datawhale数据挖掘

直接上项目：

import pandas as  pd
import numpy as np
import warnings 
import datetime
import seaborn as sns
import matplotlib.pyplot as plt
import datetime 
from scipy import stats

import warnings
warnings.filterwarnings('ignore')
# 设置数据集路径

dataset_path = '/kaggle/input/prdata/Purchase Redemption Data/'
# 读取数据

data_balance = pd.read_csv(dataset_path+'user_balance_table.csv')
# 为数据集添加时间戳

data_balance['date'] = pd.to_datetime(data_balance['report_date'], format= "%Y%m%d")
data_balance['day'] = data_balance['date'].dt.day
data_balance['month'] = data_balance['date'].dt.month
data_balance['year'] = data_balance['date'].dt.year
data_balance['week'] = data_balance['date'].dt.week
data_balance['weekday'] = data_balance['date'].dt.weekday

一、时间序列分析
# 聚合时间数据

total_balance = data_balance.groupby(['date'])['total_purchase_amt','total_redeem_amt'].sum().reset_index()
# 生成测试集区段数据

start = datetime.datetime(2014,9,1)
testdata = []
while start != datetime.datetime(2014,10,1):
    temp = [start, np.nan, np.nan]
    testdata.append(temp)
    start += datetime.timedelta(days = 1)
testdata = pd.DataFrame(testdata)
testdata.columns = total_balance.columns

# 拼接数据集

total_balance = pd.concat([total_balance, testdata], axis = 0)

# 为数据集添加时间戳

total_balance['day'] = total_balance['date'].dt.day
total_balance['month'] = total_balance['date'].dt.month
total_balance['year'] = total_balance['date'].dt.year
total_balance['week'] = total_balance['date'].dt.week
total_balance['weekday'] = total_balance['date'].dt.weekday

import matplotlib.pylab as plt
# 画出每日总购买与赎回量的时间序列图

fig = plt.figure(figsize=(20,6))
plt.plot(total_balance['date'], total_balance['total_purchase_amt'],label='purchase')
plt.plot(total_balance['date'], total_balance['total_redeem_amt'],label='redeem')

plt.legend(loc='best')
plt.title("The lineplot of total amount of Purchase and Redeem from July.13 to Sep.14")
plt.xlabel("Time")
plt.ylabel("Amount")
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-JXIUQSN4-1597938713726)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820233633327.png)]

# 画出4月份以后的时间序列图

total_balance_1 = total_balance[total_balance['date'] >= pd.to_datetime('2014-4-1')]
fig = plt.figure(figsize=(20,6))
plt.plot(total_balance_1['date'], total_balance_1['total_purchase_amt'])
plt.plot(total_balance_1['date'], total_balance_1['total_redeem_amt'])
plt.legend()
plt.title("The lineplot of total amount of Purchase and Redeem from April.14 to Sep.14")
plt.xlabel("Time")
plt.ylabel("Amount")
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-QNpz2Zmr-1597938713729)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820233832868.png)]

# 分别画出每个月中每天购买赎回量的时间序列图

fig = plt.figure(figsize=(15,15))

plt.subplot(4,1,1)
plt.title("The time series of total amount of Purchase and Redeem for August, July, June, May respectively")

total_balance_2 = total_balance[total_balance['date'] >= pd.to_datetime('2014-8-1')]
plt.plot(total_balance_2['date'], total_balance_2['total_purchase_amt'])
plt.plot(total_balance_2['date'], total_balance_2['total_redeem_amt'])
plt.legend()


total_balance_3 = total_balance[(total_balance['date'] >= pd.to_datetime('2014-7-1')) & (total_balance['date'] < pd.to_datetime('2014-8-1'))]
plt.subplot(4,1,2)
plt.plot(total_balance_3['date'], total_balance_3['total_purchase_amt'])
plt.plot(total_balance_3['date'], total_balance_3['total_redeem_amt'])
plt.legend()


total_balance_4 = total_balance[(total_balance['date'] >= pd.to_datetime('2014-6-1')) & (total_balance['date'] < pd.to_datetime('2014-7-1'))]
plt.subplot(4,1,3)
plt.plot(total_balance_4['date'], total_balance_4['total_purchase_amt'])
plt.plot(total_balance_4['date'], total_balance_4['total_redeem_amt'])
plt.legend()


total_balance_5 = total_balance[(total_balance['date'] >= pd.to_datetime('2014-5-1')) & (total_balance['date'] < pd.to_datetime('2014-6-1'))]
plt.subplot(4,1,4)
plt.plot(total_balance_5['date'], total_balance_5['total_purchase_amt'])
plt.plot(total_balance_5['date'], total_balance_5['total_redeem_amt'])
plt.legend()

plt.xlabel("Time")
plt.ylabel("Amount")
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-kQ6c4F7g-1597938713732)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820234026779.png)]

# 分别画出13年8月与9月每日购买赎回量的时序图

fig = plt.figure(figsize=(15,9))

total_balance_last8 = total_balance[(total_balance['date'] >= pd.to_datetime('2013-8-1')) & (total_balance['date'] < pd.to_datetime('2013-9-1'))]
plt.subplot(2,1,1)
plt.plot(total_balance_last8['date'], total_balance_last8['total_purchase_amt'])
plt.plot(total_balance_last8['date'], total_balance_last8['total_redeem_amt'])
plt.legend()

total_balance_last9 = total_balance[(total_balance['date'] >= pd.to_datetime('2013-9-1')) & (total_balance['date'] < pd.to_datetime('2013-10-1'))]
plt.subplot(2,1,2)
plt.plot(total_balance_last9['date'], total_balance_last9['total_purchase_amt'])
plt.plot(total_balance_last9['date'], total_balance_last9['total_redeem_amt'])
plt.legend()

plt.xlabel("Time")
plt.ylabel("Amount")
plt.show()
plt.show()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-naw8sxVN-1597938713735)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820234249449.png)]

# 画出每个翌日的数据分布于整体数据的分布图

a = plt.figure(figsize=(10,10))
scatter_para = {'marker':'.', 's':3, 'alpha':0.3}
line_kws = {'color':'k'}
plt.subplot(2,2,1)
plt.title('The distrubution of total purchase')
sns.violinplot(x='weekday', y='total_purchase_amt', data = total_balance_1, scatter_kws=scatter_para, line_kws=line_kws)
plt.subplot(2,2,2)
plt.title('The distrubution of total purchase')
sns.distplot(total_balance_1['total_purchase_amt'].dropna())
plt.subplot(2,2,3)
plt.title('The distrubution of total redeem')
sns.violinplot(x='weekday', y='total_redeem_amt', data = total_balance_1, scatter_kws=scatter_para, line_kws=line_kws)
plt.subplot(2,2,4)
plt.title('The distrubution of total redeem')
sns.distplot(total_balance_1['total_redeem_amt'].dropna())

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-eHkWwoZa-1597938713737)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820234405742.png)]

# 按翌日对数据聚合后取均值

week_sta = total_balance_1[['total_purchase_amt', 'total_redeem_amt', 'weekday']].groupby('weekday', as_index=False).mean()

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-PDnwa884-1597938713739)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820234502509.png)]

ps.写写我自己遇到的错误吧。严重至极：

源代码：

[外链图片转存失败,源站可能有防盗链机制,建议将图片保存下来直接上传(img-PTPmcD8P-1597938713740)(C:%5CUsers%5C29146%5CAppData%5CRoaming%5CTypora%5Ctypora-user-images%5Cimage-20200820234719934.png)]

这里的datetime.data得换成pd.to_datetime。