Skip to content

Title goes here

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.
import pandas as pd
import numpy as np

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

# Import any additional modules and start coding below
from sklearn.linear_model import Lasso,LinearRegression
from sklearn.tree import  DecisionTreeRegressor
from sklearn.ensemble import RandomForestRegressor
from sklearn.model_selection import RandomizedSearchCV
 
df=pd.read_csv("rental_info.csv")


df["rental_length_days"] = pd.to_datetime(df["return_date"]) - pd.to_datetime(df["rental_date"])
df["rental_length_days"] = df["rental_length_days"].dt.days
df["deleted_scenes"] =  np.where(df["special_features"].str.contains("Deleted Scenes"), 1,0)
df["behind_the_scenes"] =  np.where(df["special_features"].str.contains("Behind the Scenes"), 1,0)
y=df["rental_length_days"]
X=df.drop(columns=["rental_length_days","rental_date","return_date","special_features"],axis=1)

X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=9)
models={
    "lr":LinearRegression(),
    "dr":DecisionTreeRegressor(random_state=9),
    "rf":RandomForestRegressor(random_state=9)
}
for model in models.values():
    model.fit(X,y)
    y_pred=model.predict(X_test)
    acc=MSE(y_test,y_pred)
    print(f"MSE for {model} is {acc}")
param_grids = {
    "lr": {},  # No hyperparameters to tune

    "dr": {
        'max_depth': [3, 5, 10, None],
        'min_samples_split': [2, 5, 10],
        'min_samples_leaf': [1, 2, 4]
    },

    "rf": {
        'n_estimators': [50, 100, 200],
        'max_depth': [None, 10, 20, 30],
        'min_samples_split': [2, 5, 10],
        'min_samples_leaf': [1, 2, 4]
    }
}


best_models = {}
for name in models:
    print(f"\nTuning {name.upper()}...")
    model = models[name]
    param_grid = param_grids[name]

    if param_grid: 
        search = RandomizedSearchCV(
            estimator=model,
            param_distributions=param_grid,
            n_iter=10,
            scoring='neg_mean_squared_error',
            cv=5,
            random_state=9,
            n_jobs=-1
        )
        search.fit(X, y)
        best_models[name] = search.best_estimator_
        print("Best Params:", search.best_params_)
    else:
        model.fit(X, y)
        best_models[name] = model
        print("No tuning done (no hyperparameters)")

best_models
for model in best_models.values():
    model.fit(X,y)
    y_pred=model.predict(X_test)
    acc=round(MSE(y_test,y_pred),3)
    print(f"MSE for {model} is {acc}")
best_model=RandomForestRegressor(max_depth=10,n_estimators=200,min_samples_split=10,min_samples_leaf=4,random_state=9)
best_mse=1.947