import pandas as pd
import plotly.graph_objects as go 

colors = ['#FF0000','#FFBB00','#ffff00','#00FF00','#0000FF','#9C009C']

df = pd.read_csv("https://raw.githubusercontent.com/hangack/project-green/main/Kaggle_Survey-2021/data/kaggle-survey-2021/kaggle_survey_2021_responses.csv", dtype='unicode')
#df = pd.read_csv("../input/kaggle-survey-2021/kaggle_survey_2021_responses.csv")

df_ChJp = df[df.Q3.isin(["Japan","China"])]

df_Ch = df_ChJp[df_ChJp.Q3.isin(["China"])]
df_Jp = df_ChJp[df_ChJp.Q3.isin(["Japan"])]

def indiQ_value_counts(dataframe, indi_Qnum):
    df = dataframe[indi_Qnum][1:].value_counts()
    return df

df_Jp_age = indiQ_value_counts(df_Jp, 'Q1')
df_Ch_age = indiQ_value_counts(df_Ch, 'Q1')

Bar_C = go.Bar(name='China',
               x=df_Ch_age.index,
               y=df_Ch_age.values
              )
Bar_J = go.Bar(name='Japan',
               x=df_Jp_age.index,
               y=df_Jp_age.values
              )

fig = go.Figure(data=[Bar_C,
                      Bar_J])

fig.update_layout(title='Age: Japan & China',
                  xaxis_title="Age", yaxis_title='Counts'
                 )

fig.show()

df_Ch_sortAge = df_Ch_age.sort_index()
df_Jp_sortAge = df_Jp_age.sort_index()

df_Ch_sortAge

df_Ch_sortAge.loc['60-69'] = 0
df_Ch_sortAge = df_Ch_sortAge.sort_index()

import pandas as pd
import plotly.graph_objects as go 

colors = ['#FF0000','#FFBB00','#ffff00','#00FF00','#0000FF','#9C009C']

df = pd.read_csv("https://raw.githubusercontent.com/hangack/project-green/main/Kaggle_Survey-2021/data/kaggle-survey-2021/kaggle_survey_2021_responses.csv", dtype='unicode')
#df = pd.read_csv("../input/kaggle-survey-2021/kaggle_survey_2021_responses.csv")

df_ChJp = df[df.Q3.isin(["Japan","China"])]

df_Ch = df_ChJp[df_ChJp.Q3.isin(["China"])]
df_Jp = df_ChJp[df_ChJp.Q3.isin(["Japan"])]

fig_j = go.Figure(data=[go.Pie(labels=df_Jp['Q2'][1:].value_counts().index, 
                               values=df_Jp['Q2'][1:].value_counts().values
                              )
                       ]
                 )

fig_j.show()

def indiQ_value_counts(dataframe, indi_Qnum):
    df = dataframe[indi_Qnum][1:].value_counts()
    return df

df_Jp_gen = indiQ_value_counts(df_Jp, 'Q2')
df_Ch_gen = indiQ_value_counts(df_Ch, 'Q2')

from plotly.subplots import make_subplots

Pie_J = go.Pie(labels=df_Jp_gen.index, 
               values=df_Jp_gen.values
              )

Pie_C = go.Pie(labels=df_Ch_gen.index, 
               values=df_Ch_gen.values
              )

fig = make_subplots(rows=1, cols=2,specs=[[{"type": "domain"},{"type": "domain"}]])

fig.add_trace(Pie_J,row=1,col=1)
fig.add_trace(Pie_C,row=1,col=2)

fig.show()

Pie_J = go.Pie(labels=df_Jp_gen.index, 
               values=df_Jp_gen.values,
               title='Japan',
               textinfo ='label,percent'
              )

Pie_C = go.Pie(labels=df_Ch_gen.index, 
               values=df_Ch_gen.values,
               title='China',
               textinfo ='label,percent'
              )

fig = make_subplots(rows=1, cols=2,specs=[[{"type": "domain"},{"type": "domain"}]])

fig.add_trace(Pie_J,row=1,col=1)
fig.add_trace(Pie_C,row=1,col=2)

fig.update_layout(title_text='Gender')
fig.update_traces(marker=dict(colors=colors[1:]))

fig.show()

Pie_J = go.Pie(labels=df_Jp_gen.index, 
               values=df_Jp_gen.values,
#               pull=[0,0,0.2,0.2,0.2],    ## 중앙에서 n% 떨어진 위치 할당
               title='Japan',
               textinfo ='label,percent',
               hole=0.3
              )

Pie_C = go.Pie(labels=df_Ch_gen.index, 
               values=df_Ch_gen.values,
#               pull=[0,0,0.2,0.2,0.2],
               title='China',
               textinfo ='label,percent',
               hole=0.3
              )

fig = make_subplots(rows=1, cols=2,specs=[[{"type": "domain"},{"type": "domain"}]])

fig.add_trace(Pie_J,row=1,col=1)
fig.add_trace(Pie_C,row=1,col=2)

fig.update_layout(title_text='Gender',
#                  showlegend=False,    ## ledend(lable 목록) 시각적으로 제거
                  margin=dict(t=0, b=0, l=0, r=0)
                 )
fig.update_traces(marker=dict(colors=colors[1:]))


fig.show()

import pandas as pd

#df = pd.read_csv("D:/_Bdata/Codding-base-Python/Python/Python-jupyter/Kaggle Survey - 2021 Analysis - Plotly/kaggle_survey_2021_responses.csv")

df = pd.read_csv("E:/Fear/Univ/Big_data/Training/Github/Codding-base-Python/Python/Python-jupyter/Kaggle Survey - 2021 Analysis - Plotly/kaggle_survey_2021_responses.csv")

#df = pd.read_csv("../input/kaggle-survey-2021/kaggle_survey_2021_responses.csv")

from warnings import filterwarnings
filterwarnings('ignore')

df = pd.read_csv("csv url", low_memory=False)

df = pd.read_csv("csv url", dtype='unicode')

import numpy as np
import pandas as pd

from warnings import filterwarnings
filterwarnings('ignore')

#df = pd.read_csv("D:/_Bdata/Codding-base-Python/Python/Python-jupyter/Kaggle Survey - 2021 Analysis - Plotly/kaggle_survey_2021_responses.csv")
df = pd.read_csv("E:/Fear/Univ/Big_data/Training/Github/Codding-base-Python/Python/Python-jupyter/Kaggle Survey - 2021 Analysis - Plotly/kaggle_survey_2021_responses.csv")
df_col_name = df.columns[1:]
df_col_name

def input_num():
    print("input Question no.: ")
    Qnum = input()
    Qnum_subQ = [s for s in df_col_name if "Q"+Qnum+"_" in s]
    
    if Qnum_subQ == []:
        return "Q"+Qnum+" has not part_Q"
    
    Question_type = None
    if [s for s in Qnum_subQ if ("A"or"B") in s]:
        print("input Q"+Qnum+"'s type")
        Question_type = input().upper()
        
    if Qnum_subQ:
        print("input Q"+Qnum+"'s last part no.: ")
        part_num = input()
    
    
    return questions_count(Qnum,part_num,Question_type)

def questions_count(question_num, part_num, Question_type = False):
    part_questions = []
    
    if Question_type  in ["A","B"]:
        part_questions = ['Q'+question_num+"_"+Question_type+"_Part_"+str(j) for j in range(1,int(part_num))]
        part_questions.append("Q"+question_num+"_"+Question_type+"_OTHER")
    else:
        part_questions = ['Q'+question_num+'_Part_'+str(j) for j in range(1,int(part_num))]
        part_questions.append('Q'+question_num+'_OTHER')
        
    categories = []
    counts = []
    for i in part_questions:
        category = df[i].value_counts().index[0]
        val = df[i].value_counts()[0]
        categories.append(category)
        counts.append(val)
        
    combined_df = pd.DataFrame()
    combined_df['Category'] = categories
    combined_df['Count'] = counts
    
    combined_df = combined_df.sort_values(['Count'], ascending = False)
    return combined_df

input_num()

input_num()

input_num()

# c.NotebookApp.notebook_dir = ''

c.NotebookApp.notebook_dir = 'E:/Fear/Univ/Big_data/Training/Github/Codding-base/Python/Python-jupyter'

c.NotebookApp.notebook_dir = 'E:\\Fear\\Univ\\Big_data\\Training\\Github\\Codding-base\\Python\\Python-jupyter'

import pandas as pd       ## pandas 라이브러리

f1 = "E:\\Fear\\Univ\\4-2\\대기정보전산학\\실습\\co2.csv"
f2 = "E:\\Fear\\Univ\\4-2\\대기정보전산학\\실습\\1880-2019.csv"

data1 = pd.read_csv(f1, engine='python')

styr = 1900
edyr = 2014+1 # [이상:미만] 이므로 2014 -> 2015

year = data1['year']    ### ['year'] -> year 열만 읽어낸다.
conc = data1['data_mean_global']

time = year[styr:edyr]
co2 = conc[styr:edyr]

print(co2)
## [n번째 줄]     [co2값]

print(co2.head(3))    ## 위에서 n개
print(co2.tail(3))    ## 아래서 n개

import numpy as np        ## numpy 라이브러리

data2 = np.genfromtxt(f2,  encoding='utf8',dtype=None,delimiter=',',names=('year','value'), skip_header=5)
## 변수 / 인코딩 / 혼합 데이터 : dtype=None / 값 사이 구분 / 열 이름 지정 / 머릿말 생략 열 수

size=len(data2)

print(size)

for i in range(0,size):
    t = data2['year'][i]    ## year 열의 i번째 값을 t에 저장
    if t == 1900:
        styr = i
    elif t == 2015:
        edyr = i
    i=i+1
    
print(styr)
print(edyr)

temp = data2['value'][styr:edyr]

print(temp)

%matplotlib notebook  
## matplotlib 그림툴 로드

import matplotlib.pyplot as plt

plt.plot(time,co2,'b')   ## 'matplotlib named color' 참고
plt.xlabel('Year')
plt.ylabel('CO₂concentration')  ## 한글 유니코드, 특수문자 모두 사용가능
plt.show()

plt.close()

plt.plot(time,temp,'r')
plt.xlabel('Year')
plt.ylabel('Global Mean Surface Temperature')
plt.show()

plt.close()

fig, ax1 = plt.subplots()   ## matplotlib.pyplot.subplots 참고
ax2 = ax1.twinx()            ## 축을 하나 더 추가하기 위한 함수 twinx

ax1.set_ylabel('GMST anomaly (C)')            ##
ax1.set_xlabel('Year')                        ##   라벨 지정
ax2.set_ylabel('CO₂(ppm)')                   ##

line1 = ax1.plot(time, temp, color='crimson', label='Global temperature anomaly',linewidth = 1.5)
line2 = ax2.plot(time, co2, color='limegreen', label='CO₂concentration',linewidth = 2.)

lines = line1 + line2                         ## 두 장의 line 그림을 합친 변수
labels = [l.get_label() for l in lines]
ax1.legend(lines, labels, loc='upper left')    ## loc 'location'     ## matplotlin.axes.Axes.legend 참고


plt.show

plt.close()

fig, ax1 = plt.subplots() 
ax2 = ax1.twinx() 

ax1.set_ylabel('GMST anomaly (C)')   
ax1.set_xlabel('Year')     
ax2.set_ylabel('CO₂(ppm)')  
ax1.set_ylim([-0.46,0.72])    ## 범위 조정
ax2.set_ylim([280,390])       ##
ax1.set_xlim([1900,2014])

line1 = ax1.plot(time, temp, color='crimson', label='Global temperature anomaly',linewidth = 1.5)
line2 = ax2.plot(time, co2, color='limegreen', label='CO₂concentration',linewidth = 2.)

lines = line1 + line2      
labels = [l.get_label() for l in lines]
ax1.legend(lines, labels, loc='upper left') 


plt.show

plt.close()

import math    # math 라이브러리를 불러오는 명령어.
            ''' 라이브러리 명령어는 [라이브러리명(혹은 as로 지정한 임의의 명칭)].[명령어]로 사용할 수 있으며.
                명령어 자동완성(혹은 명령어 목록)은 tap 키로 사용 및 확인 가능하다.
            '''

print(math.cos( (300 / 180) * math.pi ))
print(math.factorial(4))

import numpy as np
print(np.__version__)

import matplotlib.pyplot as plt   # matplotlib (패키지)  pyplot (모듈)      # A as B  -> 변수 A를 B로 설정
#여기서 plt는 object 이다.   /    object(객체)는 .을 찍을 수 있다.

plt.plot([1,2,3,4])

# import '모듈 이름' : 모듈 불러오는 명령어

import math            # math 는 객체  - . 을 찍을 수 있다.
# 수학 작업을 할 때 :  math library(파이썬 내장) 혹은 numpy library(외부 다운로드)
n = math.factorial(5)
print(n)

%%writefile my_module.py
my_variable = 10
def my_factorial(n) :
    x=1
    for i in range(1,n+1):
        x=x*i
    return(x)

import my_module as math_lib        ## 원하는 이름으로 변경
print(math_lib.my_variable)

# from '모듈 이름' import '함수 이름' : factorial 함수만 import

from math import factorial             ## math.factorial -> factorial
n = factorial(5)/factorial(3)
print(n)

# 여러 함수를 import

from math import (factorial, acos, pi, sin)
n = factorial(3) + acos(1)
print(n)


# 모든 함수를 import, * : 모든 것

from math import *
n = sqrt(5) + fabs(-12.5)   ## sqrt : 루트 / fabs : 절대값
print(n)

%%writefile mod1.py

def add(x,y):
    return x+y

def sub(x,y):
    return x-y

import mod1
i = mod1.add(3,4)
print(i)

from mod1 import *
i = add(3,4)
print(i)

i = mod1.sub(4,2)
print(i)

%%writefile mod2.py

PI = 3.141592

def add(x,y):
    return x+y

# 모듈에 변수 포함 가능

import mod2
print(mod2.PI)