Skip to content

Instantly share code, notes, and snippets.

Created March 19, 2015 16:55
  • Star 0 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
Star You must be signed in to star a gist
Save e9t/5d4c2b48d8eca8c662ef to your computer and use it in GitHub Desktop.
#! /usr/bin/python
# -*- coding: utf-8 -*-
import numpy as np
from sklearn import datasets
d = datasets.fetch_mldata('MNIST original', data_home='.')
X, y = d['data'], d['target']
X_y0 = X[y==0]
X_y1 = X[y==1]
X_bin = np.concatenate((X_y0, X_y1))
np.savetxt('data-mnist-x-bin.csv', X_bin, delimiter=',', fmt='%d')
y_bin = np.concatenate(([0]*len(X_y0), [1]*len(X_y1)))
np.savetxt('data-mnist-y-bin.csv', y_bin, delimiter=',', fmt='%d')
#! /usr/bin/python
# -*- coding: utf-8 -*-
from matplotlib import pyplot as plt
from sklearn import cross_validation, datasets
from sklearn.linear_model import LogisticRegression
from time import time
print('1. data acquisition')
d = datasets.fetch_mldata('MNIST original', data_home='.')
X = d['data']
y = d['target']
from numpy import genfromtxt
X = genfromtxt('data-mnist-x-bin.csv', delimiter=',')
y = genfromtxt('data-mnist-y-bin.csv', delimiter=',')
print('2. data exploration')
print("X[0]:", X[0])
print("y[0]:", y[0])
print("min/max(X[0]):", min(X[0]), max(X[0]))
print("All classes of y:", set(y))
X0 = X[0].reshape(28, 28) # reshape 1*784 array to 28*28 array
plt.rc('image', cmap='binary') # set runtime configurations (rc) for color maps
plt.matshow(X0) # plot matrix
plt.savefig('X0.png') # save plot to image file
print('3. data partitioning')
X_train, X_test, y_train, y_test =\
cross_validation.train_test_split(X, y, test_size=0.4, random_state=1234)
print('4. training')
lr = LogisticRegression(random_state=1234) # LR instance 생성, y_train) # LR 학습
print('5. testing')
print("Training accuracy:", lr.score(X_train, y_train))
print("Testing accuracy:", lr.score(X_test, y_test))
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment