Changes to hotel booking prediction

app.py

@@ -1,24 +1,35 @@
-# app.py
+import os
 import streamlit as st
 import pandas as pd
 import numpy as np
 import pickle
 import matplotlib.pyplot as plt
 import seaborn as sns
+import boto3
+from io import StringIO
 from datetime import timedelta
 from pandas.tseries.offsets import MonthEnd
 from statsmodels.tsa.statespace.sarimax import SARIMAX
 from statsmodels.tsa.stattools import adfuller
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.model_selection import train_test_split
-from sklearn.metrics import accuracy_score
+from sklearn.metrics import accuracy_score,classification_report, confusion_matrix
 from sklearn.cluster import KMeans
 from sklearn.preprocessing import StandardScaler
+import joblib
+
+
+os.environ['AWS_ACCESS_KEY_ID'] = os.getenv("getdata")
+os.environ['AWS_SECRET_ACCESS_KEY'] = os.getenv("getdatake")
+
+def load_data_from_s3(bucket_name, file_key):
+    s3 = boto3.client('s3')
+    obj = s3.get_object(Bucket=bucket_name, Key=file_key)
+    data = pd.read_csv(StringIO(obj['Body'].read().decode('utf-8')))
+    return data
 
-# Streamlit app
 st.title('Hotel Booking Analysis')
 
-# Navigation
 st.sidebar.title('Navigation')
 options = st.sidebar.radio('Select a page:', ['Overview', 'Revenue Forecasting', 'Predict Booking Cancellations', 'Market Segmentation', 'Customer Lifetime Value'])
 
@@ -29,10 +40,21 @@ if options == 'Overview':
 elif options == 'Revenue Forecasting':
     st.header('Hotel Booking Revenue Forecasting with SARIMA')
 
-    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+    # Option to choose data source
+    data_source = st.radio("Choose data source:", ["Upload CSV", "Load from AWS S3"])
 
-    if uploaded_file is not None:
-        data = pd.read_csv(uploaded_file)
+    if data_source == "Upload CSV":
+        uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+        if uploaded_file is not None:
+            data = pd.read_csv(uploaded_file)
+    else:
+        bucket_name = st.text_input("Enter S3 bucket name:", "iitj-ap-south-1-mayank")
+        file_key = st.text_input("Enter S3 file key:", "clean/hotel_booking/hotel_booking.csv")
+        if st.button("Load Data"):
+            data = load_data_from_s3(bucket_name, file_key)
+
+    if 'data' in locals():
+        # Display the first few rows of the dataset
         st.write("## Dataset Preview")
         st.write(data.head())
         
@@ -97,53 +119,112 @@ elif options == 'Revenue Forecasting':
 elif options == 'Predict Booking Cancellations':
     st.header('Predict Booking Cancellations')
 
-    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-    
-    if uploaded_file is not None:
-        data = pd.read_csv(uploaded_file)
+    # Option to choose data source
+    data_source = st.radio("Choose data source:", ["Upload CSV", "Load from AWS S3"])
+
+    if data_source == "Upload CSV":
+        uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+        if uploaded_file is not None:
+            data = pd.read_csv(uploaded_file)
+    else:
+        bucket_name = st.text_input("Enter S3 bucket name:", "iitj-ap-south-1-mayank")
+        file_key = st.text_input("Enter S3 file key:", "clean/hotel_booking/hotel_booking.csv")
+        if st.button("Load Data"):
+            data = load_data_from_s3(bucket_name, file_key)
+
+    if 'data' in locals():
+        # Display the first few rows of the dataset
         st.write("## Dataset Preview")
         st.write(data.head())
 
         features = ['lead_time', 'arrival_date_year', 'arrival_date_week_number', 
                     'arrival_date_day_of_month', 'stays_in_weekend_nights', 
                     'stays_in_week_nights', 'adults', 'children', 'babies', 
-                    'is_repeated_guest', 'previous_cancellations', 
-                    'previous_bookings_not_canceled', 'booking_changes', 
-                    'days_in_waiting_list', 'adr', 'required_car_parking_spaces', 
-                    'total_of_special_requests']
-
+                    'previous_cancellations', 'previous_bookings_not_canceled', 
+                    'booking_changes', 'days_in_waiting_list', 'adr', 
+                    'required_car_parking_spaces', 'total_of_special_requests']
+        
+        data = data.dropna(subset=features + ['is_canceled'])
         X = data[features]
         y = data['is_canceled']
 
+        # Split the data into training and testing sets
         X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-        model = RandomForestClassifier(n_estimators=100, random_state=42)
-        model.fit(X_train, y_train)
+        # Train the Random Forest Classifier
+        rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
+        rf_model.fit(X_train, y_train)
 
-        y_pred = model.predict(X_test)
-        accuracy = accuracy_score(y_test, y_pred)
-        st.write(f'Model Accuracy: {accuracy:.2f}')
+        # Make predictions
+        y_pred = rf_model.predict(X_test)
 
-        st.write("## Predict Booking Cancellation for New Data")
+        # Display model performance metrics
+        st.write("## Model Performance Metrics")
+        st.write("### Confusion Matrix")
+        cm = confusion_matrix(y_test, y_pred)
+        st.write(cm)
         
+        st.write("### Classification Report")
+        cr = classification_report(y_test, y_pred, output_dict=True)
+        st.write(pd.DataFrame(cr).transpose())
+
+        st.write("### Accuracy Score")
+        acc = accuracy_score(y_test, y_pred)
+        st.write(acc)
+
+        # Save the model to a file
+        joblib.dump(rf_model, 'rf_model.pkl')
+        st.write("Model saved as rf_model.pkl")
+
+        st.write("## Predict Booking Cancellation")
+        st.write("Enter the details to predict if a booking will be canceled:")
+
+        # Collect user input for prediction
         input_data = {}
-        for col in features:
-            input_data[col] = float(st.text_input(f'{col}:', value='0'))
+        for feature in features:
+            input_data[feature] = st.number_input(f"Enter {feature}:", min_value=0.0)
+
+        if st.button("Predict"):
+            input_df = pd.DataFrame([input_data])
+
+            # Ensure the input data has the correct data types
+            for feature in features:
+                input_df[feature] = input_df[feature].astype(X[feature].dtype)
 
-        input_df = pd.DataFrame(input_data, index=[0])
-        prediction = model.predict(input_df)
-        st.write('Prediction:', 'Canceled' if prediction[0] else 'Not Canceled')
+            prediction = rf_model.predict(input_df)
+            prediction_proba = rf_model.predict_proba(input_df)
+
+            st.write(f"Input Data: {input_df}")
+            st.write(f"Prediction: {prediction}")
+            st.write(f"Prediction Probability: {prediction_proba}")
+
+            if prediction[0] == 1:
+                st.write("Prediction: The booking is likely to be canceled.")
+            else:
+                st.write("Prediction: The booking is not likely to be canceled.")
 
 elif options == 'Market Segmentation':
     st.header('Market Segmentation')
 
-    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-    
-    if uploaded_file is not None:
-        data = pd.read_csv(uploaded_file)
+    # Option to choose data source
+    data_source = st.radio("Choose data source:", ["Upload CSV", "Load from AWS S3"])
+
+    if data_source == "Upload CSV":
+        uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+        if uploaded_file is not None:
+            data = pd.read_csv(uploaded_file)
+    else:
+        bucket_name = st.text_input("Enter S3 bucket name:", "iitj-ap-south-1-mayank")
+        file_key = st.text_input("Enter S3 file key:", "clean/hotel_booking/hotel_booking.csv")
+        if st.button("Load Data"):
+            data = load_data_from_s3(bucket_name, file_key)
+
+    if 'data' in locals():
+        # Display the first few rows of the dataset
         st.write("## Dataset Preview")
         st.write(data.head())
 
+
         data['total_guests'] = data['adults'] + data['children'] + data['babies']
         segmentation_features = data[['total_guests', 'total_of_special_requests', 'lead_time', 'is_repeated_guest']]
         scaler = StandardScaler()
@@ -165,10 +246,21 @@ elif options == 'Market Segmentation':
 elif options == 'Customer Lifetime Value':
     st.header('Customer Lifetime Value')
 
-    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-    
-    if uploaded_file is not None:
-        data = pd.read_csv(uploaded_file)
+    # Option to choose data source
+    data_source = st.radio("Choose data source:", ["Upload CSV", "Load from AWS S3"])
+
+    if data_source == "Upload CSV":
+        uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
+        if uploaded_file is not None:
+            data = pd.read_csv(uploaded_file)
+    else:
+        bucket_name = st.text_input("Enter S3 bucket name:", "iitj-ap-south-1-mayank")
+        file_key = st.text_input("Enter S3 file key:", "clean/hotel_booking/hotel_booking.csv")
+        if st.button("Load Data"):
+            data = load_data_from_s3(bucket_name, file_key)
+
+    if 'data' in locals():
+        # Display the first few rows of the dataset
         st.write("## Dataset Preview")
         st.write(data.head())
 
@@ -183,3 +275,4 @@ elif options == 'Customer Lifetime Value':
         plt.xlabel('Lifetime Value')
         plt.ylabel('Frequency')
         st.pyplot(plt)
+

requirements.txt

@@ -4,4 +4,6 @@ numpy
 matplotlib
 seaborn
 scikit-learn
-statsmodels
+statsmodels
+boto3
+joblib