May 12, 2021

Programmingempire

This article demonstrates an example of a Multi-layer Perceptron Classifier in Python. In general, we use the following steps for implementing a Multi-layer Perceptron classifier.

To begin with, first, we import the necessary libraries of python.
After that, create a list of attribute names in the dataset and use it in a call to the read_csv() function of the pandas library along with the name of the CSV file containing the dataset.
To list the first five rows of the dataset, call the head() function.
At this point, we divide the dataset into two parts. While the first part contains the first four columns that we assign in the variable a. Likewise, the second part contains only the last column that is the class label. Further, assign it to the variable b.
Further, we call the train_test_split() function that further divides the dataset into training data and testing data with a testing data size of 25%.
In the meantime, we normalize our dataset. In order to do that we call the StandardScaler() function. Basically, the StandardScaler() function subtracts the mean from a feature and scales it to the unit variance.
Subsequently, we call the MLPClassifier() function with appropriate parameters indicating the hidden layer sizes, activation function, and the maximum number of iterations.
In order to get the predicted values we call the predict() function on the testing data set.
Finally, we call the functions confusion_matrix(), and the classification_report() in order to evaluate the performance of our classifier.

Example of Multi-layer Perceptron Classifier in Python with Three Hidden Layers

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

arr = ['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth', 'Species']
df = pd.read_csv("iris.csv", names=arr)
print(df.head())
a = df.iloc[:, 0:4]
b = df.select_dtypes(include=[object])
b = df.iloc[:,4:5]
training_a, testing_a, training_b, testing_b = train_test_split(a, b, test_size = 0.25)
myscaler = StandardScaler()
myscaler.fit(training_a)
training_a = myscaler.transform(training_a)
testing_a = myscaler.transform(testing_a)
m1 = MLPClassifier(hidden_layer_sizes=(12, 13, 14), activation='relu', solver='adam', max_iter=2500)
m1.fit(training_a, training_b.values.ravel())
predicted_values = m1.predict(testing_a)
print(confusion_matrix(testing_b,predicted_values))
print(classification_report(testing_b,predicted_values))

Output

**MLPClassifier Example with Three Hidden Layers**

Example of Multi-layer Perceptron Classifier in Python with Four Hidden Layers

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.neural_network import MLPClassifier
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix

arr = ['SepalLength', 'SepalWidth', 'PetalLength', 'PetalWidth', 'Species']
df = pd.read_csv("iris.csv", names=arr)
print(df.head())
a = df.iloc[:, 0:4]
b = df.select_dtypes(include=[object])
b = df.iloc[:,4:5]
training_a, testing_a, training_b, testing_b = train_test_split(a, b, test_size = 0.25)
myscaler = StandardScaler()
myscaler.fit(training_a)
training_a = myscaler.transform(training_a)
testing_a = myscaler.transform(testing_a)
m1 = MLPClassifier(hidden_layer_sizes=(9, 12, 10, 15), activation='relu', solver='adam', max_iter=2000)
m1.fit(training_a, training_b.values.ravel())
predicted_values = m1.predict(testing_a)
print(confusion_matrix(testing_b,predicted_values))
print(classification_report(testing_b,predicted_values))

Output

**MLPClassifier Example with Four Hidden Layers**

Programmingempire

Example of Multi-layer Perceptron Classifier in Python with Three Hidden Layers

Example of Multi-layer Perceptron Classifier in Python with Four Hidden Layers

Further Reading

You may also like...

Popular Machine Learning Algorithms for Prediction

Understanding Blockchain Concepts

Data Visualization Practice Exercise