数据分析——阿里资金流入流出分析（task2-时间序列规则）

数据分析——阿里资金流入流出分析（task2-时间序列规则）

import pandas as pd
import sklearn as skr
import numpy as np
import datetime
import matplotlib.pyplot as plt
import seaborn as sns
from dateutil.relativedelta import relativedelta

# Load the balance data
def load_data(path: str = 'user_balance_table.csv')->pd.DataFrame:
    data_balance = pd.read_csv(path)
    data_balance = add_timestamp(data_balance)
    return data_balance.reset_index(drop=True)
    

# add tiemstamp to dataset
def add_timestamp(data: pd.DataFrame, time_index: str = 'report_date')->pd.DataFrame:
    data_balance = data.copy()
    data_balance['date'] = pd.to_datetime(data_balance[time_index], 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
    return data_balance.reset_index(drop=True)

# total amount
def get_total_balance(data: pd.DataFrame, date: str = '2014-03-31')->pd.DataFrame:
    df_tmp = data.copy()
    df_tmp = df_tmp.groupby(['date'])['total_purchase_amt','total_redeem_amt'].sum()
    df_tmp.reset_index(inplace=True)
    return df_tmp[(df_tmp['date']>= date)].reset_index(drop=