Logistic Regression Model Training

Logistic Regression Training

In this module, we will see the use of Logistic regression training using the Scikit-learn library. We will use a sample data set called ‘pima_indian_diabetes.csv‘ to run our model.

Load the diabetes dataset.

 
import pandas as pd
import numpy as np

pima = pd.read_csv('pima_indian_diabetes.csv')

Verify dataset.

 
pima.head() 

Normalizing continuous features:

Normalization is required to keep all the values on the same scale.

 
df = pima[['No_Times_Pregnant', 'Plasma_Glucose', 'Diastolic_BP', 'Triceps','Insulin', 'BMI', 'Age']]
normalized_df=(df-df.mean())/df.std()
pima = pima.drop(['No_Times_Pregnant', 'Plasma_Glucose', 'Diastolic_BP', 'Triceps','Insulin', 'BMI', 'Age'], 1)
pima = pd.concat([pima,normalized_df],axis=1)
pima.head()

Output:

Split the data into train and test data.

 
from sklearn.model_selection import train_test_split

# Putting feature variable to X
X = pima.drop(['Diabetes'],axis=1)

# Putting response variable to y
y = pima['Diabetes']
# Splitting the data into train and test
X_train, X_test, y_train, y_test = train_test_split(X,y, train_size=0.7,test_size=0.3,random_state=100) 

Train the data.

Using the Scikit-learn library.

 from sklearn.linear_model import LogisticRegression
model = LogisticRegression()
model.fit(X_train, y_train)
y_pred = model.predict(X_test)

Using the statsmodel library.

 
import statsmodels.api as sm
logm1 = sm.GLM(y_train,(sm.add_constant(X_train)), family = sm.families.Binomial())
logm1.fit().summary() 

Validate the model:

The below example used the ‘confusion matrix‘ metric to validate the model.

 
from sklearn.metrics import confusion_matrix
cm = confusion_matrix(y_test, y_pred)
print(cm)

Output:

[[68 12]
 [16 22]]

Conclusion:

In this blog, you learned how to create a model with basic Logistic Regression Training. In the next blog, you will find more about confusion-matrix, sensitivity, and specificity.