Upload 6 files

app.py

@@ -0,0 +1,10 @@
+import streamlit as st
+import eda
+import prediction
+import seaborn
+
+Navigation = st.sidebar.selectbox('Pilih Halaman:', ('EDA','Predict Visitors Hotel Reservation'))
+if Navigation == 'EDA':
+    eda.run()
+else:
+    prediction.run()

best_param.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e119733908fd32e92d4116a265f26104c7b8ca893b0d30ee7147fb2f534881ec
+size 484040

eda.py

@@ -0,0 +1,85 @@
+import streamlit as st 
+import pandas as pd 
+import seaborn as sns 
+import matplotlib.pyplot as plt 
+import plotly.express as px 
+from PIL import Image 
+
+# Set page config
+st.set_page_config(
+    page_title= 'Hotel_Reservation_EDA',
+    layout= 'wide',
+    initial_sidebar_state= 'expanded'
+)
+
+# Create Function for EDA
+def run():
+    #Create title
+    st.title('Hotel Reservation Visitors')
+
+    # Create Sub Header atau Sub Judul
+    st.subheader('EDA untuk Analisis Dataset ')
+
+    # Add Image
+    st.image('https://www.hotellinksolutions.com/images/blog/avt.jpg', caption= 'Hotel Reservation')
+
+    # Create a Description
+    st.write('Page Made by Allen')
+
+
+    # Magic Syntax
+    '''
+    Pada page kali ini, penulis akan melakukan eksplorasi sederhana,
+    Dataset yang digunakan adalah Credit Card Default.
+    Dataset ini berasal dari Big Query Google
+
+    '''
+
+    # Create Straight Line
+    st.markdown('---')
+
+    # Show Dataframe
+    df = pd.read_csv('hotel_reservations.csv')
+    st.dataframe(df)
+
+    # Booking Status
+    st.write('### Plot Booking Status Customer')
+    fig= plt.figure(figsize=(20,5))
+    sns.countplot(x='booking_status', data=df)
+    st.pyplot(fig)
+    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%`.')
+
+    st.write('### Plot Room Type Customer')
+    fig= plt.figure(figsize=(20,5))
+    sns.countplot(x='room_type_reserved', data=df)
+    st.pyplot(fig)
+    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`')
+
+    st.write('### Plot Market Segment')
+    fig= plt.figure(figsize=(20,5))
+    sns.countplot(x='market_segment_type', data=df)
+    st.pyplot(fig)
+    st.write('Market segment of booking status majority from online')
+
+    st.write('### Plot Type of Meal Plan')
+    fig= plt.figure(figsize=(20,5))
+    sns.countplot(x='type_of_meal_plan', data=df)
+    st.pyplot(fig)
+    st.write('Visitors that not canceled and canceled in how they chose meal plan, the meal plan 1 is occupied the first place')
+
+    st.write('### Plot Arrival Year')
+    fig= plt.figure(figsize=(20,5))
+    sns.countplot(x='arrival_year', data=df)
+    st.pyplot(fig)
+  
+    st.write('### Plot Arrival Month')
+    fig= plt.figure(figsize=(20,5))
+    sns.countplot(x='arrival_month', data=df)
+    st.pyplot(fig)
+    st.write('The Conclusion Based on Arrival Year and Arrival Month is visitors activity in reservation hotel, crowded in October 2018')
+
+
+
+    
+if __name__ == '__main__':
+    run()

prediction.py

@@ -0,0 +1,77 @@
+import pickle
+import json
+import pandas as pd 
+import numpy as np
+import streamlit as st
+
+# Load All Files
+with open('best_param.pkl', 'rb') as file_1:
+ best_params = pickle.load(file_1)
+
+with open('preprocessing_pipeline.pkl', 'rb') as file_2:
+ preprocessing_pipeline= pickle.load(file_2)
+
+def run ():
+  with st.form(key ='PREDICT VISITORS FORM'): #Nulis nama sendiri menggunakan name= st.text_input('')
+    Booking_ID= st.text_input('Booking_ID', 'Input ID Here')
+    no_of_adults = st.number_input('Number of Adults')
+    no_of_children= st.number_input('Number of Children')
+    no_of_weekend_nights= st.number_input('Number of Weekend Nights', min_value=0, max_value=7)
+    no_of_week_nights= st.number_input('Number of Week Nights', min_value=0, max_value=17)
+    type_of_meal_plan= st.selectbox(
+    'Choose your Meal Plan',
+    ('Meal Plan 1', 'Not Selected', 'Meal Plan 2', 'Meal Plan 3'))
+    required_car_parking_space= st.number_input('Required Car Parking Space')
+    room_type_reserved=  st.selectbox(
+    'Choose your Room Type',
+    ('Room_Type 1', 'Room_Type 4', 'Room_Type 2', 'Room_Type 6',
+       'Room_Type 5', 'Room_Type 7', 'Room_Type 3'))
+    lead_time= st.number_input('The number of days between booking and arrival')
+    arrival_year= st.number_input('The year of arrival')
+    arrival_month= st.number_input('The month of arrival', min_value=1, max_value=12)
+    arrival_date= st.number_input('The date of arrival', min_value=1, max_value=31)
+    market_segment_type=  st.selectbox(
+    'What Segment Type of Customer',
+    ('Offline', 'Online', 'Corporate', 'Aviation', 'Complementary'))
+    repeated_guest= st.number_input('Repeated Guest')
+    no_of_previous_cancellations= st.number_input('The number of previous cancellations by the guest')
+    no_of_previous_bookings_not_canceled= st.number_input('The number of previous bookings not canceled by the guest')
+    avg_price_per_room= st.number_input('The average price per room')
+    no_of_special_requests= st.number_input('The number of special requests made by the guest', min_value=0, max_value=5)
+    submitted = st.form_submit_button('Predict')
+
+  # Create New Data
+  df_inf={
+    'Booking_ID': Booking_ID, 
+    'no_of_adults': no_of_adults, 
+    'no_of_children': no_of_children, 
+    'no_of_weekend_nights':no_of_weekend_nights,
+    'no_of_week_nights':no_of_week_nights, 
+    'type_of_meal_plan':type_of_meal_plan, 
+    'required_car_parking_space': required_car_parking_space,
+    'room_type_reserved':room_type_reserved, 
+    'lead_time':lead_time, 
+    'arrival_year': arrival_year, 
+    'arrival_month':arrival_month,
+    'arrival_date':arrival_date, 
+    'market_segment_type':market_segment_type, 
+    'repeated_guest':repeated_guest,
+    'no_of_previous_cancellations':no_of_previous_cancellations, 
+    'no_of_previous_bookings_not_canceled':no_of_previous_bookings_not_canceled,
+    'avg_price_per_room':avg_price_per_room, 
+    'no_of_special_requests':no_of_special_requests, 
+        }
+  df_inf = pd.DataFrame([df_inf])
+
+  if submitted: 
+    prediction = best_params.predict(df_inf)
+    st.write('This Visitor Predicted:', round(prediction[0],2))
+    # df_inf_best_params = df_inf[best_params]
+    # df_inf_classifier= df_inf[preprocessing_pipeline]
+    # df_inf_final = np.concatenate([preprocessing_pipeline], axis=1)
+    # y_pred_inf = best_params.predict(df_inf_final) 
+    # st.write(f'# Rating {best_params}:', int(y_pred_inf))
+
+
+if best_params == '__main__':
+  run()

preprocessing_pipeline.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b20647fc0cb2061834ad51b08d3c948d7ac212fbf99c80caf2e9349896603014
+size 2709