挑战Python：20分钟内搭建仪表板的实战指南

# 这些数据可以在公众号后台回复【云朵君】，联系作者获取。
# 1.导入必要的库
import pandas as pd
import numpy as np
import streamlit as st

# 2.设置页面配置
st.set_page_config(
    page_title="This is my title",  # 页面的标题
    page_icnotallow="📈",                  # favicon
    layout="wide",
)

# 3.定义你的项目中使用的所有函数
# 4.对于每一个函数，在其前面添加"@st.experimental_memo"。这就是
# 来记忆每个函数的执行。这将使应用程序运行得更快。
# 特别是当用户与仪表盘上的一些元素互动时

@st.experimental_memo
def function(x):
    return y
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.

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
  
# 我没有在这里定义所有的函数，因为这将延长文章的篇幅。
# 我将在文章的最后提供完整的代码。
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.
30.
31.
32.
33.
34.
35.
36.
37.
38.

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") # 来上传文件
1.
2.
3.
4.
5.
6.
7.
8.

If uploaded_file is not None:# 这很重要，因为没有这个。
                             # 当没有上传的文件时，会出现
                             # 一个错误，因为df没有被定义....
  df = pd.read_csv(upload_file) # 读取该文件
  df_processed = process_df(df) # 清洁数据
  
  # 仪表盘标题
  st.header("Live Dashboard")
  # 过滤器
  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') # 来下载该文件
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.

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)
    
    # 通过使用f-strings动态标题
    st.header(f"Live {cohorts.index[0]} to {cohorts.index[-1]} Cohort Dashboard")
    
    # 过滤器
    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')
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.

kpi1, kpi2, kpi3 = st.columns(3) # 创建三个占位符
if uploaded_file is not None:
    
    aov = np.mean(df['total_sales'])
    aov_goal = 95.00
    kpi1.metric(
        # 给这个指标贴上标签
        label="AOV", 
        # 计算度量值
        value=f"$ {round(aov,2)}",
        # 计算与目标相比的变化（向上/向下箭头）
        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)}%"
    )
1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.
12.
13.
14.
15.
16.
17.
18.
19.
20.
21.
22.
23.
24.
25.
26.
27.
28.
29.

streamlit run cohort-demo.py
1.

#只是简单地列出所有的库。你也可以包括版本
pandas
numpy
streamlit
matplotlib
seaborn
datetime
plotly
1.
2.
3.
4.
5.
6.
7.
8.

#只要复制和粘贴这个
mkdir -p ~/.streamlit/
echo "\
[server]\n\
headless = true\n\
port = $PORT\n
enableCORS = false\n
\n\
" > ~/.streamlit/config.toml
1.
2.
3.
4.
5.
6.
7.
8.
9.

web: sh setup.sh && streamlit run cohort-demo.py
1.