Basic Tutorial

In [21]:

    

import pandas as pd
from pandas.tools.plotting import scatter_matrix
import matplotlib.pyplot as plt
from sklearn import cross_validation
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC

names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = pd.read_csv('iris.data', names=names)


    

In [25]:

    

array = dataset.values
x, y = array[:, 0:4], array[:, 4]
validation_size = 0.20
seed = 7
x_train, x_validation, y_train, y_validation = cross_validation.train_test_split(x, y, test_size=validation_size, random_state=seed)


    

In [26]:

    

# Test options and evaluation metric
num_folds = 10
num_instances = len(x_train)
seed = 7
scoring = 'accuracy'


    

In [27]:

    

models = []
models.append(('LR', LogisticRegression()))
models.append(('LDA', LinearDiscriminantAnalysis()))
models.append(('KNN', KNeighborsClassifier()))
models.append(('CART', DecisionTreeClassifier()))
models.append(('NB', GaussianNB()))
models.append(('SVM', SVC()))

results = []
names = []

for name, model in models:
    kfold = cross_validation.KFold(n=num_instances, n_folds=num_folds, random_state=seed)
    cv_results = cross_validation.cross_val_score(model, x_train, y_train, cv=kfold, scoring=scoring)
    results.append(cv_results)
    names.append(name)
    msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
    print(msg)


    

    




LR: 0.966667 (0.040825)
LDA: 0.975000 (0.038188)
KNN: 0.983333 (0.033333)
CART: 0.966667 (0.040825)
NB: 0.975000 (0.053359)
SVM: 0.991667 (0.025000)

In [29]:

    

# Compare Algorithms
fig = plt.figure()
fig.suptitle('Algorithm Comparison')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()


    

In [31]:

    

# Make predictions on validation dataset
knn = KNeighborsClassifier()
knn.fit(x_train, y_train)
predictions = knn.predict(x_validation)
print(accuracy_score(y_validation, predictions))
print(confusion_matrix(y_validation, predictions))
print(classification_report(y_validation, predictions))


    

    




0.9
[[ 7  0  0]
 [ 0 11  1]
 [ 0  2  9]]
                 precision    recall  f1-score   support

    Iris-setosa       1.00      1.00      1.00         7
Iris-versicolor       0.85      0.92      0.88        12
 Iris-virginica       0.90      0.82      0.86        11

    avg / total       0.90      0.90      0.90        30

In [ ]: