def scale(data_matrix):
num_rows, num_cols = shape(data_matrix)
means = [mean(get_column(data_matrix,j))
for j in range(num_cols)]
stdevs = [standard_deviation(get_column(data_matrix,j))
for j in range(num_cols)]
return means, stdevs
def main():
"""The application entry point"""
print 'EXERCISE 1A'
print '==========='
print 'This program takes a CSV file, asks you to select a row from that'
print 'file, and then computes the mean and standard deviation of the'
print 'values in that row.'
print
file_path = io.get_and_confirm_input('Enter csv file with values: ')
data = io.read_csv_file(file_path)
if not data:
raise RuntimeError('No data found in file {}'.format(file_path))
column = io.choose_from_list(
'Which column would you like to use:', data[0].keys())
if column not in data[0]:
raise RuntimeError('Invalid column {}'.format(column))
values = linked_list.LinkedList()
for each in data:
values.insert(each[column])
for each in values:
print each
print 'Mean: ', statistics.mean(values)
print 'Std Dev: ', statistics.standard_deviation(values)
def scale(data_matrix):
"""вернуть средние и стандартные отклонения для каждого столбца"""
num_rows, num_cols = shape(data_matrix)
means = [mean(get_column(data_matrix,j))
for j in range(num_cols)]
stdevs = [standard_deviation(get_column(data_matrix,j))
for j in range(num_cols)]
return means, stdevs
def normalized_data(self, data):
"""Return the given data in normalized form.
Arguments:
data(list): A list of data points
Returns:
list: Same data points, normalized.
"""
mean = statistics.mean(data)
stddev = statistics.standard_deviation(data)
return [(each - mean)/stddev for each in data]
[random.random() for _ in range(50)] +
[200 + random.random() for _ in range(50)])
print("bootstrap_statistic(close_to_100, median, 100):")
print(bootstrap_statistic(close_to_100, median, 100))
print("bootstrap_statistic(far_from_100, median, 100):")
print(bootstrap_statistic(far_from_100, median, 100))
print()
random.seed(0) # so that you get the same results as me
bootstrap_betas = bootstrap_statistic(list(zip(x, daily_minutes_good)),
estimate_sample_beta, 100)
bootstrap_standard_errors = [
standard_deviation([beta[i] for beta in bootstrap_betas])
for i in range(4)
]
print("bootstrap standard errors", bootstrap_standard_errors)
print()
print("p_value(30.63, 1.174)", p_value(30.63, 1.174))
print("p_value(0.972, 0.079)", p_value(0.972, 0.079))
print("p_value(-1.868, 0.131)", p_value(-1.868, 0.131))
print("p_value(0.911, 0.990)", p_value(0.911, 0.990))
print()
print("regularization")
random.seed(0)
def least_squares_fit(x, y):
"""при заданных обучающих значениях x и y,
найти значения alpha и beta на основе МНК"""
beta = correlation(x, y) * standard_deviation(y) / standard_deviation(x)
alpha = mean(y) - beta * mean(x)
return alpha, beta
def least_squares_fit(x, y):
"""given training values for x and y,
find the least-squares values of alpha and beta"""
beta = correlation(x, y) * standard_deviation(y) / standard_deviation(x)
alpha = mean(y) - beta * mean(x)
return alpha, beta
def test_should_correctly_compute_standard_deviation(self):
self.assertAlmostEqual(
2.73861,
statistics.standard_deviation(range(1, 10)),
places=5)
