'''
Install two packages in conda, installation command:
conda install numpy, pandas
'''
# import numpy package
import numpy as np
# import pandas package
import pandas as pd

'''
Definition: 
One dimension array, parameters passed was a list[2,3,4,5]
'''
a = np.array([2,3,4,5])

# check items
a[0]

# section acess: Acquired items from designated range series number 
# a[1:3] Acquired items from series no. 1 to series no.3
a[1:3]

'''
dtype detail info link reference:
https://docs.scipy.org/doc/numpy-1.10.1/reference/arrays.dtypes.html
'''
# Check data types
a.dtype

# Statistical caculation
# mean
a.mean()

# standard deviation
a.std()

# vectorization: multiply scalar
b = np.array([1,2,3])
c = b * 4
c

'''
Numpy Two-dimensional data structure:
Array
'''
# Define Two-dimensional data array
a = np.array([[1,2,3,4],[5,6,7,8],[9,10,11,12]
])

# Acquire the items that row number is 0, and Column number is 2
a[0,2]

# Acquire first row items
a[0,:]

# Acquire first column items 
a[:,0]

'''
If the axis parameters is not designated, 
the mean of the entire array will be calculated 
'''
a.mean()

# caculate according to axis: axis = 1 , caculate evey single row
a.mean(axis = 1)

a.mean(axis = 0)

'''
Definition: 
Pandas One Dimension Data Analysis: Series 
''''''
One day stock price saved for 6 companies(USD),
Tenent 427 HKD equal to 54.74 USD.
'''
stockS = pd.Series([54.74, 190.9, 173.14, 1050.3, 181.86, 1139.49],index = ['tencent','alibaba','apple','google','facebook','amazon'])

stockS

# Acquired describe statistical info
stockS.describe()

stockS.iloc[0]

# loc attribution: used to acquire value according to the index
stockS.loc['tencent']

# vectorization: vectors addition
s1 = pd.Series([1,2,3,4], index = ['a','b','c','d'])
s2 = pd.Series([10,20,30,40], index = ['a','b','e','f'])
s3 = s1 + s2
s3

# Method 1: Delete missing value 
s3.dropna()

# Filled up the missing values
s3 = s2.add(s1, fill_value = 0)
s3

'''
Pandas Two-dimensional array: DataFrame
'''
# Step1: Define a dict, Mapping names and corresponding values 
salesDict = {'medecine purchased date':['01-01-2018 FRI','02-01-2018 SAT','06-01-2018 WED'],'social security card number':['001616528','001616528','0012602828'],'commodity code':[236701,236701,236701],'commodity name':['strong yinqiao VC tablets', 'hot detoxify clearing oral liquid','GanKang compound paracetamol and amantadine hydrochloride tablets'],'quantity sold':[6,1,2],'amount receivable':[82.8,28,16.8],'amount received':[69,24.64,15]
}# import OrdererDict
from collections import OrderedDict# Define an OrderedDict
salesOrderDict = OrderedDict(salesDict)# Define DataFrame: passing Dict, list name
salesDf = pd.DataFrame(salesOrderDict)

salesDf

# mean: caculating according to columns
salesDf.mean()

'''
iloc attributes used to acquired value according to position
'''
# check items at 1st row and 2nd column
salesDf.iloc[0,1] 

# Acquired all items of first row - collect every single colum
salesDf.iloc[0,:]

# Acquired all items of first column - collect every single row 
salesDf.iloc[:,0]

'''
loc attributes used to acquired value according to index
'''
# Check items from first row first column
salesDf.loc[0,'medecine purchased date']

# Acquired all items of column 'commodity code'
# Method 1:
salesDf.loc[:,'commodity code']

# Acquired all items of column 'commodity code'
# Method 2: Easy way
salesDf['commodity code']

# Select a few column data via list
salesDf[['commodity name','quantity sold']]

# Acquired data from define range of column via section 
salesDf.loc[:,'medecine purchased date':'quantity sold']

# Select via condition test
# Step 1: Establish query condition
querySer = salesDf.loc[:,'quantity sold'] > 1
type(querySer)

querySer

salesDf.loc[querySer,:]

# Read data from Excel
fileNameStr = 'C:UsersUSERDesktop#3Python3_The basic process of data analysisSales data of Chaoyang Hospital in 2018  - Copy.xlsx'
xls = pd.ExcelFile(fileNameStr)
salesDf = xls.parse('Sheet1')

# Print first three row to make sure data can work properly 
salesDf.head(3)

salesDf.shape

# Check the data type of one column 
salesDf.loc[:,'quantity sold'].dtype

# Check the statistics for each column
salesDf.describe()