import plot
def estimate_price(km, theta0, theta1):
return theta0 + theta1 * km
def usage():
print("Usage: " + sys.argv[0] + " [-b]")
sys.exit(2)
if len(sys.argv) != 1 and (len(sys.argv) != 2 or sys.argv[1] != "-b"):
usage()
bonus = True if len(sys.argv) == 2 else False
loop = True
while loop:
try:
km = float(input("km: "))
loop = False
except:
print("km must be a number")
theta0, theta1 = file.read_theta()
data = file.read_data()
min_km = min(data, key = lambda t: t[0])[0]
max_km = max(data, key = lambda t: t[0])[0]
km = train.scale_km(km, min_km, max_km)
price = theta0 + (theta1 * km)
print ("estimated price: %.2f" % estimate_price(km, theta0, theta1))
if bonus:
scaled_data = train.scale_data(data)
p = precision.r_squared(scaled_data, theta0, theta1)
print("precision: %.2f%%" % (p * 100))
plot.draw(data, theta0, theta1)
subject_list = ["Arithmancy", "Astronomy", "Herbology", \
"Defense Against the Dark Arts", "Divination", "Muggle Studies", \
"Ancient Runes", "History of Magic", "Transfiguration", "Potions", \
"Care of Magical Creatures", "Charms", "Flying"]
i = 1
print("Fill your marks")
for subject in subject_list:
loop = True
while loop:
try:
mark = float(input(subject + ": "))
if mark < 0.0 or mark > 20.0:
raise Exception()
mark_matrix[i][0] = mark / 20.0
i += 1
loop = False
except:
print("mark must be a number between 0 and 20")
return mark_matrix
if __name__ == '__main__':
if len(sys.argv) != 2:
usage()
if not os.path.isfile(sys.argv[1]):
error('no such file: %s' % sys.argv[1])
mark_matrix = ask_marks()
theta_data = file.read_theta(sys.argv[1], feature_number + 1)
houses = logreg_predict.logreg_predict(mark_matrix, theta_data)
print("Sorting Hat: Hum, you will go to... " + houses[0] + "!")
except:
error("invalid dataset")
return data
if __name__ == '__main__':
if len(sys.argv) != 3:
usage()
if not os.path.isfile(sys.argv[1]):
error('no such file: %s' % sys.argv[1])
if not os.path.isfile(sys.argv[2]):
error('no such file: %s' % sys.argv[2])
train_file = "resources/dataset_train.csv"
header_histo, features_histo = histogram.read_data(train_file)
feature_number = len(header_histo)
mean_features = logreg_train.calc_mean_features(features_histo,
feature_number)
data = read_data(sys.argv[1], feature_number, mean_features)
train_data = logreg_train.read_data(train_file, feature_number,
mean_features)
min_matrix = np.min(train_data["Features"], axis=1).reshape(-1, 1)
max_matrix = np.max(train_data["Features"], axis=1).reshape(-1, 1)
data = logreg_train.scale(data, min_matrix, max_matrix)
data = np.vstack((np.matrix(np.ones(len(data[0]))), data))
tn = feature_number + 1
theta_data = file.read_theta(sys.argv[2], tn)
houses = logreg_predict(data, theta_data)
file.write_houses(houses)