def test_constant_features():
learner = milk.defaultclassifier()
features = np.ones(20).reshape((-1, 1))
labels = np.zeros(20)
labels[10:] += 1
features[10:] *= -1
learner.train(features, labels)
def trainMe(directory):
classes = []
labels = []
features = []
print('[+] Reading files')
gestures = check_output(['ls', directory]).split()
print('[+] Extracting features')
for gesture in gestures:
classes.append(gesture)
gesture_dir = directory + '/' + gesture
files = check_output(['ls', gesture_dir]).split()
for filename in files:
file_dir = gesture_dir + '/' + filename
labels.append(len(classes))
image = cv.imread(file_dir)
image = resizeImage(image, width=500)
features.append(getFVector(image))
features = np.array(features)
labels = np.array(labels)
print('[+] Training')
classifier = milk.defaultclassifier()
model = classifier.train(features, labels)
print('[+] Cross validation')
confusion_matrix, names = milk.nfoldcrossvalidation(features, labels, learner=classifier)
print('[+] Accuracy %.2f' % (float(confusion_matrix.trace())/float(confusion_matrix.sum())))
return model, classes
def test_constant_features():
learner = milk.defaultclassifier()
features = np.ones(20).reshape((-1,1))
labels = np.zeros(20)
labels[10:] += 1
features[10:] *= -1
learner.train(features, labels)
def main():
oauth_filename = os.environ.get('HOME', '') + os.sep + '.twitter_oauth'
oauth_filename = os.path.expanduser(oauth_filename)
oauth_token, oauth_token_secret = read_token_file(oauth_filename)
auth = OAuth(oauth_token, oauth_token_secret, CONSUMER_KEY, CONSUMER_SECRET)
twitter = Twitter(
auth=auth,
secure=True,
api_version='1',
domain='api.twitter.com'
)
try:
tweets = pickle.load(open('tweets.pickle'))
except:
tweets = []
print "Horay! I've got %s tweets from the file!" % len(tweets)
# используем nltk
featuresets = [(get_features(tweet), tweet['good']) for tweet in tweets]
total = len(featuresets)
train_set, test_set = featuresets[total/2:], featuresets[:total/2]
classifier = nltk.NaiveBayesClassifier.train(train_set)
#tree_classifier = nltk.DecisionTreeClassifier.train(train_set)
print nltk.classify.accuracy(classifier, test_set)
classifier.show_most_informative_features(10)
#print nltk.classify.accuracy(tree_classifier, test_set)
if MILK:
# используем milk
learner = milk.defaultclassifier()
get_milk_keys(get_features(tweet) for tweet in tweets)
features = [get_milk_features(tweet) for tweet in tweets]
labels = [tweet['good'] for tweet in tweets]
model = learner.train(features, labels)
ids = set(tweet['id'] for tweet in tweets)
tweet_iter = twitter.statuses.friends_timeline(count=COUNT)
for tweet in tweet_iter:
if tweet.get('text') and tweet['id'] not in ids:
print '%s: %s' % (tweet['user']['name'], tweet['text'])
print '[nltk] I think, this tweet is interesting with probability', classifier.prob_classify(get_features(tweet)).prob(True)
if MILK:
print '[milk] I think, this tweet is interesting with probability', model.apply(get_milk_features(tweet))
good = raw_input('Interesting or not?\n(y/n): ') in ('y', 'Y', 'G', 'g')
tweet['good'] = good
tweets.append(tweet)
pickle.dump(tweets, open('tweets.pickle', 'w'))
def main():
oauth_filename = os.environ.get('HOME', '') + os.sep + '.twitter_oauth'
oauth_filename = os.path.expanduser(oauth_filename)
oauth_token, oauth_token_secret = read_token_file(oauth_filename)
auth = OAuth(oauth_token, oauth_token_secret, CONSUMER_KEY,
CONSUMER_SECRET)
twitter = Twitter(auth=auth,
secure=True,
api_version='1',
domain='api.twitter.com')
try:
tweets = pickle.load(open('tweets.pickle'))
except:
tweets = []
print "Horay! I've got %s tweets from the file!" % len(tweets)
# используем nltk
featuresets = [(get_features(tweet), tweet['good']) for tweet in tweets]
total = len(featuresets)
train_set, test_set = featuresets[total / 2:], featuresets[:total / 2]
classifier = nltk.NaiveBayesClassifier.train(train_set)
#tree_classifier = nltk.DecisionTreeClassifier.train(train_set)
print nltk.classify.accuracy(classifier, test_set)
classifier.show_most_informative_features(10)
#print nltk.classify.accuracy(tree_classifier, test_set)
if MILK:
# используем milk
learner = milk.defaultclassifier()
get_milk_keys(get_features(tweet) for tweet in tweets)
features = [get_milk_features(tweet) for tweet in tweets]
labels = [tweet['good'] for tweet in tweets]
model = learner.train(features, labels)
ids = set(tweet['id'] for tweet in tweets)
tweet_iter = twitter.statuses.friends_timeline(count=COUNT)
for tweet in tweet_iter:
if tweet.get('text') and tweet['id'] not in ids:
print '%s: %s' % (tweet['user']['name'], tweet['text'])
print '[nltk] I think, this tweet is interesting with probability', classifier.prob_classify(
get_features(tweet)).prob(True)
if MILK:
print '[milk] I think, this tweet is interesting with probability', model.apply(
get_milk_features(tweet))
good = raw_input('Interesting or not?\n(y/n): ') in ('y', 'Y', 'G',
'g')
tweet['good'] = good
tweets.append(tweet)
pickle.dump(tweets, open('tweets.pickle', 'w'))
def train_ai():
data = []
classID = []
features = []
features_temp_array = []
try:
data_filename = 'coinvision_feature_data.csv'
print 'reading features and classID: ', data_filename
f_handle = open(data_filename, 'r')
reader = csv.reader(f_handle)
#read data from file into arrays
for row in reader:
data.append(row)
for row in range(0, len(data)):
#print features[row][1]
classID.append(int(data[row][0]))
features_temp_array.append(data[row][1].split(" "))
#removes ending element which is a space
for x in range(len(features_temp_array)):
features_temp_array[x].pop()
features_temp_array[x].pop(0)
#convert all strings in array to numbers
temp_array = []
for x in range(len(features_temp_array)):
temp_array = [ float(s) for s in features_temp_array[x] ]
features.append(temp_array)
#make numpy arrays
features = np.asarray(features)
#print classID, features
learner = milk.defaultclassifier(mode='really-slow')
model = learner.train(features, classID)
pickle.dump( model, open( "coinvision_ai_model.mdl", "wb" ) )
except:
print "could not retrain.. bad file"
'''
from sklearn import svm
model = svm.SVC(gamma=0.001, C=100.)
model.fit(features, classID)
pickle.dump( model, open( "coinvision_ai_model_svc.mdl", "wb" ) )
from sklearn.neighbors import KNeighborsClassifier
neigh = KNeighborsClassifier(n_neighbors=3)
neigh.fit(features, classID)
pickle.dump( model, open( "coinvision_ai_model_knn.mdl", "wb" ) )
'''
return
def test_nov2010():
# Bug submitted by Mao Ziyang
# This was failing in 0.3.5 because SDA selected no features
np.random.seed(222)
features = np.random.randn(100,20)
features[:50] *= 2
labels = np.repeat((0,1), 50)
classifier = milk.defaultclassifier()
model = classifier.train(features, labels)
new_label = model.apply(np.random.randn(20)*2)
new_label2 = model.apply(np.random.randn(20))
assert new_label == 0
assert new_label2 == 1
def test_nov2010():
# Bug submitted by Mao Ziyang
# This was failing in 0.3.5 because SDA selected no features
np.random.seed(222)
features = np.random.randn(100, 20)
features[:50] *= 2
labels = np.repeat((0, 1), 50)
classifier = milk.defaultclassifier()
model = classifier.train(features, labels)
new_label = model.apply(np.random.randn(20) * 2)
new_label2 = model.apply(np.random.randn(20))
assert new_label == 0
assert new_label2 == 1
def train_ai():
data = []
classID = []
features = []
features_temp_array = []
try:
data_filename = 'robomow_feature_data.csv'
print 'readind features and classID: ', data_filename
f_handle = open(data_filename, 'r')
reader = csv.reader(f_handle)
#read data from file into arrays
for row in reader:
data.append(row)
for row in range(0, len(data)):
#print features[row][1]
classID.append(int(data[row][0]))
features_temp_array.append(data[row][1].split(" "))
#removes ending element which is a space
for x in range(len(features_temp_array)):
features_temp_array[x].pop()
features_temp_array[x].pop(0)
#convert all strings in array to numbers
temp_array = []
for x in range(len(features_temp_array)):
temp_array = [float(s) for s in features_temp_array[x]]
features.append(temp_array)
#make numpy arrays
#features = np.asarray(features)
print classID, features
learner = milk.defaultclassifier()
model = learner.train(features, classID)
pickle.dump(model, open("robomow_ai_model.mdl", "wb"))
except:
print "could not retrain.. bad file"
return
def train_ai():
data = []
classID = []
features = []
features_temp_array = []
try:
data_filename = 'robomow_feature_data.csv'
print 'readind features and classID: ', data_filename
f_handle = open(data_filename, 'r')
reader = csv.reader(f_handle)
#read data from file into arrays
for row in reader:
data.append(row)
for row in range(0, len(data)):
#print features[row][1]
classID.append(int(data[row][0]))
features_temp_array.append(data[row][1].split(" "))
#removes ending element which is a space
for x in range(len(features_temp_array)):
features_temp_array[x].pop()
features_temp_array[x].pop(0)
#convert all strings in array to numbers
temp_array = []
for x in range(len(features_temp_array)):
temp_array = [ float(s) for s in features_temp_array[x] ]
features.append(temp_array)
#make numpy arrays
#features = np.asarray(features)
print classID, features
learner = milk.defaultclassifier()
model = learner.train(features, classID)
pickle.dump( model, open( "robomow_ai_model.mdl", "wb" ) )
except:
print "could not retrain.. bad file"
return
def learn_model(features, labels):
learner = milk.defaultclassifier()
return learner.train(features, labels)
features = [] # features for current image
features = list(mahotas.features.haralick(img).mean(0)) #haralick
features += list(Zernike(img)) #zernike
features += (list(sift(img))) #sift
Features.append(features)
#Apply KPCA for feature reduction
# will select best 440 features out of one image
kpca = KernelPCA(n_components=440, kernel='rbf')
Features = kpca.fit_transform(Features)
labels = [1] * len(positives) + [0] * len(negatives) #Labels
#creating SVM Classifier
learner = milk.defaultclassifier()
#model = learner.train(Features, labels)
start = timer()
cm, names, preds = milk.nfoldcrossvalidation(Features,
labels,
nfolds=10,
classifier=learner,
return_predictions=True)
end = timer()
print(end - start) #Time taken to perform validation
TP = cm[0][0] # class Spliced, predicted as Spliced
TN = cm[1][1] #class Authentic, predicted as Authentic
FN = cm[0][1] #class Spliced, predicted as Authentic
FP = cm[1][0] #class Authentic, predicted as Spliced
'''
@author: patrick
'''
import csv
import milk
import numpy as np
import os
f = open('country_energy.csv', 'r')
csvrows = [r for r in csv.reader(f)]
print csvrows
frows = []
for r in csvrows:
frows.append([float(x) for x in r[3:]])
#frows = [ [float(x) for x in r[3:]] for r in csvrows]
print frows
features = np.vstack(frows)
labels = [r[2] for r in csvrows]
#confusion_matrix, names = milk.nfoldcrossvalidation(features, labels)
classifier = milk.defaultclassifier()
model = classifier.train(features, labels)
def train_ai():
data = []
classID = []
features = []
features_temp_array = []
'''
#SIMPLECV
#bows
feature_extractors = []
extractor_names = []
# Training data set paths for classification(suppervised learnning)
image_dirs = ['../coin_images/jheads/',
'../coin_images/jtails/',
'../coin_images/oheads/',
'../coin_images/otails/',
]
# Different class labels for multi class classification
class_names = ['jhead','jtail','ohead', 'otail']
#preprocess all training images
for directory in image_dirs:
for filename in glob.glob(directory + '/*.jpg'):
print "Processing:", filename
img = cv2.imread(filename)
temp_img = preprocess_houghlines (img, 100)
temp_str = filename.rsplit('/')
temp_str = temp_str[len(temp_str)-1]
temp_str = directory + '/temp/' + temp_str
print temp_str
cv2.imwrite(temp_str, temp_img)
#raw_input('press enter to continue : ')
#sys.exit(-1)
#build array of directories for bow
#image_dirs2 = []
#for directory in image_dirs:
# image_dirs2.append(directory + '/temp/')
#print image_dirs2
# Different class labels for multi class classification
extractor_name = 'hue'
if extractor_name == 'bow':
feature_extractor = BOFFeatureExtractor() # feature extrator for bag of words methodology
feature_extractor.generate(image_dirs,imgs_per_dir=40) # code book generation
elif extractor_name == 'hue':
feature_extractor = HueHistogramFeatureExtractor()
elif extractor_name == 'morphology':
feature_extractor = MorphologyFeatureExtractor()
elif extractor_name == 'haar':
feature_extractor = HaarLikeFeatureExtractor()
elif extractor_name == 'edge':
feature_extractor = EdgeHistogramFeatureExtractor()
image_dirs2 = image_dirs
#bow_features = BOFFeatureExtractor()
#bow_features.generate(image_dirs2,imgs_per_dir=40, verbose=True) # code book generation
#bow_features.generate(image_dirs2,imgs_per_dir=200,numcodes=256,sz=(11,11),img_layout=(16,16),padding=4 )
#bow_features.save('codebook.png','bow.txt')
#print "extractor_names:", extractor_names, feature_extractors
# initializing classifier with appropriate feature extractors list
#print type(bow_features), bow_features, bow_features.getFieldNames(), bow_features.getNumFields()
#raw_input('bow saved...Enter : ')
#bow_features = None
#bow_features = BOFFeatureExtractor()
#print type(bow_features), bow_features, bow_features.getFieldNames(), bow_features.getNumFields()
#bow_features.load('bow.txt')
#print type(bow_features), bow_features, bow_features.getFieldNames(), bow_features.getNumFields()
feature_extractors.append(feature_extractor)
#raw_input('bow loaded Enter : ')
#extractor_names.append(extractor_name)
classifier_name = 'naive'
if classifier_name == 'naive':
classifier = NaiveBayesClassifier(feature_extractors)
elif classifier_name == 'svm':
classifier = SVMClassifier(feature_extractors)
elif classifier_name == 'knn':
classifier = KNNClassifier(feature_extractors, 2)
elif classifier_name == 'tree':
classifier = TreeClassifier(feature_extractors)
# train the classifier to generate hypothesis function for classification
#print "image_dirs:", image_dirs, class_names
classifier.train(image_dirs2,class_names,disp=None,savedata='features.txt',verbose=True)
print 'classifier:', type(classifier), classifier
raw_input('press enter to continue :')
#pickle.dump( classifier, open( "coinvision_ai_model2.mdl", "wb" ),2 )
#classifier.save('coinvision_ai_model.mdl')
print 'classifier:', type(classifier), classifier
#classifier = NaiveBayesClassifier.load('coinvision_ai_model.mdl')
#raw_input('press enter to continue : let me try loading bow file')
#classifier2 = NaiveBayesClassifier.load('coinvision_ai_model.mdl')
#classifier2.setFeatureExtractors(feature_extractors)
#print 'classifier2:', type(classifier2), classifier2
#classifier.load("coinvision_ai_model.mdl")
#classifier2.load('coinvision_ai_model.mdl')
#print 'classifier:', type(classifier2), classifier2
raw_input('press enter to continue : ')
print 'testing ai:'
test_images_path = "../coin_images/unclassified"
extension = "*.jpg"
if not test_images_path:
path = os.getcwd() #get the current directory
else:
path = test_images_path
directory = os.path.join(path, extension)
files = glob.glob(directory)
count = 0 # counting the total number of training images
error = 0 # conuting the total number of misclassification by the trained classifier
for image_file in files:
new_image = Image(image_file)
category = classifier.classify(new_image)
print "image_file:", image_file + " classified as: " + category
if image_file[-9] == 't':
if category == 'jhead' or category == 'ohead':
print "INCORRECT CLASSIFICATION"
error += 1
if image_file[-9] == 'h':
if category == 'jtail' or category == 'otail':
print "INCORRECT CLASSIFICATION"
error += 1
count += 1
# reporting the results
print ' * classifier : ', classifier
print ' * extractors :', extractor_names
print ' *', error, 'errors out of', count
raw_input('edned press enter to continue : ')
return
'''
#try:
data_filename = 'coinvision_feature_data.csv'
print 'reading features and classID: ', data_filename
f_handle = open(data_filename, 'r')
reader = csv.reader(f_handle)
#read data from file into arrays
for row in reader:
data.append(row)
for row in range(0, len(data)):
#print features[row][1]
classID.append(int(data[row][0]))
features_temp_array.append(data[row][1].split(" "))
#removes ending element which is a space
for x in range(len(features_temp_array)):
features_temp_array[x].pop()
features_temp_array[x].pop(0)
#convert all strings in array to numbers
temp_array = []
for x in range(len(features_temp_array)):
temp_array = [ float(s) for s in features_temp_array[x] ]
features.append(temp_array)
#make numpy arrays
features = np.asarray(features)
#print classID, features
learner = milk.defaultclassifier(mode='really-slow')
model = learner.train(features, classID)
pickle.dump( model, open( "coinvision_ai_model.mdl", "wb" ) )
#except:
print "could not retrain.. bad file"
from sklearn import svm
model = svm.SVC(gamma=0.001, C=100.)
model.fit(features, classID)
pickle.dump( model, open( "coinvision_ai_model_svc.mdl", "wb" ) )
from sklearn.neighbors import KNeighborsClassifier
neigh = KNeighborsClassifier(n_neighbors=3)
neigh.fit(features, classID)
pickle.dump( neigh, open( "coinvision_ai_model_knn.mdl", "wb" ) )
from sklearn.svm import LinearSVC
clf = LinearSVC()
clf = clf.fit(features, classID)
pickle.dump( clf, open( "coinvision_ai_model_lr.mdl", "wb" ) )
from sklearn.linear_model import LogisticRegression
clf2 = LogisticRegression().fit(features, classID)
pickle.dump( clf2 , open( "coinvision_ai_model_clf2.mdl", "wb" ) )
return
def train_model((features,labels)):
import milk
learner = milk.defaultclassifier()
return learner.train(features, labels)
mypda = mlpy.Pda()
mypda.compute(xtr,ytr)
print "pda: ", mypda.predict(xts)
print "correct class:", classID[id_index]
#print np.shape(xtr), xtr.ndim, xtr.dtype
#print np.shape(ytr), ytr.ndim, ytr.dtype
#print np.shape(xts), xts.ndim, xts.dtype
#milk
#Help on function feature_selection_simple in module milk.supervised.defaultlearner:
#selector = feature_selection_simple()
learner = milk.defaultclassifier(mode='medium', multi_strategy='1-vs-1', expanded=False)
model = learner.train(xtr, ytr)
print "milk: ", model.apply(xts[0])
#from sklearn.externals import joblib
#joblib.dump(model, 'saved_model.pkl')
#model2 = joblib.load('saved_model.pkl')
#print "milk: ", model2.apply(xts[0])
from sklearn.neighbors import KNeighborsClassifier
knn = KNeighborsClassifier(leaf_size=30, n_neighbors=5, p=2,
warn_on_equidistant=True, weights='distance')
model3 = knn.fit(xtr, ytr)
print "knn sclearn: ", model3.predict(xts)
def learn_model(features, labels):
learner = milk.defaultclassifier()
return learner.train(features, labels)
def learn_model(features, labels):
learner = milk.defaultclassifier(mode='really-slow')
return learner.train(features, labels)