手書き数字をpythonでもてあそぶ その１ ref: http://qiita.com/kenmatsu4/items/79905dadb07b69f182a1

file0.py

import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm

file1.py

size = 28
raw_data= np.loadtxt('train_small.csv',delimiter=',',skiprows=1)

digit_data = []
for i in range(len(raw_data)):
    digit_data.append((raw_data[i,0],raw_data[i,1:785]))

digit_data.sort(key=lambda x: x[0]) # sort array by label

file2.py

# draw digit images
plt.figure(figsize=(15, 15))

for i in range(len(digit_data)):
    X, Y = np.meshgrid(range(size),range(size))
    Z = digit_data[i][1].reshape(size,size)   # convert from vector to 28x28 matrix
    Z = Z[::-1,:]             # flip vertical
    plt.subplot(10, 20, i+1)  # layout 200 cells
    plt.xlim(0,27)
    plt.ylim(0,27)
    plt.pcolor(X, Y, Z)
    plt.flag()
    plt.gray()
    plt.tick_params(labelbottom="off")
    plt.tick_params(labelleft="off")

plt.show()

file3.py

data_mat = []

# convert list to ndarray
for i in range(len(digit_data)):
    label = digit_data[i][0]
    data_mat.append(digit_data[i][1])

A = np.array(data_mat)
Z = np.corrcoef(A)      # generate correlation matrix

area_size = len(digit_data)
X, Y = np.meshgrid(range(area_size),range(area_size)) 

file4.py

plt.clf()
plt.figure(figsize=(10, 10))
plt.xlim(0,area_size-1)
plt.ylim(0,area_size-1)
plt.title("Correlation matrix of digit charcter vector. (corr>0.5)")

thresh = .5 
Z1 = Z.copy()
Z1[Z1 > thresh] = 1
Z1[Z1 <= thresh] = 0

plt.pcolor(X, Y, Z1, cmap=cm.get_cmap('Blues'),alpha=0.6)
plt.xticks([(i * 20) for i in range(10)],range(10))
plt.yticks([(i * 20) for i in range(10)],range(10))
plt.grid(color='deeppink',linestyle='--')
plt.show()

file5.py

summary_Z = np.zeros(100).reshape(10,10)

for i in range(10):
    for j in range(10):
        i1 = i * 20
        j1 = j * 20
        #print "[%d:%d,%d:%d]" % (i1,i1+20,j1,j1+20)
        if i==j:
            # 対角成分は1に決まっているので、値が上ぶれするのを避けるため除いて平均をとる
            summary_Z[i,j] = (np.sum(Z[i1:i1+20,j1:j1+20])-20)/380
        else:
            summary_Z[i,j] = np.sum(Z[i1:i1+20,j1:j1+20])/400

# average of each digit's grid
plt.clf()
plt.figure(figsize=(10, 10))
plt.xlim(0,10)
plt.ylim(0,10)

sX, sY = np.meshgrid(range(11),range(11))
plt.title("Correlation matrix of summuation of each digit's cell")
plt.xticks(range(10),range(10))
plt.yticks(range(10),range(10))
plt.pcolor(sX, sY, summary_Z, cmap=cm.get_cmap('Blues'),alpha=0.6)
plt.show()