You are on page 1of 3

Practical - 5

AIM :- I and F Pattern Classification Using


Perceptron

Importing Libraries

In [50]:

1 import numpy as np
2 import pandas as pd
3 from sklearn.linear_model import Perceptron

Dataset

In [51]:

1 %%html
2 <img src="I_and_F_pattern.png" width="40%">

Here, we are using -1 in place of 0

In [52]:

1 I = [1, 1, 1, -1, 1, -1, 1, 1, 1]


2 F = [1, 1, 1, 1, 1, 1, 1, -1, -1]

In [53]:

1 x = [I, F]
2 print(x)

[[1, 1, 1, -1, 1, -1, 1, 1, 1], [1, 1, 1, 1, 1, 1, 1, -1, -1]]

In [54]:

1 y = [1, -1]

Creating the Model


In [55]:

1 model = Perceptron(tol=1e-1, random_state=0)


2 model.fit(x, y)

Out[55]:

Perceptron(tol=0.1)

In [56]:

1 # Getting the mean accuracy on the given test data and labels
2 model.score(x, y)

Out[56]:

1.0

Predicting the Class Labels

In [57]:

1 # Predicting class labels for samples in X.


2 model.predict(x)

Out[57]:

array([ 1, -1])

In [58]:

1 ycal = model.predict(x[0:1])
2 print('Predicted Class:', ycal)

Predicted Class: [1]

In [59]:

1 # Predict confidence scores for samples.


2 model.decision_function(x)

Out[59]:

array([ 8., -8.])

In [60]:

1 model.densify()
2 # model.densify() function converts coefficient matrix to dense array format.

Out[60]:

Perceptron(tol=0.1)

Getting the Parameters of Model


In [61]:

1 model.get_params()

Out[61]:

{'alpha': 0.0001,

'class_weight': None,

'early_stopping': False,

'eta0': 1.0,

'fit_intercept': True,

'l1_ratio': 0.15,

'max_iter': 1000,

'n_iter_no_change': 5,

'n_jobs': None,

'penalty': None,

'random_state': 0,

'shuffle': True,

'tol': 0.1,

'validation_fraction': 0.1,

'verbose': 0,

'warm_start': False}

You might also like