Update pages/4_EDA( Exploratory Data Analysis).py

pages/4_EDA( Exploratory Data Analysis).py

@@ -16,13 +16,14 @@ if data is not None:
     st.subheader("Dataset Preview:")
     st.write(data)  # Display the first 5 rows
     
-    st.subheader('DataFrame Info:')
+    
+    st.subheader("Info of the Dataset:")
     # Redirect the output of df.info() to a string buffer
     buffer = StringIO()
     data.info(buf=buffer)
     
     # Display the content in Streamlit
-    st.text(buffer.getvalue())
+    st.write(buffer.getvalue())
     
     st.subheader("Dataset Statistics:")
     st.write(data.describe())
@@ -47,6 +48,14 @@ if data is not None:
 
     st.pyplot(fig)
 
+    # Hotel Star Insights
+    st.write("""
+        **Insight:**
+        - Majority of hotels in this data are 3-star hotels.
+        - Frequency of 4-star and 5-star hotels are also moderately good.
+        - 1-star and 2-star hotels are lower in frequency.
+    """)
+
     # Price, Cashback, and Discount Distribution
     st.subheader("Price, Cashback, and Discount Distribution")
     fig, axs = plt.subplots(1, 3, figsize=(16, 6))
@@ -66,6 +75,24 @@ if data is not None:
     axs[2].set_xlabel('Discount')
 
     st.pyplot(fig)
+      # Histogram Insights
+    st.subheader("Plot-wise Analysis of Histograms")
+    st.write("""
+        **Price Distribution Insight:**
+        - The histogram is right-skewed, showing most properties are in the lower price range.
+        - A long tail indicates the presence of a few very expensive properties.
+        
+        **Cashback Distribution Insight:**
+        - The histogram is right-skewed, with the majority of properties offering lower cashback amounts.
+        - Only a small number of properties provide higher cashback.
+        
+        **Discount Distribution Insight:**
+        - The histogram is right-skewed, indicating that most properties offer lower discount percentages.
+        - A few properties stand out with higher discounts.
+        
+        **Summary:**
+        The data suggest that Agoda properties are generally affordable, with lower cashback and discount offers being common. Further statistical analysis could help uncover more detailed insights.
+    """)
 
     # Cancellation and State Distribution
     st.subheader("Cancellation and State Distribution")
@@ -82,6 +109,20 @@ if data is not None:
     axs[1].set_ylabel('Number of Hotels')
 
     st.pyplot(fig)
+    # Bar Chart Insights
+    st.subheader("Plot Wise Analysis of Bar Charts")
+    st.write("""
+        **Cancellations:**
+        - Most cancellations fall under category "1," indicating they occur within specific conditions or timeframes.
+        
+        **State Distribution:**
+        - "Maharashtra" has the highest number of hotels, followed by "Madhya Pradesh."
+        - Other states like Gujarat, Karnataka, and Kerala also have notable hotel counts.
+        - The distribution is uneven, with some states having significantly more hotels.
+        
+        **Summary:**
+        The charts highlight cancellation trends and the regional hotel distribution in India.
+    """)
 
     # Category and Reviews Distribution
     st.subheader("Category and Reviews Distribution")
@@ -99,6 +140,19 @@ if data is not None:
     axs[1].set_ylabel('Number of Reviews')
 
     st.pyplot(fig)
+    # Hotel Categories and Reviews Insights
+    st.subheader("Plot Wise Analysis of Hotel Categories and Reviews")
+    st.write("""
+        **Category Distribution:**
+        - The histogram shows "Low Budget" hotels are the most common, followed by "Budget Hotels," while "Luxury Hotels" are the least common.
+        
+        **Review Count Distribution:**
+        - The histogram is right-skewed, with most hotels having a low number of reviews.
+        - A few hotels have a very high number of reviews, evident from the long tail.
+        
+        **Summary:**
+        The data indicates a higher concentration of low-budget hotels and relatively low review counts for most hotels.
+    """)
 
     # Top 10 Amenities
     st.subheader("Top 10 Amenities")
@@ -112,6 +166,224 @@ if data is not None:
     ax.set_ylabel('Amenity')
 
     st.pyplot(fig)
+    # Top Amenities Insights
+    st.subheader("Plot Wise Analysis of Top Amenities")
+    st.write("""
+        **Common Amenities:**
+        - Complimentary Parking is the most frequently offered amenity.
+        - Basic Toiletries and Hair Dryers are also widely available.
+        
+        **Less Common Amenities:**
+        - Fitness Center Access, Welcome Drinks, and Turndown Service are less common.
+        - Shoe Shine Service is the least frequently offered amenity.
+        
+        **Summary:**
+        Hotels tend to prioritize basic amenities like parking, toiletries, and hair dryers, while luxurious amenities are offered less frequently.
+    """)
+
+    # Streamlit app
+    st.title("Bivariate Analysis")
+    
+    # Price vs Rating scatter plot
+    st.subheader("Price vs Rating")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.scatterplot(x='rating', y='price', data=agoda_df, color='orange')
+    ax.set_title('Price vs Rating')
+    ax.set_xlabel('Rating')
+    ax.set_ylabel('Price')
+    st.pyplot(fig)
+    
+    st.write("""
+        **Plot-Wise Analysis of Scatter Plots:**
+        - **Price vs. Rating:** Higher-priced hotels slightly tend to have better ratings, but ratings vary widely across price points.
+        - **Price vs. Discount:** Some high-priced hotels still provide discounts due to promotions or special deals.
+        - **Price vs. Cashback:** Exceptions exist due to promotional campaigns.
+        - **Price vs. Category:** "Luxury" hotels have the highest prices, followed by "Premium" and "Free & Easy." "Low Budget" and "Budget" hotels occupy the lower price range.
+        - **Summary:** Scatter plots reveal that higher-priced hotels generally offer better ratings but fewer discounts and cashback incentives. Lower-priced categories compensate with more promotional benefits.
+    """)
+    
+    # Price vs Discount scatter plot
+    st.subheader("Price vs Discount")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.scatterplot(x='discount', y='price', data=agoda_df, color='green')
+    ax.set_title('Price vs Discount')
+    ax.set_xlabel('Discount')
+    ax.set_ylabel('Price')
+    st.pyplot(fig)
+    
+    # Price vs Cashback scatter plot
+    st.subheader("Price vs Cashback")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.scatterplot(x='cashback', y='price', data=agoda_df, color='blue')
+    ax.set_title('Price vs Cashback')
+    ax.set_xlabel('Cashback')
+    ax.set_ylabel('Price')
+    st.pyplot(fig)
+    
+    # Price vs Category bar plot
+    st.subheader("Price vs Category")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.barplot(x='category', y='price', data=agoda_df, palette='Set2')
+    ax.set_title('Price vs Category')
+    ax.set_xlabel('Category')
+    ax.set_ylabel('Price')
+    st.pyplot(fig)
+    
+    # Rating vs Category bar plot
+    st.subheader("Rating vs Category")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.barplot(x='category', y='rating', data=agoda_df, palette='Set1')
+    ax.set_title('Rating vs Category')
+    ax.set_xlabel('Category')
+    ax.set_ylabel('Rating')
+    st.pyplot(fig)
+    
+    # Discount vs Category box plot
+    st.subheader("Discount vs Category")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.boxplot(x='category', y='discount', data=agoda_df, palette='Set2')
+    ax.set_title('Discount vs Category')
+    ax.set_xlabel('Category')
+    ax.set_ylabel('Discount')
+    st.pyplot(fig)
+    
+    # Cashback vs Category violin plot
+    st.subheader("Cashback vs Category")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.violinplot(x='category', y='cashback', data=agoda_df, palette='Set3')
+    ax.set_title('Cashback vs Category')
+    ax.set_xlabel('Category')
+    ax.set_ylabel('Cashback')
+    st.pyplot(fig)
+    
+    # Reviews vs Category count plot
+    st.subheader("Reviews vs Category")
+    fig, ax = plt.subplots(figsize=(7, 5))
+    sns.countplot(x='category', data=agoda_df, palette='Set1')
+    ax.set_title('Reviews vs Category (Count)')
+    ax.set_xlabel('Category')
+    ax.set_ylabel('Count of Reviews')
+    st.pyplot(fig)
+    
+    # Regional price analysis by state
+    st.subheader("Price by State")
+    fig, ax = plt.subplots(figsize=(16, 6))
+    sns.barplot(data=agoda_df, x='state', y='price', ax=ax, color='green')
+    ax.set_title('Price by State')
+    ax.tick_params(axis='x', rotation=90)
+    sns.set_palette('magma')
+    plt.tight_layout()
+    st.pyplot(fig)
+    
+    # Regional category count by state
+    st.subheader("Category by State")
+    fig, ax = plt.subplots(figsize=(16, 6))
+    sns.countplot(data=agoda_df, x='state', hue='category', ax=ax, palette='Set1')
+    ax.set_title('Category by State')
+    ax.tick_params(axis='x', rotation=90)
+    plt.tight_layout()
+    st.pyplot(fig)
+    
+    st.write("""
+        **Plot-Wise Analysis of Regional Price and Category Trends:**
+        - **Hotel Prices Across Indian States:** Prices vary significantly by state, reflecting regional differences in demand and supply. Certain states with popular tourist destinations show higher hotel prices.
+        - **Hotel Categories by State:** States with more "Low Budget" and "Budget" hotels cater to cost-conscious travelers. States with more "Luxury" hotels are likely tourist hubs or cater to premium audiences.
+        - **Summary:** Regional trends indicate diverse pricing and category distributions, influenced by tourism and economic conditions in different states.
+    """)
+
+
+    st.title("Multivariate Analysis of Hotel Data")
+    
+    # Create a subset of the data for the analysis
+    subset_data = agoda_df[['category', 'price', 'reviews', 'discount', 'cashback', 'rating']]
+    
+    # Section 1: Price vs. Reviews by Category
+    st.header("Price vs. Reviews by Category")
+    fig1 = sns.catplot(data=agoda_df, x='reviews', y='price', hue='category', kind='strip', palette='Set2', height=6, aspect=1.5)
+    fig1.set_axis_labels("Reviews", "Price")
+    fig1.fig.suptitle('Price vs Reviews by Category', fontsize=16)
+    st.pyplot(fig1)
+    
+    # Section 2: Price vs. Discount by Category
+    st.header("Price vs. Discount by Category")
+    fig2 = sns.catplot(data=agoda_df, x='discount', y='price', hue='category', kind='bar', palette='Set2', height=6, aspect=1.5)
+    fig2.set_axis_labels("Discount", "Price")
+    fig2.fig.suptitle('Price vs Discount by Category', fontsize=16)
+    st.pyplot(fig2)
+    
+    # Section 3: Price vs Cashback and Rating by Category (Stripplot)
+    st.header("Price vs Cashback and Rating by Category")
+    fig3, axes2 = plt.subplots(1, 2, figsize=(16, 6))
+    
+    sns.stripplot(data=agoda_df, x='cashback', y='price', hue='category', ax=axes2[0], palette='Set2', jitter=True, dodge=True)
+    axes2[0].set_title('Price vs Cashback by Category')
+    
+    sns.stripplot(data=agoda_df, x='rating', y='price', hue='category', ax=axes2[1], palette='Set2', jitter=True, dodge=True)
+    axes2[1].set_title('Price vs Rating by Category')
+    
+    st.pyplot(fig3)
+
+    # Insights and analysis
+    st.header("Plot-Wise Analysis Insights")
+    
+    st.subheader("Price vs. Reviews by Category")
+    st.write("""
+        - Wide price ranges exist within each category, such as "Low Budget" having both low- and high-priced hotels.
+        - Slight tendency for hotels with more reviews to have higher prices, influenced by popularity and marketing efforts.
+    """)
+    
+    st.subheader("Price vs. Discount by Category")
+    st.write("""
+        - Discounts decrease as hotel prices increase, confirming a negative correlation.
+        - "Low Budget" and "Budget" hotels offer higher discounts compared to "Premium" and "Luxury" categories.
+    """)
+    
+    st.subheader("Price vs Cashback and Rating by Category")
+    st.write("""
+        - Lower-priced categories ("Budget" and "Low Budget") offer higher cashback incentives.
+        - Higher-priced categories ("Premium" and "Luxury") tend to have better ratings.
+        - Some lower-priced hotels achieve high ratings, indicating other factors like service quality influence customer satisfaction.
+    """)
+    
+    # Section 4: Correlation Heatmap
+    st.header("Correlation Matrix Heatmap")
+    numeric_columns = ['price', 'reviews', 'discount', 'cashback', 'rating']
+    
+    # Compute the correlation matrix
+    correlation_matrix = agoda_df[numeric_columns].corr()
+    
+    # Create a heatmap to visualize the correlation matrix
+    plt.figure(figsize=(10, 8))
+    sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5, vmin=-1, vmax=1)
+    
+    # Set title for the plot
+    plt.title('Correlation Matrix Heatmap')
+    
+    # Display the plot
+    st.pyplot(plt)
+    
+    st.subheader("Correlation Matrix Heatmap")
+    st.write("""
+        - Strong negative correlation observed between price and discounts/cashbacks.
+        - Weak positive correlation between price and rating.
+        - Moderate positive correlation between reviews and ratings, and a weak positive correlation between reviews and price.
+    """)
+    
+    st.header("Overall Summary")
+    st.write("""
+        - Most properties are affordable, with lower prices, cashback, and discounts dominating the dataset.
+        - Regional distribution shows states like Maharashtra and Madhya Pradesh having more hotels.
+        - The data reflects a market focused on affordability and basic amenities, with regional and category-specific variations.
+        - Cancellations and reviews provide further insights into customer behavior, while skewed distributions highlight potential outliers and trends in pricing and service offerings.
+    """)
+    
+    st.header("Why Right-Skewed Trends Are Normal, Not Outliers")
+    st.write("""
+        - Right-skewed distributions for price, cashback, discounts, cancellations, reviews, and amenities are normal trends in the market.
+        - These trends represent the expected distribution of data where higher values are less frequent but are not considered outliers.
+        - The variations in cancellation patterns and review counts reflect typical customer behavior and industry dynamics.
+    """)
+
 
 else:
     st.warning("No dataset found in session state. Please load the dataset into `st.session_state['data']`.")