# 這些數(shù)據(jù)可以在公眾號后臺回復(fù)【云朵君】，聯(lián)系作者獲取。
# 1.導(dǎo)入必要的庫
import pandas as pd
import numpy as np
import streamlit as st

# 2.設(shè)置頁面配置
st.set_page_config(
    page_title="This is my title",  # 頁面的標(biāo)題
    page_icnotallow="??",                  # favicon
    layout="wide",
)

# 3.定義你的項(xiàng)目中使用的所有函數(shù)
# 4.對于每一個(gè)函數(shù)，在其前面添加"@st.experimental_memo"。這就是
# 來記憶每個(gè)函數(shù)的執(zhí)行。這將使應(yīng)用程序運(yùn)行得更快。
# 特別是當(dāng)用戶與儀表盤上的一些元素互動(dòng)時(shí)

@st.experimental_memo
def function(x):
    return y

import pandas as pd
import numpy as np 
import matplotlib.pyplot as plt 
import seaborn as sns
import matplotlib as mpl 
from datetime import date, datetime
import streamlit as st  

st.set_page_config(
    page_title="Cohorts Dashboard",
    page_icnotallow="??",
    layout="wide",
)

@st.experimental_memo
def purchase_rate(customer_id):
    purchase_rate = [1]
    counter = 1
    for i in range(1,len(customer_id)):
        if customer_id[i] != customer_id[i-1]:
            purchase_rate.append(1)
            counter = 1
        else:
            counter += 1
            purchase_rate.append(counter)
    return purchase_rate
@st.experimental_memo
def join_date(date, purchase_rate):
    join_date = list(range(len(date)))
    for i in range(len(purchase_rate)):
        if purchase_rate[i] == 1:
            join_date[i] = date[i]
        else:
            join_date[i] = join_date[i-1]
    return join_date
  
# 我沒有在這里定義所有的函數(shù)，因?yàn)檫@將延長文章的篇幅。
# 我將在文章的最后提供完整的代碼。

st.title("Cohort Interactive Dashboard Demo")
st.markdown("""
This webapp performs cohort analysis of my_company data!
* **Python libraries used:** base64, pandas, streamlit, numpy, matplotlib, seaborn
* **Data source:** [Shopify](https://company_name.myshopify.com/admin)
* You need to select the data file first to proceed.
""")
uploaded_file = st.file_uploader("Choose a file") # 來上傳文件

If uploaded_file is not None:# 這很重要，因?yàn)闆]有這個(gè)。
                             # 當(dāng)沒有上傳的文件時(shí)，會(huì)出現(xiàn)
                             # 一個(gè)錯(cuò)誤，因?yàn)閐f沒有被定義....
  df = pd.read_csv(upload_file) # 讀取該文件
  df_processed = process_df(df) # 清潔數(shù)據(jù)
  
  # 儀表盤標(biāo)題
  st.header("Live Dashboard")
  # 過濾器
  first_filter = st.selectbox('Select first filter',['Option 1', 'Option 2', 'Option 3])

    second_filter = st.multiselect('Select second filter', ['Option 1','Option 2','Option 3','Option 4'])

    output = display_function(data_input,first_filter,second_filter)
    st.dataframe(output)
    st.download_button(label='Download csv', data=output.to_csv(), mime='text/csv') # 來下載該文件

if uploaded_file is not None:
    df = pd.read_csv(uploaded_file)
    df_processed = process_df(df)
    df_cohorts = cohort_numbers(df_processed)
    cohorts = cohort_percent(df_cohorts)
    
    # 通過使用f-strings動(dòng)態(tài)標(biāo)題
    st.header(f"Live {cohorts.index[0]} to {cohorts.index[-1]} Cohort Dashboard")
    
    # 過濾器
    first_filter= st.selectbox('Select type of cohort',['By unique customers', 'By percentage', 'By AOV'])

    second_filter = st.multiselect('Select cohort', list(cohorts.index))

    output = select_which_table_to_draw(df_processed,first_filter,second_filter)
    st.dataframe(output)
    st.download_button(label='Download csv', data=output.to_csv(), mime='text/csv')

kpi1, kpi2, kpi3 = st.columns(3) # 創(chuàng)建三個(gè)占位符
if uploaded_file is not None:
    
    aov = np.mean(df['total_sales'])
    aov_goal = 95.00
    kpi1.metric(
        # 給這個(gè)指標(biāo)貼上標(biāo)簽
        label="AOV", 
        # 計(jì)算度量值
        value=f"$ {round(aov,2)}",
        # 計(jì)算與目標(biāo)相比的變化（向上/向下箭頭）
        delta=f"-${round(aov_goal-aov,2)}" if aov_goal>aov else f"${round(aov-aov_goal,2)}",
    )

    nc = np.mean(df.loc[df['customer_type']=='First-time'].groupby(['day']).count()['customer_id'])
    nc_goal = 30
    kpi2.metric(
        label="New customers/day",
        value=int(nc),
        delta=f"-{round((nc_goal-nc)/nc_goal*100,2)}%" if nc_goal>nc else f"{round((nc - nc_goal)/nc_goal*100,0)}%",
    )

    rc = np.mean(df.loc[df['customer_type']=='Returning'].groupby(['day']).count()['customer_id'])
    rc_goal = 250
    kpi3.metric(
        label="Returning customers/day",
        value= int(rc),
        delta=f"-{round((rc_goal - rc)/rc_goal*100,2)}%" if rc_goal>rc else f"{round((rc-rc_goal)/rc_goal*100,2)}%"
    )

streamlit run cohort-demo.py

#只是簡單地列出所有的庫。你也可以包括版本
pandas
numpy
streamlit
matplotlib
seaborn
datetime
plotly

#只要復(fù)制和粘貼這個(gè)
mkdir -p ~/.streamlit/
echo "\
[server]\n\
headless = true\n\
port = $PORT\n
enableCORS = false\n
\n\
" > ~/.streamlit/config.toml

web: sh setup.sh && streamlit run cohort-demo.py