def scale(data_matrix):
"""returns the mean and standard deviation of each column"""
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 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 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 scale(data_matrix):
"""returns the mean and standard deviation of each column"""
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 make_scatterplot_matrix():
# first, generate some random data
#初始化点数量
num_points = 100
def random_row():
row = [None, None, None, None]
row[0] = random_normal()
row[1] = -5 * row[0] + random_normal()
row[2] = row[0] + row[1] + 5 * random_normal()
row[3] = 6 if row[2] > -2 else 0
return row
random.seed(0)
#生成上方函数的矩阵
data = [random_row()
for _ in range(num_points)]
# then plot it
_, num_columns = shape(data)
#创建子图
fig, ax = plt.subplots(num_columns, num_columns)
for i in range(num_columns):
for j in range(num_columns):
# scatter column_j on the x-axis vs column_i on the y-axis
#i,j不相等则绘制散点图
if i != j: ax[i][j].scatter(get_column(data, j), get_column(data, i))
# unless i == j, in which case show the series name
else: ax[i][j].annotate("series " + str(i), (0.5, 0.5),
xycoords='axes fraction',
ha="center", va="center")
# then hide axis labels except left and bottom charts
#隐藏部分坐标轴
if i < num_columns - 1: ax[i][j].xaxis.set_visible(False)
if j > 0: ax[i][j].yaxis.set_visible(False)
# fix the bottom right and top left axis labels, which are wrong because
# their charts only have text in them
#固化左上右下图像
ax[-1][-1].set_xlim(ax[0][-1].get_xlim())
ax[0][0].set_ylim(ax[0][1].get_ylim())
plt.show()
def make_scatterplot_matrix():
# first, generate some random data
num_points = 100
def random_row():
row = [None for _ in range(6)]
row[0] = random_normal()
row[1] = -5 * row[0] + random_normal()
row[2] = row[0] + row[1] + 5 * random_normal()
row[3] = 6 if row[2] > -2 else 0
row[4] = row[0] + row[1] + -1 * random_normal()
row[5] = 3 if row[2] < -2 else 0
return row
random.seed(0)
data = [random_row()
for _ in range(num_points)]
# then plot it
_, num_columns = shape(data)
fig, ax = plt.subplots(num_columns, num_columns)
for i in range(num_columns):
for j in range(num_columns):
# scatter column_j on the x-axis vs column_i on the y-axis
if i != j:
ax[i][j].scatter(get_column(data, j), get_column(data, i))
# unless i == j, in which case show the series name
else:
ax[i][j].annotate("series " + str(i), (0.5, 0.5),
xycoords='axes fraction',
ha="center", va="center")
# then hide axis labels except left and bottom charts
if i < num_columns - 1: ax[i][j].xaxis.set_visible(False)
if j > 0: ax[i][j].yaxis.set_visible(False)
# fix the bottom right and top left axis labels, which are wrong because
# their charts only have text in them
ax[-1][-1].set_xlim(ax[0][-1].get_xlim())
ax[0][0].set_ylim(ax[0][1].get_ylim())
plt.show()
def visual_approach():
num_points = 100
def random_row():
row = [None, None, None, None]
row[0] = random_normal()
row[1] = -5 * row[0] + random_normal()
row[2] = row[0] + row[1] + 5 * random_normal()
row[3] = 6 if row[2] > -2 else 0
return row
random.seed(0)
data = [random_row()
for _ in range(num_points)]
_, num_columns = shape(data)
fig, ax = plt.subplots(num_columns, num_columns)
for i in range(num_columns):
for j in range(num_columns):
# Scatter columm_j on the x-axis vs column_i on the y-axis
if i != j:
ax[i][j].scatter(get_column(data, j), get_column(data, i))
# unlesss i == j, in which case show the series name
else:
ax[i][j].annotate("series {}".format(i), (0.5, 0.5),
xycoords='axes fraction',
ha="center", va="center")
# then hide dxis labels except left and bottom charts
if i < num_columns - 1: ax[i][j].xaxis.set_visible(False)
if j > 0: ax[i][j].yaxis.set_visible(False)
# fix the bottom right and top left except left and bottom charts
ax[-1][-1].set_xlim(ax[0][-1].get_xlim())
ax[1][1].set_xlim(ax[0][1].get_ylim())
plt.show()
def matrix_product_entry(A, B, i, j):
return dot(get_row(A, i), get_column(B, j))
def matrix_product_entry(A, B, i, j):
return dot(get_row(A, i), get_column(B, j))
def matrix_entry(i, j):
return correlation(get_column(data, i), get_column(data, j))
C = la.distance(A, B)
print("A's distance = ", C)
print()
print("*** matrix ......")
M = [[1, 2, 3], [5, 6, 7], [3, 6, 9]]
print("M = ", M)
shape = la.shape(M)
print("M's shape = ", shape)
row_1 = la.get_row(M, 1)
print("M[1,:] = ", row_1)
col_1 = la.get_column(M, 1)
print("M[:1] = ", col_1)
I = la.make_matrix(5, 5, la.is_diagonal)
print("identity matrix = ", I)
print("\n\n")
print("*** Test Module <stats> ***")
A = [1, 3, 5, 7, 9, 2, 3, 4, 4, 4, 6, 8, 10, 13, 15, 17]
print("vector A = ", A)
print("sorted A = ", sorted(A))
mean = st.mean(A)
print("A's mean = ", mean)
def matrix_entry(i, j):
return correlation(get_column(data, i), get_column(data, j))
def matrix_entry(i, j):
return correlation(get_column(data, i), get_column(data, j))
return make_matrix(num_colums, num_colums, matrix_entry)
_, num_colums = shape(data)
fig, ax = plt.subplots(num_colums, num_colums)
for i in range(num_colums):
for j in range(num_colums):
#X軸のcolumns_j、Y軸のcolumns_iの位置に散布図を描画する
if i != j:
ax[i][j].scatter(get_column(data, j), get_column(data, i))
#i == jであれば列名を表示する
else:
ax[i][j].annotate("series " + str(i), (0.5, 0.5),
xycoords='axes fraction',
ha="center",
va='center')
#左端と一番下のサブプロット以外は軸ラベルを表示しない
if i < num_colums - 1: ax[i][j].xaxis.set_visible(False)
if j > 0: ax[i][j].yaxis.set_visible(False)
#右下と左上のサブプロットはテキストのみ表示しているため
#軸ラベルが誤っている
ax[-1][-1].set_xlim(ax[0][-1].get_xlim())
def matrix_entry(i, j):
#得到相关系数（第i列和第j列）
return correlation(get_column(data, i), get_column(data, j))
