# panda data analyze

## Series

import pandas    # Usually, we will set pandas as pd 

# create column


column = pandas.Series([12,32,43,12]) 
print(column)

print("print Max",column.max())
print("print min",column .min())
print("print media",column.median())
print("print arerage",column.mean())

column*=2     #the column multiple 2 
print(column)


# 
column=column==24
print(column)

## Dataframe

Dim2Data=pandas.DataFrame(
    {
        "name":["jacky","mandy","meowhecker"],
        "salary":[999999999,12,9999999999999999999999999999],
        "age":[20,40,23]
    },index={"a","b","c"}  #set up table index
)
print(Dim2Data)

print("=======================================")
#basis information 

print(Dim2Data.iloc[2])    #iloc=I location -＞　using list show the row  , sequence 
print("data_type"+"(rows,columns)",Dim2Data.shape)
print("data index",Dim2Data.index)

print("======================================")

print(Dim2Data.loc["c"],sep="\n") # lic -> indext

# calculate the average of salarys

columnSalary = Dim2Data["salary"]
'''
total = columnSalary[0]+columnSalary[1]
print(total)
'''
print(columnSalary.mean()) # mean get average

## Create new columns

import pandas as pd 
Dim2Data=pandas.DataFrame(
    {
        "name":["jacky","mandy","meowhecker"],
        "salary":[9921319,23213421,99999],
        "age":[20,40,23]
    }, index=range(3)  #set up table index
)


Dim2Data["rank"] = pandas.Series([3,2,1])  #　正式寫法
Dim2Data["test"] = [1,2,3] # 偷懶寫法

print(Dim2Data)

# Fillter data

import pandas

testColumn = pandas.Series([54,23,90])

#filter value

condition = testColumn>30
print("filterCondition",condition,sep="\n")


print("=================================================")

filterTestColumn = testColumn[condition]
print(filterTestColumn,sep="\n")


print("=================================================")

testColumn2 = pandas.Series(["智晟王者","家偉盜賊","冠霖盜賊"])


print(testColumn2)


print("===================================================")
print("display what you want to show")

stringCondition= testColumn2.str.contains("王者") #options   #stringCondition = [True,False,True,]

testColumn2 = testColumn2[stringCondition]
print(testColumn2)

print("==================================================")

studentTable = pandas.DataFrame(
    {
        "name":["智晟","家偉","冠霖","佑豪"],
        "score":[100,80,75,34,]

    }
)
print(studentTable)
print("=================================================")
print("pass > 60")

condition = studentTable["score"] >= 60           #condition = [True,False,False,True]

print(studentTable[condition])

print("==================================================")
print("取得智晟的成績")

condition = studentTable["name"] == "智晟"
print(studentTable[condition])

# Analyze Data

resource file : by 澎澎 youtuber video

# Analyze data


import pandas 

#to read the data and to ransport csv into dataFrame

dataTable = pandas.read_csv("googleplaystore.csv")
print(dataTable)

print("==================================================")

print("trying to get information")

print("table 大概的形狀", dataTable.shape)
print("tuble columns",dataTable.columns) 
print("==================================================")


print("Showing data that is we want to know.")

print(dataTable["Rating"])

rating = dataTable["Rating"]

print("Average of Rating", rating.mean())
print("MedianNumber of Rating", rating.median())
print("前一百名 rating 平均",rating.nlargest(100).mean())




print("===================================================")
print("找出奇怪的數值")

condictionFindOver5 = rating >5
print(dataTable[condictionFindOver5]) 


print("===================================================")
print("Exclude the odd data")

conditionExcludeOver5 = rating <=5
exData = dataTable[conditionExcludeOver5]
print(exData)



print("前一百名 rating 平均",exData["Rating"].nlargest(100).mean())

print("====================================================")
print("to Analye Install")

print(dataTable.columns)
print(dataTable["Installs"])




print("=======================================================")
print("filter the odd data ")
# We could know odd charator (+ and ,)

dataTable["Installs"] = pandas.to_numeric(dataTable["Installs"].str.replace("[+,]","").replace("Free","")) 
#print(dataTable["Installs"][10472]) # Fucking Free 



print("Average of install is ", dataTable["Installs"].mean())


over100000Condition =  dataTable["Installs"]> 100000
print("Over 100000 installed ",dataTable[over100000Condition].shape) 




print("========================================================")
print("Using keywords search the APP")

keywords = input("Enter the keywords")
conditionKeyword = dataTable["App"].str.contains(keywords,case= False) # contains(variable, ignore 大小寫)
print("The result of a searching is:", dataTable[conditionKeyword])