def load_data(self, sample, x_axi_attr_index, y_axi_attr_index):
from Preprocessing import Preprocess
from Postprocessing import Postprocess
creditdata = Preprocess("default of credit card clients.xls")
raw_X_train, raw_X_test, raw_y_train, raw_y_test = creditdata.load()
low_dim_X_train, low_dim_X_test, low_dim_Y_train, low_dim_Y_test = creditdata.dimension_decrease(
)
postp = Postprocess(low_dim_X_train, low_dim_X_test, low_dim_Y_train,
low_dim_Y_test)
x1, x2, y1, y2 = postp.improve_data()
return self.data_simplification(x1, y1, sample, x_axi_attr_index,
y_axi_attr_index)
def __init__(self):
self.classifier = []
self.processor = []
self.result = []
creditdata = Preprocess("default of credit card clients.xls")
self.raw_X_train, self.raw_X_test, self.raw_Y_train, self.raw_Y_test = creditdata.load(
)
self.low_dim_X_train, self.low_dim_X_test, self.low_dim_Y_train, self.low_dim_Y_test = \
creditdata.dimension_decrease()
x1, x2, y1, y2 = self.low_dim_X_train, self.low_dim_X_test, self.low_dim_Y_train, self.low_dim_Y_test
self.discretizer = Postprocess(x1, x2, y1, y2)
self.discretized_X_train, self.discretized_X_test, self.discretized_Y_train, self.discretized_Y_test = \
self.discretizer.improve_data()
self.buildclf()
self.buildprocessor()
self.logfile = open("execution_Log", "a")
def trainmodel(self):
prep = Preprocess("default of credit card clients.xls")
prep.load()
low_dim_x1, low_dim_x2, low_dim_y1, low_dim_y2 = prep.dimension_decrease(
)
postp = Postprocess(low_dim_x1, low_dim_x2, low_dim_y1, low_dim_y2)
discretized_x1, discretized_x2, discretized_y1, discretized_y2 = postp.improve_data(
)
x = np.concatenate((discretized_x1, discretized_x2))
y = np.concatenate((discretized_y1, discretized_y2))
self.c.fit(x, y)
y_pred = self.c.predict(x)
mislabeled = (y != y_pred).sum()
totaltest = x.shape[0]
print(
"Mislabeled points (%s Classification) out of a total %d points : %d"
% ("SVC", totaltest, mislabeled))
Precision = 1 - mislabeled / totaltest
print("Precision of %s is %4.2f%%" % ("SVC", Precision * 100))
# group owed amount into different intervals
if -100000 <= temp_owe < 0:
self.x_test[row, 6] = -1
elif -500000 <= temp_owe < -100000:
self.x_test[row, 6] = -2
elif temp_owe < -500000:
self.x_test[row, 6] = -3
elif self.x_test[row, 6] == 0:
continue
elif 1 <= temp_owe < 100001:
self.x_test[row, 6] = 1
elif 10000 <= temp_owe < 500001:
self.x_test[row, 6] = 2
else:
self.x_test[row, 6] = 3
def improve_data(self):
self.set_age()
self.set_amount()
return self.x_train, self.x_test, self.y_train, self.y_test
if __name__ == '__main__':
a = Preprocess("default of credit card clients.xls")
rx1, rx2, ry1, ry2 = a.load()
x1, x2, y1, y2 = a.dimension_decrease()
b = Postprocess(x1, x2, y1, y2)
xd1, xd2, yd1, yd2 = b.improve_data()