In [1]:
# Load libraries
import pandas as pd
from pandas.tools.plotting import scatter_matrix
import matplotlib.pyplot as plt
import seaborn as sns
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
In [2]:
# Load dataset
url = "https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data"
names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = pd.read_csv(url, names=names)
In [3]:
print(dataset.shape)
In [4]:
print(dataset.head(20))
In [5]:
# box and whisker plot for each attribute
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
plt.show()
In [6]:
dataset.hist()
plt.show()
In [7]:
scatter_matrix(dataset)
plt.show()
In [8]:
# Split-out validation dataset
array = dataset.values
X = array[:,0:4]
Y = 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 [9]:
# Test options and evaluation metric
seed = 7
scoring = 'accuracy'
In [10]:
# Spot Check Algorithms
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()))
# evaluate each model in turn
results = []
names = []
for name, model in models:
cv_results=cross_validation.cross_val_score(model, X_train, Y_train, cv=10, scoring=scoring)
results.append(cv_results)
names.append(name)
msg = "%s: %f (%f)" % (name, cv_results.mean(), cv_results.std())
print(msg)
In [11]:
# Compare Algorithms
fig = plt.figure()
fig.suptitle('Algorithm Comparsion')
ax = fig.add_subplot(111)
plt.boxplot(results)
ax.set_xticklabels(names)
plt.show()
In [12]:
knn = KNeighborsClassifier()
knn.fit(X_train, Y_train)
predictions = knn.predict(X_validation)
In [13]:
print("Accuracy: %.2f" % accuracy_score(Y_validation, predictions))
indexes = ['Iris-setosa', 'Iris-versicolor', 'Iris-virginica']
#accuracy_score(Y_validation,predictions)[0:,:]
confusion_matrix_df = pd.DataFrame(
data = confusion_matrix(Y_validation, predictions),
index = indexes,
columns = indexes
)
print()
print(confusion_matrix_df)
print()
print(classification_report(Y_validation, predictions))
In [ ]: