%pylab inline
import pylab as pl
import numpy as np

from sklearn.linear_model import LinearRegression

model = LinearRegression(normalize=True)
print model.normalize

print model

x = np.array([0, 1, 2])
y = np.array([0, 1, 2])

_ = pl.plot(x, y, marker='o')

X = x[:, np.newaxis] # The input data for sklearn is 2D: (samples == 3 x features == 1)
X

model.fit(X, y) 
model.coef_

from sklearn import neighbors, datasets
iris = datasets.load_iris()
X, y = iris.data, iris.target
knn = neighbors.KNeighborsClassifier(n_neighbors=1)
knn.fit(X, y)
# What kind of iris has 3cm x 5cm sepal and 4cm x 2cm petal?
print iris.target_names[knn.predict([[3, 5, 4, 2]])]

# A plot of the sepal space and the prediction of the KNN
from helpers import plot_iris_knn
plot_iris_knn()

# Create some simple data
import numpy as np
np.random.seed(0)
X = np.random.random(size=(20, 1))
y = 3 * X.squeeze() + 2 + np.random.normal(size=20)

# Fit a linear regression to it
from sklearn.linear_model import LinearRegression
model = LinearRegression(fit_intercept=True)
model.fit(X, y)
print "Model coefficient: %.5f, and intercept: %.5f" % (model.coef_, model.intercept_)

# Plot the data and the model prediction
X_test = np.linspace(0, 1, 100)[:, np.newaxis]
y_test = model.predict(X_test)
import pylab as pl
pl.plot(X.squeeze(), y, 'o')
pl.plot(X_test.squeeze(), y_test)

X, y = iris.data, iris.target
from sklearn.decomposition import PCA
pca = PCA(n_components=2)
pca.fit(X)
X_reduced = pca.transform(X)
print "Reduced dataset shape:", X_reduced.shape

import pylab as pl
pl.scatter(X_reduced[:, 0], X_reduced[:, 1], c=y)

print "Meaning of the 2 components:"
for component in pca.components_:
    print " + ".join("%.3f x %s" % (value, name)
                     for value, name in zip(component, iris.feature_names))

from sklearn.cluster import KMeans
k_means = KMeans(n_clusters=3, random_state=0) # Fixing the RNG in kmeans
k_means.fit(X_reduced)
y_pred = k_means.predict(X_reduced)

pl.scatter(X_reduced[:, 0], X_reduced[:, 1], c=y_pred)

rng = np.random.RandomState(0)
x = 2 * rng.rand(100) - 1

f = lambda t: 1.2 * t ** 2 + .1 * t ** 3 - .4 * t ** 5 - .5 * t ** 9
y = f(x) + .4 * rng.normal(size=100)

pl.figure()
pl.scatter(x, y, s=4)

x_test = np.linspace(-1, 1, 100)

pl.figure()
pl.scatter(x, y, s=4)

X = np.array([x**i for i in range(5)]).T
X_test = np.array([x_test**i for i in range(5)]).T
order4 = LinearRegression()
order4.fit(X, y)
pl.plot(x_test, order4.predict(X_test), label='4th order')

X = np.array([x**i for i in range(10)]).T
X_test = np.array([x_test**i for i in range(10)]).T
order9 = LinearRegression()
order9.fit(X, y)
pl.plot(x_test, order9.predict(X_test), label='9th order')

pl.legend(loc='best')
pl.axis('tight')
pl.title('Fitting a 4th and a 9th order polynomial')

pl.figure()
pl.scatter(x, y, s=4)
pl.plot(x_test, f(x_test), label="truth")
pl.axis('tight')
pl.title('Ground truth (9th order polynomial)')