电商用户行为可视化分析

最新推荐文章于 2024-11-21 17:37:46 发布

原创最新推荐文章于 2024-11-21 17:37:46 发布

· 458 阅读

5 ·

版权

文章标签：

#python #开发语言

数据分析专栏收录该内容

14 篇文章

订阅专栏

1、导包

import pandas as pd
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import pyecharts.options as opts
from pyecharts.charts import Line
from pyecharts.charts import Grid

2、导数据

t_f_user = pd.read_csv("tianchi_fresh_comp_train_user.csv")

tianchi_fresh_comp_train_user_2w，包含如下字段：

字段字段说明提取说明

user_id 用户标识抽样&字段脱敏

item_id 商品标识字段脱敏

behavior_type 用户对商品的行为类型包括浏览、收藏、加购物车、购买，对应取值分别是1、2、3、4。

user_geohash 用户位置的空间标识，可以为空由经纬度通过保密的算法生成

item_category 商品分类标识字段脱敏

time 行为时间精确到小时级别

3、数据探索

t_f_user.shape

(23291027, 6)

t_f_user.info()

t_f_user.describe()

查看缺失值

t_f_user.isnull().sum()

查看重复值

t_f_user.duplicated().sum()

4、数据预处理

去重

t_f_user.drop_duplicates(keep="last",inplace=True)

转换时间类型

t_f_user["time"] = pd.to_datetime(t_f_user["time"],errors="coerce")

5、统计每日PV和UV数据

t_f_user["date_time"] =t_f_user["time"].dt.date


pv_day = t_f_user[t_f_user["behavior_type"]==1].groupby(["date_time"])["behavior_type"].count()



uv_day = t_f_user[t_f_user["behavior_type"]==1].drop_duplicates(subset=["user_id","date_time"]).groupby("date_time")["user_id"].count()

attr = list(pv_day.index)

pv = (

    Line(
        init_opts=opts.InitOpts(
            width="1000px",
            height = "500px"
         )
    )
    .add_xaxis(
        xaxis_data=attr
    
    )
    
    .add_yaxis(
        "pv",
        np.around(pv_day.values/10000,decimals=2),
        label_opts=opts.LabelOpts(is_show=False)
    
    )
    .add_yaxis(
        series_name="uv",
        yaxis_index=1,
        y_axis = np.around(uv_day.values / 10000,decimals=2),
        label_opts= opts.LabelOpts(is_show=False)
    
    )
    
    .extend_axis(
        yaxis=opts.AxisOpts(
            name ="uv",
            type_="value",
            min_=0,
            max_=1.6,
            interval=0.4,
            axislabel_opts=opts.LabelOpts(formatter="{value}万人")
        
        )
    
    )
    
    .set_global_opts(
        tooltip_opts=opts.TooltipOpts(
            is_show=True,
            trigger="axis",
            axis_pointer_type="cross"
        
        ),
        xaxis_opts= opts.AxisOpts(
            type_="category",
            axispointer_opts=opts.AxisPointerOpts(
                is_show = True,
                   type_ = "shadow"
            )
        ),
        yaxis_opts=opts.AxisOpts(
            name="pv",
            type_="value",
            min_ =0,
            max_ = 100,
            interval=20,
            axislabel_opts= opts.LabelOpts(formatter="{value}万次"),
            axistick_opts=opts.AxisTickOpts(is_show=True),
            splitline_opts=opts.SplitLineOpts(is_show=True)
        
        ),
       title_opts = opts.TitleOpts(title="PV与UV趋势图")
     
    )

)
pv.render_notebook()

通过 PV、UV趋势图可以发现在双十二期间PV量和 UV量都有了明显的提升，并在12月12日达到顶峰。非活动期间 PV和UV 每天波动性都不是很大，其中 PV 值在42万上下小幅度波动，UV值在1.2万上下小幅度波动

6、pv、uv日差异分析

pv_uv_diff = pd.concat([pv_day,uv_day],join="outer",axis=1)
pv_uv_diff.columns=["pv_diff","uv_diff"]
pv_uv_diff = pv_uv_diff.diff()


attr = pv_uv_diff.index

pv = pv_uv_diff["pv_diff"]
uv = pv_uv_diff["uv_diff"]

diff =(
    Line(
        init_opts=opts.InitOpts(
            width="1000px",
            height="500px"
        )
    )
    .add_xaxis(xaxis_data=attr)
    .add_yaxis(
        "新增PPV",
        pv,
        label_opts=opts.LabelOpts(is_show=False)
    )
    .extend_axis(
        yaxis=opts.AxisOpts(
            name="新增UV",
            type_ = "value",
            min_ = -2000,
            max_ = 1600,
            axislabel_opts=opts.LabelOpts(formatter="{value}")
        
        )
    
    )
    .set_global_opts(
        tooltip_opts=opts.TooltipOpts(
            is_show=True,
            trigger="axis",
            axis_pointer_type="cross"
        ),
        xaxis_opts=opts.AxisOpts(
            type_="category",
            axispointer_opts=opts.AxisPointerOpts(is_show=True, type_="shadow"),
        ),
        yaxis_opts=opts.AxisOpts(
            name="新增PV",
            type_="value",
            min_=-350000,
            max_=250000,
            interval=100000,
            axislabel_opts=opts.LabelOpts(formatter="{value}"),
            axistick_opts=opts.AxisTickOpts(is_show=True),
            splitline_opts=opts.SplitLineOpts(is_show=True),
            
        ),
        
        title_opts = opts.TitleOpts(title="pv、uv日差异分析")
    )

)
diff2 =(
    Line()
    .add_xaxis(xaxis_data=attr)
    .add_yaxis(
        "新增uv",
        uv ,
        yaxis_index='1',
        label_opts=opts.LabelOpts(is_show=False)
    )
)
t =diff.overlap(diff2)
t.render_notebook()

7、不同时期用户行为分析

collect = t_f_user[t_f_user["behavior_type"]==2].groupby("date_time")["behavior_type"].count()
shapping_cart = t_f_user[t_f_user["behavior_type"]==3].groupby("date_time")["behavior_type"].count()
buy = t_f_user[t_f_user["behavior_type"]==4].groupby("date_time")["behavior_type"].count()

sns.set()
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
fig = plt.figure(figsize=(10,5))
ax=plt.subplot()
plt.plot(collect.index,collect.values,color="g",marker="^")
plt.plot(shapping_cart.index,shapping_cart.values,color="r",marker="^")
plt.plot(buy.index,buy.values,color="b",marker="^")
plt.legend(["收藏","添加购物车","购买"])
plt.title("不同时期用户行为分析")
plt.yticks([i for i in range(0,50001,10000)])
plt.xticks(collect.index,rotation=90)
ax.spines["top"].set_visible(False)
ax.spines["right"].set_visible(False)

plt.ylabel("人数")
plt.show()

8、不同时期的转化率

pv_day = t_f_user[t_f_user["behavior_type"]==1].groupby(["date_time"])["behavior_type"].count()

buy_day = t_f_user[t_f_user["behavior_type"]==4].groupby(["date_time"])["behavior_type"].count()



rate  = np.around(buy_day.values /  pv_day.values,3)
attr = buy_day.index

b_rate =(
    Line()
    .add_xaxis(xaxis_data=buy_day.index.to_list())
    .add_yaxis(
        series_name= "转化率",
       y_axis=rate
    )
     .set_global_opts(title_opts=opts.TitleOpts(title="不同时期的转化率"))
)

b_rate.render_notebook()

seaborn 绘图

rate  = np.around(buy_day /  pv_day,3).reset_index()
sns.set()
fig = plt.figure(figsize=(10,5))
plt.rcParams['font.sans-serif'] = ['Microsoft YaHei']
sns.lineplot(data = rate,x="date_time",y="behavior_type",markers="o")
plt.xlabel("日期")
plt.ylabel("转化率")
plt.title("不同时期转化率")
plt.xticks(rate["date_time"],rotation=90)
plt.show()

9、选取活动数据子集和日常数据子集

由于数据里面包含双十二大促的数据，因此整理分析用户的不同时段行为可能会导致分析结果与实际差异较大，因此拆分开来做不同的对比分析

active_data=t_f_user[t_f_user["date_time"].isin(["2014/12/11","2014/12/12","2014/12/13"])]
daily_data =t_f_user[~t_f_user["date_time"].isin(["2014/12/11","2014/12/12","2014/12/13"])]

双十二期间不同时段的用户行为分析

t_f_user["hour"] = t_f_user["time"].dt.hour 


active_collect_hour = active_data[active_data["behavior_type"]==2].groupby("hour")["behavior_type"].count()
active_shapping_cart_hour = active_data[active_data["behavior_type"]==3].groupby("hour")["behavior_type"].count()
active_buy_hour = active_data[active_data["behavior_type"]==4].groupby("hour")["behavior_type"].count()


active_pv_hour = active_data[active_data["behavior_type"]==1].groupby("hour")["user_id"].count()



active_collect_hour_m = np.round(active_collect_hour.values / 3,0).tolist()
active_shapping_cart_hour_m = np.round(active_shapping_cart_hour.values / 3,0).tolist()
active_buy_hour_m  = np.round(active_buy_hour.values / 3,0).tolist()
active_pv_hour_m  = np.round(active_pv_hour.values  /3,0).tolist()


attr = list(active_collect_hour.index)

plt.figure(figsize=(12,8))
ax1 = plt.subplot(2,1,1)
ax1.spines["top"].set_visible(False)
ax1.spines["right"].set_visible(False)
ax1 = plt.bar(attr,active_pv_hour_m)
plt.title("双十二期间各时间段PV值")
plt.xticks([i for i in range(0,24,1)])

ax2 = plt.subplot(2,1,2)
ax2.spines["top"].set_visible(False)
ax2.spines["right"].set_visible(False)
ax2.plot(attr,active_collect_hour_m,label="收藏",color="b",marker="^")
ax2.plot(attr,active_shapping_cart_hour_m,label="添加购物车",color="r",marker="^")
ax2.plot(attr,active_buy_hour_m ,label="购买",color="g",marker="^")
ax2.legend(loc="best")

plt.title("正常期间各时间段用户行为")
plt.xticks([i for i in range(0,24,1)])
plt.show()

日常期间不同时段的用户行为分析

from pyecharts.charts import Bar



daily_collect_hour = daily_data[daily_data["behavior_type"]==2].groupby("hour")["behavior_type"].count()
daily_shapping_cart_hour = daily_data[daily_data["behavior_type"]==3].groupby("hour")["behavior_type"].count()
daily_buy_hour = daily_data[daily_data["behavior_type"]==4].groupby("hour")["behavior_type"].count()

daily_pv_hour =daily_data[daily_data["behavior_type"]==1].groupby("hour")["user_id"].count()

daily_collect_hour_m = np.round(daily_collect_hour.values / 3,0).tolist()
daily_shapping_cart_hour_m = np.round(daily_shapping_cart_hour.values / 3,0).tolist()
daily_buy_hour_m  = np.round(daily_buy_hour.values / 3,0).tolist()
daily_pv_hour_m  = np.round(daily_pv_hour.values  /3,0).tolist()



pv_m=( 
    Bar()
    .add_xaxis(xaxis_data=attr)
    .add_yaxis(
    "浏览人数",
        daily_pv_hour_m  ,
        label_opts=opts.LabelOpts(is_show=False)
    )
    .set_global_opts(
        title_opts=opts.TitleOpts(title="日常PV各时间段数据"),
    )
)

daily_m =(
      Line(init_opts=opts.InitOpts(width="1000px",height="500px"))
      .add_xaxis(xaxis_data=attr)
      .add_yaxis(
        "加购人数",
        daily_shapping_cart_hour_m ,
        label_opts=opts.LabelOpts(is_show=False)
    )
    .add_yaxis(
        "收藏人数",
        daily_collect_hour_m,
        label_opts=opts.LabelOpts(is_show=False)
    )
     .add_yaxis(
        "购买人数",
        daily_buy_hour_m ,
        label_opts=opts.LabelOpts(is_show=False)
    )
    .set_global_opts(
        xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=15)),
        title_opts=opts.TitleOpts(title="日均各时段活动用户行为",pos_top="48%"),
        legend_opts=opts.LegendOpts(pos_top="48%"),
    )

)
ggrid = (
    Grid()
    .add(pv_m, grid_opts=opts.GridOpts(pos_bottom="60%"))
    .add(daily_m , grid_opts=opts.GridOpts(pos_top="60%"))
)
ggrid.render_notebook()

不同时段的购买率

#活动期间
active_hour_buy_user_num = active_data[active_data["behavior_type"] == 4].drop_duplicates(['user_id','date_time','hour']).groupby('hour')['user_id'].count()

active_hour_user_num = active_data.drop_duplicates(['user_id','date_time','hour']).groupby('hour')['user_id'].count()

active_hour_buy_rate = np.around(active_hour_buy_user_num.values / active_hour_user_num.values,3)


#日常期间

daily_hour_buy_user_num = daily_data[daily_data["behavior_type"] == 4].drop_duplicates(['user_id','date_time','hour']).groupby('hour')['user_id'].count()
daily_hour_user_num = daily_data.drop_duplicates(['user_id','date_time','hour']).groupby('hour')['user_id'].count()
daily_buy_rate = np.around(daily_hour_buy_user_num.values / daily_hour_user_num.values,3)





buy_rate=(
    Line()
    .add_xaxis(xaxis_data=attr)
    .add_yaxis(
        "日常购买率",
       daily_buy_rate,
    )
    .add_yaxis(
        "活动购买率",
       active_hour_buy_rate,
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="不同时段购买率"))
)

buy_rate.render_notebook()

转化漏斗分析

活动期间的转化漏斗

active_pv_num = active_data[active_data["behavior_type"]==1]["user_id"].count()
active_collect_num=active_data[active_data["behavior_type"]==2]["user_id"].count()
active_cart_num=active_data[active_data["behavior_type"]==3]["user_id"].count()
active_buy_num=active_data[active_data["behavior_type"]==4]["user_id"].count()


attr=["点击","加入购物车","收藏","购买"]


values=[np.around((active_pv_num/active_pv_num*100),2),
        np.around((active_cart_num/active_pv_num*100),2),
        np.around((active_collect_num/active_pv_num*100),2),
        np.around((active_buy_num/active_pv_num*100),2),
       ]


data = [[attr[i], values[i]] for i in range(len(attr))]


a=(
    Funnel()
    .add(
        series_name="用户行为",
        data_pair=data,
        gap=2,
        tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b} : {c}%",is_show=True),
        label_opts=opts.LabelOpts(is_show=True, position="ourside"),
        itemstyle_opts=opts.ItemStyleOpts(border_color="#fff", border_width=1),
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="用户转化漏斗", subtitle="活动"))
)
a.render_notebook()

日常漏斗

daily_pv_num = daily_data[daily_data["behavior_type"]==1]["user_id"].count()
daily_collect_num=daily_data[daily_data["behavior_type"]==2]["user_id"].count()
daily_cart_num=daily_data[daily_data["behavior_type"]==3]["user_id"].count()
daily_buy_num=daily_data[daily_data["behavior_type"]==4]["user_id"].count()


attr=["点击","加入购物车","收藏","购买"]

values=[np.around((daily_pv_num/daily_pv_num*100),2),
        np.around((daily_cart_num/daily_pv_num*100),2),
        np.around((daily_collect_num/daily_pv_num*100),2),
        np.around((daily_buy_num/daily_pv_num*100),2),
       ]

data = [[attr[i], values[i]] for i in range(len(attr))]


a=(
    Funnel()
    .add(
        series_name="用户行为",
        data_pair=data,
        gap=2,
        tooltip_opts=opts.TooltipOpts(trigger="item", formatter="{a} <br/>{b} : {c}%",is_show=True),
        label_opts=opts.LabelOpts(is_show=True, position="ourside"),
        itemstyle_opts=opts.ItemStyleOpts(border_color="#fff", border_width=1),
    )
    .set_global_opts(title_opts=opts.TitleOpts(title="用户转化漏斗", subtitle="活动"))
)
a.render_notebook()

按照“点击-加入购物车-收藏-购买”这一用户行为路径，我们可通过优化“点击-加入购物车”这一环节进而提升购买的转化率，可以通过鼓励用户收藏加购后可以领券来刺激用户加购收藏从而刺激用户的购买欲望。