ML1

Perform the following operations using Python on the given data sets 
a)Importing the libraries 
b) Importing the Dataset 
c) Handling of Missing Data 
d) Handling of Categorical Data 
e) Splitting the dataset into training and testing datasets 
f) Feature Scaling 
Region  Age  Income  Online Shopper 
India 49 86400 No 
Brazil   32 57600  Yes 
USA  35 64800  No 
Brazil  43  73200  No 
USA  45   Yes 
India  40  69600  Yes 
Brazil   62400  No 
India  53  94800  Yes 
USA  55  99600  No 
India  42  80400  Yes


a)
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score
b)
dataset = pd.read_csv("given_data.csv")
c)
print(dataset.isnull())
print(dataset.isnull().sum()) #check if any

#also can be done using SimpleImputer of sci-kit library 

dataset["Age"].fillna(dataset["Age"].mean(), inplace=True)

dataset["Income"].fillna(dataset["Income"].mean(), inplace=True)
dataset["Region"].fillna(dataset["Region"].mode().iloc[0], inplace=True)
print(dataset.isnull().sum())
d)
categorical_columns=dataset.select_dtype(include=[np.number]).columns
print(categorial_columns)

imputer=SimpleImputer(strategy='most_frequent')
data[categorical_columns]=imputer.fit_transform(data[categorical_columns])
print(dataset.isnull().sum())



#oneHotEncoder
encoder=OneHotEncoder(sparse_output=False,drop='first')
encoder_data=encoder.fit_transform(data[categorical_columns])

encoder_columns=encoder.get_feature_names_out(categorical_columns)

data=data.drop(categorical_columns,axis=1)
data=pd.concat([data,pd.DataFrame(encode_data,columns=encoded_columns)},axis=1)
e)
x=data.drop('Online Shopper',axis=1)
y=data['Online Shopper'] #dependant variable




x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.2,random_state=42)

print("Traning set shape :",x_train.shape,y_train.shape)
print("Testing set shape :",x_test.shape,y_test.shape)


f)
# Scale the features
scaler = StandardScaler()
X_train_scaled = scaler.fit_transform(X_train)
X_test_scaled = scaler.transform(X_test)

# Train a logistic regression model
model = LogisticRegression()
model.fit(X_train_scaled, y_train)

# Make predictions on the test set
y_pred = model.predict(X_test_scaled)

# Evaluate the model
accuracy = accuracy_score(y_test, y_pred)
print(f'Accuracy: {accuracy * 100:.2f}%')