머신러닝 기반 전자상거래 데이터 마이닝 |

import pandas as pd
import numpy as np

import time
import os
from datetime import datetime
import matplotlib.pyplot as plt
import seaborn as sns
%matplotlib inline
#设置中文编码和负号的正常显示
plt.rcParams['font.sans-serif']=['SimHei']
plt.rcParams['axes.unicode_minus']=False

import plotly_express as px
import plotly.graph_objects as go

import missingno as ms

from sklearn.cluster import KMeans
from sklearn.preprocessing import MinMaxScaler

df = pd.read_csv(
"ic_sale.csv",
 encoding="utf-8",# 指定编码
 cnotallow={"order_id":str,"product_id":str,"category_id":str,"user_id":str} # 指定字段类型
)
df.head()

# 1、数据shape

df.shape

(564169, 11)

# 2、数据字段类型

df.dtypes

event_timeobject
order_idobject
product_idobject
category_id object
category_code object
brand object
pricefloat64
user_id object
ageint64
sex object
local object
dtype: object

# 4、总共多少个不同客户

df["user_id"].nunique()

6908

# 5、总共多少个不同品牌

df["brand"].nunique()

868

# 6、总共多少个订单

df["order_id"].nunique()

234232

# 7、总共多少个产品

df["product_id"].nunique()

3756

df = df[df["price"] > 0]

df.isnull().sum()

event_time0
order_id0
product_id0
category_id 0
category_code129344
brand 27215
price 0
user_id 0
age 0
sex 0
local 0
dtype: int64

ms.bar(df,color="blue")# 缺失值可视化

plt.show()

df.fillna("missing",inplace=True)

df.isnull().sum()# 填充之后无缺失值

event_time 0
order_id 0
product_id 0
category_id0
category_code0
brand0
price0
user_id0
age0
sex0
local0
dtype: int64

df["event_time"][:5] # 处理前

02020-04-24 11:50:39 UTC
12020-04-24 11:50:39 UTC
22020-04-24 14:37:43 UTC
32020-04-24 14:37:43 UTC
42020-04-24 19:16:21 UTC
Name: event_time, dtype: object

# 去掉最后的UTC
df["event_time"] = df["event_time"].apply(lambda x: x[:19])

# 时间数据类型转化：字符类型---->指定时间格式

df['event_time'] = pd.to_datetime(df['event_time'], format="%Y-%m-%d %H:%M:%S")

# 提取多个时间相关字段

df['month']=df['event_time'].dt.month
df['day'] = df['event_time'].dt.day
df['dayofweek']=df['event_time'].dt.dayofweek
df['hour']=df['event_time'].dt.hour

df["event_time"][:5] # 处理后

0 2020-04-24 11:50:39
1 2020-04-24 11:50:39
2 2020-04-24 14:37:43
3 2020-04-24 14:37:43
4 2020-04-24 19:16:21
Name: event_time, dtype: datetime64[ns]

amount_by_month = df.groupby("month")["price"].sum().reset_index()
amount_by_month

fig = px.scatter(amount_by_month,x="month",y="price",size="price",color="price")

fig.update_layout(height=500, width=1000, title_text="每月成交金额")

fig.show()

order_by_month = df.groupby("month")["order_id"].nunique().reset_index()
order_by_month

fig = px.line(order_by_month,x="month",y="order_id")

fig.update_layout(height=500, width=1000, title_text="每月成交订单量")

fig.show()

# nunique：对每个user_id进行去重：消费人数
# count：统计user_id 的次数；消费人次（存在一人多次购买）

people_by_month = df.groupby("month")["user_id"].agg(["nunique","count"]).reset_index()
people_by_month