def setUp(self):
self.size = 100
self.X = np.random.rand(self.size, 1)
self.y = self.X + np.random.randn(self.size, 1)
concatenator = Concatenator()
gaussian_clustering = GaussianMixture(n_components=3)
dbscan = DBSCAN(eps=0.5)
mixer = CustomCombination()
linear_model = LinearRegression()
self.steps = steps = [
('Concatenate_Xy', concatenator),
('Gaussian_Mixture', gaussian_clustering),
('Dbscan', dbscan),
('Combine_Clustering', mixer),
('Regressor', linear_model),
]
self.connections = {
'Concatenate_Xy':
dict(df1='X', df2='y'),
'Gaussian_Mixture':
dict(X=('Concatenate_Xy', 'Xy')),
'Dbscan':
dict(X=('Concatenate_Xy', 'Xy')),
'Combine_Clustering':
dict(dominant=('Dbscan', 'predict'),
other=('Gaussian_Mixture', 'predict')),
'Regressor':
dict(X='X', y='y')
}
def setUp(self):
self.size = 1000
self.X = pd.DataFrame(dict(X=np.random.rand(self.size, )))
self.y = pd.DataFrame(dict(y=(np.random.rand(self.size, ))))
concatenator = Concatenator()
gaussian_clustering = GaussianMixture(n_components=3)
dbscan = DBSCAN(eps=0.5)
mixer = CustomCombination()
linear_model = LinearRegression()
steps = [
('Concatenate_Xy', concatenator),
('Gaussian_Mixture', gaussian_clustering),
('Dbscan', dbscan),
('Combine_Clustering', mixer),
('Regressor', linear_model),
]
connections = {
'Concatenate_Xy':
dict(df1='X', df2='y'),
'Gaussian_Mixture':
dict(X=('Concatenate_Xy', 'predict')),
'Dbscan':
dict(X=('Concatenate_Xy', 'predict')),
'Combine_Clustering':
dict(dominant=('Dbscan', 'predict'),
other=('Gaussian_Mixture', 'predict')),
'Regressor':
dict(X='X', y='y')
}
self.steps_external = [
('_External', concatenator),
('Gaussian_Mixture', gaussian_clustering),
('Dbscan', dbscan),
('Combine_Clustering', mixer),
('Regressor', linear_model),
]
self.connections_external = {
'_External':
dict(df1='X', df2='y'),
'Gaussian_Mixture':
dict(X=('Concatenate_Xy', 'predict')),
'Dbscan':
dict(X=('Concatenate_Xy', 'predict')),
'Combine_Clustering':
dict(dominant=('Dbscan', 'predict'),
other=('Gaussian_Mixture', 'predict')),
'Regressor':
dict(X='X', y='y')
}
self.steps = steps
self.connections = connections
self.pgraph = PipeGraph(steps=steps, fit_connections=connections)
self.pgraph.fit(self.X, self.y)
def setUp(self):
self.size = 100
self.X = pd.DataFrame(dict(X=np.random.rand(self.size, )))
self.y = pd.DataFrame(dict(y=np.random.rand(self.size, )))
concatenator = Concatenator()
gaussian_clustering = GaussianMixture(n_components=3)
dbscan = DBSCAN(eps=0.5)
mixer = CustomCombination()
paellaModel = Paella(regressor=LinearRegression,
noise_label=None,
max_it=10,
regular_size=100,
minimum_size=30,
width_r=0.95,
power=10,
random_state=42)
linear_model = LinearRegression()
steps = [
('Concatenate_Xy', concatenator),
('Gaussian_Mixture', gaussian_clustering),
('Dbscan', dbscan),
('Combine_Clustering', mixer),
('Paella', paellaModel),
('Regressor', linear_model),
]
connections = {
'Concatenate_Xy':
dict(df1='X', df2='y'),
'Gaussian_Mixture':
dict(X=('Concatenate_Xy', 'predict')),
'Dbscan':
dict(X=('Concatenate_Xy', 'predict')),
'Combine_Clustering':
dict(dominant=('Dbscan', 'predict'),
other=('Gaussian_Mixture', 'predict')),
'Paella':
dict(X='X',
y='y',
classification=('Combine_Clustering', 'predict')),
'Regressor':
dict(X='X', y='y', sample_weight=('Paella', 'predict'))
}
self.steps = steps
self.connections = connections
self.pgraph = PipeGraph(steps=steps, fit_connections=connections)
from pipegraph.base import PipeGraph, Concatenator
import matplotlib.pyplot as plt
from sklearn.datasets import load_iris
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.neural_network import MLPClassifier
iris = load_iris()
X = iris.data
y = iris.target
scaler = MinMaxScaler()
gaussian_nb = GaussianNB()
svc = SVC()
mlp = MLPClassifier()
concatenator = Concatenator()
steps = [('scaler', scaler), ('gaussian_nb', gaussian_nb), ('svc', svc),
('concat', concatenator), ('mlp', mlp)]
###############################################################################
# In this example we use a :class:`PipeGraphClassifier` because the result is a classification and we want to take advantage of Scikit-Learn default scoring method for classifiers.
pgraph = PipeGraph(steps=steps)
(pgraph.inject(sink='scaler', sink_var='X', source='_External',
source_var='X').inject('gaussian_nb', 'X', 'scaler').inject(
'gaussian_nb', 'y',
source_var='y').inject('svc', 'X', 'scaler').inject(
'svc', 'y',
source_var='y').inject('concat', 'X1', 'scaler').inject(
'concat', 'X2',