Update pages/3_EDA_and_Feature_Engineering.py

pages/3_EDA_and_Feature_Engineering.py

@@ -1,20 +1,106 @@
-import streamlit as st
-import pandas as pd
-import seaborn as sns
+import streamlit as st 
+import numpy as np 
+import pandas as pd 
 import matplotlib.pyplot as plt
-import plotly.express as px
-from sklearn.preprocessing import LabelEncoder, PolynomialFeatures
+import seaborn as sns
+from io import StringIO
+import sys
+
+st.markdown("<h1 style='text-align:center; color:white;'>EDA and Feature Engineering</h1>",unsafe_allow_html=True)
+
+# Define the URL of the background image (use your own image URL)
+background_image_url = "https://cdn-uploads.huggingface.co/production/uploads/67441c51a784a9d15cb12871/7ZCmkouk1pS37_kREZmYJ.jpeg"
+
+# Apply custom CSS for the background image and overlay
+st.markdown(
+    f"""
+    <style>
+        .stApp {{
+            background-image: url("{background_image_url}");
+            background-size: cover;  /* Ensures the image covers the full screen */
+            background-position: center;  /* Centers the background image */
+            background-attachment: fixed;  /* Keeps the background fixed as you scroll */
+            height: 100vh;
+            width: 100%;
+            overflow: hidden;  /* Prevents any overflow that might cause the background image to zoom */
+        }}
+        
+        /* Semi-transparent overlay */
+        .stApp::before {{
+            content: "";
+            position: absolute;
+            top: 0;
+            left: 0;
+            width: 100%;
+            height: 100%;
+            background: rgba(0, 0, 0, 0.4);  /* Adjust transparency here (0.4 for 40% transparency) */
+            z-index: -1;
+        }}
+        /* Styling the content to ensure text visibility */
+        .stMarkdown {{
+            color: white;  /* White text to ensure visibility */
+            font-size: 100px;  /* Adjust font size for better readability */
+        }}
+    </style>
+    """, 
+    unsafe_allow_html=True
+)
+# Title of the Streamlit app
+st.title("Exploratory Data Analysis (EDA) on Agoda Hotel Dataset")
+
+# Introduction and Aim
+st.header("Aim of the EDA")
+st.write("""
+    The main objective of this EDA is to analyze Agoda's hotel dataset to identify key factors influencing hotel pricing strategies and customer booking preferences. 
+    The analysis will focus on uncovering patterns, trends, and relationships in hotel ratings, pricing structures, discounts, and free services.
+    By leveraging these insights, Agoda can optimize its pricing strategy, predict booking preferences, and enhance revenue generation while maintaining customer satisfaction.
+""")
 
-# Page Title
-st.title("Complete EDA and Feature Engineering")
+# Description of the Data
+st.header("Description of the Data")
+st.write("""
+    **Overall Summary:** We are analyzing the Agoda dataset by performing EDA and Statistical Tests on the data that has already been cleaned through data wrangling to address any messiness or missing information.
+    
+    **Table - Agoda_df:** The cleaned dataset consists of over 3,500 hotel listings, which will be used as test subjects for the hotel pricing period.
+    **Dataset Details:**
+    The dataset contains information about 3,219 hotel room listings with 12 features, each detailing aspects of the listing. Below is the description of each column:
+    | Column Name     | Description                                                               |
+    |-----------------|---------------------------------------------------------------------------|
+    | hotel_name      | Name of the hotel.                                                        |
+    | rating          | Average customer rating of the hotel (float, range 1-5).                   |
+    | location        | Address or locality of the hotel.                                          |
+    | review_text     | Customer feedback or comments about the hotel.                             |
+    | reviews         | Total number of customer reviews for the hotel.                            |
+    | cashback        | Cashback amount offered for the booking.                                  |
+    | discount        | Discount percentage applied to the room price.                             |
+    | free_services   | Free services provided (e.g., breakfast, Wi-Fi).                          |
+    | cancellation    | Cancellation policy for the booking (e.g., free, non-refundable).         |
+    | price           | Price of the room after discounts and cashback (float).                    |
+    | state           | The state where the hotel is located.                                      |
+    | category        | Target variable representing the room type or category (e.g., budget, luxury). |
+""")
 
-st.markdown("""
-This page provides advanced Exploratory Data Analysis (EDA) and Feature Engineering using the dataset loaded in memory.
----
+# Table-wise EDA & Necessary Tests
+st.header("Table-wise EDA and Necessary Statistical Tests")
+st.write("""
+    **Agoda_df:** Cleaned dataset with hotel details and key features like ratings, price, reviews, cashback, discounts, and free services.
+    The EDA will involve the following steps:
+    - **Summary Statistics:** Analyze the central tendency, spread, and shape of the distribution of each feature.
+    - **Data Distribution:** Visualize the distribution of key features like price, ratings, reviews, cashback, etc.
+    - **Correlation Analysis:** Analyze relationships between numeric features like price, ratings, reviews, cashback, etc.
+    - **Categorical Data Analysis:** Explore categorical variables like hotel category, cancellation policy, state, and location using frequency tables and visualizations.
+    - **Missing Value Analysis:** Ensure no missing values remain, and check the need for imputations.
+    - **Outlier Detection:** Identify any outliers that may skew the analysis or predictions.
+    - **Statistical Tests:** Apply appropriate statistical tests to identify significant differences or relationships (e.g., t-tests for comparing means, chi-squared for categorical variables).
 """)
 
-# Check if dataset exists in session state
-if 'df' in st.session_state:
+# Placeholder for further detailed code or visualizations
+st.write("Further steps will include generating visualizations and statistical tests to explore relationships between features in more detail.")
+
+# Access dataset from session state
+data= st.session_state.get("dataset")
+
+if data is not None:
     df = st.session_state['df']
     st.success("Dataset loaded successfully.")
 
@@ -453,4 +539,5 @@ if 'df' in st.session_state:
     - 1: Perfect positive correlation (as one variable increases, the other increases)''')
 
 else:
-    st.error("No dataset found. Please upload a dataset on the main page first.")
+   st.warning("No dataset found in session state. Please load the dataset into `st.session_state['data']`.")
+