def main(readcsv=read_csv, method='defaultDense'):
# Input data set parameters
train_file = os.path.join('data', 'batch', 'k_nearest_neighbors_train.csv')
predict_file = os.path.join('data', 'batch',
'k_nearest_neighbors_test.csv')
# Read data. Let's use 5 features per observation
nFeatures = 5
nClasses = 5
train_data = readcsv(train_file, range(nFeatures))
train_labels = readcsv(train_file, range(nFeatures, nFeatures + 1))
# Create an algorithm object and call compute
train_algo = d4p.kdtree_knn_classification_training(nClasses=nClasses)
# 'weights' is optional argument, let's use equal weights
# in this case results must be the same as without weights
weights = np.ones((train_data.shape[0], 1))
train_result = train_algo.compute(train_data, train_labels, weights)
# Now let's do some prediction
predict_data = readcsv(predict_file, range(nFeatures))
predict_labels = readcsv(predict_file, range(nFeatures, nFeatures + 1))
# Create an algorithm object and call compute
predict_algo = d4p.kdtree_knn_classification_prediction()
predict_result = predict_algo.compute(predict_data, train_result.model)
# We expect less than 170 mispredicted values
assert np.count_nonzero(predict_labels != predict_result.prediction) < 170
return (train_result, predict_result, predict_labels)
def predict(self, X):
# Check is fit had been called
check_is_fitted(self, ['n_features_', 'n_classes_'])
# Input validation
X = check_array(X, dtype=[np.single, np.double])
if X.shape[1] != self.n_features_:
raise ValueError(
'Shape of input is different from what was seen in `fit`')
# Trivial case
if self.n_classes_ == 1:
return np.full(X.shape[0], self.classes_[0])
check_is_fitted(self, ['daal_model_'])
# Define type of data
fptype = getFPType(X)
# Prediction
predict_algo = d4p.kdtree_knn_classification_prediction(
fptype=fptype, k=self.n_neighbors)
predict_result = predict_algo.compute(X, self.daal_model_)
# Decode labels
le = preprocessing.LabelEncoder()
le.classes_ = self.classes_
return le.inverse_transform(predict_result.prediction.ravel().astype(
np.int64, copy=False))
def predict(self, X):
# Check is fit had been called
if LooseVersion(sklearn_version) >= LooseVersion("0.22"):
check_is_fitted(self)
else:
check_is_fitted(self, ['n_features_', 'n_classes_'])
# Input validation
X = check_array(X, dtype=[np.single, np.double])
if X.shape[1] != self.n_features_:
raise ValueError('Shape of input is different from what was seen in `fit`')
# Trivial case
if self.n_classes_ == 1:
return np.full(X.shape[0], self.classes_[0])
if not hasattr(self, 'daal_model_'):
raise ValueError(("The class {} instance does not have 'daal_model_' attribute set. "
"Call 'fit' with appropriate arguments before using this method.").format(type(self).__name__))
# Define type of data
fptype = getFPType(X)
# Prediction
predict_algo = d4p.kdtree_knn_classification_prediction(fptype=fptype,
k=self.n_neighbors)
predict_result = predict_algo.compute(X, self.daal_model_)
# Decode labels
le = preprocessing.LabelEncoder()
le.classes_ = self.classes_
return le.inverse_transform(predict_result.prediction.ravel().astype(np.int64, copy=False))
def predict(cls, input):
"""For the input, do the predictions and return them.
Args:
input (a pandas dataframe): The data on which to do the predictions. There will be
one prediction per row in the dataframe"""
with open(param_path, "r") as pf:
params = json.load(pf)
predict_algo = kdtree_knn_classification_prediction(
nClasses=int(params["nClasses"]),
fptype=params["fptype"],
method=params["method"],
dataUseInModel=params["dataUseInModel"],
k=int(params["k"]),
distributed=(True
if params["distributed"] == "True" else False))
clf = cls.get_model()
return predict_algo.compute(input, clf)
def main():
# Input data set parameters
train_file = os.path.join('data', 'batch', 'k_nearest_neighbors_train.csv')
predict_file = os.path.join('data', 'batch',
'k_nearest_neighbors_test.csv')
# Read data. Let's use 5 features per observation
nFeatures = 5
train_data = read_csv(train_file, range(nFeatures))
train_labels = read_csv(train_file, range(nFeatures, nFeatures + 1))
# Create an algorithm object and call compute
train_algo = d4p.kdtree_knn_classification_training()
train_result = train_algo.compute(train_data, train_labels)
# Now let's do some prediction
predict_data = read_csv(predict_file, range(nFeatures))
predict_labels = read_csv(predict_file, range(nFeatures, nFeatures + 1))
# Create an algorithm object and call compute
predict_algo = d4p.kdtree_knn_classification_prediction()
predict_result = predict_algo.compute(predict_data, train_result.model)
return (train_result, predict_result, predict_labels)