In this post, you will learn about how to train a model using machine learning algorithm such as Logistic Regression.

Here is the code we can use for fitting a model using Logistic Regression. We will use IRIS data set for training the model.

First and foremost, we will load the appropriate packages, sklearn modules and classes.

# Importing basic packages
#
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt

# Importing Sklearn module and classes
from sklearn.linear_model import LogisticRegression
from sklearn.preprocessing import StandardScaler
from sklearn import metrics
from sklearn import datasets
from sklearn.model_selection import train_test_split


As a next step, we will load the dataset and do the data preparation.

iris = datasets.load_iris()
X = iris.data[:, [0, 2]]
Y = iris.target


## Create Training / Test Data

Next step is to create a train and test split. Note the stratification parameter. This is used to ensure that class distribution in training / test split remains consistent / balanced.

X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.3, random_state=1, stratify=Y)


## Perform Feature Scaling

Next step is to perform feature scaling in order to make sure features are in fixed range irrespective of their values / units etc.

sc = StandardScaler()
sc.fit(X_train)
X_train_std = sc.transform(X_train)
X_test_std = sc.transform(X_test)


## Train a Logistic Regression Model

Next step is to train a logistic regression model. The following needs to be noted while using LogisticRegression algorithm sklearn.linear_model implementation:

• Usage of C parameters. Smaller values of C specify stronger regularization.
• The multi_class parameter is assigned to ‘ovr‘. It represents one-vs-rest algorithm to be used. Other option is multinomial.
• The solver parameter is assigned to ‘lbfsg‘. Other solvers which can be used are newton-cg, sag, saga, lib linear
# Create an instance of LogisticRegression classifier
lr = LogisticRegression(C=100.0, random_state=1, solver='lbfgs', multi_class='ovr')

# Fit the model
#
lr.fit(X_train_std, Y_train)


## Measure Model Performance

Next step is to measure the model performance of the model trained using LogisticRegression as shown above.

# Create the predictions
#
Y_predict = lr.predict(X_test_std)

# Use metrics.accuracy_score to measure the score
print("LogisticRegression Accuracy %.3f" %metrics.accuracy_score(Y_test, Y_predict))