赞
踩
本篇文章给大家谈谈python3 数据分析项目案例,以及用python做数据分析案例,希望对各位有所帮助,不要忘了收藏本站喔。
- df = pd.read_csv('./data/CDNOW_master.txt',header=None,sep='\s+',names=['user_id','order_dt','order_product','order_amount']) #sep='\s+' 分割间隔 一个或多个空格
- df.head()
- df.shape
- (69659, 4)
- #查看数据类型
- df.info()
-
- <class 'pandas.core.frame.DataFrame'>
- RangeIndex: 69659 entries, 0 to 69658
- Data columns (total 4 columns):
- user_id 69659 non-null int64
- order_dt 69659 non-null int64
- order_product 69659 non-null int64
- order_amount 69659 non-null float64
- dtypes: float64(1), int64(3)
- memory usage: 2.1 MB
- #order_dt转换成时间序列,且加一列为购买商品的月份
- df['order_dt'] = pd.to_datetime(df['order_dt'],format="%Y%m%d")
- df.head()
- df['month'] = df['order_dt'].astype('datetime64[M]')
- df.head()
df.describe() #对数据源中的数值型数据的描述
- #用户每月花费的总金额
- df.groupby(by='month')['order_amount'].sum()
- month
- 1997-01-01 299060.17
- 1997-02-01 379590.03
- 1997-03-01 393155.27
- 1997-04-01 142824.49
- 1997-05-01 107933.30
- 1997-06-01 108395.87
- 1997-07-01 122078.88
- 1997-08-01 88367.69
- 1997-09-01 81948.80
- 1997-10-01 89780.77
- 1997-11-01 115448.64
- 1997-12-01 95577.35
- 1998-01-01 76756.78
- 1998-02-01 77096.96
- 1998-03-01 108970.15
- 1998-04-01 66231.52
- 1998-05-01 70989.66
- 1998-06-01 76109.30
- Name: order_amount, dtype: float64
-
- #绘制曲线图展示
- df.groupby(by='month')['order_amount'].sum().plot()
- #所有用户每月的产品购买量
- df.groupby(by='month')['order_product'].sum()
-
- month
- 1997-01-01 19416
- 1997-02-01 24921
- 1997-03-01 26159
- 1997-04-01 9729
- 1997-05-01 7275
- 1997-06-01 7301
- 1997-07-01 8131
- 1997-08-01 5851
- 1997-09-01 5729
- 1997-10-01 6203
- 1997-11-01 7812
- 1997-12-01 6418
- 1998-01-01 5278
- 1998-02-01 5340
- 1998-03-01 7431
- 1998-04-01 4697
- 1998-05-01 4903
- 1998-06-01 5287
- Name: order_product, dtype: int64
-
- #所有用户每月的消费总次数
- df.groupby(by='month')['user_id'].count()
-
- month
- 1997-01-01 8928
- 1997-02-01 11272
- 1997-03-01 11598
- 1997-04-01 3781
- 1997-05-01 2895
- 1997-06-01 3054
- 1997-07-01 2942
- 1997-08-01 2320
- 1997-09-01 2296
- 1997-10-01 2562
- 1997-11-01 2750
- 1997-12-01 2504
- 1998-01-01 2032
- 1998-02-01 2026
- 1998-03-01 2793
- 1998-04-01 1878
- 1998-05-01 1985
- 1998-06-01 2043
- Name: user_id, dtype: int64
-
- #统计每月的消费人数
- df.groupby(by='month')['user_id'].nunique()
-
- month
- 1997-01-01 7846
- 1997-02-01 9633
- 1997-03-01 9524
- 1997-04-01 2822
- 1997-05-01 2214
- 1997-06-01 2339
- 1997-07-01 2180
- 1997-08-01 1772
- 1997-09-01 1739
- 1997-10-01 1839
- 1997-11-01 2028
- 1997-12-01 1864
- 1998-01-01 1537
- 1998-02-01 1551
- 1998-03-01 2060
- 1998-04-01 1437
- 1998-05-01 1488
- 1998-06-01 1506
- Name: user_id, dtype: int64
- #所有用户消费总金额和消费总购买量的统计描述
- df['order_product'].sum(),df['order_amount'].sum()
-
- (167881, 2500315.6300000004)
- #各个用户消费金额和消费产品数量的散点图
- users_amount_s = df.groupby(by='user_id')['order_amount'].sum()
- users_product_s = df.groupby(by='user_id')['order_product'].sum()
-
- plt.scatter(users_amount_s,usea_product_s)
#各个用户消费总金额的直方分布图(消费金额在1000之内的分布)
#1.先将满足要求的用户的行数据找出,在做分组聚合
user_amount_1000_s = df.query('order_amount <= 1000').groupby(by='user_id')['order_amount'].sum()
user_amount_1000_s
- #各个用户消费的总数量的直方分布图(消费商品的数量在100之内的分布)
- df.query('order_product <= 100').groupby(by='user_id')['order_product'].sum()
- #df有两个常用方法
- # - apply:可以作为df的运算工具,运算df的行或者列
- # - applymap:针对df中每一个元素进行指定形式的运算
- # 用户第一次消费的月份分布,和人数统计
- # 绘制线形图
- # 用户最后一次消费的时间分布,和人数统计
- # 绘制线形图
- df.groupby(by='user_id')['month'].min().value_counts()
-
- 1997-02-01 8476
- 1997-01-01 7846
- 1997-03-01 7248
- Name: month, dtype: int64
-
- df.groupby(by='user_id')['month'].max().value_counts()
- 1997-02-01 4912
- 1997-03-01 4478
- 1997-01-01 4192
- 1998-06-01 1506
- 1998-05-01 1042
- 1998-03-01 993
- 1998-04-01 769
- 1997-04-01 677
- 1997-12-01 620
- 1997-11-01 609
- 1998-02-01 550
- 1998-01-01 514
- 1997-06-01 499
- 1997-07-01 493
- 1997-05-01 480
- 1997-10-01 455
- 1997-09-01 397
- 1997-08-01 384
- Name: month, dtype: int64
-
- #新老客户的占比
- df_new_old = df.groupby(by='user_id')['order_dt'].agg(['min','max'])
- (df_new_old['min'] == df_new_old['max']).value_counts()
-
- True 12054
- False 11516
- dtype: int64
-
- #分析得出每个用户的总购买量和总消费金额and最近一次消费的时间的表格rfm
- rfm = df.pivot_table(index='user_id',aggfunc={'order_product':'sum','order_amount':'sum','order_dt':'max'}) #采用透视操作
- rfm.head()
- rfm['R'] = (df['order_dt'].max() - rfm['order_dt'])/np.timedelta64(1,'D')
-
- rfm = rfm[['order_amount','order_product','R']]
- rfm.columns = ['M','F','R']
-
- rfm.head()
- #rfm分层算法
- def rfm_func(x):
- #存储存储的是三个字符串形式的0或者1
- level = x.map(lambda x :'1' if x >= 0 else '0')
- # M '0'
- # F '0'
- # R '1'
- label = level['R'] + level.F + level.M
- d = {
- '111':'重要价值客户',
- '011':'重要保持客户',
- '101':'重要挽留客户',
- '001':'重要发展客户',
- '110':'一般价值客户',
- '010':'一般保持客户',
- '100':'一般挽留客户',
- '000':'一般发展客户'
- }
- result = d[label]
- return result
- #df.apply(func):可以对df中的行或者列进行某种(func)形式的运算
- rfm['label'] = rfm.apply(lambda x : x - x.mean(),axis=0).apply(rfm_func,axis = 1)
- rfm.head()
- #统计每个用户每个月的消费次数
- df_purchase = df.pivot_table(index='user_id',values='order_dt',aggfunc='count',columns='month',fill_value=0) #columns='month' 对 values='order_dt'又做了一次划分
- df_purchase.head()
- #统计每个用户每个月是否消费,消费记录为1否则记录为0
- df_purchase = df_purchase.applymap(lambda x:1 if x > 0 else 0)
-
- df_purchase.head()
- #将df_purchase中的原始数据0和1修改为new,unactive......,返回新的df叫做df_purchase_new
- #固定算法 修改参数即可用
- def active_status(data):
- status = []#某个用户每一个月的活跃度
- for i in range(18):
-
- #若本月没有消费
- if data[i] == 0:
- if len(status) > 0:
- if status[i-1] == 'unreg':
- status.append('unreg')
- else:
- status.append('unactive')
- else:
- status.append('unreg')
-
- #若本月消费
- else:
- if len(status) == 0:
- status.append('new')
- else:
- if status[i-1] == 'unactive':
- status.append('return')
- elif status[i-1] == 'unreg':
- status.append('new')
- else:
- status.append('active')
- return status
-
- pivoted_status = df_purchase.apply(active_status,axis = 1)
- pivoted_status.head()
-
- user_id
- 1 [new, unactive, unactive, unactive, unactive, ...
- 2 [new, unactive, unactive, unactive, unactive, ...
- 3 [new, unactive, return, active, unactive, unac...
- 4 [new, unactive, unactive, unactive, unactive, ...
- 5 [new, active, unactive, return, active, active...
- dtype: object
-
- df_purchase_new = DataFrame(data=pivoted_status.tolist(),index=df_purchase.index,columns=df_purchase.columns)
- df_purchase_new.head()
每月【不同活跃】用户的计数
df_purchase_new.apply(lambda x:pd.value_counts(x),axis=0).fillna(0).T
Copyright © 2003-2013 www.wpsshop.cn 版权所有,并保留所有权利。