Python fetch_growth示例

示例#1

import skfda
import numpy as np
import matplotlib.pyplot as plt
from skfda.datasets import fetch_growth
from skfda.representation.interpolation import SplineInterpolator
from skfda.preprocessing.registration import elastic_registration_warping, elastic_registration

data = fetch_growth()

fd = data['data']

fd = fd[data['target'] == 0]

fd = fd.derivative()
fd.interpolator = SplineInterpolator(3)
#fd = fd.to_grid(np.linspace(*fd.domain_range[0], 150))
fd.dataset_label = None
fd.axes_labels = [
    "age (year)", r"$\partial \, height \, / \, \partial \, age$ (cm/year)"
]

plt.figure("berkeley-males")
fd.plot()

plt.xlim(fd.domain_range[0])
a, b = plt.ylim()
plt.ylim(a, 20)

plt.tight_layout()

plt.figure("berkeley-warping")

示例#2

# consists in finite values dispersed over points in a domain range.
# We initialize and setup the FPCADiscretized object and run the fit method to
# obtain the first two components. By default, if we do not specify the number
# of components, it's 3. Other parameters are weights and centering. For more
# information please visit the documentation.
fpca_discretized = FPCA(n_components=2)
fpca_discretized.fit(fd)
fpca_discretized.components_.plot()

##############################################################################
# In the second case, the data is first converted to use a basis representation
# and the FPCA is done with the basis representation of the original data.
# We obtain the same dataset again and transform the data to a basis
# representation. This is because the FPCA module modifies the original data.
# We also plot the data for better visual representation.
dataset = fetch_growth()
fd = dataset['data']
basis = skfda.representation.basis.BSpline(n_basis=7)
basis_fd = fd.to_basis(basis)
basis_fd.plot()

##############################################################################
# We initialize the FPCABasis object and run the fit function to obtain the
# first 2 principal components. By default the principal components are
# expressed in the same basis as the data. We can see that the obtained result
# is similar to the discretized case.
fpca = FPCA(n_components=2)
fpca.fit(basis_fd)
fpca.components_.plot()

##############################################################################

示例#3

if __name__ == "__main__":
    from skfda import datasets
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.linear_model import LogisticRegression
    from sklearn.ensemble import RandomForestClassifier
    from sklearn.svm import SVC
    from sklearn.ensemble import GradientBoostingClassifier
    from sklearn.ensemble import ExtraTreesClassifier
    from sklearn.ensemble import AdaBoostClassifier
    from sklearn.ensemble import BaggingClassifier
    from sklearn.neural_network import MLPClassifier
    from sklearn.model_selection import train_test_split
    from sklearn.metrics import accuracy_score, f1_score

    data = datasets.fetch_growth()
    X = data['data'].data_matrix.squeeze()
    target = data['target']
    sample_points = np.arange(31)
    Ncomps = 3
    model = SVC()

    Xtrain, Xtest, ytrain, ytest = train_test_split(X,
                                                    target,
                                                    test_size=0.3,
                                                    random_state=0)
    SFMClassifier_SVC = SFMClassifier(model, sample_points, Ncomps)
    SFMClassifier_SVC.fit(Xtrain, ytrain)
    ypred = SFMClassifier_SVC.predict(Xtest, Xtrain)

    f1 = f1_score(ytest, ypred, average='macro')

示例#4

fd_align = elastic_registration.fit_transform(fd)

fd_align.plot()


##############################################################################
# In general these type of alignments are not possible, in the following
# figure it is shown how it works with a real dataset.
# The :func:`berkeley growth dataset<skfda.datasets.fetch_growth>`
# contains the growth curves of a set children, in this case will be used only
# the males. The growth curves will be resampled using cubic interpolation and
# derived to obtain the velocity curves.
#
# First we show the original curves:

growth = fetch_growth()

# Select only one sex
fd = growth['data'][growth['target'] == 0]

# Obtain velocity curves
fd.interpolation = skfda.representation.interpolation.SplineInterpolation(3)
fd = fd.to_grid(np.linspace(*fd.domain_range[0], 200)).derivative()
fd = fd.to_grid(np.linspace(*fd.domain_range[0], 50))
fd.plot()

##############################################################################
# We now show the aligned curves:

fd_align = elastic_registration.fit_transform(fd)
fd_align.dataset_name += " - aligned"