Update pages/1_Data_Card_and_Data_collection.py

pages/1_Data_Card_and_Data_collection.py

@@ -51,23 +51,44 @@ if df is not None:
     st.subheader("Dataset Shape (Rows, Columns):")
     st.write(df.shape)
 
-    st.markdown('''
-    # About the Dataset
-    ## Description:
-    This dataset provides insights into consumer electronics sales, featuring product categories, brands, prices, customer demographics, purchase behavior, and satisfaction metrics. It aims to analyze factors influencing purchase intent and customer satisfaction in the consumer electronics market.
-    ## Features:
-    - **ProductID**: Unique identifier for each product.
-    - **ProductCategory**: Category of the consumer electronics product (e.g., Smartphones, Laptops).
-    - **ProductBrand**: Brand of the product (e.g., Apple, Samsung).
-    - **ProductPrice**: Price of the product ($).
-    - **CustomerAge**: Age of the customer.
-    - **CustomerGender**: Gender of the customer (0 - Male, 1 - Female).
-    - **PurchaseFrequency**: Average number of purchases per year.
-    - **CustomerSatisfaction**: Customer satisfaction rating (1 - 5).
-    - **PurchaseIntent** (Target Variable): Intent to purchase.
-    ## Conclusion:
-    This dataset facilitates analysis on consumer behavior and purchase patterns in the consumer electronics sector, providing valuable insights into market dynamics and customer preferences.
-    ''')
+    st.markdown('''**Dataset :**
+
+| **Feature**              | **Description**                                                    | **Example**                  |
+|-------------------------|--------------------------------------------------------------------|------------------------------|
+| **ProductID**            | Unique identifier for each product.                                | 12345                        |
+| **ProductCategory**      | Category of the consumer electronics product.                      | Smartphones, Laptops         |
+| **ProductBrand**         | Brand of the product.                                              | Apple, Samsung               |
+| **ProductPrice**         | Price of the product (in dollars).                                 | 999.99                       |
+| **CustomerAge**          | Age of the customer.                                               | 35                           |
+| **CustomerGender**       | Gender of the customer (0 - Male, 1 - Female).                     | 1                            |
+| **PurchaseFrequency**    | Average number of purchases per year.                              | 3                            |
+| **CustomerSatisfaction** | Customer satisfaction rating (1 - 5).                              | 4                            |
+| **PurchaseIntent**       | Target variable: Intent to purchase (classification target).       | 0 (No), 1 (Yes)              |
+''')
+
+    st.markdown("### Import Necessary Libraries:")
+    st.code("""
+    import numpy as np
+    import pandas as pd
+    import matplotlib.pyplot as plt
+    import seaborn as sns
+    import plotly.express as px
+    import warnings
+    warnings.filterwarnings('ignore')
+    
+    from sklearn.linear_model import LogisticRegression
+    from sklearn.neighbors import KNeighborsClassifier
+    from sklearn.model_selection import train_test_split, cross_val_score
+    from sklearn.preprocessing import StandardScaler, LabelEncoder
+    from sklearn.metrics import accuracy_score, classification_report, confusion_matrix, log_loss
+    
+    import optuna
+    import imblearn
+    from imblearn.under_sampling import RandomUnderSampler
+    from imblearn.over_sampling import RandomOverSampler, SMOTE
+    
+    import pickle
+    """, language="python")
 
 else:
     st.info("No dataset found. Please upload a CSV file.")