Update pages/3_EDA_and_Feature_Engineering.py

pages/3_EDA_and_Feature_Engineering.py

@@ -2,8 +2,6 @@ import streamlit as st
 import pandas as pd
 import seaborn as sns
 import matplotlib.pyplot as plt
-import matplotlib.patches as mpatches
-import plotly.express as px
 from sklearn.preprocessing import LabelEncoder
 
 st.title("Exploratory Data Analysis (EDA)")
@@ -24,170 +22,159 @@ if 'df' in st.session_state:
 
     st.markdown("Complete EDA + Feature Engineering")
     st.markdown("## **Univariate Analysis**")
+
     st.markdown("### PRODUCT CATEGORY")
-    plt.figure(figsize=(10, 6))
-    sns.countplot(x='Category', data=df, palette='viridis')
-    plt.title("Product Category Distribution")
-    plt.xlabel("Product Category")
-    plt.ylabel("Count")
-    plt.xticks(rotation=45)
-    plt.show()
-    st.markdown('''**Insights :**
-    - We've 5 Product Categories:
-    1. Smart Phones & Laptops are the most highest and similar in frequency,
-    2. Followed by Smart Watches,
-    3. Tablets and Headphones are little less in frequency overall.''')
-    
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.countplot(x='Category', data=df, palette='viridis', ax=ax)
+    ax.set_title("Product Category Distribution")
+    ax.set_xlabel("Product Category")
+    ax.set_ylabel("Count")
+    ax.tick_params(axis='x', rotation=45)
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - 5 product categories observed.
+    - Highest frequency: Smart Phones and Laptops.
+    - Lowest frequency: Tablets and Headphones.
+    """)
+
     st.markdown("### BRANDS")
-    plt.figure(figsize=(10, 6))
-    sns.countplot(x='Brand', data=df, palette='cubehelix')
-    plt.title("Product Brand Distribution")
-    plt.xlabel("Product Brand")
-    plt.ylabel("Count")
-    plt.xticks(rotation=45)
-    plt.show()
-    st.markdown('''**Insights :**
-    - We've 5 Brand Categories:
-    1. Samsung & HP are the most highest and similar in frequency,
-    2. Followed by Sony, Apple, and other brands.''')
-    
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.countplot(x='Brand', data=df, palette='cubehelix', ax=ax)
+    ax.set_title("Product Brand Distribution")
+    ax.set_xlabel("Product Brand")
+    ax.set_ylabel("Count")
+    ax.tick_params(axis='x', rotation=45)
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Samsung and HP have the highest frequencies.
+    - Sony, Apple, and other brands follow behind.
+    """)
+
     st.markdown("### PRICE DISTRIBUTION")
-    plt.figure(figsize=(10, 6))
-    sns.histplot(df['Price'], kde=True, color='orange')  # 'orange' mimics Agsunset
-    plt.title("Product Price Distribution")
-    plt.xlabel("Product Price")
-    plt.ylabel("Count")
-    plt.show()
-    st.markdown('''**Insights :**
-    - **Wide Range:** The products span a considerable price range (from near 0 to 3000).
-    - **Concentration:** There's a noticeable concentration of products priced between roughly 200 and 2500.
-    - **Roughly Uniform:** The distribution appears somewhat uniform with some peaks and valleys. This indicates there isn't a single dominant price point, and products are fairly evenly distributed across the price range (with some exceptions).''')
-
-    st.markdown("### PRODUCT PRICE BINING")
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.histplot(df['Price'], kde=True, color='orange', ax=ax)
+    ax.set_title("Product Price Distribution")
+    ax.set_xlabel("Product Price")
+    ax.set_ylabel("Count")
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Products span a wide price range, from near 0 to 3000.
+    - Significant concentration between 200 and 2500.
+    """)
+
+    st.markdown("### PRODUCT PRICE BINNING")
     df['ProductPriceBucket'] = pd.cut(df['Price'], bins=[100, 500, 1000, 1500, 2000, 3000], labels=['Very Low', 'Low', 'Medium', 'High', 'Very High'])
-    plt.figure(figsize=(10, 6))
-    sns.countplot(x='ProductPriceBucket', data=df, palette='icefire')
-    plt.title("Product Price Distribution")
-    plt.xlabel("Product Price Bucket")
-    plt.ylabel("Count")
-    plt.xticks(rotation=45)
-    plt.show()
-    st.markdown('''**Insights :**
-    - **Uneven Distribution:** The most striking observation is that the distribution is not even across the price buckets. This suggests that certain price ranges are more common or more popular than others.
-    - **"Very High" Dominance:** The "Very High" price bucket has the highest concentration of products. This indicates that a significant portion of your products fall into this top-tier price range. This could mean you have a focus on premium items, or it might reflect a pricing strategy that emphasizes higher-priced goods.
-    - **Lower Representation in "Very Low":** The "Very Low" bucket has the fewest products. This could indicate a limited number of budget or entry-level items in your product catalog.
-    - **Similar Counts in "Low", "Medium", and "High":** The counts for "Low", "Medium", and "High" appear relatively similar. This suggests a moderate and somewhat consistent distribution of products across these mid-range price points.''')
-
-    st.markdown("### AGE DISTRIBUTION")
-    st.markdown("### AGE BINNING")
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.countplot(x='ProductPriceBucket', data=df, palette='icefire', ax=ax)
+    ax.set_title("Product Price Distribution")
+    ax.set_xlabel("Product Price Bucket")
+    ax.set_ylabel("Count")
+    ax.tick_params(axis='x', rotation=45)
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - "Very High" price bucket has the highest concentration.
+    - Fewer products in the "Very Low" bucket.
+    - "Low", "Medium", and "High" have moderate distribution.
+    """)
+
+    st.markdown("### AGE DISTRIBUTION AND BINNING")
     df['CustomerAgeGroup'] = pd.qcut(df['CustomerAge'], q=4, labels=['Young', 'Middle-aged', 'Mature', 'Senior'])
     fig, axs = plt.subplots(1, 2, figsize=(15, 6))
-    
-    # First plot with a new palette
-    sns.countplot(x='CustomerAgeGroup', data=df, ax=axs[0], palette='magma')  # 'magma' palette for a different feel
+
+    sns.countplot(x='CustomerAgeGroup', data=df, ax=axs[0], palette='magma')
     axs[0].set_title("Customer Age Group Distribution")
     axs[0].set_xlabel("Customer Age Group")
-    
-    # Second plot with a new color
-    sns.histplot(df['CustomerAge'], kde=True, ax=axs[1], color='teal')  # 'teal' for a distinct color in the second plot
+
+    sns.histplot(df['CustomerAge'], kde=True, ax=axs[1], color='teal')
     axs[1].set_title("Customer Age Distribution")
     axs[1].set_xlabel("Customer Age")
-    
-    # Adjust layout for better spacing
+
     plt.tight_layout()
-    plt.show()
-    st.markdown('''**Insights :**
-    - **Relatively Even Distribution:** The most prominent feature is the relatively even distribution of customers across all four age groups. The bars are of similar height, indicating that each age group represents a comparable portion of the customer base.
-    - **Slight Variation:** While generally even, there are slight variations:
-      - **Young:** Appears to have a marginally higher count than the others.
-      - **Senior:** Has a slightly lower count compared to "Young" but is very close to "Mature" and "Middle-aged."
-    - **No Dominant Age Group:** There's no single dominant age group that significantly outweighs the others. This suggests a broad appeal across different age demographics.''')
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Age groups are relatively evenly distributed.
+    - Slightly higher representation for "Young".
+    """)
 
     st.markdown("### GENDER DISTRIBUTION")
-    print(df['CustomerGender'].value_counts())
-    plt.figure(figsize=(10, 8))
+    fig, ax = plt.subplots(figsize=(10, 8))
     df['CustomerGender'].value_counts().plot(kind='pie',
-                                              colors=['lightblue', 'lightpink'],
-                                              autopct='%1.1f%%',  # Shows percentage on pie chart
-                                              startangle=90,      # Start the pie chart at a specific angle
-                                              wedgeprops={'edgecolor': 'black'})  # Adds borders to the slices
-    
-    plt.title("Customer Gender Distribution")
-    plt.legend(labels=['Female', 'Male'], loc='upper left', fontsize=12, title="Customer Gender")
-    
-    plt.show()
-    st.markdown('''**Insights :** Almost same proportion for both the genders
-    - Male (49.1%)
-    - Female (50.9%)''')
+                                             colors=['lightblue', 'lightpink'],
+                                             autopct='%1.1f%%',
+                                             startangle=90,
+                                             wedgeprops={'edgecolor': 'black'},
+                                             ax=ax)
+    ax.set_title("Customer Gender Distribution")
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Gender distribution is almost equal.
+    - Female: 50.9%, Male: 49.1%.
+    """)
 
     st.markdown("### PURCHASE FREQUENCY DISTRIBUTION")
-    plt.figure(figsize=(10, 6))
-    sns.histplot(df['PurchaseFrequency'], kde=True, color='purple', bins=30)
-    plt.title("Purchase Frequency Distribution")
-    plt.xlabel("Purchase Frequency")
-    plt.ylabel("Count")
-    plt.show()
-    st.markdown('''**Insights :**
-    - The Range is 1 - 19''')
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.histplot(df['PurchaseFrequency'], kde=True, color='purple', bins=30, ax=ax)
+    ax.set_title("Purchase Frequency Distribution")
+    ax.set_xlabel("Purchase Frequency")
+    ax.set_ylabel("Count")
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Purchase frequencies range from 1 to 19.
+    """)
 
     st.markdown("### CUSTOMER SATISFACTION DISTRIBUTION")
-    plt.figure(figsize=(10, 6))
-    sns.histplot(df['CustomerSatisfaction'], kde=True, color=sns.color_palette("crest", n_colors=1)[0])  # Use the first color from the palette
-    plt.title("Customer Satisfaction Distribution")
-    plt.xlabel("Customer Satisfaction")
-    plt.ylabel("Count")
-    plt.show()
-    st.markdown('''**Insights :**
-    - **Multimodal Distribution:** The most striking aspect is the multimodal nature of the distribution. There are distinct peaks around the integer values (1, 2, 3, 4, 5). This suggests that customers tend to provide whole-number ratings rather than choosing intermediate values.
-    - **Relatively Uniform Peaks:** The peaks seem relatively uniform in height, indicating a somewhat even distribution of satisfaction levels across the rating scale. This might imply that there isn't a strong concentration of extremely satisfied or dissatisfied customers.''')
+    fig, ax = plt.subplots(figsize=(10, 6))
+    sns.histplot(df['CustomerSatisfaction'], kde=True, color=sns.color_palette("crest", n_colors=1)[0], ax=ax)
+    ax.set_title("Customer Satisfaction Distribution")
+    ax.set_xlabel("Customer Satisfaction")
+    ax.set_ylabel("Count")
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Distinct peaks around integer values (1-5).
+    - Indicates customers tend to provide whole-number ratings.
+    """)
 
     st.markdown("### PURCHASE INTENT DISTRIBUTION")
+    fig, ax = plt.subplots(figsize=(8, 6))
     purchase_intent_counts = df['PurchaseIntent'].value_counts()
-    plt.figure(figsize=(8, 6))
-    wedges, texts, autotexts = plt.pie(purchase_intent_counts,
-                                       labels=purchase_intent_counts.index,
-                                       colors=sns.color_palette("coolwarm", n_colors=len(purchase_intent_counts)),
-                                       autopct='%1.1f%%',
-                                       startangle=90,
-                                       wedgeprops={'edgecolor': 'black'})
-    plt.legend(wedges, purchase_intent_counts.index, title="Purchase Intent", loc="center left", bbox_to_anchor=(1, 0, 0.5, 1))
-    plt.title("Purchase Intent Distribution")
-    plt.show()
-    
-    st.markdown('''**Insights :**
-    \n- We've 0 and 1 which means Not Purchase and Purchase.
-    
-    \n- A binary classification problem.
-    
-    \n- 0: Not Purchase --> 43.4%
-    
-    \n- 1: Purchase --> 56.6%''')
-
-    st.markdown("## **Bivariate Analysis**")
-    st.markdown("### Price vs. Customer Age Group")
-    plt.figure(figsize=(10, 6))
-    sns.boxplot(x='CustomerAgeGroup', y='Price', data=df, palette='Set2')
-    plt.title("Price Distribution by Customer Age Group")
-    plt.xlabel("Customer Age Group")
-    plt.ylabel("Price")
-    plt.show()
-    st.markdown('''**Insights :**
-    - **Wide Price Range Across Groups:** All customer age groups seem to span the full range of product prices, indicating that no specific age group is restricted to a certain price range.
-    - **Higher Price for Mature and Senior:** There appears to be a slightly higher concentration of products with higher prices in the "Mature" and "Senior" age groups.
-    - **Middle-aged Customers:** Middle-aged customers tend to purchase more moderately priced products.''')
-
-    # Apply Label Encoding for categorical columns
+    ax.pie(purchase_intent_counts,
+           labels=purchase_intent_counts.index,
+           colors=sns.color_palette("coolwarm", n_colors=len(purchase_intent_counts)),
+           autopct='%1.1f%%',
+           startangle=90,
+           wedgeprops={'edgecolor': 'black'})
+    ax.set_title("Purchase Intent Distribution")
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Binary classification problem (0: Not Purchase, 1: Purchase).
+    - 56.6% intent to purchase, 43.4% do not.
+    """)
+
+    st.markdown("### CORRELATION HEATMAP")
     label_encoder = LabelEncoder()
     df['CustomerGender'] = label_encoder.fit_transform(df['CustomerGender'])
     df['Brand'] = label_encoder.fit_transform(df['Brand'])
     df['Category'] = label_encoder.fit_transform(df['Category'])
 
-    st.markdown("### Correlation Heatmap")
     corr_matrix = df.corr()
-    plt.figure(figsize=(12, 8))
-    sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5)
-    plt.title("Correlation Heatmap")
-    plt.show()
+    fig, ax = plt.subplots(figsize=(12, 8))
+    sns.heatmap(corr_matrix, annot=True, cmap='coolwarm', fmt='.2f', linewidths=0.5, ax=ax)
+    ax.set_title("Correlation Heatmap")
+    st.pyplot(fig)
+    st.markdown("""
+    **Insights:**
+    - Strong correlations can be observed between certain variables.
+    - Customer Satisfaction and Purchase Intent might have meaningful relationships.
+    """)
 
 else:
     st.write("Please upload your data.")