# Import necessary libraries

import pandas as pd

import numpy as np

from sklearn.model$\_$selection import train$\_$test$\_$split

from sklearn.linear$\_$model import Lasso

from sklearn.metrics import mean$\_$squared$\_$error, r$2\_$score

from sklearn.preprocessing import StandardScaler

import matplotlib.pyplot as plt

import seaborn as sns

# Load the dataset

data $=$pd$.$read$\_$csv$(\text{'}$movie$\_$dataset.csv$\text{'})$ # Update path if necessary

# Check the data structure to confirm column names

print$($data$.$columns$)$

print$($data$.$head$())$

print$($data$.$info$())$

# Choose relevant features and target variable based on the actual dataset structure

# Update these based on the dataset columns

features $=[\text{'}$budget$\text{'},\text{'}$runtime$\text{'},$ 'popularity', 'release$\_$year', 'genre$\_$Action', 'genre$\_$Drama'$]$

target $=\text{'}$revenue$\text{'}$

# Verify if 'release$\_$year' or 'genres' exist; if not, use alternatives or skip

if 'release$\_$year' not in data.columns:

$$ print$("$Column 'release$\_$year' not found. Using 'year' as an alternative if available."$)$

$$ features.remove$(\text{'}$release$\_$year'$)$

$$ if 'year' in data.columns:

$$ features.append$(\text{'}$year$\text{'})$

# Check if genres are available and process accordingly

if 'genres' in data.columns:

$$ # Assume genres are categorical and create dummy variables

$$ data $=$pd$.$get$\_$dummies$($data$,$columns$=[\text{'}$genres$\text{'}],$prefix$=$'genre', drop$\_$first$=$True$)$

$$ # Update features to include new genre columns created

$$ genre$\_$cols $=[$col for col in data.columns if col.startswith$(\text{'}$genre$\_\text{'})]$

$$ features.extend$($genre$\_$cols$)$

# Handle missing values in the selected features and target

available$\_$features $=[$feature for feature in features if feature in data.columns$]$

data $=$data$.$dropna$($subset$=$available$\_$features $+[$target$])$

# Split the data into features and target

X $=$data$[$available$\_$features$]$

y $=$data$[$target$]$

# Standardize the feature data

scaler $=$StandardScaler$()$

X $=$scaler$.$fit$\_$transform$($X$)$

# Split the data into training and testing sets

X$\_$train, X$\_$test, y$\_$train, y$\_$test $=$train$\_$test$\_$split$($X$,$y$,$test$\_$size$=0\mathrm{.}2,$random$\_$state$=42)$

# Initialize and fit the Lasso Regression model

lasso $=$Lasso$($alpha$=0\mathrm{.}1)$ # Adjust alpha as needed

lasso.fit$($X$\_$train, y$\_$train$)$

# Make predictions

y$\_$train$\_$pred $=$lasso$.$predict$($X$\_$train$)$

y$\_$test$\_$pred $=$lasso$.$predict$($X$\_$test$)$

# Evaluate the model

train$\_$mse $=$mean$\_$squared$\_$error$($y$\_$train, y$\_$train$\_$pred$)$

test$\_$mse $=$mean$\_$squared$\_$error$($y$\_$test, y$\_$test$\_$pred$)$

train$\_$r$2=$r$2\_$score$($y$\_$train, y$\_$train$\_$pred$)$

test$\_$r$2=$r$2\_$score$($y$\_$test, y$\_$test$\_$pred$)$

print$($f$"$Train MSE: $\{$train$\_$mse$\},$Train R$2$: $\{$train$\_$r$2\}")$

print$($f$"$Test MSE: $\{$test$\_$mse$\},$Test R$2$: $\{$test$\_$r$2\}")$

# Plotting actual vs$.$predicted values

plt$.$figure$($figsize$=(10,5))$

plt$.$scatter$($y$\_$test, y$\_$test$\_$pred, alpha$=0\mathrm{.}5)$

plt$.$xlabel$("$Actual Box Office Revenue"$)$

plt$.$ylabel$("$Predicted Box Office Revenue"$)$

plt$.$title$("$Actual vs$.$Predicted Box Office Revenue $($Lasso Regression$)")$

plt$.$show$()$

# Plotting feature coefficients

coefficients $=$pd$.$Series$($lasso$.$coef$\_,$index$=$available$\_$features$)$

plt$.$figure$($figsize$=(10,5))$

coefficients.plot$($kind$=$'bar'$)$

plt$.$title$("$Feature Coefficients after Lasso Regularization"$)$

plt$.$xlabel$("$Features$")$

plt$.$ylabel$("$Coefficient Value"$)$

plt$.$show$()$GIVE METHODOLOGY in $500$to $999$words$.$ GIVE RESULT$$AND$$DISCUSSION in $600$to $999$words$.$ project name :Lasso Regression for Predicting Movie Success. Use lasso regression to predict movie box office success based on various features.