Experiment No. 5

#Implement the program to avoid dataleakage with name data preparation select an appropriate dataset for your expeeriment and validate the results

from sklearn.datasets import make_classification
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import MinMaxScaler
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score

x,y = make_classification(n_samples=1000,n_features=20,n_informative=15,n_redundant=5,random_state=7)
scaler = MinMaxScaler()
x = scaler.fit_transform(x)
x_train, x_test, y_train, y_test = train_test_split(x,y, test_size=0.33, random_state = 1)
model=LogisticRegression()
model.fit(x_train, y_train)
yhat=model.predict(x_test)
accuracy = accuracy_score(y_test, yhat)
print("Accuracy: %.3f"%(accuracy*100))