mrgloom

import numpy as np
import time

def read_data():
	#M x N
	data= np.loadtxt("data_3d.txt",delimiter=" ", skiprows=1, usecols=(0,1,2))
	print data.shape
	# print data
	return data
	

mrgloom

def pca(data,k):
	#data M x N
	#get mean
	mean= np.mean(data,axis=0) # N long
	# print mean.shape
	# print mean

	#M x N
	data_c= (data-mean) 
	print data_c.shape

mrgloom

#test save and load of numpy matrix
#test matrix multiplication in memory and using memmap

#in case of memmap no need to use batch processing

#also can test hdf5 and pytables for matrix mult

#can use matrix mult for pca (more smart to use randompca)

#need to test it on x64 machine

mrgloom

import numpy as np
import matplotlib.pyplot as plt

from sklearn.datasets import fetch_mldata
from sklearn.decomposition import FastICA, PCA
from sklearn.cluster import KMeans

# fetch natural image patches
image_patches = fetch_mldata("natural scenes data")
X = image_patches.data

mrgloom

#test save and load of numpy matrix
#test matrix multiplication in memory and using memmap

#in case of memmap no need to use batch processing

#also can test hdf5 and pytables for matrix mult

#can use matrix mult for pca (more smart to use randompca)

#need to test it on x64 machine

mrgloom

#!/usr/bin/python
#
# K-means clustering using Lloyd's algorithm in pure Python.
# Written by Lars Buitinck. This code is in the public domain.
#
# The main program runs the clustering algorithm on a bunch of text documents
# specified as command-line arguments. These documents are first converted to
# sparse vectors, represented as lists of (index, value) pairs.

from collections import defaultdict

mrgloom

import numpy as np
from sklearn.svm import SVC
from sklearn.svm import LinearSVC
from sklearn.linear_model.stochastic_gradient import SGDClassifier
from sklearn.datasets import fetch_mldata
from sklearn.utils import shuffle
import time

#out-of-core \ online
#http://scikit-learn.org/stable/auto_examples/applications/plot_out_of_core_classification.html

mrgloom

from sklearn.grid_search import GridSearchCV
from sklearn.cross_validation import StratifiedKFold

def main():
    mnist = fetch_mldata("MNIST original")
    X_all, y_all = mnist.data/255., mnist.target
    print("scaling")
    X = X_all[:60000, :]
    y = y_all[:60000]

mrgloom

import numpy as np
import matplotlib.pyplot as plt
from itertools import product
from sklearn.decomposition import RandomizedPCA
from sklearn.datasets import fetch_mldata
from sklearn.utils import shuffle

#use all digits
mnist = fetch_mldata("MNIST original")
X_train, y_train = mnist.data[:70000] / 255., mnist.target[:70000]

mrgloom

import numpy as np
import matplotlib.pyplot as plt
from itertools import product
from sklearn.decomposition import RandomizedPCA
from sklearn.datasets import fetch_mldata
from sklearn.utils import shuffle

mnist = fetch_mldata("MNIST original")
X_train, y_train = mnist.data[:60000] / 255., mnist.target[:60000]