Machine Learning Tutorial [Iris Dataset]

import pandas

names = ['sepal-length', 'sepal-width', 'petal-length', 'petal-width', 'class']
dataset = pandas.read_csv("https://archive.ics.uci.edu/ml/machine-learning-databases/iris/iris.data", names=names)

print(dataset.shape)

(150, 5)

# pandas.set_option('display.max_columns', None) 
print(dataset.head(5))

   sepal-length  sepal-width  petal-length  petal-width        class
0           5.1          3.5           1.4          0.2  Iris-setosa
1           4.9          3.0           1.4          0.2  Iris-setosa
2           4.7          3.2           1.3          0.2  Iris-setosa
3           4.6          3.1           1.5          0.2  Iris-setosa
4           5.0          3.6           1.4          0.2  Iris-setosa

print(dataset.describe())

       sepal-length  sepal-width  petal-length  petal-width
count    150.000000   150.000000    150.000000   150.000000
mean       5.843333     3.054000      3.758667     1.198667
std        0.828066     0.433594      1.764420     0.763161
min        4.300000     2.000000      1.000000     0.100000
25%        5.100000     2.800000      1.600000     0.300000
50%        5.800000     3.000000      4.350000     1.300000
75%        6.400000     3.300000      5.100000     1.800000
max        7.900000     4.400000      6.900000     2.500000

print(dataset.groupby('class').size())

class
Iris-setosa        50
Iris-versicolor    50
Iris-virginica     50
dtype: int64

import matplotlib.pyplot as plt
dataset.plot(kind='box', subplots=True, layout=(2,2), sharex=False, sharey=False)
print("Displaying univariate plots...")
plt.show()

Displaying univariate plots...

dataset.hist()
plt.show()

from pandas.plotting import scatter_matrix
scatter_matrix(dataset)
plt.show()

from sklearn import model_selection
array = dataset.values
X = array[:,0:4]  # x values i.e. features
Y = array[:,4]    # y value i.e. class or Label
validation_size = 0.20
seed = 7
X_train, X_validation, Y_train, Y_validation = model_selection.train_test_split(X, Y, test_size=validation_size, random_state=seed)
scoring = 'accuracy'

print("Number of samples")
print("-------------------")
print("Training - ", len(X_train))
print("Validation - ", len(X_validation))

Number of samples
-------------------
Training -  120
Validation -  30

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
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()))

import warnings
warnings.filterwarnings("ignore", category=FutureWarning) #Disable future warnings

results = []
names = []
for name, model in models:
	kfold = model_selection.KFold(n_splits=10, random_state=seed)
	cv_results = model_selection.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: 0.975000 (0.038188)
NB: 0.975000 (0.053359)
SVM: 0.991667 (0.025000)

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

from sklearn.metrics import accuracy_score

#Use Logistic Regression to make prediction
print("\nMake predictions using Logistic Regression")
print("-----------------------------------------------------------")
lr = LogisticRegression()
lr.fit(X_train, Y_train)
predictions_lr = lr.predict(X_validation)
#print(predictions_lr)
print(accuracy_score(Y_validation, predictions_lr))

#Use Naïve Bayes to make predictions
print("\nMake predictions using Naïve Bayes")
print("-----------------------------------------------------------")
nb = GaussianNB()
nb.fit(X_train, Y_train)
predictions_nb = nb.predict(X_validation)
#print(predictions_nb)
print(accuracy_score(Y_validation, predictions_nb))

# Use Linear Discriminant Analysis (LDA)
print("\nMake predictions using Linear Discriminant Analysis")
print("-----------------------------------------------------------")
lda = LinearDiscriminantAnalysis()
lda.fit(X_train, Y_train)
predictions_lda = lda.predict(X_validation)
#print(predictions_lda)
print(accuracy_score(Y_validation, predictions_lda))

# Use Statistical Mode to cast vote
print("\nMake predictions using majority voting with LR, NB and LDA:")
print("-----------------------------------------------------------")

voted_predictions = []

import statistics
for i in range(0, 30):
    voted_predictions.append(statistics.mode([predictions_lr[i], predictions_nb[i], predictions_lda[i]]))

print(accuracy_score(Y_validation, voted_predictions))

Make predictions using Logistic Regression
-----------------------------------------------------------
0.8

Make predictions using Naïve Bayes
-----------------------------------------------------------
0.8333333333333334

Make predictions using Linear Discriminant Analysis
-----------------------------------------------------------
0.9666666666666667

Make predictions using majority voting with LR, NB and LDA:
-----------------------------------------------------------
0.9333333333333333