Spaces:
Sleeping
Sleeping
Upload 6 files
Browse files- app.py +10 -0
- best_param.pkl +3 -0
- eda.py +85 -0
- hotel_reservations.csv +0 -0
- prediction.py +77 -0
- preprocessing_pipeline.pkl +3 -0
app.py
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import eda
|
3 |
+
import prediction
|
4 |
+
import seaborn
|
5 |
+
|
6 |
+
Navigation = st.sidebar.selectbox('Pilih Halaman:', ('EDA','Predict Visitors Hotel Reservation'))
|
7 |
+
if Navigation == 'EDA':
|
8 |
+
eda.run()
|
9 |
+
else:
|
10 |
+
prediction.run()
|
best_param.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e119733908fd32e92d4116a265f26104c7b8ca893b0d30ee7147fb2f534881ec
|
3 |
+
size 484040
|
eda.py
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import pandas as pd
|
3 |
+
import seaborn as sns
|
4 |
+
import matplotlib.pyplot as plt
|
5 |
+
import plotly.express as px
|
6 |
+
from PIL import Image
|
7 |
+
|
8 |
+
# Set page config
|
9 |
+
st.set_page_config(
|
10 |
+
page_title= 'Hotel_Reservation_EDA',
|
11 |
+
layout= 'wide',
|
12 |
+
initial_sidebar_state= 'expanded'
|
13 |
+
)
|
14 |
+
|
15 |
+
# Create Function for EDA
|
16 |
+
def run():
|
17 |
+
#Create title
|
18 |
+
st.title('Hotel Reservation Visitors')
|
19 |
+
|
20 |
+
# Create Sub Header atau Sub Judul
|
21 |
+
st.subheader('EDA untuk Analisis Dataset ')
|
22 |
+
|
23 |
+
# Add Image
|
24 |
+
st.image('https://www.hotellinksolutions.com/images/blog/avt.jpg', caption= 'Hotel Reservation')
|
25 |
+
|
26 |
+
# Create a Description
|
27 |
+
st.write('Page Made by Allen')
|
28 |
+
|
29 |
+
|
30 |
+
# Magic Syntax
|
31 |
+
'''
|
32 |
+
Pada page kali ini, penulis akan melakukan eksplorasi sederhana,
|
33 |
+
Dataset yang digunakan adalah Credit Card Default.
|
34 |
+
Dataset ini berasal dari Big Query Google
|
35 |
+
|
36 |
+
'''
|
37 |
+
|
38 |
+
# Create Straight Line
|
39 |
+
st.markdown('---')
|
40 |
+
|
41 |
+
# Show Dataframe
|
42 |
+
df = pd.read_csv('hotel_reservations.csv')
|
43 |
+
st.dataframe(df)
|
44 |
+
|
45 |
+
# Booking Status
|
46 |
+
st.write('### Plot Booking Status Customer')
|
47 |
+
fig= plt.figure(figsize=(20,5))
|
48 |
+
sns.countplot(x='booking_status', data=df)
|
49 |
+
st.pyplot(fig)
|
50 |
+
st.write('From information above we can take an information that visitors that not canceled their booking is bigger than canceled their booking `67.2%` to `32.8%`.')
|
51 |
+
|
52 |
+
st.write('### Plot Room Type Customer')
|
53 |
+
fig= plt.figure(figsize=(20,5))
|
54 |
+
sns.countplot(x='room_type_reserved', data=df)
|
55 |
+
st.pyplot(fig)
|
56 |
+
st.write('From the information above `Room type 1` is the highest room type reserved by booking status and then the second popular is `Room type 4`')
|
57 |
+
|
58 |
+
st.write('### Plot Market Segment')
|
59 |
+
fig= plt.figure(figsize=(20,5))
|
60 |
+
sns.countplot(x='market_segment_type', data=df)
|
61 |
+
st.pyplot(fig)
|
62 |
+
st.write('Market segment of booking status majority from online')
|
63 |
+
|
64 |
+
st.write('### Plot Type of Meal Plan')
|
65 |
+
fig= plt.figure(figsize=(20,5))
|
66 |
+
sns.countplot(x='type_of_meal_plan', data=df)
|
67 |
+
st.pyplot(fig)
|
68 |
+
st.write('Visitors that not canceled and canceled in how they chose meal plan, the meal plan 1 is occupied the first place')
|
69 |
+
|
70 |
+
st.write('### Plot Arrival Year')
|
71 |
+
fig= plt.figure(figsize=(20,5))
|
72 |
+
sns.countplot(x='arrival_year', data=df)
|
73 |
+
st.pyplot(fig)
|
74 |
+
|
75 |
+
st.write('### Plot Arrival Month')
|
76 |
+
fig= plt.figure(figsize=(20,5))
|
77 |
+
sns.countplot(x='arrival_month', data=df)
|
78 |
+
st.pyplot(fig)
|
79 |
+
st.write('The Conclusion Based on Arrival Year and Arrival Month is visitors activity in reservation hotel, crowded in October 2018')
|
80 |
+
|
81 |
+
|
82 |
+
|
83 |
+
|
84 |
+
if __name__ == '__main__':
|
85 |
+
run()
|
hotel_reservations.csv
ADDED
The diff for this file is too large to render.
See raw diff
|
|
prediction.py
ADDED
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pickle
|
2 |
+
import json
|
3 |
+
import pandas as pd
|
4 |
+
import numpy as np
|
5 |
+
import streamlit as st
|
6 |
+
|
7 |
+
# Load All Files
|
8 |
+
with open('best_param.pkl', 'rb') as file_1:
|
9 |
+
best_params = pickle.load(file_1)
|
10 |
+
|
11 |
+
with open('preprocessing_pipeline.pkl', 'rb') as file_2:
|
12 |
+
preprocessing_pipeline= pickle.load(file_2)
|
13 |
+
|
14 |
+
def run ():
|
15 |
+
with st.form(key ='PREDICT VISITORS FORM'): #Nulis nama sendiri menggunakan name= st.text_input('')
|
16 |
+
Booking_ID= st.text_input('Booking_ID', 'Input ID Here')
|
17 |
+
no_of_adults = st.number_input('Number of Adults')
|
18 |
+
no_of_children= st.number_input('Number of Children')
|
19 |
+
no_of_weekend_nights= st.number_input('Number of Weekend Nights', min_value=0, max_value=7)
|
20 |
+
no_of_week_nights= st.number_input('Number of Week Nights', min_value=0, max_value=17)
|
21 |
+
type_of_meal_plan= st.selectbox(
|
22 |
+
'Choose your Meal Plan',
|
23 |
+
('Meal Plan 1', 'Not Selected', 'Meal Plan 2', 'Meal Plan 3'))
|
24 |
+
required_car_parking_space= st.number_input('Required Car Parking Space')
|
25 |
+
room_type_reserved= st.selectbox(
|
26 |
+
'Choose your Room Type',
|
27 |
+
('Room_Type 1', 'Room_Type 4', 'Room_Type 2', 'Room_Type 6',
|
28 |
+
'Room_Type 5', 'Room_Type 7', 'Room_Type 3'))
|
29 |
+
lead_time= st.number_input('The number of days between booking and arrival')
|
30 |
+
arrival_year= st.number_input('The year of arrival')
|
31 |
+
arrival_month= st.number_input('The month of arrival', min_value=1, max_value=12)
|
32 |
+
arrival_date= st.number_input('The date of arrival', min_value=1, max_value=31)
|
33 |
+
market_segment_type= st.selectbox(
|
34 |
+
'What Segment Type of Customer',
|
35 |
+
('Offline', 'Online', 'Corporate', 'Aviation', 'Complementary'))
|
36 |
+
repeated_guest= st.number_input('Repeated Guest')
|
37 |
+
no_of_previous_cancellations= st.number_input('The number of previous cancellations by the guest')
|
38 |
+
no_of_previous_bookings_not_canceled= st.number_input('The number of previous bookings not canceled by the guest')
|
39 |
+
avg_price_per_room= st.number_input('The average price per room')
|
40 |
+
no_of_special_requests= st.number_input('The number of special requests made by the guest', min_value=0, max_value=5)
|
41 |
+
submitted = st.form_submit_button('Predict')
|
42 |
+
|
43 |
+
# Create New Data
|
44 |
+
df_inf={
|
45 |
+
'Booking_ID': Booking_ID,
|
46 |
+
'no_of_adults': no_of_adults,
|
47 |
+
'no_of_children': no_of_children,
|
48 |
+
'no_of_weekend_nights':no_of_weekend_nights,
|
49 |
+
'no_of_week_nights':no_of_week_nights,
|
50 |
+
'type_of_meal_plan':type_of_meal_plan,
|
51 |
+
'required_car_parking_space': required_car_parking_space,
|
52 |
+
'room_type_reserved':room_type_reserved,
|
53 |
+
'lead_time':lead_time,
|
54 |
+
'arrival_year': arrival_year,
|
55 |
+
'arrival_month':arrival_month,
|
56 |
+
'arrival_date':arrival_date,
|
57 |
+
'market_segment_type':market_segment_type,
|
58 |
+
'repeated_guest':repeated_guest,
|
59 |
+
'no_of_previous_cancellations':no_of_previous_cancellations,
|
60 |
+
'no_of_previous_bookings_not_canceled':no_of_previous_bookings_not_canceled,
|
61 |
+
'avg_price_per_room':avg_price_per_room,
|
62 |
+
'no_of_special_requests':no_of_special_requests,
|
63 |
+
}
|
64 |
+
df_inf = pd.DataFrame([df_inf])
|
65 |
+
|
66 |
+
if submitted:
|
67 |
+
prediction = best_params.predict(df_inf)
|
68 |
+
st.write('This Visitor Predicted:', round(prediction[0],2))
|
69 |
+
# df_inf_best_params = df_inf[best_params]
|
70 |
+
# df_inf_classifier= df_inf[preprocessing_pipeline]
|
71 |
+
# df_inf_final = np.concatenate([preprocessing_pipeline], axis=1)
|
72 |
+
# y_pred_inf = best_params.predict(df_inf_final)
|
73 |
+
# st.write(f'# Rating {best_params}:', int(y_pred_inf))
|
74 |
+
|
75 |
+
|
76 |
+
if best_params == '__main__':
|
77 |
+
run()
|
preprocessing_pipeline.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b20647fc0cb2061834ad51b08d3c948d7ac212fbf99c80caf2e9349896603014
|
3 |
+
size 2709
|