用户特征表单+商品特征表单+数据清洗+购买因素分析
3. 构建用户特征表单
3.1 检查是否存在用户注册时间不合理的情况
import pandas as pd
df_user = pd.read_csv('data\JData_User.csv',encoding='gbk')
df_user['user_reg_tm']=pd.to_datetime(df_user['user_reg_tm'])
df_user.loc[df_user.user_reg_tm >= '2016-4-15']
检查异常数据:
df_month = pd.read_csv('data\JData_Action_201604.csv')
df_month['time'] = pd.to_datetime(df_month['time'])
df_month.loc[df_month.time >= '2016-4-16']
结论:说明用户没有异常操作数据,所以这一批用户不删除
3.1.1 年龄区间的处理:映射成区间
import pandas as pd
df_user = pd.read_csv('data\JData_User.csv',encoding='gbk')
def tranAge(x):
if x == u'15岁以下':
x='1'
elif x==u'16-25岁':
x='2'
elif x==u'26-35岁':
x='3'
elif x==u'36-45岁':
x='4'
elif x==u'46-55岁':
x='5'
elif x==u'56岁以上':
x='6'
return x
df_user['age']=df_user['age'].apply(tranAge)
print (df_user.groupby(df_user['age']).count())
df_user.to_csv('data\JData_User.csv',index=None)
结果:
为了能够进行上述清洗,在此首先构造了简单的用户(user)行为特征和商品(item)行为特征,对应于两张表user_table和item_table
(每种行为都可以提取出来:)
user_table
特征包括:
- user_id(用户id),age(年龄),sex(性别),
- user_lv_cd(用户级别),browse_num(浏览数),
- addcart_num(加购数),delcart_num(删购数),
- buy_num(购买数),favor_num(收藏数),
- click_num(点击数),buy_addcart_ratio(购买加购转化率),
- buy_browse_ratio(购买浏览转化率),
- buy_click_ratio(购买点击转化率),
- buy_favor_ratio(购买收藏转化率)
涉及到行业的一些业务指标
item_table
特征包括:
- sku_id(商品id),attr1,attr2,
- attr3,cate,brand,browse_num,(品牌、点击数)
- addcart_num,delcart_num,
- buy_num,favor_num,click_num,
- buy_addcart_ratio,buy_browse_ratio,
- buy_click_ratio,buy_favor_ratio,
- comment_num(评论数),
- has_bad_comment(是否有差评),
- bad_comment_rate(差评率)
3.1.2 构建User_table
#定义文件名
ACTION_201602_FILE = "data/JData_Action_201602.csv"
ACTION_201603_FILE = "data/JData_Action_201603.csv"
ACTION_201604_FILE = "data/JData_Action_201604.csv"
COMMENT_FILE = "data/JData_Comment.csv"
PRODUCT_FILE = "data/JData_Product.csv"
USER_FILE = "data/JData_User.csv"
USER_TABLE_FILE = "data/User_table.csv"
ITEM_TABLE_FILE = "data/Item_table.csv"
# 导入相关包
import pandas as pd
import numpy as np
from collections import Counter
# 功能函数: 对每一个user分组的数据进行统计
def add_type_count(group):
behavior_type = group.type.astype(int)
# 用户行为类别
type_cnt = Counter(behavior_type)
# 1: 浏览 2: 加购 3: 删除
# 4: 购买 5: 收藏 6: 点击
group['browse_num'] = type_cnt[1]
group['addcart_num'] = type_cnt[2]
group['delcart_num'] = type_cnt[3]
group['buy_num'] = type_cnt[4]
group['favor_num'] = type_cnt[5]
group['click_num'] = type_cnt[6]
return group[['user_id', 'browse_num', 'addcart_num',
'delcart_num', 'buy_num', 'favor_num',
'click_num']]
由于用户行为数据量较大,一次性读入可能造成内存错误(Memory Error),因而使用pandas的分块(chunk)读取
#对action数据进行统计
#根据自己调节chunk_size大小
def get_from_action_data(fname, chunk_size=50000):
reader = pd.read_csv(fname, header=0, iterator=True,encoding='gbk')
chunks = []
loop = True
while loop:
try:
# 只读取user_id和type两个字段
chunk = reader.get_chunk(chunk_size)[["user_id", "type"]]
chunks.append(chunk)
except StopIteration:
loop = False
print("Iteration is stopped")
# 将块拼接为pandas dataframe格式
df_ac = pd.concat(chunks, ignore_index=True)
# 按user_id分组,对每一组进行统计,as_index 表示无索引形式返回数据
df_ac = df_ac.groupby(['user_id'], as_index=False).apply(add_type_count)
# 将重复的行丢弃
df_ac = df_ac.drop_duplicates('user_id')
return df_ac
# 将各个action数据的统计量进行聚合
def merge_action_data():
df_ac = []
df_ac.append(get_from_action_data(fname=ACTION_201602_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201603_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201604_FILE))
df_ac = pd.concat(df_ac, ignore_index=True)
# 用户在不同action表中统计量求和
df_ac = df_ac.groupby(['user_id'], as_index=False).sum()
# 构造转化率字段
df_ac['buy_addcart_ratio'] = df_ac['buy_num'] / df_ac['addcart_num']
df_ac['buy_browse_ratio'] = df_ac['buy_num'] / df_ac['browse_num']
df_ac['buy_click_ratio'] = df_ac['buy_num'] / df_ac['click_num']
df_ac['buy_favor_ratio'] = df_ac['buy_num'] / df_ac['favor_num']
# 将大于1的转化率字段置为1(100%)
df_ac.ix[df_ac['buy_addcart_ratio'] > 1., 'buy_addcart_ratio'] = 1.
df_ac.ix[df_ac['buy_browse_ratio'] > 1., 'buy_browse_ratio'] = 1.
df_ac.ix[df_ac['buy_click_ratio'] > 1., 'buy_click_ratio'] = 1.
df_ac.ix[df_ac['buy_favor_ratio'] > 1., 'buy_favor_ratio'] = 1.
return df_ac
# 从FJData_User表中抽取需要的字段
def get_from_jdata_user():
df_usr = pd.read_csv(USER_FILE, header=0)
df_usr = df_usr[["user_id", "age", "sex", "user_lv_cd"]]
return df_usr
user_base = get_from_jdata_user()
user_behavior = merge_action_data()
# 连接成一张表,类似于SQL的左连接(left join)
user_behavior = pd.merge(user_base, user_behavior, on=['user_id'], how='left')
# 保存为user_table.csv
user_behavior.to_csv(USER_TABLE_FILE, index=False)
user_table = pd.read_csv(USER_TABLE_FILE)
user_table.head()
4. 构建商品特征表单:Item_table
#定义文件名
ACTION_201602_FILE = "data/JData_Action_201602.csv"
ACTION_201603_FILE = "data/JData_Action_201603.csv"
ACTION_201604_FILE = "data/JData_Action_201604.csv"
COMMENT_FILE = "data/JData_Comment.csv"
PRODUCT_FILE = "data/JData_Product.csv"
USER_FILE = "data/JData_User.csv"
USER_TABLE_FILE = "data/User_table.csv"
ITEM_TABLE_FILE = "data/Item_table.csv"
# 导入相关包
import pandas as pd
import numpy as np
from collections import Counter
# 读取Product中商品
def get_from_jdata_product():
df_item = pd.read_csv(PRODUCT_FILE, header=0,encoding='gbk')
return df_item
# 对每一个商品分组进行统计
def add_type_count(group):
behavior_type = group.type.astype(int)
type_cnt = Counter(behavior_type)
group['browse_num'] = type_cnt[1]
group['addcart_num'] = type_cnt[2]
group['delcart_num'] = type_cnt[3]
group['buy_num'] = type_cnt[4]
group['favor_num'] = type_cnt[5]
group['click_num'] = type_cnt[6]
return group[['sku_id', 'browse_num', 'addcart_num',
'delcart_num', 'buy_num', 'favor_num',
'click_num']]
#对action中的数据进行统计
def get_from_action_data(fname, chunk_size=50000):
reader = pd.read_csv(fname, header=0, iterator=True)
chunks = []
loop = True
while loop:
try:
chunk = reader.get_chunk(chunk_size)[["sku_id", "type"]]
chunks.append(chunk)
except StopIteration:
loop = False
print("Iteration is stopped")
df_ac = pd.concat(chunks, ignore_index=True)
df_ac = df_ac.groupby(['sku_id'], as_index=False).apply(add_type_count)
# Select unique row
df_ac = df_ac.drop_duplicates('sku_id')
return df_ac
# 获取评论中的商品数据,如果存在某一个商品有两个日期的评论,我们取最晚的那一个
def get_from_jdata_comment():
df_cmt = pd.read_csv(COMMENT_FILE, header=0)
df_cmt['dt'] = pd.to_datetime(df_cmt['dt'])
# find latest comment index
idx = df_cmt.groupby(['sku_id'])['dt'].transform(max) == df_cmt['dt']
df_cmt = df_cmt[idx]
return df_cmt[['sku_id', 'comment_num',
'has_bad_comment', 'bad_comment_rate']]
def merge_action_data():
df_ac = []
df_ac.append(get_from_action_data(fname=ACTION_201602_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201603_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201604_FILE))
df_ac = pd.concat(df_ac, ignore_index=True)
df_ac = df_ac.groupby(['sku_id'], as_index=False).sum()
df_ac['buy_addcart_ratio'] = df_ac['buy_num'] / df_ac['addcart_num']
df_ac['buy_browse_ratio'] = df_ac['buy_num'] / df_ac['browse_num']
df_ac['buy_click_ratio'] = df_ac['buy_num'] / df_ac['click_num']
df_ac['buy_favor_ratio'] = df_ac['buy_num'] / df_ac['favor_num']
df_ac.ix[df_ac['buy_addcart_ratio'] > 1., 'buy_addcart_ratio'] = 1.
df_ac.ix[df_ac['buy_browse_ratio'] > 1., 'buy_browse_ratio'] = 1.
df_ac.ix[df_ac['buy_click_ratio'] > 1., 'buy_click_ratio'] = 1.
df_ac.ix[df_ac['buy_favor_ratio'] > 1., 'buy_favor_ratio'] = 1.
return df_ac
item_base = get_from_jdata_product()
item_behavior = merge_action_data()
item_comment = get_from_jdata_comment()
# SQL: left join
item_behavior = pd.merge(
item_base, item_behavior, on=['sku_id'], how='left')
item_behavior = pd.merge(
item_behavior, item_comment, on=['sku_id'], how='left')
item_behavior.to_csv(ITEM_TABLE_FILE, index=False)
item_table = pd.read_csv(ITEM_TABLE_FILE)
item_table.head()
5. 数据清洗
5.1 用户清洗
import pandas as pd
df_user = pd.read_csv('data/User_table.csv',header=0)
pd.options.display.float_format = '{:,.3f}'.format #输出格式设置,保留三位小数
df_user.describe()
由上述统计信息发现: 第一行中根据User_id统计发现有105321个用户,发现有3个用户没有age,sex字段,而且根据浏览、加购、删购、购买等记录却只有105180条记录,说明存在用户无任何交互记录,因此可以删除上述用户。
- 删除没有age,sex字段的用户
- 删除无交互记录的用户
- 统计并删除无购买记录的用户
df_user[df_user['age'].isnull()]
delete_list = df_user[df_user['age'].isnull()].index
df_user.drop(delete_list,axis=0,inplace=True)
#删除无交互记录的用户
df_naction = df_user[(df_user['browse_num'].isnull()) & (df_user['addcart_num'].isnull()) & (df_user['delcart_num'].isnull()) & (df_user['buy_num'].isnull()) & (df_user['favor_num'].isnull()) & (df_user['click_num'].isnull())]
df_user.drop(df_naction.index,axis=0,inplace=True)
print (len(df_user))
#统计无购买记录的用户
df_bzero = df_user[df_user['buy_num']==0]
#输出购买数为0的总记录数
print (len(df_bzero))
#删除无购买记录的用户
df_user = df_user[df_user['buy_num']!=0]
df_user.describe()
- 删除爬虫及惰性用户
由上表所知,浏览购买转换比和点击购买转换比均值为0.018,0.030,因此这里认为浏览购买转换比和点击购买转换比小于0.0005的用户为惰性用户
bindex = df_user[df_user['buy_browse_ratio']<0.0005].index
print (len(bindex))
df_user.drop(bindex,axis=0,inplace=True)
cindex = df_user[df_user['buy_click_ratio']<0.0005].index
print (len(cindex))
df_user.drop(cindex,axis=0,inplace=True)
df_user.describe()
最后这29070个用户为最终预测用户数据集
6. 数据EDA
# 导入相关包
%matplotlib inline
# 绘图包
import matplotlib
import matplotlib.pyplot as plt
import numpy as np
import pandas as pd
#定义文件名
ACTION_201602_FILE = "data/JData_Action_201602.csv"
ACTION_201603_FILE = "data/JData_Action_201603.csv"
ACTION_201604_FILE = "data/JData_Action_201604.csv"
COMMENT_FILE = "data/JData_Comment.csv"
PRODUCT_FILE = "data/JData_Product.csv"
USER_FILE = "data/JData_User.csv"
USER_TABLE_FILE = "data/User_table.csv"
ITEM_TABLE_FILE = "data/Item_table.csv"
6.1 周一到周日各天购买情况
# 提取购买(type=4)的行为数据
def get_from_action_data(fname, chunk_size=50000):
reader = pd.read_csv(fname, header=0, iterator=True)
chunks = []
loop = True
while loop:
try:
chunk = reader.get_chunk(chunk_size)[
["user_id", "sku_id", "type", "time"]]
chunks.append(chunk)
except StopIteration:
loop = False
print("Iteration is stopped")
df_ac = pd.concat(chunks, ignore_index=True)
# type=4,为购买
df_ac = df_ac[df_ac['type'] == 4]
return df_ac[["user_id", "sku_id", "time"]]
df_ac = []
df_ac.append(get_from_action_data(fname=ACTION_201602_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201603_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201604_FILE))
df_ac = pd.concat(df_ac, ignore_index=True)
print(df_ac.dtypes)
# 将time字段转换为datetime类型
df_ac['time'] = pd.to_datetime(df_ac['time'])
# 使用lambda匿名函数将时间time转换为星期(周一为1, 周日为7)
df_ac['time'] = df_ac['time'].apply(lambda x: x.weekday() + 1)
df_ac.head()
# 周一到周日每天购买用户个数
df_user = df_ac.groupby('time')['user_id'].nunique()
df_user = df_user.to_frame().reset_index()
df_user.columns = ['weekday', 'user_num']
# 周一到周日每天购买商品个数
df_item = df_ac.groupby('time')['sku_id'].nunique()
df_item = df_item.to_frame().reset_index()
df_item.columns = ['weekday', 'item_num']
# 周一到周日每天购买记录个数
df_ui = df_ac.groupby('time', as_index=False).size()
df_ui = df_ui.to_frame().reset_index()
df_ui.columns = ['weekday', 'user_item_num']
# 条形宽度
bar_width = 0.2
# 透明度
opacity = 0.4
plt.bar(df_user['weekday'], df_user['user_num'], bar_width,
alpha=opacity, color='c', label='user')
plt.bar(df_item['weekday']+bar_width, df_item['item_num'],
bar_width, alpha=opacity, color='g', label='item')
plt.bar(df_ui['weekday']+bar_width*2, df_ui['user_item_num'],
bar_width, alpha=opacity, color='m', label='user_item')
plt.xlabel('weekday')
plt.ylabel('number')
plt.title('A Week Purchase Table')
plt.xticks(df_user['weekday'] + bar_width * 3 / 2., (1,2,3,4,5,6,7))
plt.tight_layout()
plt.legend(prop={'size':10})
![](https://img-blog.csdnimg.cn/d59f2b725a804fa19c712a9f71b75f76.png)
分析:周六,周日购买量较少
7. 购买因素分析
7.1 一个月中各天购买量
2016年2月
df_ac = get_from_action_data(fname=ACTION_201602_FILE)
# 将time字段转换为datetime类型并使用lambda匿名函数将时间time转换为天
df_ac['time'] = pd.to_datetime(df_ac['time']).apply(lambda x: x.day)
df_ac.head()
df_ac.tail()
![](https://img-blog.csdnimg.cn/abae916a69634e918980db39a0d4af9a.png)
df_user = df_ac.groupby('time')['user_id'].nunique()
df_user = df_user.to_frame().reset_index()
df_user.columns = ['day', 'user_num']
df_item = df_ac.groupby('time')['sku_id'].nunique()
df_item = df_item.to_frame().reset_index()
df_item.columns = ['day', 'item_num']
df_ui = df_ac.groupby('time', as_index=False).size()
df_ui = df_ui.to_frame().reset_index()
df_ui.columns = ['day', 'user_item_num']
# 条形宽度
bar_width = 0.2
# 透明度
opacity = 0.4
# 天数
day_range = range(1,len(df_user['day']) + 1, 1)
# 设置图片大小
plt.figure(figsize=(14,10))
plt.bar(df_user['day'], df_user['user_num'], bar_width,
alpha=opacity, color='c', label='user')
plt.bar(df_item['day']+bar_width, df_item['item_num'],
bar_width, alpha=opacity, color='g', label='item')
plt.bar(df_ui['day']+bar_width*2, df_ui['user_item_num'],
bar_width, alpha=opacity, color='m', label='user_item')
plt.xlabel('day')
plt.ylabel('number')
plt.title('February Purchase Table')
plt.xticks(df_user['day'] + bar_width * 3 / 2., day_range)
# plt.ylim(0, 80)
plt.tight_layout()
plt.legend(prop={'size':9})
分析: 2月份5,6,7,8,9,10 这几天购买量非常少,原因可能是中国农历春节,快递不营业
2016年3月
df_ac = get_from_action_data(fname=ACTION_201603_FILE)
# 将time字段转换为datetime类型并使用lambda匿名函数将时间time转换为天
df_ac['time'] = pd.to_datetime(df_ac['time']).apply(lambda x: x.day)
df_user = df_ac.groupby('time')['user_id'].nunique()
df_user = df_user.to_frame().reset_index()
df_user.columns = ['day', 'user_num']
df_item = df_ac.groupby('time')['sku_id'].nunique()
df_item = df_item.to_frame().reset_index()
df_item.columns = ['day', 'item_num']
df_ui = df_ac.groupby('time', as_index=False).size()
df_ui = df_ui.to_frame().reset_index()
df_ui.columns = ['day', 'user_item_num']
# 条形宽度
bar_width = 0.2
# 透明度
opacity = 0.4
# 天数
day_range = range(1,len(df_user['day']) + 1, 1)
# 设置图片大小
plt.figure(figsize=(14,10))
plt.bar(df_user['day'], df_user['user_num'], bar_width,
alpha=opacity, color='c', label='user')
plt.bar(df_item['day']+bar_width, df_item['item_num'],
bar_width, alpha=opacity, color='g', label='item')
plt.bar(df_ui['day']+bar_width*2, df_ui['user_item_num'],
bar_width, alpha=opacity, color='m', label='user_item')
plt.xlabel('day')
plt.ylabel('number')
plt.title('March Purchase Table')
plt.xticks(df_user['day'] + bar_width * 3 / 2., day_range)
# plt.ylim(0, 80)
plt.tight_layout()
plt.legend(prop={'size':9})
分析:3月份14,15,16不知名节日,造成购物大井喷,总体来看,购物记录多于2月份
2016年4月
df_ac = get_from_action_data(fname=ACTION_201604_FILE)
# 将time字段转换为datetime类型并使用lambda匿名函数将时间time转换为天
df_ac['time'] = pd.to_datetime(df_ac['time']).apply(lambda x: x.day)
df_user = df_ac.groupby('time')['user_id'].nunique()
df_user = df_user.to_frame().reset_index()
df_user.columns = ['day', 'user_num']
df_item = df_ac.groupby('time')['sku_id'].nunique()
df_item = df_item.to_frame().reset_index()
df_item.columns = ['day', 'item_num']
df_ui = df_ac.groupby('time', as_index=False).size()
df_ui = df_ui.to_frame().reset_index()
df_ui.columns = ['day', 'user_item_num']
# 条形宽度
bar_width = 0.2
# 透明度
opacity = 0.4
# 天数
day_range = range(1,len(df_user['day']) + 1, 1)
# 设置图片大小
plt.figure(figsize=(14,10))
plt.bar(df_user['day'], df_user['user_num'], bar_width,
alpha=opacity, color='c', label='user')
plt.bar(df_item['day']+bar_width, df_item['item_num'],
bar_width, alpha=opacity, color='g', label='item')
plt.bar(df_ui['day']+bar_width*2, df_ui['user_item_num'],
bar_width, alpha=opacity, color='m', label='user_item')
plt.xlabel('day')
plt.ylabel('number')
plt.title('April Purchase Table')
plt.xticks(df_user['day'] + bar_width * 3 / 2., day_range)
# plt.ylim(0, 80)
plt.tight_layout()
plt.legend(prop={'size':9})
7.2 商品类别销售统计
周一到周日各商品类别销售情况
# 从行为记录中提取商品类别数据
def get_from_action_data(fname, chunk_size=50000):
reader = pd.read_csv(fname, header=0, iterator=True)
chunks = []
loop = True
while loop:
try:
chunk = reader.get_chunk(chunk_size)[
["cate", "brand", "type", "time"]]
chunks.append(chunk)
except StopIteration:
loop = False
print("Iteration is stopped")
df_ac = pd.concat(chunks, ignore_index=True)
# type=4,为购买
df_ac = df_ac[df_ac['type'] == 4]
return df_ac[["cate", "brand", "type", "time"]]
df_ac = []
df_ac.append(get_from_action_data(fname=ACTION_201602_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201603_FILE))
df_ac.append(get_from_action_data(fname=ACTION_201604_FILE))
df_ac = pd.concat(df_ac, ignore_index=True)
# 将time字段转换为datetime类型
df_ac['time'] = pd.to_datetime(df_ac['time'])
# 使用lambda匿名函数将时间time转换为星期(周一为1, 周日为7)
df_ac['time'] = df_ac['time'].apply(lambda x: x.weekday() + 1)
df_ac.head()
# 观察有几个类别商品
df_ac.groupby(df_ac['cate']).count()
# 周一到周日每天购买商品类别数量统计
df_product = df_ac['brand'].groupby([df_ac['time'],df_ac['cate']]).count()
df_product=df_product.unstack()
df_product.plot(kind='bar',title='Cate Purchase Table in a Week',figsize=(14,10))
分析:星期二买类别8的最多,星期天最少。
2016年2,3,4月
df_ac2 = get_from_action_data(fname=ACTION_201602_FILE)
# 将time字段转换为datetime类型并使用lambda匿名函数将时间time转换为天
df_ac2['time'] = pd.to_datetime(df_ac2['time']).apply(lambda x: x.day)
df_ac3 = get_from_action_data(fname=ACTION_201603_FILE)
# 将time字段转换为datetime类型并使用lambda匿名函数将时间time转换为天
df_ac3['time'] = pd.to_datetime(df_ac3['time']).apply(lambda x: x.day)
df_ac4 = get_from_action_data(fname=ACTION_201604_FILE)
# 将time字段转换为datetime类型并使用lambda匿名函数将时间time转换为天
df_ac4['time'] = pd.to_datetime(df_ac4['time']).apply(lambda x: x.day)
dc_cate2 = df_ac2[df_ac2['cate']==8]
dc_cate2 = dc_cate2['brand'].groupby(dc_cate2['time']).count()
dc_cate2 = dc_cate2.to_frame().reset_index()
dc_cate2.columns = ['day', 'product_num']
dc_cate3 = df_ac3[df_ac3['cate']==8]
dc_cate3 = dc_cate3['brand'].groupby(dc_cate3['time']).count()
dc_cate3 = dc_cate3.to_frame().reset_index()
dc_cate3.columns = ['day', 'product_num']
dc_cate4 = df_ac4[df_ac4['cate']==8]
dc_cate4 = dc_cate4['brand'].groupby(dc_cate4['time']).count()
dc_cate4 = dc_cate4.to_frame().reset_index()
dc_cate4.columns = ['day', 'product_num']
# 条形宽度
bar_width = 0.2
# 透明度
opacity = 0.4
# 天数
day_range = range(1,len(dc_cate3['day']) + 1, 1)
# 设置图片大小
plt.figure(figsize=(14,10))
plt.bar(dc_cate2['day'], dc_cate2['product_num'], bar_width,
alpha=opacity, color='c', label='February')
plt.bar(dc_cate3['day']+bar_width, dc_cate3['product_num'],
bar_width, alpha=opacity, color='g', label='March')
plt.bar(dc_cate4['day']+bar_width*2, dc_cate4['product_num'],
bar_width, alpha=opacity, color='m', label='April')
plt.xlabel('day')
plt.ylabel('number')
plt.title('Cate-8 Purchase Table')
plt.xticks(dc_cate3['day'] + bar_width * 3 / 2., day_range)
# plt.ylim(0, 80)
plt.tight_layout()
plt.legend(prop={'size':9})
分析:2月份对类别8商品的购买普遍偏低,3,4月份普遍偏高,3月15日购买极多。
可以对比3月份的销售记录,发现类别8将近占了3月15日总销售的一半。
同时发现,3,4月份类别8销售记录在前半个月特别相似,除了4月8号,9号和3月15号。
查看特定用户对特定商品的的轨迹
def spec_ui_action_data(fname, user_id, item_id, chunk_size=100000):
reader = pd.read_csv(fname, header=0, iterator=True)
chunks = []
loop = True
while loop:
try:
chunk = reader.get_chunk(chunk_size)[
["user_id", "sku_id", "type", "time"]]
chunks.append(chunk)
except StopIteration:
loop = False
print("Iteration is stopped")
df_ac = pd.concat(chunks, ignore_index=True)
df_ac = df_ac[(df_ac['user_id'] == user_id) & (df_ac['sku_id'] == item_id)]
return df_ac
def explore_user_item_via_time():
user_id = 266079
item_id = 138778
df_ac = []
df_ac.append(spec_ui_action_data(ACTION_201602_FILE, user_id, item_id))
df_ac.append(spec_ui_action_data(ACTION_201603_FILE, user_id, item_id))
df_ac.append(spec_ui_action_data(ACTION_201604_FILE, user_id, item_id))
df_ac = pd.concat(df_ac, ignore_index=False)
print(df_ac.sort_values(by='time'))
explore_user_item_via_time()