Spaces:
Runtime error
Runtime error
File size: 11,489 Bytes
2c2ffac b965b34 2c2ffac b965b34 aea9fdb 2c2ffac 9bd2d1f 2c2ffac b965b34 a56815a b965b34 aea9fdb b965b34 2c2ffac b965b34 2c2ffac b965b34 9bd2d1f b965b34 aea9fdb b965b34 9bd2d1f b965b34 2c2ffac 9bd2d1f aea9fdb 2c2ffac aea9fdb 2c2ffac aea9fdb 9bd2d1f 2c2ffac aea9fdb 2c2ffac aea9fdb 2c2ffac aea9fdb 2c2ffac 9bd2d1f 2c2ffac b965b34 2c2ffac b965b34 9bd2d1f 2c2ffac 9bd2d1f 2c2ffac aea9fdb 9bd2d1f b965b34 9bd2d1f 2c2ffac 9bd2d1f aea9fdb 9bd2d1f 2c2ffac |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 |
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,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
st.title('Accomodation Booking Analysis')
st.sidebar.title('Navigation')
options = st.sidebar.radio('Select a page:', ['Overview', 'Revenue Forecasting', 'Predict Booking Cancellations', 'Market Segmentation', 'Customer Lifetime Value'])
if options == 'Overview':
st.header('Overview')
st.write('This app provides insights and predictions for hotel bookings.')
elif options == 'Revenue Forecasting':
st.header('Hotel Booking Revenue Forecasting with SARIMA')
# 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['arrival_date'] = pd.to_datetime(data['arrival_date_year'].astype(str) + '-' +
data['arrival_date_month'].astype(str) + '-01')
data['arrival_date'] += MonthEnd(0)
monthly_revenue = data[data['is_canceled'] == 0].groupby('arrival_date')['adr'].sum().reset_index()
st.write("## Monthly Revenue")
plt.figure(figsize=(12, 6))
sns.lineplot(x='arrival_date', y='adr', data=monthly_revenue)
plt.title('Monthly Revenue')
plt.xlabel('Month')
plt.ylabel('Revenue')
plt.xticks(rotation=45)
plt.tight_layout()
st.pyplot(plt)
result = adfuller(monthly_revenue['adr'])
st.write(f'## ADF Statistic: {result[0]}')
st.write(f'## p-value: {result[1]}')
if result[1] > 0.05:
monthly_revenue['adr_diff'] = monthly_revenue['adr'].diff().dropna()
p = st.slider('AR order (p)', 0, 5, 1)
d = st.slider('Differencing order (d)', 0, 2, 1)
q = st.slider('MA order (q)', 0, 5, 1)
P = st.slider('Seasonal AR order (P)', 0, 2, 1)
D = st.slider('Seasonal differencing order (D)', 0, 2, 1)
Q = st.slider('Seasonal MA order (Q)', 0, 2, 1)
model = SARIMAX(monthly_revenue['adr'],
order=(p, d, q),
seasonal_order=(P, D, Q, 12))
model_fit = model.fit(disp=False)
forecast_steps = 12
forecast = model_fit.get_forecast(steps=forecast_steps)
forecast_index = pd.date_range(start=monthly_revenue['arrival_date'].max() + pd.DateOffset(months=1),
periods=forecast_steps, freq='M')
forecast_df = pd.DataFrame({'arrival_date': forecast_index,
'forecast': forecast.predicted_mean})
st.write("## Revenue Forecast")
plt.figure(figsize=(12, 6))
sns.lineplot(x='arrival_date', y='adr', data=monthly_revenue, label='Historical Revenue')
sns.lineplot(x='arrival_date', y='forecast', data=forecast_df, label='Forecasted Revenue')
plt.title('Revenue Forecast')
plt.xlabel('Month')
plt.ylabel('Revenue')
plt.xticks(rotation=45)
plt.legend()
plt.tight_layout()
st.pyplot(plt)
st.write("## Forecasted Revenue for the Next 12 Months")
st.write(forecast_df.set_index('arrival_date'))
elif options == 'Predict Booking Cancellations':
st.header('Predict Booking Cancellations')
# 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',
'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)
# Train the Random Forest Classifier
rf_model = RandomForestClassifier(n_estimators=100, random_state=42)
rf_model.fit(X_train, y_train)
# Make predictions
y_pred = rf_model.predict(X_test)
# 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 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)
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')
# 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()
segmentation_features_scaled = scaler.fit_transform(segmentation_features)
kmeans = KMeans(n_clusters=4, random_state=42)
data['customer_segment'] = kmeans.fit_predict(segmentation_features_scaled)
st.write("## Customer Segmentation Results")
st.write(data[['customer_segment']].head())
plt.figure(figsize=(10, 5))
sns.scatterplot(x=segmentation_features_scaled[:, 0], y=segmentation_features_scaled[:, 1], hue=data['customer_segment'], palette='viridis')
plt.title('Customer Segmentation')
plt.xlabel('Total Guests (Standardized)')
plt.ylabel('Total Special Requests (Standardized)')
st.pyplot(plt)
elif options == 'Customer Lifetime Value':
st.header('Customer Lifetime Value')
# 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['customer_id'] = data['lead_time'].astype(str) + '_' + data['arrival_date_year'].astype(str) + '_' + data['arrival_date_month'].astype(str) + '_' + data['arrival_date_day_of_month'].astype(str)
clv_df = data.groupby('customer_id')['adr'].sum().reset_index()
clv_df.columns = ['customer_id', 'lifetime_value']
st.write("## Customer Lifetime Value Distribution")
plt.figure(figsize=(10, 5))
sns.histplot(clv_df['lifetime_value'], kde=True)
plt.title('Customer Lifetime Value Distribution')
plt.xlabel('Lifetime Value')
plt.ylabel('Frequency')
st.pyplot(plt)
|