ms762wu/EMG_Biometrics_2021
2
1
Fork 0
Code Issues Pull Requests Releases Wiki Activity

chore: add information about sessions

Browse Source 
into the mfcc json file
This commit is contained in:
Skudalen 2021-07-09 16:58:16 +02:00
parent 8faa352af9
commit 4ba390a268
4 changed files with 2913 additions and 589286 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
Handle_emg_data.py
View File

@ -528,12 +528,12 @@ class NN_handler:
4: [],
5: []
}
# Should med 4 sessions * (~150, 208) of mfcc samples per person. One DataFrame per subject
self.mfcc_samples_per_subject = {1: None,
2: None,
3: None,
4: None,
5: None
# Should med 4 sessions * (~150, 208) of mfcc samples per person. One [DataFrame, session_length_list] per subject
self.mfcc_samples_per_subject = {1: [],
2: [],
3: [],
4: [],
5: []
}
# GET method for reg_samples_dict
@ -627,8 +627,8 @@ class NN_handler:
# Takes in all EMG session Dataframe and creates DataFrame of MFCC samples
# Input: DataFrame(shape[1]=16, EMG data)
# Output: DataFrame(merged MFCC data, shape: (n, 13*16))
def make_mfcc_df_from_session_df(self, session_df) -> DataFrame:
# Output: DataFrame(merged MFCC data, shape: (n, 13*16)), length of session datapoints
def make_mfcc_df_from_session_df(self, session_df):
session_df.rename(columns={0:'timestamp'}, inplace=True)
samplerate = get_samplerate(session_df)
attach_func = lambda list_1, list_2: list_1.extend(list_2)
@ -645,16 +645,19 @@ class NN_handler:
mfcc_i = DataFrame(mfcc_i).dropna()
mfcc_i['combined'] = mfcc_i.values.tolist()
df = result_df.combine(mfcc_i['combined'], attach_func)
session_length = (len(result_df.index)) # Add the length of session data points
return result_df
return result_df, session_length
# Merges MFCC data from all sessions and stores the sample data in
# the NN_handler's mfcc_samples_per_subject dict
# Input: None(NN_handler)
# Output: None -> stores in NN_handler
# Output: None -> stores in NN_handler [samples, session_length_list] for each subject
def store_mfcc_samples(self) -> None:
for subject_nr in range(5):
subj_samples = []
session_length_list = []
for session_nr in range(4):
list_of_emg = self.get_emg_list(subject_nr+1, session_nr+1)
tot_session_df = self.make_subj_sample(list_of_emg)
@ -663,11 +666,12 @@ class NN_handler:
if tot_session_df.isnull().values.any():
print('NaN in: subject', subject_nr+1, 'session:', session_nr+1, 'where? HERE')
mfcc_df_i = self.make_mfcc_df_from_session_df(tot_session_df)
mfcc_df_i, session_length = self.make_mfcc_df_from_session_df(tot_session_df)
subj_samples.append(mfcc_df_i)
session_length_list.append(session_length)
result_df = pd.concat(subj_samples, axis=0, ignore_index=True)
self.mfcc_samples_per_subject[subject_nr+1] = result_df
self.mfcc_samples_per_subject[subject_nr+1] = [result_df, session_length_list]
# Makes MFCC data from reg_samples_per_subject and stores it in a json file
@ -735,7 +739,9 @@ class NN_handler:
data = {
"mapping": [],
"labels": [],
"mfcc": []
"mfcc": [],
"session_lengths": []
}
raw_data_dict = self.get_mfcc_samples_dict()
@ -746,13 +752,15 @@ class NN_handler:
# save subject label in the mapping
subject_label = 'Subject ' + str(key)
print("\nProcessing: {}".format(subject_label))
data["mapping"].append(subject_label)
data["mapping"].append(subject_label) # Subject label
data["session_lengths"].append(value[1]) # List[subject][session_length_list]
# process all samples per subject
for i, sample in enumerate(value):
for i, sample in enumerate(value[0]):
data["labels"].append(key-1)
data["mfcc"].append(sample)
data["labels"].append(key-1) # Subject nr
data["mfcc"].append(sample[0]) # MFCC sample on same index
print("sample:{} is done".format(i+1))
#print(np.array(mfcc_data).shape)

61
Neural_Network_Analysis.py
View File

@ -13,7 +13,7 @@ DATA_PATH_MFCC = str(Path.cwd()) + "/mfcc_data.json"
# Loads data from the json file and reshapes X_data(samples, 1, 208) and y_data(samples, 1)
# Input: JSON path
# Ouput: X(mfcc data), y(labels)
# Ouput: X(mfcc data), y(labels), session_lengths
def load_data_from_json(data_path):
with open(data_path, "r") as fp:
@ -27,11 +27,13 @@ def load_data_from_json(data_path):
y = np.array(data["labels"])
y = y.reshape(y.shape[0], 1)
#print(y.shape)
session_lengths = data['session_lengths']
print("Data succesfully loaded!")
return X, y
return X, y, session_lengths
# Plots the training history with two subplots. First training and test accuracy, and then
# loss with respect to epochs
@ -62,17 +64,56 @@ def plot_history(history):
plt.show()
# Takes in data and labels, and splits it into train, validation and test sets
# Takes in data and labels, and splits it into train, validation and test sets by percentage
# Input: Data, labels, whether to shuffle, % validatiion, % test
# Ouput: X_train, X_validation, X_test, y_train, y_validation, y_test
def prepare_datasets_percentsplit(X, y, shuffle_vars:bool, validation_size=0.2, test_size=0.25,):
# create train, validation and test split
# Create train, validation and test split
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=test_size, shuffle=shuffle_vars)
X_train, X_validation, y_train, y_validation = train_test_split(X_train, y_train, test_size=validation_size, shuffle=shuffle_vars)
return X_train, X_validation, X_test, y_train, y_validation, y_test
# Takes in data, labels, and session_lengths and splits it into train and test sets by session_index
# Input: Data, labels, session_lengths, test_session_index
# Ouput: X_train, X_test, y_train, y_test
def prepare_datasets_sessions(X, y, session_lengths, test_session_index=4, nr_subjects=5):
subject_starting_index = 0
X_train = np.empty((1, 1, 208))
y_train = np.empty((1, 208))
X_test = np.empty((1, 1, 208))
y_test = np.empty((1, 208))
for i in range(nr_subjects):
start_test_index = sum(session_lengths[i][:test_session_index])
end_test_index = start_test_index + session_lengths[i][test_session_index-1]
end_subject_index = sum(session_lengths[i])
if start_test_index == subject_starting_index:
X_test.append(X[start_test_index:end_test_index])
y_test.append(y[start_test_index:end_test_index])
X_train.append(X[end_test_index:end_subject_index])
y_train.append(y[end_test_index:end_subject_index])
elif end_test_index == end_subject_index:
X_train.append(X[subject_starting_index:start_test_index])
y_train.append(y[subject_starting_index:start_test_index])
X_test.append(X[start_test_index:end_test_index])
y_test.append(y[start_test_index:end_test_index])
else:
X_train.append(X[subject_starting_index:start_test_index])
y_train.append(y[subject_starting_index:start_test_index])
X_test.append(X[start_test_index:end_test_index])
y_test.append(y[start_test_index:end_test_index])
X_train.append(X[end_test_index:end_subject_index])
y_train.append(y[end_test_index:end_subject_index])
subject_starting_index = end_subject_index
return X_train, X_test, y_train, y_test
# Creates a RNN_LSTM neural network model
# Input: input shape, classes of classification
# Ouput: model:Keras.model
@ -119,14 +160,14 @@ def train(model, batch_size, epochs, X_train, X_validation, y_train, y_validatio
if __name__ == "__main__":
# Load data
X, y = load_data_from_json(DATA_PATH_MFCC)
X, y, session_lengths = load_data_from_json(DATA_PATH_MFCC)
# Get prepared data: train, validation, and test
X_train, X_validation, X_test, y_train, y_validation, y_test = prepare_datasets_percentsplit(X, y,
validation_size=0.2,
test_size=0.25,
shuffle_vars=True)
print(X_train.shape)
(X_train, X_validation,
X_test, y_train,
y_validation,
y_test) = prepare_datasets_percentsplit(X, y, validation_size=0.2, test_size=0.25, shuffle_vars=True)
#print(X_train.shape)
# Make model
model = RNN_LSTM(input_shape=(1, 208))

BIN
__pycache__/Handle_emg_data.cpython-38.pyc
View File

Binary file not shown.

592096
mfcc_data.json
View File

File diff suppressed because it is too large Load Diff