Part 1: Mutual Information Classification

# Import necessary libraries

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_selection import SelectKBest, mutual_info_classif
from sklearn.preprocessing import LabelEncoder
import matplotlib.pyplot as plt
import seaborn as sns

# Load the loan dataset

df = pd.read_csv("C:\\Users\\bharg\\Downloads\\loan.csv")

# Display the first few rows of the dataset

print(df.head())

# Separate features (X) and the target variable (y)

target_column = 'Loan_Status'
X = df.drop(columns=[target_column])
y = df[target_column]

# Apply label encoding to handle categorical variables

label_encoder = LabelEncoder()
X_encoded = X.apply(label_encoder.fit_transform)

# Split the dataset into training and testing sets (80:20 ratio)
X_train, X_test, y_train, y_test = train_test_split(X_encoded, y,
test_size=0.2, random_state=42)

# Perform Mutual Information Classification-based feature selection

k_features = 5 # Choose an appropriate value of K (number of features
to select)
selector = SelectKBest(score_func=mutual_info_classif, k=k_features)
X_selected = selector.fit_transform(X_train, y_train)

# Get the indices of the selected features

selected_feature_indices = selector.get_support(indices=True)

# Print the names or indices of the selected features

selected_feature_names = X_train.columns[selected_feature_indices]
print(f'Selected features: {selected_feature_names}')

# Bonus Task: Visualize mutual information scores for each feature

mi_scores = pd.Series(selector.scores_, index=X_train.columns)
mi_scores = mi_scores.sort_values(ascending=False)

plt.figure(figsize=(10, 6))
sns.barplot(x=mi_scores.values, y=mi_scores.index, palette='viridis')
plt.title('Mutual Information Scores for Features')
plt.xlabel('Mutual Information Score')
plt.ylabel('Features')
plt.show()

Loan_ID Gender Married Dependents Education Self_Employed \

0 LP001002 Male No 0 Graduate No
1 LP001003 Male Yes 1 Graduate No
2 LP001005 Male Yes 0 Graduate Yes
3 LP001006 Male Yes 0 Not Graduate No
4 LP001008 Male No 0 Graduate No

ApplicantIncome CoapplicantIncome LoanAmount Loan_Amount_Term \

0 5849 0.0 NaN 360.0
1 4583 1508.0 128.0 360.0
2 3000 0.0 66.0 360.0
3 2583 2358.0 120.0 360.0
4 6000 0.0 141.0 360.0

Credit_History Property_Area Loan_Status

0 1.0 Urban Y
1 1.0 Rural N
2 1.0 Urban Y
3 1.0 Urban Y
4 1.0 Urban Y
Selected features: Index(['Dependents', 'ApplicantIncome',
'LoanAmount', 'Loan_Amount_Term',
'Credit_History'],
dtype='object')
Part 2: Mutual Information Regression
pip install pandas scikit-learn

Requirement already satisfied: pandas in c:\users\bharg\anaconda3\lib\

site-packages (2.0.3)
Requirement already satisfied: scikit-learn in c:\users\bharg\
anaconda3\lib\site-packages (1.3.0)
Requirement already satisfied: python-dateutil>=2.8.2 in c:\users\
bharg\anaconda3\lib\site-packages (from pandas) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in c:\users\bharg\
anaconda3\lib\site-packages (from pandas) (2023.3.post1)
Requirement already satisfied: tzdata>=2022.1 in c:\users\bharg\
anaconda3\lib\site-packages (from pandas) (2023.3)
Requirement already satisfied: numpy>=1.21.0 in c:\users\bharg\
anaconda3\lib\site-packages (from pandas) (1.24.3)
Requirement already satisfied: scipy>=1.5.0 in c:\users\bharg\
anaconda3\lib\site-packages (from scikit-learn) (1.11.1)
Requirement already satisfied: joblib>=1.1.1 in c:\users\bharg\
anaconda3\lib\site-packages (from scikit-learn) (1.2.0)
Requirement already satisfied: threadpoolctl>=2.0.0 in c:\users\bharg\
anaconda3\lib\site-packages (from scikit-learn) (2.2.0)
Requirement already satisfied: six>=1.5 in c:\users\bharg\anaconda3\
lib\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)
Note: you may need to restart the kernel to use updated packages.

# Import necessary libraries

import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_selection import SelectKBest,
mutual_info_regression
from sklearn.preprocessing import LabelEncoder
import matplotlib.pyplot as plt
import seaborn as sns

# Load the Housing dataset

df = pd.read_csv('C:\\Users\\bharg\\Downloads\\housing.csv')

# Separate features (X) and the target variable (y)

target_column = 'SalePrice'
X = df.drop(columns=[target_column])
y = df[target_column]

# Apply label encoding to handle categorical variables

label_encoder = LabelEncoder()
X_encoded = X.apply(label_encoder.fit_transform)

# Split the dataset into training and testing sets (80:20 ratio)
X_train, X_test, y_train, y_test = train_test_split(X_encoded, y,
test_size=0.2, random_state=42)
# Perform Mutual Information Regression-based feature selection
k_features = 3# Choose an appropriate value of K (number of features
to select)
selector = SelectKBest(score_func=mutual_info_regression,
k=k_features)
X_selected = selector.fit_transform(X_train, y_train)

# Get the indices of the selected features

selected_feature_indices = selector.get_support(indices=True)

# Print the names or indices of the selected features

selected_feature_names = X_train.columns[selected_feature_indices]
print(f'Selected features: {selected_feature_names}')

# Bonus Task: Visualize mutual information scores for each feature

mi_scores = pd.Series(selector.scores_, index=X_train.columns)
mi_scores = mi_scores.sort_values(ascending=False)

plt.figure(figsize=(10, 6))
sns.barplot(x=mi_scores.values, y=mi_scores.index, palette='viridis')
plt.title('Mutual Information Scores for Features')
plt.xlabel('Mutual Information Score')
plt.ylabel('Features')
plt.show()

Selected features: Index(['OverallQual', 'GrLivArea', 'GarageCars'],

dtype='object')
Part 3 : Linear Regression on the Housing Dataset
# Import necessary libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression
from sklearn.impute import SimpleImputer
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import OneHotEncoder
from sklearn.metrics import mean_squared_error, r2_score
import matplotlib.pyplot as plt
# Load the Housing dataset
df = pd.read_csv('C:\\Users\\bharg\\Downloads\\housing.csv')

# Separate features (X) and the target variable (y)

target_column = 'SalePrice'
X = df.drop(columns=[target_column])
y = df[target_column]

# Identify numerical and categorical features

numerical_features = X.select_dtypes(include=['int64',
'float64']).columns
categorical_features = X.select_dtypes(include=['object']).columns

# Create preprocessing pipelines for numerical and categorical

features
numerical_pipeline = Pipeline([ ('imputer',
SimpleImputer(strategy='mean')),('num', 'passthrough')])

categorical_pipeline = Pipeline([('imputer',
SimpleImputer(strategy='most_frequent')),
('cat',
OneHotEncoder(handle_unknown='ignore'))])

# Combine the preprocessing pipelines using ColumnTransformer

preprocessor = ColumnTransformer(transformers=[('num',
numerical_pipeline, numerical_features),
('cat',
categorical_pipeline, categorical_features))

# Apply preprocessing on the entire dataset

X_preprocessed = preprocessor.fit_transform(X)

# Split the dataset into training and testing sets (80:20 ratio)
X_train, X_test, y_train, y_test = train_test_split(X_preprocessed, y,
test_size=0.2, random_state=42)

# Initialize the Linear Regression model

linear_reg_model = LinearRegression()
# Create the final pipeline with feature preprocessing and model
training
pipeline = Pipeline([('regressor', linear_reg_model)])

# Fit the model to the training data

pipeline.fit(X_train, y_train)

# Predict house prices for the testing data

y_pred = pipeline.predict(X_test)

# Evaluate the performance of the model

mse = mean_squared_error(y_test, y_pred)
r2 = r2_score(y_test, y_pred)

# Print the MSE and R^2 values

print(f'Mean Squared Error (MSE): {mse}')
print(f'R-squared (R^2): {r2}')

# Plot a scatter plot between predicted and actual house prices

plt.scatter(y_test, y_pred)
plt.xlabel('Actual House Prices')
plt.ylabel('Predicted House Prices')
plt.title('Scatter Plot of Actual vs Predicted House Prices')
plt.show()

Mean Squared Error (MSE): 980359454.4892789

R-squared (R^2): 0.8721880363353154
# Import necessary libraries
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.feature_selection import SelectKBest, mutual_info_classif
from sklearn.preprocessing import LabelEncoder

# Load the dataset (Assuming it's a CSV file)

loan_data = pd.read_csv("C:\\Users\\bharg\\Downloads\\loan.csv")

# Display the first few rows of the dataset

print("Original Dataset:")
print(loan_data.head())

# Separate features (X) and target variable (y)

X = loan_data.drop("Loan_Status", axis=1)
y = loan_data["Loan_Status"]

# Apply label encoding for categorical variables

label_encoder = LabelEncoder()
for column in X.select_dtypes(include=['object']).columns:
X[column] = label_encoder.fit_transform(X[column])

# Handle null values (You may need to customize this based on your
dataset)
X.fillna(0, inplace=True) # Filling null values with 0 for simplicity

# Split the dataset into training and testing sets (80% training, 20%
testing)
X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.2, random_state=42)

# Use SelectKBest with Mutual Information Classification

k_best = 5 # Choose an appropriate value of K
selector = SelectKBest(mutual_info_classif, k=k_best)
X_train_selected = selector.fit_transform(X_train, y_train)

# Get the selected feature indices

selected_indices = selector.get_support(indices=True)

# Get the selected feature names

selected_features = X.columns[selected_indices]

# Print the selected features

print(f"\nSelected Features (Top {k_best}):")
print(selected_features)