trainpoints=750
testpoints=25
num_train_imgs=209
num_test_imgs=19
minhash=4
#param_values= np.logspace(np.log2(1),np.log2(30),num=10,base=2).astype(np.int)
param_values=np.linspace(10,300,num=10).astype(np.int)
print param_values
values=[]
f_maxes=[]
#for val in param_values:
# candidates=val
train_input, train_label=knn_trainer_helper.sortClasses(pad,trainpoints,knn_trainer_helper.readImages(num_train_imgs,'input/train/','labels/train/'),seed=42)
test_input, test_label=knn_trainer_helper.sortClasses(pad,testpoints,knn_trainer_helper.readImages(num_test_imgs,'input/test/','labels/test/'),seed=42,equalClasses=False)
#reduce dimensionality of data
pca = PCA().fit(train_input[:(trainpoints*num_train_imgs)*.1])
variance=pca.explained_variance_ratio_
sum = 0
components=0
while sum<=.995:
sum+=variance[components]
components+=1
pca = PCA(n_components=components)
train_data_fit=pca.fit(train_input[:(trainpoints*num_train_imgs)*.1])
train_data_transform=pca.transform(train_input[:])
del train_input
import numpy as np import time import sklearn.metrics import random test_imgcount = 19 testPoints = 5 train_imgcount = 209 trainPoints = 12500 pad = 4 train_inputpath='input/train/' train_labelpath='labels/train/' test_inputpath='input/test/' test_labelpath='labels/test/' testimages = knn_trainer_helper.readImages(test_imgcount, test_inputpath, test_labelpath) trainimages = knn_trainer_helper.readImages(train_imgcount, train_inputpath, train_labelpath) start = time.time() train_data=knn_trainer_helper.sortClasses(10,trainPoints, trainimages, 1) test_data=knn_trainer_helper.sortClasses(10,testPoints, testimages, 1) knn = sklearn.neighbors.KNeighborsClassifier(n_neighbors=25, weights='uniform')#, algorithm='ball_tree') print "hi" knn.fit(train_data[0], train_data[1]) print time.time()-start test_predict = knn.predict(test_data[0]) score = sklearn.metrics.accuracy_score(test_data[1], test_predict, normalize=True) print score print time.time()-start
import test
import knn_trainer_helper
import sklearn.neighbors
from sklearn.neighbors import LSHForest
import time
import border
import matplotlib.pyplot as plt
import mahotas
import numpy as np
from scipy import stats
side = 1024
start = time.time()
k=25
pad=200
numpoints=12
train_data=knn_trainer_helper.sortClasses(pad,numpoints,knn_trainer_helper.readImages(209,'input/train/','labels/train/'),seed=42)[0]
#plt.gray()
#print train_data[0]
#print len(train_data[0])
#plt.imshow(np.array(train_data[0]).reshape(401,401))
#mahotas.imsave('results/pca images/normal.tif', np.uint16(np.array(train_data[0]).reshape(401,401)))
#plt.title('normal')
#plt.show()
pca = PCA().fit(train_data)
variance=pca.explained_variance_ratio_
sum = 0
i=0
accuracy=.995
test_imgcount = 19
train_imgcount = 209
numPoints=1000
k = 20
estimators=20
candidates=200
minhash=4
padValues = np.linspace(1, 30,6).astype(np.int)
knn_times = []
lshf_times = []
for pad in padValues:
train_input, train_label=knn_trainer_helper.sortClasses(pad,numPoints,knn_trainer_helper.readImages(209,'input/train/','labels/train/'),seed=42)
test_input, test_label=knn_trainer_helper.sortClasses(pad,1,knn_trainer_helper.readImages(1,'input/test/','labels/test/'),seed=42,equalClasses=False)
knn = NearestNeighbors(n_neighbors=k, weights='uniform', algorithm='brute').fit(train_input)
knn_start = time.time()
exact_neighbors = knn.kneighbors(test_input, return_distance=False)
knn_end = time.time()
lshf = LSHForest(n_estimators=estimators,n_candidates=candidates,min_hash_match=minhash,n_neighbors=k,random_state=1).fit(train_input)
lshf_start=time.time()
approx_neighbors = lshf.kneighbors(test_input, return_distance=False)
lshf_end=time.time()
knn_times.append(knn_end-knn_start)
lshf_times.append(lshf_end-lshf_start)
print pad
test_imgcount = 19
train_imgcount = 209
pad = 24
k = 20
estimators = 20
candidates = 200
minhash = 4
pointValues = np.linspace(1, 5000, 6).astype(np.int)
knn_times = []
lshf_times = []
for numPoints in pointValues:
train_input, train_label = knn_trainer_helper.sortClasses(
pad, numPoints, knn_trainer_helper.readImages(209, "input/train/", "labels/train/"), seed=42
)
test_input, test_label = knn_trainer_helper.sortClasses(
pad, 1, knn_trainer_helper.readImages(1, "input/test/", "labels/test/"), seed=42, equalClasses=False
)
knn = NearestNeighbors(n_neighbors=k, weights="uniform", algorithm="brute").fit(train_input)
knn_start = time.time()
exact_neighbors = knn.kneighbors(test_input, return_distance=False)
knn_end = time.time()
lshf = LSHForest(
n_estimators=estimators, n_candidates=candidates, min_hash_match=minhash, n_neighbors=k, random_state=1
).fit(train_input)
lshf_start = time.time()
approx_neighbors = lshf.kneighbors(test_input, return_distance=False)
estimators = 20
candidates = 20
numpoints = 100
num_train_imgs = 209
minhash = 4
use_equal_classes = True
usePCA = True
input_img = mahotas.imread("input/test/0.tif")
input_bordered = border.createBorder(pad, input_img)
label = "labels/test/0.tif"
# input = border.outputMatrix(pad,input_img)
train_input, train_label = knn_trainer_helper.sortClasses(
pad,
numpoints,
knn_trainer_helper.readImages(num_train_imgs, "input/train/", "labels/train/"),
seed=42,
equalClasses=use_equal_classes,
)
if usePCA:
# reduce dimensionality of training data
pca = PCA().fit(train_input)
variance = pca.explained_variance_ratio_
sum = 0
components = 0
while sum <= 0.995:
sum += variance[components]
components += 1
pca = PCA(n_components=components)
train_data = pca.fit_transform(train_input)
elif(dump):
file=open(filepath, 'wb')
cPickle.dump(list, file, -1)
file.close()
start=time.time()
plt.gray()
pad=8
k=27
trainImgs=209
numPoints=200
inputpath = 'input/train/'
labelpath = 'labels/train'
print 'generating data'
training_data=knn_trainer_helper.sortClasses(pad, numPoints,knn_trainer_helper.readImages(trainImgs, inputpath, labelpath))
time1=time.time()
print 'this step took ' +str(time1-start) + ' seconds' +' seconds, total time elapsed: ' + str(time1-start) + ' seconds'
#print 'pickling/unpickling data'
#pickle_help('pickle/full_data.pkl', list=full_data, dump=True)
#full_data=pickle_help('pickle/full_data.pkl', load=True)
#tree_input = sklearn.neighbors.BallTree(training_data[0], leaf_size=30)
#pickle_help('pickle/ball_tree.pkl', list=tree_input, dump=True)
time2=time.time()
#print 'this step took ' +str(time2-time1) +' seconds, total time elapsed: ' + str(time2-start) + ' seconds'
print 'creating classifier'
knn=sklearn.neighbors.KNeighborsClassifier(n_neighbors=k, weights='uniform', algorithm='ball_tree')
import numpy as np
import matplotlib.pyplot as plt
import sklearn.neighbors
test_imgcount = 19
train_imgcount = 209
pad = 5
k = 20
numPoints=3
train_inputpath='input/train/'
train_labelpath='labels/train/'
test_inputpath='input/test/'
test_labelpath='labels/test/'
while numPoints < 400:
start = time.time()
train_data=knn_trainer_helper.sortClasses(pad, numPoints, knn_trainer_helper.readImages(train_imgcount, train_inputpath, train_labelpath), seed=42)
test_data=knn_trainer_helper.sortClasses(pad,500,knn_trainer_helper.readImages(test_imgcount, test_inputpath, test_labelpath), seed=42)
knn = sklearn.neighbors.KNeighborsClassifier(n_neighbors=k, weights='uniform', algorithm='ball_tree')
knn.fit(train_data[0], train_data[1])
test_predict = knn.predict(test_data[0])
end = time.time()
total = end-start
print '('+str(numPoints)+', '+str(total)+')'
plt.plot(numPoints, total, 'ro')
numPoints *=2
plt.show()