, :])
plt.plot(signals_filtered[240, 0, :])
plt.show()
################## TRAIN TEST SPLIT #################
from sklearn.model_selection import train_test_split
x_train, x_test, y_train, y_test = train_test_split(signals_ffts,
labels,
test_size=0.4)
clf = classificator.SignalClassificator("medium_correlation")
clf.fit(x_train, y_train, verbose=True)
y_pred = clf.predict(x_test, 0, verbose=True)
from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))
plt.figure(1, figsize=(20, 5))
plt.plot(clf.master_dict["0"][0, :], color="yellow")
plt.plot(clf.master_dict["1"][0, :], color="green")
plt.plot(clf.master_dict["2"][0, :], color="red")
plt.show()