A DVD rental company needs your help! They want to figure out how many days a customer will rent a DVD for based on some features and has approached you for help. They want you to try out some regression models which will help predict the number of days a customer will rent a DVD for. The company wants a model which yeilds a MSE of 3 or less on a test set. The model you make will help the company become more efficient inventory planning.

The data they provided is in the csv file rental_info.csv. It has the following features:

  • "rental_date": The date (and time) the customer rents the DVD.
  • "return_date": The date (and time) the customer returns the DVD.
  • "amount": The amount paid by the customer for renting the DVD.
  • "amount_2": The square of "amount".
  • "rental_rate": The rate at which the DVD is rented for.
  • "rental_rate_2": The square of "rental_rate".
  • "release_year": The year the movie being rented was released.
  • "length": Lenght of the movie being rented, in minuites.
  • "length_2": The square of "length".
  • "replacement_cost": The amount it will cost the company to replace the DVD.
  • "special_features": Any special features, for example trailers/deleted scenes that the DVD also has.
  • "NC-17", "PG", "PG-13", "R": These columns are dummy variables of the rating of the movie. It takes the value 1 if the move is rated as the column name and 0 otherwise. For your convinience, the reference dummy has already been dropped.
# Start your coding from below
import pandas as pd
import numpy as np

from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error

# For lasso
from sklearn.linear_model import Lasso
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler

# Run OLS
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error

# Random forest
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import RandomizedSearchCV

# Read in data
df_rental = pd.read_csv("rental_info.csv")

# Add information on rental duration
df_rental["rental_length"] = pd.to_datetime(df_rental["return_date"]) - pd.to_datetime(df_rental["rental_date"])
df_rental["rental_length_days"] = df_rental["rental_length"].dt.days

### Add dummy variables
# Add dummy for deleted scenes
df_rental["deleted_scenes"] =  np.where(df_rental["special_features"].str.contains("Deleted Scenes"), 1, 0)
# Add dummy for behind the scenes
df_rental["behind_the_scenes"] =  np.where(df_rental["special_features"].str.contains("Behind the Scenes"), 1, 0)

# Choose columns to drop
cols_to_drop = ["special_features", "rental_length", "rental_length_days", "rental_date", "return_date"]

# Split into feature and target sets
X = df_rental.drop(cols_to_drop, axis=1)
y = df_rental["rental_length_days"]

# Further split into training and test data
X_train,X_test,y_train,y_test = train_test_split(X, 
                                                 y, 
                                                 test_size=0.2, 
                                                 random_state=9)

# Create the Lasso model
lasso = Lasso(alpha=0.3, random_state=9) 

# Train the model and access the coefficients
lasso.fit(X_train, y_train)
lasso_coef = lasso.coef_
print(f"lasso_coef: {lasso_coef}")

# Perform feature selectino by choosing columns with positive coefficients
X_lasso_train, X_lasso_test = X_train.iloc[:, lasso_coef > 0], X_test.iloc[:, lasso_coef > 0]

# Run OLS models on lasso chosen regression
ols = LinearRegression()
ols = ols.fit(X_lasso_train, y_train)
y_test_pred = ols.predict(X_lasso_test)
mse_lin_reg_lasso = mean_squared_error(y_test, y_test_pred)

# Random forest hyperparameter space
param_dist = {'n_estimators': np.arange(1,101,1),
          'max_depth':np.arange(1,11,1)}

# Create a random forest regressor
rf = RandomForestRegressor()

# Use random search to find the best hyperparameters
rand_search = RandomizedSearchCV(rf, 
                                 param_distributions=param_dist, 
                                 cv=5, 
                                 random_state=9)

# Fit the random search object to the data
rand_search.fit(X_train, y_train)

# Create a variable for the best hyper param
hyper_params = rand_search.best_params_

# Run the random forest on the chosen hyper parameters
rf = RandomForestRegressor(n_estimators=hyper_params["n_estimators"], 
                           max_depth=hyper_params["max_depth"], 
                           random_state=9)
rf.fit(X_train,y_train)
rf_pred = rf.predict(X_test)
mse_random_forest= mean_squared_error(y_test, rf_pred)

# Random forest gives lowest MSE so:
best_model = rf
best_mse = mse_random_forest

print(f"Best MSE: {best_mse}")

lasso_coef: [ 5.84104424e-01  0.00000000e+00 -0.00000000e+00  0.00000000e+00
 -0.00000000e+00  0.00000000e+00  0.00000000e+00  0.00000000e+00
 -0.00000000e+00  4.36220109e-02  3.01167812e-06 -1.52983561e-01
 -0.00000000e+00  0.00000000e+00]
Best MSE: 2.225667528098759