基于机器学习的IC电商数据挖掘-数据探索篇

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
     converters={"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_time        object
order_id          object
product_id        object
category_id       object
category_code     object
brand             object
price            float64
user_id           object
age                int64
sex               object
local             object
dtype: object

# 3、数据描述统计信息

df.describe()

# 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_time            0
order_id              0
product_id            0
category_id           0
category_code    129344
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_id      0
category_code    0
brand            0
price            0
user_id          0
age              0
sex              0
local            0
dtype: int64

df["event_time"][:5]   # 处理前

0    2020-04-24 11:50:39 UTC
1    2020-04-24 11:50:39 UTC
2    2020-04-24 14:37:43 UTC
3    2020-04-24 14:37:43 UTC
4    2020-04-24 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

fig = px.line(people_by_month,x="month",y="nunique")

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

fig.show()

fig = px.line(people_by_month,x="month",y="count")

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

fig.show()

amount_by_month  # 每月成交金额

order_by_month  # 每月订单数

amount_by_userid = pd.merge(amount_by_month,order_by_month)

amount_by_userid

amount_by_userid["average"] = amount_by_userid["price"] / amount_by_userid["order_id"]

amount_by_userid

fig = px.line(amount_by_userid,x="month",y="average")

fig.update_layout(height=500, width=1000, title_text="每月客单价")

fig.show()

product_by_order = df.groupby("order_id")["product_id"].count().reset_index().sort_values("product_id",ascending=False)

product_by_order.head(10)

fig = px.bar(product_by_order[:20],
             x="order_id",
             y="product_id",
             text="product_id"
            )

fig.show()

local = df.groupby("local").agg({"order_id":"nunique","user_id":"nunique","price":sum}).reset_index()
local.head()

df1 = local.sort_values("order_id",ascending=True)  # 订单量升序
df1

fig = px.pie(df1, names="local",labels="local",values="price")

fig.update_traces(
    textposition="inside",
    textinfo="percent+label"
)

fig.show()

fig = px.bar(df1,x="order_id",y="local",orientation="h")

fig.show()

# 整体的可视化效果

fig = px.scatter_3d(local,
              x="order_id",
              y="user_id",
              z="price",
              color="order_id",
              hover_name="local"
             )

fig.show()

local_brand = df.groupby(["local","brand"]).size().to_frame().reset_index()

local_brand.columns = ["local","brand","number"]  # 修改字段名

local_brand

# 根据local和number进行排序
local_brand.sort_values(["local","number"],ascending=[True,False],inplace=True,ignore_index=True)
local_brand = local_brand[local_brand["brand"] != "missing"]
# 每个local下面最受欢迎的前3个品牌
local_brand = local_brand.groupby("local").head(3)
local_brand

fig = px.bar(local_brand,
             x="brand",
             y="number",
             color="number",
             facet_col="local")

fig.update_layout(height=500,width=1000)

fig.show()

df.columns

Index(['event_time', 'order_id', 'product_id', 'category_id', 'category_code',
       'brand', 'price', 'user_id', 'age', 'sex', 'local', 'month', 'day',
       'dayofweek', 'hour'],
      dtype='object')

df2 = df.groupby("dayofweek")["order_id"].nunique().reset_index()
df2

plt.figure(figsize=(12,7))

df2["order_id"].plot.bar()

plt.xticks(range(7),['周一','周二','周三','周四','周五','周六','周日'],rotation=0)
plt.xlabel('星期')
plt.ylabel('订单量')
plt.title('订单数随星期变化')

plt.show()

df3 = df.groupby("hour")["order_id"].nunique().reset_index()
df3.head(10)

plt.figure(figsize=(14,8))
df3["order_id"].plot()

plt.xlabel('小时')
plt.ylabel('订单数量')
plt.title('订单随小时数变化')

plt.grid()
plt.show()

df4 = df.groupby("user_id").agg({"order_id":"nunique", "price":sum})

fig = px.scatter(df4,
                x="order_id",
                y="price",
                color="price",
                size="price")

fig.show()

# 用户消费周期

# shift函数：移动一个单位

purchase_time=df.groupby('user_id').apply(lambda x: x['event_time'] - x['event_time'].shift()).dt.days
purchase_time

user_id
1515915625439950000  96014      NaN
1515915625440030000  374760     NaN
                     484927    35.0
1515915625440050000  463812     NaN
                     473430     1.0
                               ...
1515915625514880000  564132     0.0
                     564143     0.0
                     564164     0.0
1515915625514890000  564158     NaN
                     564165     0.0
Name: event_time, Length: 564130, dtype: float64

purchase_time[purchase_time>0].describe()

count    120629.000000
mean         35.494500
std         663.803583
min           1.000000
25%           2.000000
50%           4.000000
75%          12.000000
max       18466.000000
Name: event_time, dtype: float64

pivoted_counts = df.pivot_table(index='user_id',
               columns='month',
               values='order_id',
               aggfunc='nunique').fillna(0)

pivoted_counts

pivoted_counts_map.sum() / pivoted_counts_map.count()

# 结果
month
1     0.406340
2     0.439655
3     0.474640
4     0.700328
5     0.829861
6     0.792990
7     0.891452
8     0.920328
9     0.781153
10    0.609963
11    0.419592
dtype: float64

(pivoted_counts_map.sum()/pivoted_counts_map.count()).plot(figsize=(12,6))

plt.xticks(range(11),columns_month)

plt.title('复购率')
plt.show()