Logistic Regression Practice: Diabetes¶

Practice of Logistic Regression to predict diabetes from a set of patient data¶

Import Libraries, File and Inspect Data¶

In [1]:
import pandas as pd
import numpy as np
import matplotlib
import matplotlib.pyplot as plt
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report

import warnings
warnings.filterwarnings('ignore')
In [2]:
df = pd.read_csv('diabetes.csv')
In [3]:
df.head()
Out[3]:
Pregnancies Glucose BloodPressure SkinThickness Insulin BMI DiabetesPedigreeFunction Age Outcome
0 6 148 72 35 0 33.6 0.627 50 1
1 1 85 66 29 0 26.6 0.351 31 0
2 8 183 64 0 0 23.3 0.672 32 1
3 1 89 66 23 94 28.1 0.167 21 0
4 0 137 40 35 168 43.1 2.288 33 1
In [4]:
df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 768 entries, 0 to 767
Data columns (total 9 columns):
 #   Column                    Non-Null Count  Dtype  
---  ------                    --------------  -----  
 0   Pregnancies               768 non-null    int64  
 1   Glucose                   768 non-null    int64  
 2   BloodPressure             768 non-null    int64  
 3   SkinThickness             768 non-null    int64  
 4   Insulin                   768 non-null    int64  
 5   BMI                       768 non-null    float64
 6   DiabetesPedigreeFunction  768 non-null    float64
 7   Age                       768 non-null    int64  
 8   Outcome                   768 non-null    int64  
dtypes: float64(2), int64(7)
memory usage: 54.1 KB

Count Outcomes (0 = Non Diabetic, 1 = Diabetic)¶

In [5]:
df['Outcome'].value_counts()
Out[5]:
Outcome
0    500
1    268
Name: count, dtype: int64

Set Up Training and Test Data¶

In [6]:
features = df[['Pregnancies','Glucose','BloodPressure','SkinThickness','Insulin','BMI','DiabetesPedigreeFunction','Age']]
label = df['Outcome']
In [7]:
X_train, X_test, y_train, y_test = train_test_split(features, label, test_size=0.3)

Normalise The Data, Fit the Model and Score It (over 0.7 is a good fit)¶

In [8]:
scaler = StandardScaler()
X_train = scaler.fit_transform(X_train)
X_test = scaler.transform(X_test)


model = LogisticRegression()
model.fit(X_train, y_train)


print(model.score(X_train, y_train))


print(model.score(X_test, y_test))

0.7690875232774674
0.8008658008658008

Comparing Outcomes of Test Data to Predicted Outcomes¶

In [9]:
y_pred = model.predict(X_test)
In [10]:
ComparisonDF = pd.DataFrame({'TestOutcomes': y_test, 'PredictedOutcomes': y_pred})
In [11]:
ComparisonDF.head()
Out[11]:
TestOutcomes PredictedOutcomes
157 0 0
425 1 1
605 0 0
127 0 0
700 0 0
In [12]:
def assign_value(row):
    if row['TestOutcomes'] == 1 and row['PredictedOutcomes'] == 1:
        return 'True Positive'
    elif row['TestOutcomes'] == 0 and row['PredictedOutcomes'] == 0:
        return 'True Negative'
    elif row['TestOutcomes'] == 1 and row['PredictedOutcomes'] == 0:
        return 'False Negative'
    elif row['TestOutcomes'] == 0 and row['PredictedOutcomes'] == 1:
        return 'False Postive'

ComparisonDF['Confusion'] = ComparisonDF.apply(assign_value, axis=1)

ComparisonDF.head()
Out[12]:
TestOutcomes PredictedOutcomes Confusion
157 0 0 True Negative
425 1 1 True Positive
605 0 0 True Negative
127 0 0 True Negative
700 0 0 True Negative

Accuracy Summary¶

In [13]:
print('Confusion matrix: ')

test_conf_matrix = pd.DataFrame(
    confusion_matrix(y_test, y_pred), 
    index=['Actual 0:', 'Actual 1:'], 
    columns=['Predicted 0:', 'Predicted 1:']
)

print(test_conf_matrix)

Confusion matrix: 
           Predicted 0:  Predicted 1:
Actual 0:           138            16
Actual 1:            30            47
In [14]:
print(classification_report(y_test,y_pred))

              precision    recall  f1-score   support

           0       0.82      0.90      0.86       154
           1       0.75      0.61      0.67        77

    accuracy                           0.80       231
   macro avg       0.78      0.75      0.76       231
weighted avg       0.80      0.80      0.80       231