【BI学习作业11-资金流入流出预测】

---

1.编程题

1.1资金流入流出预测

数据集地址：https://tianchi.aliyun.com/competition/entrance/231573/information

• 数据集一共包括4张表：用户基本信息数据、用户申购赎回数据、收益率表和银行间拆借利率表
• 2.8万用户，284万行为数据，294天拆解利率，427天收益率
• 2013-07-01到2014-08-31，预测2014年9月的申购和赎回

1.1.1数据集信息

用户信息表，user_profile_table
总共随机抽取了约3万用户，主要包含了用户的性别、城市和星座，其中部分用户在 2014 年 9 月份第一次出现，这些用户只在测试数据中

列名	类型	含义	示例
user_id	bigint	用户 ID	1234
Sex	bigint	用户性别{1:男,0:女)}	0
City	bigint	所在城市	6081949
constellation	string	星座	射手座

用户申购赎回数据表 user_balance_table

• 数据包括了 20130701 至 20140831 申购和赎回信息，字段包括用户操作时间和操作记录，其中操作记录包括申购和赎回两个部分
• 金额的单位是分，即0.01元
• 如果用户今日消费总量为0，即consume_amt=0，同时四个category字段为空
• 数据经过了脱敏，同时保证了：
  今日余额 = 昨日余额 + 今日申购 - 今日赎回，不会出现负值

列名	类型	含义	示例
user_id	bigint	用户 ID	1234
report_date	string	日期	20140407
tBalance	bigint	今日余额	109004
total_purchase_amt	bigint	今日总购买量=直接购买+收益	21876
direct_purchase_amt	bigint	今日直接购买量	21863
purchase_bal_amt	bigint	今日支付宝余额购买量	0
purchase_bank_amt	bigint	今日银行卡购买量	21863
total_redeem_amt	bigint	今日总赎回量=消费+转出	10261
consume_amt	bigint	今日消费总量	0
transfer_amt	bigint	今日转出总量	10261
tftobal_amt	bigint	今日转出到支付宝余额总量	0
tftocard_amt	bigint	今日转出到银行卡总量	10261
share_amt	bigint	今日收益	13
category1	bigint	今日类目1消费总额	0
category2	bigint	今日类目2消费总额	0
category3	bigint	今日类目3消费总额	0
category4	bigint	今日类目4消费总额	0

收益率表 mfd_day_share_interest

• 收益表为余额宝在 14 个月内的收益率表

列名	类型	含义	示例
mfd_date	string	日期	20140102
mfd_daily_yield	double	万份收益，即1万块钱的收益	1.5787
mfd_7daily_yield	double	七日年化收益率（%）	6.307

收益计算方式

• 主要基于实际余额宝收益计算方法，进行了简化

1）收益计算的时间不再是会计日，而是自然日，以0点为分隔（0点之前算昨天，0点之后算今天）

2）收益的显示时间，即实际将第一份收益打入用户账户的时间，以周一转入周三显示为例，如果用户在周一存入10000元，即1000000分，那么这笔金额是周一确认，周二是开始产生收益，在周三将周二产生的收益打入到用户的账户中，此时用户的账户中显示的是1000110分

转入时间	首次显示收益时间
周一	周三
周二	周四
周三	周五
周四	周六
周五	下周二
周六	下周三
周天	下周三

提交结果表 tc_comp_predict_table

字段	类型	含义	示例
report_date	bigint	日期	20140901
purchase	bigint	申购总额	40000000
redeem	bigint	赎回总额	30000000

每一行数据是一天对申购、赎回总额的预测值，输出2014年9月每天的预测，共30行。 purchase 和 redeem 都是金额数据，精确到分

输出示意：

20140901	40000000	30000000
20140902	40000000	30000000
20140903	40000000	30000000

1.1.2数据探索

导入相关模块

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from fbprophet import Prophet
from sklearn.metrics import mean_squared_error, mean_absolute_error
plt.style.use('fivethirtyeight') # For plots

ubt = pd.read_csv(PATH+'user_balance_table.csv',parse_dates=(['report_date']))

查看数据集

ubt.head()

plt.rcParams['figure.figsize'] = (25, 4.0)  # set figure size

ubt[['total_purchase_amt', 'total_redeem_amt']].plot()
plt.grid(True, linestyle="-", color="green", linewidth="0.5")
plt.legend()
plt.title('purchase and redeem of every month')

plt.gca().spines["top"].set_alpha(0.0)
plt.gca().spines["bottom"].set_alpha(0.3)
plt.gca().spines["right"].set_alpha(0.0)
plt.gca().spines["left"].set_alpha(0.3)

plt.show()

完整代码

import math
import numpy
import pandas
from keras.layers import LSTM, RNN, GRU, SimpleRNN
from keras.layers import Dense, Dropout
from keras.callbacks import EarlyStopping
import matplotlib.pyplot as plt
from keras.models import Sequential
from sklearn.preprocessing import MinMaxScaler
import os

numpy.random.seed(2019)


class RNNModel(object):
    def __init__(self, look_back=1, epochs_purchase=20, epochs_redeem=40, batch_size=1, verbose=2, patience=10, store_result=False):
        self.look_back = look_back
        self.epochs_purchase = epochs_purchase
        self.epochs_redeem = epochs_redeem
        self.batch_size = batch_size
        self.verbose = verbose
        self.store_result = store_result
        self.patience = patience
        self.purchase = df_tmp.values[:, 0:1]
        self.redeem = df_tmp.values[:, 1:2]
        
    def access_data(self, data_frame):
        # load the data set
        data_set = data_frame
        data_set = data_set.astype('float32')

        # LSTMs are sensitive to the scale of the input data, specifically when the sigmoid (default) or tanh activation functions are used. It can be a good practice to rescale the data to the range of 0-to-1, also called normalizing.
        scaler = MinMaxScaler(feature_range=(0, 1))
        data_set = scaler.fit_transform(data_set)

        # reshape into X=t and Y=t+1
        train_x, train_y, test = self.create_data_set(data_set)

        # reshape input to be [samples, time steps, features]
        train_x = numpy.reshape(train_x, (train_x.shape[0], 1, train_x.shape[1]))
        return train_x, train_y, test, scaler

    # convert an array of values into a data set matrix
    def create_data_set(self, data_set):
        data_x, data_y = [], []
        for i in range(len(data_set)-self.look_back - 30):
            a = data_set[i:(i + self.look_back), 0]
            data_x.append(a)
            data_y.append(list(data_set[i + self.look_back: i + self.look_back + 30, 0]))
        # print(numpy.array(data_y).shape)
        return numpy.array(data_x), numpy.array(data_y), data_set[-self.look_back:, 0].reshape(1, 1, self.look_back)

    def rnn_model(self, train_x, train_y, epochs):
        model = Sequential()
        model.add(LSTM(64, input_shape=(1, self.look_back), return_sequences=True))
        model.add(LSTM(32, return_sequences=False))
        model.add(Dense(32))
        model.add(Dense(30))
        model.compile(loss='mean_squared_error', optimizer='adam')
        model.summary()
        early_stopping = EarlyStopping('loss', patience=self.patience)
        history = model.fit(train_x, train_y, epochs=epochs, batch_size=self.batch_size, verbose=self.verbose, callbacks=[early_stopping])
        return model

    def predict(self, model, data):
        prediction = model.predict(data)
        return prediction

    def plot_show(self, predict):
        predict = predict[['purchase', 'redeem']]
        predict.plot()
        plt.show()

    def run(self):
        purchase_train_x, purchase_train_y, purchase_test, purchase_scaler = self.access_data(self.purchase)
        redeem_train_x, redeem_train_y, redeem_test, redeem_scaler = self.access_data(self.redeem)

        purchase_model = self.rnn_model(purchase_train_x, purchase_train_y, self.epochs_purchase)
        redeem_model = self.rnn_model(redeem_train_x, redeem_train_y, self.epochs_redeem)

        purchase_predict = self.predict(purchase_model, purchase_test)
        redeem_predict = self.predict(redeem_model, redeem_test)

        test_user = pandas.DataFrame({'report_date': [20140900 + i for i in range(1, 31)]})

        purchase = purchase_scaler.inverse_transform(purchase_predict).reshape(30, 1)
        redeem = redeem_scaler.inverse_transform(redeem_predict).reshape(30, 1)

        test_user['purchase'] = purchase
        test_user['redeem'] = redeem
        print(test_user)

        """Store submit file"""
        if self.store_result is True:
            test_user.to_csv('submit_lstm.csv', encoding='utf-8', index=None, header=None)
            
        """plot result picture"""
        self.plot_show(test_user)
        
if __name__ == '__main__':
	PATH = '/content/purchase/Purchase Redemption Data/'
	ubt = pd.read_csv(PATH+'user_balance_table.csv')
	df_tmp = ubt.groupby(['report_date'])['total_purchase_amt', 'total_redeem_amt'].sum()
	df_tmp.index = pd.to_datetime(df_tmp.index, format='%Y%m%d')
    initiation = RNNModel(look_back=40, epochs_purchase=150, epochs_redeem=230, batch_size=16, verbose=2, patience=50, store_result=True)
    initiation.run()

提交结果得到的分数：

1.2新闻内容自动提取及呈现

数据地址：https://3w.huanqiu.com/a/c36dc8/3xqGPRBcUE6?agt=8
输入任意的新闻网址，对其进行：
1）抓取正文内容，对非中文内容进行清洗
2）文章关键词
3）文章摘要，即关键句
4）词云可视化

#!/usr/bin/python3
# -*- coding: utf-8 -*-
"""
# @author : biao chen
# @Project : Python_Files
# @File : chinese_cut.py
# @Software: PyCharm
# @Time : 2021/1/29 下午9:09
# code is far away from bugs with the god animal protecting
    I love animals. They taste delicious.
             ┏ ┓    ┏┓
            ┏ ┛┻ ━━━┛┻┓
            ┃     ☃   ┃
            ┃  ┳┛  ┗┳  ┃
            ┃     ┻    ┃
            ┗━┓      ┏━┛
              ┃      ┗━━━┓
              ┃  神兽保佑 ┣┓
              ┃　永无BUG！┏┛
              ┗┓┓┏━┳┓┏┛
               ┃┫┫  ┃┫┫
               ┗┻┛  ┗┻┛
"""
import re
import jieba
import requests
from bs4 import BeautifulSoup
import jieba.posseg as pseg
from wordcloud import WordCloud

# 要解析的新闻地址
url = 'https://3w.huanqiu.com/a/c36dc8/3xqGPRBcUE6?agt=8'

html = requests.get(url, timeout=10)
content = html.content
soup = BeautifulSoup(content,'html.parser', from_encoding='utf-8')
text = soup.get_text()
# 获取人物，地点
words = pseg.lcut(text)

# 人物集合
news_person = {word for word, flag in words if flag=='nr'}
news_place = {word for word, flag in words if flag=='ns'}
print('新闻中的人物:', news_person)
print('新闻中的地点:', news_place)

# 提取中文以及相关标点
new_text = re.sub('^[\u4e00-\u9fa5。，！：、]{3,}','',text)

# 去掉停用词
def remove_stop_words(f):
  stop_words = []
  for stop_word in stop_words:
    f = f.replace(stop_word, '')
  return f

def create_word_cloud(f):
  f = remove_stop_words(f)
  seg_list = jieba.lcut(f)
  cut_list = ' '.join(seg_list)
  wc = WordCloud(max_words=100, width=2000, height=1200, font_path='msyh.ttf')
  wordcloud = wc.generate(cut_list)
  wordcloud.to_file("wordcloud_prefect.jpg")

create_word_cloud(text)