import numpy as np
import matplotlib.pyplot as plt
from sklearn import neighbors
%matplotlib inline
np.random.seed(0)
X = np.sort(5 * np.random.rand(40, 1), axis=0)
T = np.linspace(0, 5, 500)[:, np.newaxis]
y = np.sin(X).ravel()
# Add noise to targets
y[::5] += 1 * (0.5 - np.random.rand(8))
###############################################################################
# Fit regression model
n_neighbors = 5
for i, weights in enumerate(['uniform', 'distance']):
knn = neighbors.KNeighborsRegressor(n_neighbors, weights=weights)
y_ = knn.fit(X, y).predict(T)
plt.subplot(2, 1, i + 1)
plt.scatter(X, y, c='k', label='data')
plt.plot(T, y_, c='g', label='prediction')
plt.axis('tight')
plt.legend()
plt.title("KNeighborsRegressor (k = %i, weights = '%s')" % (n_neighbors,
weights))
print(__doc__)
# Import the necessary modules and libraries
import numpy as np
from sklearn.tree import DecisionTreeRegressor
import matplotlib.pyplot as plt
# Create a random dataset
rng = np.random.RandomState(1)
X = np.sort(5 * rng.rand(80, 1), axis=0)
y = np.sin(X).ravel()
y[::5] += 3 * (0.5 - rng.rand(16))
# Fit regression model
regr_1 = DecisionTreeRegressor(max_depth=2)
regr_2 = DecisionTreeRegressor(max_depth=5)
regr_1.fit(X, y)
regr_2.fit(X, y)
# Predict
X_test = np.arange(0.0, 5.0, 0.01)[:, np.newaxis]
y_1 = regr_1.predict(X_test)
y_2 = regr_2.predict(X_test)
# Plot the results
plt.figure()
plt.scatter(X, y, c="k", label="data")
plt.plot(X_test, y_1, c="g", label="max_depth=2", linewidth=2)
plt.plot(X_test, y_2, c="r", label="max_depth=5", linewidth=2)
plt.xlabel("data")
plt.ylabel("target")
plt.title("Decision Tree Regression")
plt.legend()
plt.show()
Automatically created module for IPython interactive environment
print(__doc__)
import numpy as np
from sklearn.svm import SVR
import matplotlib.pyplot as plt
###############################################################################
# Generate sample data
X = np.sort(5 * np.random.rand(40, 1), axis=0)
y = np.sin(X).ravel()
###############################################################################
# Add noise to targets
y[::5] += 3 * (0.5 - np.random.rand(8))
###############################################################################
# Fit regression model
svr_rbf = SVR(kernel='rbf', C=1e3, gamma=0.1)
svr_lin = SVR(kernel='linear', C=1e3)
svr_poly = SVR(kernel='poly', C=1e3, degree=2)
y_rbf = svr_rbf.fit(X, y).predict(X)
y_lin = svr_lin.fit(X, y).predict(X)
y_poly = svr_poly.fit(X, y).predict(X)
###############################################################################
# look at the results
plt.scatter(X, y, c='k', label='data')
plt.hold('on')
plt.plot(X, y_rbf, c='g', label='RBF model')
plt.plot(X, y_lin, c='r', label='Linear model')
plt.plot(X, y_poly, c='b', label='Polynomial model')
plt.xlabel('data')
plt.ylabel('target')
plt.title('Support Vector Regression')
plt.legend()
plt.show()
Automatically created module for IPython interactive environment
print(__doc__)
import numpy as np
import matplotlib.pyplot as plt
from sklearn.datasets import fetch_olivetti_faces
from sklearn.utils.validation import check_random_state
from sklearn.ensemble import ExtraTreesRegressor
from sklearn.neighbors import KNeighborsRegressor
from sklearn.linear_model import LinearRegression
from sklearn.linear_model import RidgeCV
# Load the faces datasets
data = fetch_olivetti_faces()
targets = data.target
data = data.images.reshape((len(data.images), -1))
train = data[targets < 30]
test = data[targets >= 30] # Test on independent people
# Test on a subset of people
n_faces = 5
rng = check_random_state(4)
face_ids = rng.randint(test.shape[0], size=(n_faces, ))
test = test[face_ids, :]
n_pixels = data.shape[1]
X_train = train[:, :np.ceil(0.5 * n_pixels)] # Upper half of the faces
y_train = train[:, np.floor(0.5 * n_pixels):] # Lower half of the faces
X_test = test[:, :np.ceil(0.5 * n_pixels)]
y_test = test[:, np.floor(0.5 * n_pixels):]
# Fit estimators
ESTIMATORS = {
"Extra trees": ExtraTreesRegressor(n_estimators=10, max_features=32,
random_state=0),
"K-nn": KNeighborsRegressor(),
"Linear regression": LinearRegression(),
"Ridge": RidgeCV(),
}
y_test_predict = dict()
for name, estimator in ESTIMATORS.items():
estimator.fit(X_train, y_train)
y_test_predict[name] = estimator.predict(X_test)
# Plot the completed faces
image_shape = (64, 64)
n_cols = 1 + len(ESTIMATORS)
plt.figure(figsize=(2. * n_cols, 2.26 * n_faces))
plt.suptitle("Face completion with multi-output estimators", size=16)
for i in range(n_faces):
true_face = np.hstack((X_test[i], y_test[i]))
if i:
sub = plt.subplot(n_faces, n_cols, i * n_cols + 1)
else:
sub = plt.subplot(n_faces, n_cols, i * n_cols + 1,
title="true faces")
sub.axis("off")
sub.imshow(true_face.reshape(image_shape),
cmap=plt.cm.gray,
interpolation="nearest")
for j, est in enumerate(sorted(ESTIMATORS)):
completed_face = np.hstack((X_test[i], y_test_predict[est][i]))
if i:
sub = plt.subplot(n_faces, n_cols, i * n_cols + 2 + j)
else:
sub = plt.subplot(n_faces, n_cols, i * n_cols + 2 + j,
title=est)
sub.axis("off")
sub.imshow(completed_face.reshape(image_shape),
cmap=plt.cm.gray,
interpolation="nearest")
plt.show()
Automatically created module for IPython interactive environment
/usr/local/lib/python2.7/dist-packages/ipykernel/__main__.py:29: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future /usr/local/lib/python2.7/dist-packages/ipykernel/__main__.py:30: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future /usr/local/lib/python2.7/dist-packages/ipykernel/__main__.py:31: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future /usr/local/lib/python2.7/dist-packages/ipykernel/__main__.py:32: DeprecationWarning: using a non-integer number instead of an integer will result in an error in the future