Machine Learning: scikit-learn

Bikash Santra

Research Scholar, Indian Statistical Institute, Kolkata

Loading dataset from scikit-learn package

import sklearn
from sklearn.datasets import load_iris
from matplotlib import pyplot as plt

iris = load_iris()

print(iris.data.shape)
n_samples, n_features = iris.data.shape
print(n_samples)
print(n_features)
print(iris.data[0])
print(iris.target.shape)
print(iris.target)
print(iris.target_names)

# 2D views of the iris dataset

# The indices of the features that we are plotting
x_index = 0
y_index = 1

# this formatter will label the colorbar with the correct target names
formatter = plt.FuncFormatter(lambda i, *args: iris.target_names[int(i)])

plt.figure(figsize=(5, 4))
plt.scatter(iris.data[:, x_index], iris.data[:, y_index], c=iris.target)
plt.colorbar(ticks=[0, 1, 2], format=formatter)
plt.xlabel(iris.feature_names[x_index])
plt.ylabel(iris.feature_names[y_index])

plt.tight_layout()
plt.show()

scikit-learn estimator object

from sklearn.linear_model import LinearRegression

# Estimator parameters: All the parameters of an estimator can be set when it is instantiated:
model = LinearRegression(normalize=True)
print(model.normalize)

print(model)

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

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

model.fit(X, y)

# Estimated parameters:

model.coef_

Supervised Learning: Classification and regression

KNN classifier

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]])])

# Nearest-neighbor prediction on iris

#Plot the decision boundary of nearest neighbor decision on iris,
# first with a single nearest neighbor, and then using 3 nearest neighbors.


import numpy as np
from matplotlib import pyplot as plt
from sklearn import neighbors, datasets
from matplotlib.colors import ListedColormap

# Create color maps for 3-class classification problem, as with iris
cmap_light = ListedColormap(['#FFAAAA', '#AAFFAA', '#AAAAFF'])
cmap_bold = ListedColormap(['#FF0000', '#00FF00', '#0000FF'])

iris = datasets.load_iris()
X = iris.data[:, :2]  # we only take the first two features. We could
                    # avoid this ugly slicing by using a two-dim dataset
y = iris.target

knn = neighbors.KNeighborsClassifier(n_neighbors=1)
knn.fit(X, y)

x_min, x_max = X[:, 0].min() - .1, X[:, 0].max() + .1
y_min, y_max = X[:, 1].min() - .1, X[:, 1].max() + .1
xx, yy = np.meshgrid(np.linspace(x_min, x_max, 100),
                        np.linspace(y_min, y_max, 100))
Z = knn.predict(np.c_[xx.ravel(), yy.ravel()])

# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure()
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)

# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)
plt.xlabel('sepal length (cm)')
plt.ylabel('sepal width (cm)')
plt.axis('tight')


# And now, redo the analysis with 3 neighbors
knn = neighbors.KNeighborsClassifier(n_neighbors=3)
knn.fit(X, y)

Z = knn.predict(np.c_[xx.ravel(), yy.ravel()])

# Put the result into a color plot
Z = Z.reshape(xx.shape)
plt.figure()
plt.pcolormesh(xx, yy, Z, cmap=cmap_light)

# Plot also the training points
plt.scatter(X[:, 0], X[:, 1], c=y, cmap=cmap_bold)
plt.xlabel('sepal length (cm)')
plt.ylabel('sepal width (cm)')
plt.axis('tight')

plt.show()

A simple linear regression

import numpy as np
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression

# x from 0 to 30
x = 30 * np.random.random((20, 1))

# y = a*x + b with noise
y = 0.5 * x + 1.0 + np.random.normal(size=x.shape)

# create a linear regression model
model = LinearRegression()
model.fit(x, y)

# predict y from the data
x_new = np.linspace(0, 30, 100)
y_new = model.predict(x_new[:, np.newaxis])

# plot the results
plt.figure(figsize=(4, 3))
ax = plt.axes()
ax.scatter(x, y)
ax.plot(x_new, y_new)

ax.set_xlabel('x')
ax.set_ylabel('y')

ax.axis('tight')


plt.show()

Visualizing Data on it's Principle Components

from sklearn.datasets import load_digits
digits = load_digits()

# plot the digits: each image is 8x8 pixels
from matplotlib import pyplot as plt
fig = plt.figure(figsize=(6, 6))  # figure size in inches
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)

for i in range(64):
    ax = fig.add_subplot(8, 8, i + 1, xticks=[], yticks=[])
    ax.imshow(digits.images[i], cmap=plt.cm.binary, interpolation='nearest')
    # label the image with the target value
    ax.text(0, 7, str(digits.target[i]))
plt.show()

from sklearn.decomposition import PCA
pca = PCA(n_components=2)
proj = pca.fit_transform(digits.data)
plt.scatter(proj[:, 0], proj[:, 1], c=digits.target) 

plt.colorbar() 
plt.show()

Support Vector Machine

import numpy as np
from matplotlib import pyplot as plt

from sklearn import svm

# data that is linearly separable
def linear_model(rseed=42, n_samples=30):
    " Generate data according to a linear model"
    np.random.seed(rseed)

    data = np.random.normal(0, 10, (n_samples, 2))
    data[:n_samples // 2] -= 15
    data[n_samples // 2:] += 15

    labels = np.ones(n_samples)
    labels[:n_samples // 2] = -1

    return data, labels


X, y = linear_model()
clf = svm.SVC(kernel='linear')
clf.fit(X, y)

plt.figure(figsize=(6, 4))
ax = plt.subplot(111, xticks=[], yticks=[])
ax.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.bone)

ax.scatter(clf.support_vectors_[:, 0],
            clf.support_vectors_[:, 1],
            s=80, edgecolors="k", facecolors="none")

delta = 1
y_min, y_max = -50, 50
x_min, x_max = -50, 50
x = np.arange(x_min, x_max + delta, delta)
y = np.arange(y_min, y_max + delta, delta)
X1, X2 = np.meshgrid(x, y)
Z = clf.decision_function(np.c_[X1.ravel(), X2.ravel()])
Z = Z.reshape(X1.shape)

ax.contour(X1, X2, Z, [-1.0, 0.0, 1.0], colors='k',
           linestyles=['dashed', 'solid', 'dashed'])
plt.show()

# data with a non-linear separation
def nonlinear_model(rseed=42, n_samples=30):
    radius = 40 * np.random.random(n_samples)
    far_pts = radius > 20
    radius[far_pts] *= 1.2
    radius[~far_pts] *= 1.1

    theta = np.random.random(n_samples) * np.pi * 2

    data = np.empty((n_samples, 2))
    data[:, 0] = radius * np.cos(theta)
    data[:, 1] = radius * np.sin(theta)

    labels = np.ones(n_samples)
    labels[far_pts] = -1

    return data, labels


X, y = nonlinear_model()
clf = svm.SVC(kernel='rbf', gamma=0.001, coef0=0, degree=3)
clf.fit(X, y)

plt.figure(figsize=(6, 4))
ax = plt.subplot(1, 1, 1, xticks=[], yticks=[])
ax.scatter(X[:, 0], X[:, 1], c=y, cmap=plt.cm.bone, zorder=2)

ax.scatter(clf.support_vectors_[:, 0], clf.support_vectors_[:, 1],
           s=80, edgecolors="k", facecolors="none")

delta = 1
y_min, y_max = -50, 50
x_min, x_max = -50, 50
x = np.arange(x_min, x_max + delta, delta)
y = np.arange(y_min, y_max + delta, delta)
X1, X2 = np.meshgrid(x, y)
Z = clf.decision_function(np.c_[X1.ravel(), X2.ravel()])
Z = Z.reshape(X1.shape)

ax.contour(X1, X2, Z, [-1.0, 0.0, 1.0], colors='k',
            linestyles=['dashed', 'solid', 'dashed'], zorder=1)

plt.show()

Classify with Gaussian naive Bayes

from sklearn.naive_bayes import GaussianNB
from sklearn.model_selection import train_test_split

from sklearn.datasets import load_digits
digits = load_digits()


# split the data into training and validation sets
X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target)

# train the model
clf = GaussianNB()
clf.fit(X_train, y_train)

# use the model to predict the labels of the test data
predicted = clf.predict(X_test)
expected = y_test

# Plot the prediction
fig = plt.figure(figsize=(6, 6))  # figure size in inches
fig.subplots_adjust(left=0, right=1, bottom=0, top=1, hspace=0.05, wspace=0.05)

# plot the digits: each image is 8x8 pixels
for i in range(64):
    ax = fig.add_subplot(8, 8, i + 1, xticks=[], yticks=[])
    ax.imshow(X_test.reshape(-1, 8, 8)[i], cmap=plt.cm.binary,
              interpolation='nearest')

    # label the image with the target value
    if predicted[i] == expected[i]:
        ax.text(0, 7, str(predicted[i]), color='green')
    else:
        ax.text(0, 7, str(predicted[i]), color='red')
plt.show()

Quantify the performance

matches = (predicted == expected)
print(matches.sum())

print(len(matches))

corrPred = matches.sum() / float(len(matches))
print(corrPred)

from sklearn import metrics
print(metrics.classification_report(expected, predicted))

print(metrics.confusion_matrix(expected, predicted))

Unsupervised Learning

K-Means Clustering

from pylab import plot,show
from numpy import vstack,array
from numpy.random import rand
from scipy.cluster.vq import kmeans,vq

# data generation
data = vstack((rand(150,2) + array([.5,.5]),rand(150,2)))

# computing K-Means with K = 2 (2 clusters)
centroids,_ = kmeans(data,2)
# assign each sample to a cluster
idx,_ = vq(data,centroids)

# some plotting using numpy's logical indexing
plot(data[idx==0,0],data[idx==0,1],'ob',
     data[idx==1,0],data[idx==1,1],'or')
plot(centroids[:,0],centroids[:,1],'sg',markersize=8)
show()

# now with K = 3 (3 clusters)
centroids,_ = kmeans(data,3)
idx,_ = vq(data,centroids)

plot(data[idx==0,0],data[idx==0,1],'ob',
     data[idx==1,0],data[idx==1,1],'or',
     data[idx==2,0],data[idx==2,1],'og') # third cluster points
plot(centroids[:,0],centroids[:,1],'sm',markersize=8)
show()

DB Scan Clustering

import numpy as np

from sklearn.cluster import DBSCAN
from sklearn import metrics
from sklearn.datasets.samples_generator import make_blobs
from sklearn.preprocessing import StandardScaler


# #############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers, cluster_std=0.4,
                            random_state=0)

X = StandardScaler().fit_transform(X)

# #############################################################################
# Compute DBSCAN
db = DBSCAN(eps=0.3, min_samples=10).fit(X)
core_samples_mask = np.zeros_like(db.labels_, dtype=bool)
core_samples_mask[db.core_sample_indices_] = True
labels = db.labels_

# Number of clusters in labels, ignoring noise if present.
n_clusters_ = len(set(labels)) - (1 if -1 in labels else 0)

print('Estimated number of clusters: %d' % n_clusters_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f"
      % metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f"
      % metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f"
      % metrics.silhouette_score(X, labels))

# #############################################################################
# Plot result
import matplotlib.pyplot as plt

# Black removed and is used for noise instead.
unique_labels = set(labels)
colors = [plt.cm.Spectral(each)
          for each in np.linspace(0, 1, len(unique_labels))]
for k, col in zip(unique_labels, colors):
    if k == -1:
        # Black used for noise.
        col = [0, 0, 0, 1]

    class_member_mask = (labels == k)

    xy = X[class_member_mask & core_samples_mask]
    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
             markeredgecolor='k', markersize=14)

    xy = X[class_member_mask & ~core_samples_mask]
    plt.plot(xy[:, 0], xy[:, 1], 'o', markerfacecolor=tuple(col),
             markeredgecolor='k', markersize=6)

plt.title('Estimated number of clusters: %d' % n_clusters_)
plt.show()

References

a) http://scikit-learn.org/stable/tutorial/index.html
b) https://www.scipy-lectures.org/packages/scikit-learn/index.html

Click here to download the source code of this tutorial.