Update eda.py

eda.py

@@ -24,88 +24,103 @@ st.markdown(hide_streamlit_style, unsafe_allow_html=True)
 
 
 def run():
-    with st.sidebar:
-        st.title('EDA')
-    
-        d = pd.read_csv('hotel_bookings.csv')
-    
-        fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(15, 10))
+
+    st.title('EDA')
     
-        sns.histplot(data=d, x='lead_time', hue='is_canceled',
-                     kde=True, ax=ax[0][0], palette='Set1').set_title("distribution of Lead Time")
-        
-        sns.histplot(data=d, x='booking_changes', hue='is_canceled',
-                     ax=ax[0][1], palette='Set1').set_title("distribution of Booking Changes")
+    with st.sidebar:
+
+        st.markdown('
+        - Bookings made well in advance, such as 250 days before the stay, often face cancellations. This suggests the need for flexible cancellation policies.
+
+        - Despite "Non Refundable" deposits, a significant number of cancellations occur. Unforeseen events may be causing these cancellations.
         
-        sns.histplot(data=d, x='deposit_type', hue='is_canceled',
-                     ax=ax[1][0], palette='Set1').set_title("distribution of Deposit Type")
+        - April and May witness increased hotel bookings. This highlights the potential to optimize pricing and resources during these peak demand periods.
         
-        plt.tight_layout()
-        st.pyplot(fig)
-    
-        booking_counts = d.groupby(['arrival_date_year', 'arrival_date_month', 'arrival_date_week_number', 'hotel']).size().reset_index(name='booking_count')
-    
-        pivot_table = booking_counts.pivot_table(index=['arrival_date_month', 'arrival_date_week_number'], columns=['arrival_date_year', 'hotel'], values='booking_count', fill_value=0)
+        - The difficulty in identifying strong connections between columns is due to the unequal data distribution between city and resort hotels. Caution is advised when interpreting findings.
         
-        plt.figure(figsize=(12, 10))
-        pivot_table.plot(kind='line')
-        plt.title('Seasonal Booking Trends')
-        plt.xlabel('Month and Week Number')
-        plt.ylabel('Booking Count')
-        plt.legend(title='Hotel Type')
-        plt.xticks(rotation=45)
-        plt.tight_layout()
-        st.pyplot()
+        - Online Travel agents are favored for bookings. We can Strengthen partnerships with Online Travel agents, offering them exclusive deals or promotions to encourage more bookings through this channel. Focus marketing efforts on promoting these partnerships to attract a broader customer base. By implementing these solutions, hotels can adapt to changing customer preferences and market dynamics, ultimately enhancing customer satisfaction and revenue generation.
+        ')
     
-        demographics_counts = d[['babies', 'adults', 'children']].sum()
-        
-        # creating the pie chart
-        plt.figure(figsize=(8, 8))
-        plt.pie(demographics_counts, labels=demographics_counts.index, autopct='%1.1f%%', startangle=140)
-        plt.title('Distribution of Guest Demographics')
-        plt.axis('equal')  
-        
-        st.pyplot()
+
+    d = pd.read_csv('hotel_bookings.csv')
+
+    fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(15, 10))
+
+    sns.histplot(data=d, x='lead_time', hue='is_canceled',
+                 kde=True, ax=ax[0][0], palette='Set1').set_title("distribution of Lead Time")
     
-            
-        fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(12, 10))
+    sns.histplot(data=d, x='booking_changes', hue='is_canceled',
+                 ax=ax[0][1], palette='Set1').set_title("distribution of Booking Changes")
     
-        sns.histplot(data=d, x='lead_time', hue='hotel', multiple='stack', bins=20, ax=ax[0, 0], palette='Set1')
-        ax[0, 0].set_title("Booking Behavior by Hotel Type (Lead Time)")
+    sns.histplot(data=d, x='deposit_type', hue='is_canceled',
+                 ax=ax[1][0], palette='Set1').set_title("distribution of Deposit Type")
     
-        sns.barplot(data=d, x='hotel', y='is_canceled', ax=ax[0, 1], palette='Set1')
-        ax[0, 1].set_title("Cancellation Rate by Hotel Type")
+    plt.tight_layout()
+    st.pyplot(fig)
+
+    booking_counts = d.groupby(['arrival_date_year', 'arrival_date_month', 'arrival_date_week_number', 'hotel']).size().reset_index(name='booking_count')
+
+    pivot_table = booking_counts.pivot_table(index=['arrival_date_month', 'arrival_date_week_number'], columns=['arrival_date_year', 'hotel'], values='booking_count', fill_value=0)
     
-        sns.countplot(data=d, x='booking_changes', hue='hotel', ax=ax[1, 0], palette='Set1')
-        ax[1, 0].set_title("Booking Changes by Hotel Type")
+    plt.figure(figsize=(12, 10))
+    pivot_table.plot(kind='line')
+    plt.title('Seasonal Booking Trends')
+    plt.xlabel('Month and Week Number')
+    plt.ylabel('Booking Count')
+    plt.legend(title='Hotel Type')
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    st.pyplot()
+
+    demographics_counts = d[['babies', 'adults', 'children']].sum()
     
-        sns.countplot(data=d, x='hotel', ax=ax[1, 1], palette='Set1')
-        ax[1, 1].set_title("Total Bookings by Hotel Type")
+    # creating the pie chart
+    plt.figure(figsize=(8, 8))
+    plt.pie(demographics_counts, labels=demographics_counts.index, autopct='%1.1f%%', startangle=140)
+    plt.title('Distribution of Guest Demographics')
+    plt.axis('equal')  
     
+    st.pyplot()
+
+        
+    fig, ax = plt.subplots(nrows=2, ncols=2, figsize=(12, 10))
+
+    sns.histplot(data=d, x='lead_time', hue='hotel', multiple='stack', bins=20, ax=ax[0, 0], palette='Set1')
+    ax[0, 0].set_title("Booking Behavior by Hotel Type (Lead Time)")
+
+    sns.barplot(data=d, x='hotel', y='is_canceled', ax=ax[0, 1], palette='Set1')
+    ax[0, 1].set_title("Cancellation Rate by Hotel Type")
+
+    sns.countplot(data=d, x='booking_changes', hue='hotel', ax=ax[1, 0], palette='Set1')
+    ax[1, 0].set_title("Booking Changes by Hotel Type")
+
+    sns.countplot(data=d, x='hotel', ax=ax[1, 1], palette='Set1')
+    ax[1, 1].set_title("Total Bookings by Hotel Type")
+
+
+    plt.tight_layout()
+
+    st.pyplot(fig)
+
+    plt.figure(figsize=(12, 6))
+    sns.countplot(data=d, x='market_segment', palette='Set3')
+    plt.title('Distribution of Market Segmentation')
+    plt.xlabel('Market Segment')
+    plt.ylabel('Count')
+    plt.xticks(rotation=45, ha='right')
+    plt.tight_layout()
     
-        plt.tight_layout()
+    st.pyplot()
     
-        st.pyplot(fig)
+    # create a count plot for distribution channels
+    plt.figure(figsize=(10, 6))
+    sns.countplot(data=d, x='distribution_channel', palette='Set2')
+    plt.title('Distribution of Distribution Channels')
+    plt.xlabel('Distribution Channel')
+    plt.ylabel('Count')
+    plt.tight_layout()
     
-        plt.figure(figsize=(12, 6))
-        sns.countplot(data=d, x='market_segment', palette='Set3')
-        plt.title('Distribution of Market Segmentation')
-        plt.xlabel('Market Segment')
-        plt.ylabel('Count')
-        plt.xticks(rotation=45, ha='right')
-        plt.tight_layout()
-        
-        st.pyplot()
-        
-        # create a count plot for distribution channels
-        plt.figure(figsize=(10, 6))
-        sns.countplot(data=d, x='distribution_channel', palette='Set2')
-        plt.title('Distribution of Distribution Channels')
-        plt.xlabel('Distribution Channel')
-        plt.ylabel('Count')
-        plt.tight_layout()
-        
-        st.pyplot()
+    st.pyplot()
         
 
 if __name__ == '__main__':