├── README.md
└── data_visualization
    └── datavisualization.py


/README.md:
--------------------------------------------------------------------------------
1 | # Amazon_shipment


--------------------------------------------------------------------------------
/data_visualization/datavisualization.py:
--------------------------------------------------------------------------------
 1 | import numpy as np
 2 | import pandas as pd
 3 | import matplotlib.pyplot as plt
 4 | import seaborn as sb
 5 | 
 6 | df=pd.read_csv("C:/Users/yvsya/OneDrive/Desktop/amazon_product_shipment_dataset.csv")
 7 | df
 8 | 
 9 | 
10 | print(df.info())
11 | print(df.describe())
12 | 
13 | df['Mode_of_Shipment'].fillna(df['Mode_of_Shipment'].mode().iloc[0],inplace=True)
14 | df['Cost_of_the_Product'].fillna(df['Cost_of_the_Product'].mean(),inplace=True)
15 | df['Prior_purchases'].fillna(df['Prior_purchases'].mean(),inplace=True)
16 | df['Product_importance'].fillna(df['Product_importance'].mode().iloc[0],inplace=True)
17 | df['Gender'].fillna(df['Gender'].mode().iloc[0],inplace=True)
18 | df['Discount_offered'].fillna(df['Discount_offered'].mean(),inplace=True)
19 | print(df.info())
20 | 
21 | #1. Histograms
22 | plt.figure(figsize=(12, 5))
23 | sb.histplot(df['Cost_of_the_Product'],bins=30,kde=True, color='skyblue')
24 | plt.title('Cost of the Product')
25 | plt.xlabel('Cost')
26 | plt.ylabel('Frequency')
27 | plt.show()
28 | 
29 | #2. Pie chart for shipment mode
30 | shipment_counts = df['Mode_of_Shipment'].value_counts()
31 | plt.figure(figsize=(6, 6))
32 | plt.pie(shipment_counts, labels=shipment_counts.index, autopct='%1.1f%%', startangle=140)
33 | plt.title('Shipment Mode Distribution')
34 | plt.axis('equal')
35 | plt.show()
36 | 
37 | #3. Bar plot of product importance
38 | sb.countplot(data=df, x='Product_importance', palette='Set2')
39 | plt.title('Product Importance Levels')
40 | plt.xlabel('Importance Level')
41 | plt.ylabel('Count')
42 | plt.show()
43 | 
44 | #4. Countplot of delivery status by mode of shipment
45 | sb.countplot(data=df, x='Mode_of_Shipment', hue='Reached.on.Time_Y.N', palette='Set1')
46 | plt.title('Delivery Status by Shipment Mode')
47 | plt.xlabel('Mode of Shipment')
48 | plt.ylabel('Count')
49 | plt.legend(title='Reached On Time (1=Yes)')
50 | plt.show()
51 | 
52 | #5. Boxplot: weight vs delivery status
53 | sb.boxplot(data=df, x='Reached.on.Time_Y.N', y='Weight_in_gms')
54 | plt.title('Weight of Shipment vs Delivery Status')
55 | plt.xlabel('Reached on Time (1=Yes)')
56 | plt.ylabel('Weight (grams)')
57 | plt.show()
58 | 
59 | #6. Histogram for discount
60 | plt.figure(figsize=(8, 4))
61 | sb.histplot(df['Discount_offered'],bins=30,kde=True, color='orange')
62 | plt.title('Distribution of Discounts Offered')
63 | plt.xlabel('Discount Offered')
64 | plt.ylabel('Frequency')
65 | plt.show()
66 | 
67 | #7. Correlation heatmap
68 | plt.figure(figsize=(10, 6))
69 | sb.heatmap(df.corr(numeric_only=True), annot=True, cmap='coolwarm', linewidths=0.5)
70 | plt.title('Correlation Heatmap')
71 | plt.show()
72 | 


--------------------------------------------------------------------------------