In [1]:

    

from sklearn.datasets import load_digits
digits = load_digits()
digits.keys()


    

    
Out[1]:





['images', 'data', 'target_names', 'DESCR', 'target']

In [2]:

    

digits.images.shape


    

    
Out[2]:





(1797, 8, 8)

In [3]:

    

print(digits.images[0])


    

    




[[  0.   0.   5.  13.   9.   1.   0.   0.]
 [  0.   0.  13.  15.  10.  15.   5.   0.]
 [  0.   3.  15.   2.   0.  11.   8.   0.]
 [  0.   4.  12.   0.   0.   8.   8.   0.]
 [  0.   5.   8.   0.   0.   9.   8.   0.]
 [  0.   4.  11.   0.   1.  12.   7.   0.]
 [  0.   2.  14.   5.  10.  12.   0.   0.]
 [  0.   0.   6.  13.  10.   0.   0.   0.]]

In [4]:

    

import matplotlib.pyplot as plt
%matplotlib inline

plt.matshow(digits.images[0], cmap=plt.cm.Greys)


    

    
Out[4]:





<matplotlib.image.AxesImage at 0x7f3759fce810>






    

In [6]:

    

digits.data.shape


    

    
Out[6]:





(1797, 64)

In [7]:

    

digits.target.shape


    

    
Out[7]:





(1797,)

In [8]:

    

digits.target


    

    
Out[8]:





array([0, 1, 2, ..., 8, 9, 8])

In [9]:

    

from sklearn.cross_validation import train_test_split
X_train, X_test, y_train, y_test = train_test_split(digits.data, digits.target)


    

In [10]:

    

from sklearn.svm import LinearSVC


    

In [11]:

    

svm = LinearSVC(C=0.1)


    

In [12]:

    

svm.fit(X_train, y_train)


    

    
Out[12]:





LinearSVC(C=0.1, class_weight=None, dual=True, fit_intercept=True,
     intercept_scaling=1, loss='squared_hinge', max_iter=1000,
     multi_class='ovr', penalty='l2', random_state=None, tol=0.0001,
     verbose=0)

In [13]:

    

print(svm.predict(X_train))
print(y_train)


    

    




[3 9 0 ..., 0 9 2]
[3 9 0 ..., 0 9 2]

In [14]:

    

svm.score(X_train, y_train)


    

    
Out[14]:





0.99703043801039348

In [15]:

    

svm.score(X_test, y_test)


    

    
Out[15]:





0.96888888888888891

In [16]:

    

from sklearn.ensemble import RandomForestClassifier


    

In [17]:

    

rf = RandomForestClassifier(n_estimators=50)


    

In [18]:

    

rf.fit(X_train, y_train)


    

    
Out[18]:





RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',
            max_depth=None, max_features='auto', max_leaf_nodes=None,
            min_samples_leaf=1, min_samples_split=2,
            min_weight_fraction_leaf=0.0, n_estimators=50, n_jobs=1,
            oob_score=False, random_state=None, verbose=0,
            warm_start=False)

In [19]:

    

rf.score(X_test, y_test)


    

    
Out[19]:





0.97999999999999998

In [ ]:

    

#%load from github


    

In [20]:

    

import numpy as np
import pylab as pl
from matplotlib.colors import ListedColormap
from sklearn.cross_validation import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.datasets import make_moons, make_circles, make_classification
from sklearn.neighbors import KNeighborsClassifier
from sklearn.svm import SVC
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.lda import LDA
from sklearn.qda import QDA

h = .02  # step size in the mesh

names = ["Nearest Neighbors", "Linear SVM", "RBF SVM", "Decision Tree",
         "Random Forest", "AdaBoost", "Naive Bayes", "LDA", "QDA"]
classifiers = [
    KNeighborsClassifier(3),
    SVC(kernel="linear", C=0.025),
    SVC(gamma=2, C=1),
    DecisionTreeClassifier(max_depth=5),
    RandomForestClassifier(max_depth=5, n_estimators=10, max_features=1),
    AdaBoostClassifier(),
    GaussianNB(),
    LDA(),
    QDA()]

X, y = make_classification(n_features=2, n_redundant=0, n_informative=2,
                           random_state=1, n_clusters_per_class=1)
rng = np.random.RandomState(2)
X += 2 * rng.uniform(size=X.shape)
linearly_separable = (X, y)

datasets = [make_moons(noise=0.3, random_state=0),
            make_circles(noise=0.2, factor=0.5, random_state=1),
            linearly_separable
            ]

figure = pl.figure(figsize=(27, 9))
i = 1
# iterate over datasets
for ds in datasets:
    # preprocess dataset, split into training and test part
    X, y = ds
    X = StandardScaler().fit_transform(X)
    X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=.4)

    x_min, x_max = X[:, 0].min() - .5, X[:, 0].max() + .5
    y_min, y_max = X[:, 1].min() - .5, X[:, 1].max() + .5
    xx, yy = np.meshgrid(np.arange(x_min, x_max, h),
                         np.arange(y_min, y_max, h))

    # just plot the dataset first
    cm = pl.cm.RdBu
    cm_bright = ListedColormap(['#FF0000', '#0000FF'])
    ax = pl.subplot(len(datasets), len(classifiers) + 1, i)
    # Plot the training points
    ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
    # and testing points
    ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright, alpha=0.6)
    ax.set_xlim(xx.min(), xx.max())
    ax.set_ylim(yy.min(), yy.max())
    ax.set_xticks(())
    ax.set_yticks(())
    i += 1

    # iterate over classifiers
    for name, clf in zip(names, classifiers):
        ax = pl.subplot(len(datasets), len(classifiers) + 1, i)
        clf.fit(X_train, y_train)
        score = clf.score(X_test, y_test)

        # Plot the decision boundary. For that, we will assign a color to each
        # point in the mesh [x_min, m_max]x[y_min, y_max].
        if hasattr(clf, "decision_function"):
            Z = clf.decision_function(np.c_[xx.ravel(), yy.ravel()])
        else:
            Z = clf.predict_proba(np.c_[xx.ravel(), yy.ravel()])[:, 1]

        # Put the result into a color plot
        Z = Z.reshape(xx.shape)
        ax.contourf(xx, yy, Z, cmap=cm, alpha=.8)

        # Plot also the training points
        ax.scatter(X_train[:, 0], X_train[:, 1], c=y_train, cmap=cm_bright)
        # and testing points
        ax.scatter(X_test[:, 0], X_test[:, 1], c=y_test, cmap=cm_bright,
                   alpha=0.6)

        ax.set_xlim(xx.min(), xx.max())
        ax.set_ylim(yy.min(), yy.max())
        ax.set_xticks(())
        ax.set_yticks(())
        ax.set_title(name)
        ax.text(xx.max() - .3, yy.min() + .3, ('%.2f' % score).lstrip('0'),
                size=15, horizontalalignment='right')
        i += 1

figure.subplots_adjust(left=.02, right=.98)


    

In [ ]: