%matplotlib inline
import numpy as np
import matplotlib.pyplot as plt

# use seaborn for plot defaults
# this can be safely commented out
import seaborn; seaborn.set()

from sklearn.linear_model import LinearRegression

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

print(model)

x = np.arange(10)
y = 2 * x + 1

print(x)
print(y)

plt.plot(x, y, 'o');

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

# fit the model on our data
model.fit(X, y)

# underscore at the end indicates a fit parameter
print(model.coef_)
print(model.intercept_)

# residual error around fit
model.residues_

from sklearn import neighbors, datasets

iris = datasets.load_iris()
X, y = iris.data, iris.target

# create the model
knn = neighbors.KNeighborsClassifier(n_neighbors=5)

# fit the model
knn.fit(X, y)

# What kind of iris has 3cm x 5cm sepal and 4cm x 2cm petal?
# call the "predict" method:
result = knn.predict([[3, 5, 4, 2],])

print(iris.target_names[result])

knn.predict_proba([[3, 5, 4, 2],])

from fig_code import plot_iris_knn
plot_iris_knn()

from sklearn.svm import SVC



# 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.randn(20)

plt.plot(X.squeeze(), y, 'o');

model = LinearRegression()
model.fit(X, y)

# Plot the data and the model prediction
X_fit = np.linspace(0, 1, 100)[:, np.newaxis]
y_fit = model.predict(X_fit)

plt.plot(X.squeeze(), y, 'o')
plt.plot(X_fit.squeeze(), y_fit);

# Fit a Random Forest
from sklearn.ensemble import RandomForestRegressor
model = RandomForestRegressor()
model.fit(X, y)

# Plot the data and the model prediction
X_fit = np.linspace(0, 1, 100)[:, np.newaxis]
y_fit = model.predict(X_fit)

plt.plot(X.squeeze(), y, 'o')
plt.plot(X_fit.squeeze(), y_fit);

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,
           cmap='RdYlBu')

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)
y_pred = k_means.predict(X)

pl.scatter(X_reduced[:, 0], X_reduced[:, 1], c=y_pred,
           cmap='RdYlBu');

from sklearn.neighbors import KNeighborsClassifier
X, y = iris.data, iris.target
clf = KNeighborsClassifier(n_neighbors=1)
clf.fit(X, y)
y_pred = clf.predict(X)
print(np.all(y == y_pred))

from sklearn.metrics import confusion_matrix
print(confusion_matrix(y, y_pred))

from sklearn.cross_validation import train_test_split
Xtrain, Xtest, ytrain, ytest = train_test_split(X, y)
clf.fit(Xtrain, ytrain)
ypred = clf.predict(Xtest)
print(confusion_matrix(ytest, ypred))

from IPython.display import Image
Image("http://scikit-learn.org/dev/_static/ml_map.png")

from sklearn import datasets
digits = datasets.load_digits()
digits.images.shape

fig, axes = plt.subplots(10, 10, figsize=(8, 8))
fig.subplots_adjust(hspace=0.1, wspace=0.1)

for i, ax in enumerate(axes.flat):
    ax.imshow(digits.images[i], cmap='binary')
    ax.text(0.05, 0.05, str(digits.target[i]),
            transform=ax.transAxes, color='green')
    ax.set_xticks([])
    ax.set_yticks([])

# The images themselves
print(digits.images.shape)
print(digits.images[0])

# The data for use in our algorithms
print(digits.data.shape)
print(digits.data[0])

# The target label
print(digits.target)

from sklearn.manifold import Isomap

iso = Isomap(n_components=2)
data_projected = iso.fit_transform(digits.data)

data_projected.shape

plt.scatter(data_projected[:, 0], data_projected[:, 1], c=digits.target,
            edgecolor='none', alpha=0.5, cmap=plt.cm.get_cmap('nipy_spectral', 10));
plt.colorbar(label='digit label', ticks=range(10))
plt.clim(-0.5, 9.5)

from sklearn.cross_validation import train_test_split
Xtrain, Xtest, ytrain, ytest = train_test_split(digits.data, digits.target,
                                                random_state=2)
print(Xtrain.shape, Xtest.shape)

from sklearn.linear_model import LogisticRegression
clf = LogisticRegression(penalty='l2')
clf.fit(Xtrain, ytrain)
ypred = clf.predict(Xtest)

from sklearn.metrics import accuracy_score
accuracy_score(ytest, ypred)

from sklearn.metrics import confusion_matrix
print(confusion_matrix(ytest, ypred))

plt.imshow(np.log(confusion_matrix(ytest, ypred)),
           cmap='Blues', interpolation='nearest')
plt.grid(False)
plt.ylabel('true')
plt.xlabel('predicted');

fig, axes = plt.subplots(10, 10, figsize=(8, 8))
fig.subplots_adjust(hspace=0.1, wspace=0.1)

for i, ax in enumerate(axes.flat):
    ax.imshow(Xtest[i].reshape(8, 8), cmap='binary')
    ax.text(0.05, 0.05, str(ypred[i]),
            transform=ax.transAxes,
            color='green' if (ytest[i] == ypred[i]) else 'red')
    ax.set_xticks([])
    ax.set_yticks([])