###########################################
############## SEEDS DATASET ##############
###########################################
from main.ch02.load import load_dataset
feature_names = [
'area',
'perimeter',
'compactness',
'length of kernel',
'width of kernel',
'asymmetry coefficien',
'length of kernel groove',
]
features, labels = load_dataset('seeds')
from sklearn.neighbors import KNeighborsClassifier
classifier = KNeighborsClassifier(n_neighbors=1)
from sklearn.cross_validation import KFold
kf = KFold(len(features), n_folds=5, shuffle=True)
means = []
for training, testing in kf:
# We learn a model for this fold with `fit` and then apply it to the
# testing data with `predict`:
classifier.fit(features[training], labels[training])
prediction = classifier.predict(features[testing])
# np.mean on an array of booleans returns fraction
def __init__(self):
global features, labels
features, labels = load.load_dataset("seeds")
load.test_load(features, labels)
logging.info("data loaded successfully")