'''returns the means and standard deviations of each column'''

num_rows, num_cols = data_matrix.shape

means = [data_matrix[:,j].mean() for j in range(num_cols)]

stdevs = [data_matrix[:,j].std() for j in range(num_cols)]

'''rescales the input data so that each column

has mean 0 and standard deviation 1

leaves alone columns with no deviation'''

means, stdevs = scale(data_matrix)

def rescaled(i, j):

if stdevs[j] > 0:

return (data_matrix[i,j] - means[j]) / stdevs[j]

else:

return data_matrix[i,j]

num_rows, num_cols = data_matrix.shape

"""returns the result of subtracting from every value in A the mean

value of its column. the resulting matrix has mean 0 in every column"""

nr, nc = A.shape

column_means, _ = scale(A)

Y = de_mean_matrix(X)

plt.subplot(2, 1, 1)

plt.scatter(X[:,0], X[:,1])

plt.title('Data')

plt.subplot(2, 1, 2)

plt.scatter(Y[:,0], Y[:,1])

plt.title('De-meaned')

plt.gca().set_aspect('equal', adjustable='box')

# output to static HTML file

bplt.output_file("data.html", title="Rescaling")

# create a new plot with a title and axis labels

p = bplt.figure(title="Data", x_axis_label='x', y_axis_label='y')

# add a line renderer with legend and line thickness

p.scatter(X[:,0].A1, X[:,1].A1, marker="circle",

line_color="#6666ee", fill_color="#ee6666",

fill_alpha=0.5, size=12)

# show the results

Y = de_mean_matrix(X)

TOOLS="resize,crosshair,pan,wheel_zoom,box_zoom,reset,previewsave,box_select"

hover = HoverTool(

tooltips=[

("index", "$index"),

("(x,y)", "($x, $y)"),

("desc", "@desc"),

]

)

bplt.output_file("data.html", title="Rescaling")

s1 = bplt.figure(width=500, plot_height=250, title="Data", tools=[hover, TOOLS])

s1.scatter(X[:,0].A1, X[:,1].A1, marker="circle",

line_color="#6666ee", fill_color="#ee6666",

fill_alpha=0.5, size=12)

s2 = bplt.figure(width=500, plot_height=250, title="De-meaned", tools=TOOLS)

s2.scatter(Y[:,0].A1, Y[:,1].A1, marker="circle",

line_color="#6666ee", fill_color="#ee6666",

fill_alpha=0.5, size=12)

# put all the plots in a VBox

p = bplt.vplot(s1, s2)

# show the results