preprocessing.py

# load CSV file

data=pd.read_csv('winequality_red.csv')

#plot the Countplot for the column quality

sns.countplot(x='quality',data=data)

# store the quality dataframe

quality=data['quality']

# now if quality is less than 6.5 then it is assigned as 0 and if it is above 6.5 it is assigned to be 1

data['quality']=pd.cut(data['quality'],bins=(2,6.5,8),labels=[0,1])

#change the datatype of data['quality'] from category to int64

data['quality']=data['quality'].astype('int64')

#Now plot correlation heat map

plt.figure(figsize=(60,30))
sns.heatmap(data.corr(),annot=True,fmt='.2f')
plt.show()

# Seperate data into features and labels

x=data.iloc[:,:-1]
y=data.iloc[:,-1]

#Split the data into training and testing dataset by taking train_size as 75%

x_train,x_test,y_train,y_test=train_test_split(x,y,train_size=0.75,random_state=42)