Functions | |
def | create_ROC |
def | extract_data |
def | process |
Variables | |
list | ACT_LIST = ['WINCE', 'NOD', 'SHAKE', 'JOY', "FEAR", "SUPRISE", "ANGER", "DISGUST", "SADNESS"] |
dictionary | ACTIONS |
list | all_tpr = [] |
tuple | args = parser.parse_args() |
tuple | cv = StratifiedKFold(y, k=9) |
Code below modified from http://scikit-learn.org/stable/auto_examples/plot_roc_crossval.html#example-plot-roc-crossval-py. | |
dictionary | DEGREES |
string | help = "One or more training data files to process" |
string | label = 'Mean ROC (area = %0.2f)' |
tuple | mean_auc = auc(mean_fpr, mean_tpr) |
tuple | mean_fpr = np.linspace(0, 1, n_samples) |
float | mean_tpr = 0.0 |
tuple | parser |
tuple | probas_ = classifier.fit(X[train], y[train]) |
tuple | roc_auc = auc(fpr, tpr) |
def data_parser.create_ROC | ( | filename | ) |
Definition at line 170 of file data_parser.py.
def data_parser.extract_data | ( | files | ) |
Definition at line 34 of file data_parser.py.
def data_parser.process | ( | files, | |
SVM_DATA_FILE, | |||
WINDOW_DUR, | |||
MAG_THRESH, | |||
plot | |||
) |
Definition at line 43 of file data_parser.py.
list data_parser::ACT_LIST = ['WINCE', 'NOD', 'SHAKE', 'JOY', "FEAR", "SUPRISE", "ANGER", "DISGUST", "SADNESS"] |
Definition at line 31 of file data_parser.py.
dictionary data_parser::ACTIONS |
00001 {'WINCE' : [0,0,0], 00002 'SMILE' : [0.5,0,0] , 00003 'FROWN' : [0,0.5,0], 00004 'LAUGH' : [0,0,0.5], 00005 'GLARE' : [0.5,0.5,0], 00006 'NOD' : [0.5,0,0.5], 00007 'SHAKE' : [0,0.5,0.5], 00008 'REQUEST FOR BOARD': [0.5,0.5,0.5], 00009 'EYE-ROLL':[1,0,0], 00010 'JOY' : [0,1,0], 00011 'SUPRISE': [0,0,1], 00012 'FEAR' : [1,1,0], 00013 'ANGER' : [0,1,1], 00014 'DISGUST': [1,0,1], 00015 'SADNESS': [0.5,0,0]}
Definition at line 16 of file data_parser.py.
list data_parser::all_tpr = [] |
Definition at line 207 of file data_parser.py.
tuple data_parser::args = parser.parse_args() |
Definition at line 252 of file data_parser.py.
tuple data_parser::cv = StratifiedKFold(y, k=9) |
Code below modified from http://scikit-learn.org/stable/auto_examples/plot_roc_crossval.html#example-plot-roc-crossval-py.
Classification and ROC analysis Run classifier with crossvalidation and plot ROC curves
Definition at line 203 of file data_parser.py.
dictionary data_parser::DEGREES |
00001 {'WEAK' : 0.33, 00002 'AVERAGE': 0.66, 00003 'STRONG' : 1.0}
Definition at line 12 of file data_parser.py.
string data_parser::help = "One or more training data files to process" |
Definition at line 241 of file data_parser.py.
string data_parser::label = 'Mean ROC (area = %0.2f)' |
Definition at line 224 of file data_parser.py.
tuple data_parser::mean_auc = auc(mean_fpr, mean_tpr) |
Definition at line 222 of file data_parser.py.
tuple data_parser::mean_fpr = np.linspace(0, 1, n_samples) |
Definition at line 206 of file data_parser.py.
float data_parser::mean_tpr = 0.0 |
Definition at line 205 of file data_parser.py.
tuple data_parser::parser |
00001 argparse.ArgumentParser( 00002 description="Process raw wouse training data to output plots," 00003 "statistics, and SVM-ready formatted data", 00004 formatter_class=argparse.ArgumentDefaultsHelpFormatter)
Definition at line 236 of file data_parser.py.
tuple data_parser::probas_ = classifier.fit(X[train], y[train]) |
Definition at line 210 of file data_parser.py.
tuple data_parser::roc_auc = auc(fpr, tpr) |
Definition at line 215 of file data_parser.py.