五个Pandas 实战案例带你分析操作数据

目录

• 构建数据
• 分析维度1：时间
• 2019-2021年每月销量走势
• 2019-2021销售额走势
• 年度销量、销售额和平均销售额
• 分析维度2：商品
• 水果年度销量占比
• 各水果年度销售金额对比
• 商品月度销量变化
• 分析维度3：地区
• 不同地区的销量
• 分析维度4：用户
• 用户订单量、金额对比
• 用户水果喜好
• 用户分层—RFM模型
• 用户复购周期分析

import pandas as pd
import numpy as np
import random
from datetime import *
import time

import plotly.express as px
import plotly.graph_objects as go
import plotly as py

# 绘制子图
from plotly.subplots import make_subplots

order = pd.DataFrame({
    "time":time_range,  # 下单时间
    "fruit":fruit_list,  # 水果名称
    "name":name_list,  # 顾客名
    # 购买量
    "kilogram":np.random.choice(list(range(50,100)), size=len(time_range),replace=True) 
})

order

infortmation = pd.DataFrame({
    "fruit":fruits,
    "price":[3.8, 8.9, 12.8, 6.8, 15.8, 4.9, 5.8, 7],
    "region":["华南","华北","西北","华中","西北","华南","华北","华中"]
})

infortmation

df["year"] = df["time"].dt.year
df["month"] = df["time"].dt.month
# 同时提取年份和月份
df["year_month"] = df["time"].dt.strftime("%Y%m")

df

# 分年月统计销量
df1 = df.groupby(["year_month"])["kilogram"].sum().reset_index()

fig = px.bar(df1,x="year_month",y="kilogram",color="kilogram")
fig.update_layout(xaxis_tickangle=45)   # 倾斜角度

fig.show()

df2 = df.groupby(["year_month"])["amount"].sum().reset_index()

df2["amount"] = df2["amount"].apply(lambda x:round(x,2))

fig = go.Figure()
fig.add_trace(go.Scatter(  #
    x=df2["year_month"],
    y=df2["amount"],
    mode="lines+markers", # mode模式选择
    name="lines")) # 名字

fig.update_layout(xaxis_tickangle=45)   # 倾斜角度

fig.show()

df4 = df.groupby(["year","fruit"]).agg({"kilogram":"sum","amount":"sum"}).reset_index()
df4["year"] = df4["year"].astype(str)
df4["amount"] = df4["amount"].apply(lambda x: round(x,2))

from plotly.subplots import make_subplots
import plotly.graph_objects as go

fig = make_subplots(
    rows=1, 
    cols=3,
    subplot_titles=["2019年","2020年","2021年"],
    specs=[[{"type": "domain"},   # 通过type来指定类型
           {"type": "domain"},
           {"type": "domain"}]]
)  

years = df4["year"].unique().tolist()

for i, year in enumerate(years):
    name = df4[df4["year"] == year].fruit
    value = df4[df4["year"] == year].kilogram
    
    fig.add_traces(go.Pie(labels=name,
                        values=value
                       ),
                 rows=1,cols=i+1
                )

fig.update_traces(
    textposition="inside",   # "inside","outside","auto","none"
    textinfo="percent+label",
    insidetextorientation="radial",   # horizontal、radial、tangential
    hole=.3,
    hoverinfo="label+percent+name"
)

fig.show()

years = df4["year"].unique().tolist()

for _, year in enumerate(years):
    
    df5 = df4[df4["year"]==year]
    fig = go.Figure(go.Treemap( 
        labels = df5["fruit"].tolist(),
        parents = df5["year"].tolist(),
        values = df5["amount"].tolist(),
        textinfo = "label+value+percent root"
    ))
    
    fig.show()

fig = px.bar(df5,x="year_month",y="amount",color="fruit")
fig.update_layout(xaxis_tickangle=45)   # 倾斜角度
fig.show()

df7 = df.groupby(["year","region"])["amount"].mean().reset_index()

df8 = df.groupby(["name"]).agg({"time":"count","amount":"sum"}).reset_index().rename(columns={"time":"order_number"})
df8.style.background_gradient(cmap="Spectral_r")

df9 = df.groupby(["name","fruit"]).agg({"time":"count","amount":"sum"}).reset_index().rename(columns={"time":"number"})

df10 = df9.sort_values(["name","number","amount"],ascending=[True,False,False])

df10.style.bar(subset=["number","amount"],color="#a97fcf")

px.bar(df10,
       x="fruit",
       y="amount",
#            color="number",
       facet_col="name"
      )

px.bar(df16,
       x="day",
       y="name",
       orientation="h",
       color="day",
       color_continuous_scale="spectral"   # purples
      )