import numpy as np
import matplotlib.pyplot as plt
import feature_utils as utils
import time
from sklearn.cluster import KMeans
from sklearn.decomposition import PCA
from sklearn.cross_validation import KFold
from multiprocessing.dummy import Pool
from multiprocessing import cpu_count
X, labels = utils.load_features("gist")
n_samples, n_features = X.shape
n_targets = labels.shape[1]
#n_targets = 1
print(X.shape)
n_folds = 4
# runs for each fold
def run(args):
start_time = time.time()
train, test = args
# for GIST only
mult = 32 # split each input row into 32 rows
fv_dims = 512 / mult
X_train = X[train].reshape((-1, fv_dims))
# cluster data
kmeans = KMeans()
import numpy as np
import matplotlib.pyplot as plt
import feature_utils as utils
import time
from sklearn import neighbors, metrics
from sklearn.decomposition import PCA
from sklearn.cross_validation import StratifiedKFold
X, labels = utils.load_features('histograms')
n_samples, n_features = X.shape
n_targets = labels.shape[1]
#n_targets = 1
print(X.shape)
pca = PCA(n_components=0.95)
X = pca.fit_transform(X)
print(X.shape)
c = X.shape[1]
n_folds = 10
accuracy = np.ndarray((n_folds, n_targets))
tpr = np.ndarray((n_folds, n_targets))
fpr = np.ndarray((n_folds, n_targets))
k = 5
for target in range(n_targets):
print("target : %i/%i" % (target + 1, n_targets))
y = labels[:, target]
skf = StratifiedKFold(y, n_folds=n_folds)
start_time = time.time()
import numpy as np
import matplotlib.pyplot as plt
import feature_utils as utils
import time
from sklearn.naive_bayes import GaussianNB
from sklearn.cross_validation import StratifiedKFold
f_name = 'hog_9'
X, labels = utils.load_features(f_name)
n_samples, n_features = X.shape
n_targets = labels.shape[1]
#n_targets = 1
print(X.shape)
n_folds = 10
accuracy = np.ndarray((n_folds, n_targets))
tpr = np.ndarray((n_folds, n_targets))
fpr = np.ndarray((n_folds, n_targets))
for target in range(n_targets):
print("target : %i/%i" % (target + 1, n_targets))
y = labels[:, target]
skf = StratifiedKFold(y, n_folds=n_folds)
start_time = time.time()
for i, (train, test) in enumerate(skf):
print("fold : %i/%i" % (i + 1, n_folds))
classifier = GaussianNB()
classifier.fit(X[train], y[train])
classes = classifier.predict(X[test])
import numpy as np
import matplotlib.pyplot as plt
import feature_utils as utils
import time
from sklearn import neighbors, metrics
from sklearn.decomposition import PCA
X, y = utils.load_features('histograms')
n_samples, n_features = X.shape
y = y[:, 0]
print(X.shape)
pca = PCA(n_components=0.7)
X = pca.fit_transform(X)
print(X.shape)
start_time = time.time()
k = 5
classifier = neighbors.KNeighborsClassifier(k)
classifier.fit(X, y)
p = classifier.predict_proba(X)
idx = np.argmax(p, axis=1)
scores = p[np.arange(p.shape[0]), idx]
genuine = classifier.classes_[idx] == y
elapsed_time = time.time() - start_time
fpr, tpr, _ = metrics.roc_curve(genuine, scores)
print("elapsed time : " + str(elapsed_time))