基于Python 实现亚马逊销售数据可视化

python 复制代码

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
from sklearn.preprocessing import LabelEncoder
from sklearn.neighbors import KNeighborsRegressor
from sklearn.metrics import mean_squared_error, r2_score
from sklearn.linear_model import LinearRegression
import xgboost as xgb
from tabulate import tabulate

# 显示设置
sns.set(style='whitegrid', palette='muted', color_codes=True)

# 预测建模
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LogisticRegression
from sklearn.metrics import accuracy_score, confusion_matrix, classification_report, roc_curve, auc
from sklearn.ensemble import RandomForestClassifier
from sklearn.inspection import permutation_importance

# 随机安装/随机固定
import random
random.seed(42)
np.random.seed(42)

# 随机性的确定性、统计学知识及警告信息
import scipy.stats as stats
import warnings
warnings.filterwarnings('ignore')

python 复制代码

df = pd.read_csv("/Amazon.csv")
df.head()

|---|------------|------------|------------|---------------|-----------|---------------------|-----------------|------------|----------|-----------|----------|-------|--------------|-------------|------------------|-------------|-------------|-------|---------------|-----------|
| | OrderID | OrderDate | CustomerID | CustomerName | ProductID | ProductName | Category | Brand | Quantity | UnitPrice | Discount | Tax | ShippingCost | TotalAmount | PaymentMethod | OrderStatus | City | State | Country | SellerID |
| 0 | ORD0000001 | 2023-01-31 | CUST001504 | Vihaan Sharma | P00014 | Drone Mini | Books | BrightLux | 3 | 106.59 | 0.00 | 0.00 | 0.09 | 319.86 | Debit Card | Delivered | Washington | DC | India | SELL01967 |
| 1 | ORD0000002 | 2023-12-30 | CUST000178 | Pooja Kumar | P00040 | Microphone | Home & Kitchen | UrbanStyle | 1 | 251.37 | 0.05 | 19.10 | 1.74 | 259.64 | Amazon Pay | Delivered | Fort Worth | TX | United States | SELL01298 |
| 2 | ORD0000003 | 2022-05-10 | CUST047516 | Sneha Singh | P00044 | Power Bank 20000mAh | Clothing | UrbanStyle | 3 | 35.03 | 0.10 | 7.57 | 5.91 | 108.06 | Debit Card | Delivered | Austin | TX | United States | SELL00908 |
| 3 | ORD0000004 | 2023-07-18 | CUST030059 | Vihaan Reddy | P00041 | Webcam Full HD | Home & Kitchen | Zenith | 5 | 33.58 | 0.15 | 11.42 | 5.53 | 159.66 | Cash on Delivery | Delivered | Charlotte | NC | India | SELL01164 |
| 4 | ORD0000005 | 2023-02-04 | CUST048677 | Aditya Kapoor | P00029 | T-Shirt | Clothing | KiddoFun | 2 | 515.64 | 0.25 | 38.67 | 9.23 | 821.36 | Credit Card | Cancelled | San Antonio | TX | Canada | SELL01411 |

python 复制代码

df.tail()

|-------|------------|------------|------------|---------------|-----------|-------------------|--------------------|-----------|----------|-----------|----------|--------|--------------|-------------|------------------|-------------|--------------|-------|---------------|-----------|
| | OrderID | OrderDate | CustomerID | CustomerName | ProductID | ProductName | Category | Brand | Quantity | UnitPrice | Discount | Tax | ShippingCost | TotalAmount | PaymentMethod | OrderStatus | City | State | Country | SellerID |
| 99995 | ORD0099996 | 2023-03-07 | CUST001356 | Karan Joshi | P00047 | Memory Card 128GB | Electronics | Apex | 2 | 492.34 | 0.00 | 78.77 | 2.75 | 1066.20 | UPI | Delivered | Jacksonville | FL | India | SELL00041 |
| 99996 | ORD0099997 | 2021-11-24 | CUST031254 | Sunita Kapoor | P00046 | Car Charger | Sports & Outdoors | Apex | 5 | 449.30 | 0.00 | 179.72 | 6.07 | 2432.29 | Credit Card | Delivered | San Jose | CA | United States | SELL01449 |
| 99997 | ORD0099998 | 2023-04-29 | CUST012579 | Aman Gupta | P00030 | Dress Shirt | Sports & Outdoors | BrightLux | 4 | 232.40 | 0.00 | 74.37 | 12.43 | 1016.40 | Cash on Delivery | Delivered | Indianapolis | IN | United States | SELL00028 |
| 99998 | ORD0099999 | 2021-11-01 | CUST026243 | Simran Gupta | P00046 | Car Charger | Sports & Outdoors | HomeEase | 1 | 294.05 | 0.00 | 23.52 | 13.09 | 330.66 | Debit Card | Delivered | Charlotte | NC | United States | SELL00324 |
| 99999 | ORD0100000 | 2021-12-04 | CUST029492 | Sunita Reddy | P00019 | LED Desk Lamp | Home & Kitchen | CoreTech | 5 | 166.70 | 0.05 | 63.35 | 3.34 | 858.52 | Debit Card | Delivered | New York | NY | United States | SELL00761 |

python 复制代码

df.describe()

|-------|---------------|---------------|---------------|---------------|---------------|---------------|
| | Quantity | UnitPrice | Discount | Tax | ShippingCost | TotalAmount |
| count | 100000.000000 | 100000.000000 | 100000.000000 | 100000.000000 | 100000.000000 | 100000.000000 |
| mean | 3.001400 | 302.905748 | 0.074226 | 68.468902 | 7.406660 | 918.256479 |
| std | 1.413548 | 171.840797 | 0.082583 | 74.131180 | 4.324057 | 724.508332 |
| min | 1.000000 | 5.000000 | 0.000000 | 0.000000 | 0.000000 | 4.270000 |
| 25% | 2.000000 | 154.190000 | 0.000000 | 15.920000 | 3.680000 | 340.890000 |
| 50% | 3.000000 | 303.070000 | 0.050000 | 45.250000 | 7.300000 | 714.315000 |
| 75% | 4.000000 | 451.500000 | 0.100000 | 96.060000 | 11.150000 | 1349.765000 |
| max | 5.000000 | 599.990000 | 0.300000 | 538.460000 | 15.000000 | 3534.980000 |

python 复制代码

plt.figure(figsize=(10,6))
sns.heatmap(df.corr(numeric_only=True), annot=True, cmap="coolwarm", fmt=".2f")
plt.title("Correlation Heatmap")
plt.show()

python 复制代码

plt.figure(figsize=(10,6))
sns.heatmap(df.isnull(), cbar=False, cmap="viridis")
plt.title("Missing Values Heatmap")
plt.show()

python 复制代码

numeric_cols = df.select_dtypes(include=['number']).columns

# رسم التوزيع لكل عمود رقمي
for col in numeric_cols:
    sns.histplot(x=col, data=df, kde=True)
    plt.show()

python 复制代码

for col in df:
    if df[col].dtype == 'O':
        sns.countplot(x=col,data=df)
        plt.show()