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 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
plot_cities()
# try several different values for k
for k in range(1,76):
num_correct = 0
for location, actual_language in cities:
other_cities = [other_city
for other_city in cities
if other_city != (location, actual_language)]
predicted_language = knn_classify(k, other_cities, location)
if predicted_language == actual_language:
num_correct += 1
print k, "neighbor[s]:", num_correct, "correct out of", len(cities)
dimensions = range(1, 101, 5)
avg_distances = []
min_distances = []
random.seed(0)
for dim in dimensions:
distances = random_distances(dim, 10000) # 10,000 random pairs
avg_distances.append(mean(distances)) # track the average
min_distances.append(min(distances)) # track the minimum
print dim, min(distances), mean(distances), min(distances) / mean(distances)