correlation.py

#Correlation
#loading dataset
import seaborn as sns
df=pd.read_csv(r"C:\Users\heena\Downloads\diabetes1.csv")

df.shape
# Output: (768, 9)

df.corr()
#Output: 	Pregnancies	Glucose	BloodPressure	SkinThickness	Insulin	BMI	DiabetesPedigreeFunction	Age	Outcome
#Pregnancies	1.000000	0.128311	0.141282	-0.081672	-0.073535	0.017683	-0.033523	0.544341	0.221898
#Glucose	0.128311	1.000000	0.152446	0.058441	0.330940	0.223410	0.137096	0.263705	0.466401
#BloodPressure	0.141282	0.152446	1.000000	0.207371	0.088933	0.281805	0.041265	0.239528	0.065068
#SkinThickness	-0.081672	0.058441	0.207371	1.000000	0.436783	0.392573	0.183928	-0.113970	0.074752
#Insulin	-0.073535	0.330940	0.088933	0.436783	1.000000	0.197859	0.185071	-0.042163	0.130548
#BMI	0.017683	0.223410	0.281805	0.392573	0.197859	1.000000	0.140647	0.036242	0.292695
#DiabetesPedigreeFunction	-0.033523	0.137096	0.041265	0.183928	0.185071	0.140647	1.000000	0.033561	0.173844
#Age	0.544341	0.263705	0.239528	-0.113970	-0.042163	0.036242	0.033561	1.000000	0.238356
#Outcome	0.221898	0.466401	0.065068	0.074752	0.130548	0.292695	0.173844	0.238356	1.000000

# We see that age and pregnancies are the most related features, whereas some others like age and skin thickness are inversely correlated.

# To view the results graphically
sns.pairplot(df)