Table of Contents

• 1  Total Reimbursement Spending
  • 1.1  Trend
  • 1.2  Difference
  • 1.3  Statistic Data
• 2  Parent Expense Type
  • 2.1  Overall Amount
  • 2.2  Percentage of total
  • 2.3  Changes over time
• 3  Child Expense Type
  • 3.1  Interesting Trend in 2018
  • 3.2  Business Purposes in End of 2018
  • 3.3  Employee Spending by Categories in the End of 2018
• 4  TODO:

Reimbursement Exploratory Data Analysis

This is a exploratory data analysis for global reimbursement amount.

• The date used is "Sent for Payment Date"
• Jun 2017 and July 2017 has been dropped in this dataset as that time we are under initial implementation status

Target:

1. To generate a complete picture of global reimbursement spending over time
2. To prepare for modeling cash forecast
3. To help day-to-day management and decision making

Benefit:

1. Generate cash forecast model to help prediction
2. Get insights and intuitions into global reimbursement spendings

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
import seaborn as sns
import time
from datetime import datetime

import warnings
warnings.filterwarnings('ignore')

def fxn():
    warnings.warn("deprecated", DeprecationWarning)

with warnings.catch_warnings():
    warnings.simplefilter("ignore")
    fxn()

%matplotlib inline
sns.set(font_scale = 1.2)

#plotly.offline doesn't push your charts to the clouds
import plotly.offline as pyo
#allows us to create the Data and Figure objects
from plotly.graph_objs import *
import plotly.graph_objs as go
#plotly.plotly pushes your charts to the cloud  
import plotly.plotly as py

#lets us see the charts in an iPython Notebook
pyo.offline.init_notebook_mode() # run at the start of every ipython