import numpy as np import pandas as pd

#beta from Problem 1 beta = [-1.74695522, 0.40816854, 0.10884091, 0.10102536, 0.02222656, 0.04382357, -0.06633965, -1.3309358 , 0.15952172]

data = pd.read_csv('data.csv')

data.shape

data.head()

data.columns

features = ['prop_starrating', 'prop_review_score', 'prop_brand_bool', 'prop_location_score', 'prop_accesibility_score', 'prop_log_historical_price', 'price_usd', 'promotion_flag', 'srch_booking_window', 'srch_adults_count', 'srch_children_count', 'srch_room_count', 'srch_saturday_night_bool'] mean = {} std = {} for feature in features: s = pd.Series(data[feature]) mean[feature] = s.mean() std[feature] =s.std()

data1 = pd.read_csv('data1.csv')

data1.columns

new_features = ['prop_starrating', 'prop_review_score', 'prop_brand_bool', 'prop_location_score', 'prop_accesibility_score', 'prop_log_historical_price', 'price_usd', 'promotion_flag']

def revenue(assortment, beta): num_hotel = assortment.shape[0] base = 1 top = 0 for i in range(num_hotel): u = 0 u += beta[0] for j in range(1,9): u += beta[j] * assortment.iloc[i][j-1] # print(u) v = np.exp(u) base += v p = assortment.iloc[i][-2] top += v*p expected_revenue = top / base return expected_revenue

def find_optimal(df): for feature in new_features: df[feature] = (df[feature] - mean[feature]) / std[feature] df = df.sort_values(["price_usd"],ascending=False) sorted_df = df.reset_index(drop=True) num = sorted_df.shape[0] revenue_list = [] for i in range(num): assortment = sorted_df.head(i+1) revenue_list.append(revenue(assortment,beta)) maximum = max(revenue_list) for i in range(len(revenue_list)): if revenue_list[i] == maximum: print('The optimal assortment is a display of ', (i+1), ' highest priced products.')

find_optimal(data1)

def expected_revenue(num, df): optimal_assortment = df.head(num) num_hotel = optimal_assortment.shape[0] base = 1 top = 0 for i in range(num_hotel): u = 0 u += beta[0] for j in range(1,9): u += beta[j] * optimal_assortment.iloc[i][j-1] # print(u) v = np.exp(u) base += v p = optimal_assortment.iloc[i][-2] * std['price_usd'] + mean['price_usd'] top += v*p expected_revenue = top / base print('expected revenue is', expected_revenue)

expected_revenue(4, data1)

data2 = pd.read_csv('data2.csv')

find_optimal(data2)

expected_revenue(3, data2)

data3 = pd.read_csv('data3.csv')

data3.shape

find_optimal(data3)

expected_revenue(9, data3)

data4 = pd.read_csv('data4.csv')

data4.shape

find_optimal(data4)

expected_revenue(1, data4)