class PimaIndiansExample:
""" Runs Pima Indians Example.
More info: https://machinelearningmastery.com/standard-machine-learning-datasets/
Dataset source: https://machinelearningmastery.com/standard-machine-learning-datasets/"""
def __init__(self, algorithm):
self.dataset = pd.read_csv('data/indian-dataset.txt')
self.algorithm = Classification(algorithm)
def run(self):
"""
Runs example.
"""
X_train, X_test, y_train, y_test = self.__prepare_data(
'Class', 'Class')
self.algorithm.train_model(X_train, X_test, y_train, y_test)
def __prepare_data(self, drop_columns, output_column):
"""
Splits the data into train and test batches.
:param drop_columns: columns to drop
:param output_column: output column
:returns: Data split into X_train, X_test, y_train, y_test
"""
columns = [
"No times pregnant", "Plasma glucose", "blood pressure",
"skinfold thickness", "2-Hour serum insulin", "BMI",
"Diabetes pedigree function", "Age", "Class"
]
self.dataset.columns = columns
X = self.dataset.drop(drop_columns, axis='columns')
y = self.dataset[output_column]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2)
return X_train, X_test, y_train, y_test
class Cifar10Example:
""" Runs CIFAR10 example. Uses keras (tensorflow) to fetch dataset"""
def __init__(self, algorithm):
self.dataset = cifar10.load_data()
self.algorithm = Classification(algorithm)
def run(self):
"""
Runs example.
"""
X_train, X_test, y_train, y_test = self.__prepare_data()
self.algorithm.train_model(X_train, X_test, y_train, y_test)
def __prepare_data(self):
"""
Prepares the data. Based on
'athena.ecs.csus.edu/~hoangkh/Image Classification with Fashion-MNIST and CIFAR-10.html'.
:returns: Data split into X_train, X_test, y_train, y_test
"""
(X_train, y_train), (X_test, y_test) = self.dataset
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train /= 255
X_test /= 255
x_train_flat = X_train.reshape(X_train.shape[0], X_train.shape[1] * X_train.shape[2] * X_train.shape[3])
x_test_flat = X_test.reshape(X_test.shape[0], X_test.shape[1] * X_test.shape[2] * X_test.shape[3])
y_train = y_train.reshape(y_train.shape[0], )
y_test = y_test.reshape(y_test.shape[0], )
return x_train_flat, x_test_flat, y_train, y_test
class FashionMNISTExample:
""" Runs Fashion MNIST Example.
More info: https://github.com/zalandoresearch/fashion-mnist"""
def __init__(self, algorithm):
self.dataset = pd.read_csv('data/Fashion-MNIST/train.csv')
self.algorithm = Classification(algorithm)
def run(self):
"""
Runs example.
"""
X_train, X_test, y_train, y_test = self.__prepare_data(['Id', 'Category'], 'Category')
self.algorithm.train_model(X_train, X_test, y_train, y_test)
def __prepare_data(self, drop_columns, output_column):
"""
Splits the data into train and test batches.
:param drop_columns: columns to drop
:param output_column: output column
:returns: Data split into X_train, X_test, y_train, y_test
"""
X = self.dataset.drop(drop_columns, axis='columns')
y = self.dataset[output_column]
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
return X_train, X_test, y_train, y_test
class LetterRecognitionExample:
""" Runs Lette rRecognition Example.
Dataset source: https://archive.ics.uci.edu/ml/datasets/letter+recognition?fbclid=IwAR0VhB2EGYaFlHO2xaUuDbEvhBgmBGcvdoFGOKUBxk3nVa8926zsL3DF-Nk """
def __init__(self, algorithm):
self.dataset = pd.read_csv('data/letter-recognition.data')
self.algorithm = Classification(algorithm)
def run(self):
"""
Runs example.
"""
X_train, X_test, y_train, y_test = self.__prepare_data(
'Letter', 'Letter')
self.algorithm.train_model(X_train, X_test, y_train, y_test)
def __prepare_data(self, drop_columns, output_column):
"""
Splits the data into train and test batches.
:param drop_columns: columns to drop
:param output_column: output column
:returns: Data split into X_train, X_test, y_train, y_test
"""
columns = [
"Letter", "x-box horizontal pos", "y-box vertical pos", "width",
"height", "onpix total #", "x-bar mean x of on pixels",
"y-bar mean y of on pixels", "x2bar mean x var",
"y2bar mean y var", "xybar mean x y correl",
"x2ybr mean of x * x * y", "xy2br mean of x * y * y",
"x-ege mean edge count left to right",
"xegvy correlation of x-ege with y",
"y-ege mean edge count bottom to top",
"yegvx correlation of y-ege with x"
]
self.dataset.columns = columns
X = self.dataset.drop(drop_columns, axis='columns')
y = self.dataset[output_column]
X_train, X_test, y_train, y_test = train_test_split(X,
y,
test_size=0.2)
return X_train, X_test, y_train, y_test
def __init__(self, algorithm):
self.dataset = pd.read_csv('data/indian-dataset.txt')
self.algorithm = Classification(algorithm)
def __init__(self, algorithm):
self.dataset = cifar10.load_data()
self.algorithm = Classification(algorithm)
def __init__(self, algorithm):
self.dataset = pd.read_csv('data/letter-recognition.data')
self.algorithm = Classification(algorithm)
def __init__(self, algorithm):
self.dataset = pd.read_csv('data/Fashion-MNIST/train.csv')
self.algorithm = Classification(algorithm)