Practical 6

Ans 1: INPUT:
# Import required libraries

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import StandardScaler

from sklearn.naive_bayes import GaussianNB

from sklearn.metrics import confusion_matrix, classification_report

from matplotlib.colors import ListedColormap

# Load the Iris dataset

iris = load_iris()

dataset = pd.DataFrame(data= np.c_[iris['data'], iris['target']], columns= iris['feature_names'] + ['target'])

x = dataset.iloc[:, [0, 1]].values # Selecting first two features for simplicity

y = dataset.iloc[:, 4].values

# Splitting the dataset into the Training set and Test set

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=0)

# Feature Scaling

sc = StandardScaler()

x_train = sc.fit_transform(x_train)

x_test = sc.transform(x_test)

# Fitting Naive Bayes to the Training set

classifier = GaussianNB()

classifier.fit(x_train, y_train)

# Predicting the Test set results

y_pred = classifier.predict(x_test)
# Accuracy

from sklearn import metrics

print("Gaussian Naive Bayes model accuracy(in %):", metrics.accuracy_score(y_test, y_pred)*100)

y_pred_train = classifier.predict(x_train)

print("Gaussian Naive Bayes model accuracy(in %):", metrics.accuracy_score(y_train, y_pred_train)*100)

# Confusion matrix

cm = confusion_matrix(y_test, y_pred)

print('Confusion matrix\n\n', cm)

print('\nTrue Positives(TP) = ', cm[0,0])

print('\nTrue Negatives(TN) = ', cm[1,1])

print('\nFalse Positives(FP) = ', cm[0,1])

print('\nFalse Negatives(FN) = ', cm[1,0])

# Classification report

print(classification_report(y_test, y_pred))

# Plotting

fig, ax = plt.subplots(1, 2, figsize=(12, 6))

# Test set

x_set, y_set = x_test, y_test

X1, X2 = np.meshgrid(np.arange(start=x_set[:, 0].min() - 1, stop=x_set[:, 0].max() + 1, step=0.01),

np.arange(start=x_set[:, 1].min() - 1, stop=x_set[:, 1].max() + 1, step=0.01))

ax[0].contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), alpha=0.75,

cmap=ListedColormap(('purple', 'green', 'red')))

ax[0].set_xlim(X1.min(), X1.max())

ax[0].set_ylim(X2.min(), X2.max())

for i, j in enumerate(np.unique(y_set)):

ax[0].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1], color=ListedColormap(('purple', 'green','red'))(i),

label=j)

ax[0].set_title('Naive Bayes (Test set)')

ax[0].set_xlabel('Sepal Length (cm)')

ax[0].set_ylabel('Sepal Width (cm)')

ax[0].legend()

# Training set

x_set, y_set = x_train, y_train

X1, X2 = np.meshgrid(np.arange(start=x_set[:, 0].min() - 1, stop=x_set[:, 0].max() + 1, step=0.01),

np.arange(start=x_set[:, 1].min() - 1, stop=x_set[:, 1].max() + 1, step=0.01))

ax[1].contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), alpha=0.75,

cmap=ListedColormap(('purple', 'green', 'red')))

ax[1].set_xlim(X1.min(), X1.max())

ax[1].set_ylim(X2.min(), X2.max())

for i, j in enumerate(np.unique(y_set)):

ax[1].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1], color=ListedColormap(('purple', 'green', 'red'))(i),

label=j)

ax[1].set_title('Naive Bayes (Training set)')

ax[1].set_xlabel('Sepal Length (cm)')

ax[1].set_ylabel('Sepal Width (cm)')

ax[1].legend()

plt.show()

OUTPUT:
Gaussian Naive Bayes model accuracy(in %): 90.0

Gaussian Naive Bayes model accuracy(in %): 88.33333333333333

Confusion matrix

[[65 3]

[ 7 25]]

True Positives(TP) = 65

True Negatives(TN) = 25

False Positives(FP) = 3

False Negatives(FN) = 7

precision recall f1-score support

0 0.90 0.96 0.93 68

1 0.89 0.78 0.83 32

accuracy 0.90 100

 macro avg 0.90 0.87 0.88 100

weighted avg 0.90 0.90 0.90 100

d:\sem 7\fai\practical\pf2\untitled0.py:60: UserWarning: *c* argument looks like a single numeric RGB or
RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches
with *x* & *y*. Please use the *color* keyword-argument or provide a 2D array with a single row if you
intend to specify the same RGB or RGBA value for all points.

mtp.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],

d:\sem 7\fai\practical\pf2\untitled0.py:76: UserWarning: *c* argument looks like a single numeric RGB or
RGBA sequence, which should be avoided as value-mapping will have precedence in case its length matches
with *x* & *y*. Please use the *color* keyword-argument or provide a 2D array with a single row if you
intend to specify the same RGB or RGBA value for all points.

mtp.scatter(x_set[y_set == j, 0], x_set[y_set == j, 1],

This version of python seems to be incorrectly compiled

(internal generated filenames are not absolute).

This may make the debugger miss breakpoints.

Related bug: http://bugs.python.org/issue1666807

Practical : 7
ANS 1: INPUT
# Import required libraries

import numpy as np

import pandas as pd

import matplotlib.pyplot as plt

from sklearn.datasets import load_iris

from sklearn.model_selection import train_test_split

from sklearn.preprocessing import StandardScaler

from sklearn.naive_bayes import GaussianNB

from sklearn.metrics import confusion_matrix, classification_report

from matplotlib.colors import ListedColormap

# Load the Iris dataset

iris = load_iris()

dataset = pd.DataFrame(data= np.c_[iris['data'], iris['target']], columns= iris['feature_names'] + ['target'])

x = dataset.iloc[:, [0, 1]].values # Selecting first two features for simplicity

y = dataset.iloc[:, 4].values

# Splitting the dataset into the Training set and Test set

x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25, random_state=0)

# Feature Scaling

sc = StandardScaler()

x_train = sc.fit_transform(x_train)

x_test = sc.transform(x_test)

# Fitting Naive Bayes to the Training set

classifier = GaussianNB()

classifier.fit(x_train, y_train)

# Predicting the Test set results

y_pred = classifier.predict(x_test)

# Accuracy

from sklearn import metrics

print("Gaussian Naive Bayes model accuracy(in %):", metrics.accuracy_score(y_test, y_pred)*100)

y_pred_train = classifier.predict(x_train)

print("Gaussian Naive Bayes model accuracy(in %):", metrics.accuracy_score(y_train, y_pred_train)*100)

# Confusion matrix

cm = confusion_matrix(y_test, y_pred)

print('Confusion matrix\n\n', cm)

print('\nTrue Positives(TP) = ', cm[0,0])

print('\nTrue Negatives(TN) = ', cm[1,1])

print('\nFalse Positives(FP) = ', cm[0,1])

print('\nFalse Negatives(FN) = ', cm[1,0])

# Classification report

print(classification_report(y_test, y_pred))

# Plotting

fig, ax = plt.subplots(1, 2, figsize=(12, 6))

# Test set

x_set, y_set = x_test, y_test

X1, X2 = np.meshgrid(np.arange(start=x_set[:, 0].min() - 1, stop=x_set[:, 0].max() + 1, step=0.01),

np.arange(start=x_set[:, 1].min() - 1, stop=x_set[:, 1].max() + 1, step=0.01))

ax[0].contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), alpha=0.75,

cmap=ListedColormap(('purple', 'green', 'red')))

ax[0].set_xlim(X1.min(), X1.max())

ax[0].set_ylim(X2.min(), X2.max())

for i, j in enumerate(np.unique(y_set)):

ax[0].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1], color=ListedColormap(('purple', 'green','red'))(i),

label=j)

ax[0].set_title('Naive Bayes (Test set)')

ax[0].set_xlabel('Sepal Length (cm)')

ax[0].set_ylabel('Sepal Width (cm)')

ax[0].legend()

# Training set

x_set, y_set = x_train, y_train

X1, X2 = np.meshgrid(np.arange(start=x_set[:, 0].min() - 1, stop=x_set[:, 0].max() + 1, step=0.01),

np.arange(start=x_set[:, 1].min() - 1, stop=x_set[:, 1].max() + 1, step=0.01))

ax[1].contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape), alpha=0.75,

cmap=ListedColormap(('purple', 'green', 'red')))

ax[1].set_xlim(X1.min(), X1.max())

ax[1].set_ylim(X2.min(), X2.max())

for i, j in enumerate(np.unique(y_set)):

ax[1].scatter(x_set[y_set == j, 0], x_set[y_set == j, 1], color=ListedColormap(('purple', 'green', 'red'))(i),

label=j)

ax[1].set_title('Naive Bayes (Training set)')

ax[1].set_xlabel('Sepal Length (cm)')

ax[1].set_ylabel('Sepal Width (cm)')

ax[1].legend()

plt.show()

OUTPUT:
Gaussian Naive Bayes model accuracy(in %): 76.31578947368422

Gaussian Naive Bayes model accuracy(in %): 81.25

Confusion matrix

[[13 0 0]

[ 0 12 4]

[ 0 5 4]]

True Positives(TP) = 13

True Negatives(TN) = 12

False Positives(FP) = 0

False Negatives(FN) = 0

precision recall f1-score support

0.0 1.00 1.00 1.00 13

 1.0 0.71 0.75 0.73 16

2.0 0.50 0.44 0.47 9

accuracy 0.76 38

macro avg 0.74 0.73 0.73 38

weighted avg 0.76 0.76 0.76 38