python資料分析--------電商打折套路為例
阿新 • • 發佈：2021-07-02
如今大資料行業十分火熱，本人認為python是比較強大的分析工具，在網易雲課堂上學習了python資料分析。做了案例，寫下程式碼分析過程以及分析結論。
以下是電商打折套路的python資料分析專案。
# -*- coding: utf-8 -*- """ Created on Wed Jan 9 15:31:45 2019 @author: Administrator """ import numpy as np import pandas as pd import matplotlib.pyplot as plt import warnings from datetime import datetime from bokeh.transform import jitter warnings.filterwarnings('ignore') from bokeh.plotting import figure ,show,output_file from bokeh.models import ColumnDataSource #匯入資料 import os os.chdir('C:\\Users\\Administrator\\Desktop\\python專案\\2電商打折') #工作路徑 df=pd.read_excel('雙十一資料.xlsx',sheetname=0) df.fillna(0,inplace=True) df.index=df['update-time'] df['date']=df.index.day #雙十一當天在售商品佔比數 data1=df[["id","title","店名","date"]] d1=data1[["id","date"]].groupby(by="id").agg(["max","min"])["date"] #統計不同商品的銷售開始和結束日期 id_11=data1[data1["date"]==11]["id"] d2=pd.DataFrame({"id":id_11,"雙十一是否售賣":True}) id_data=pd.merge(d1,d2,left_index=True,right_on="id",how="left") id_data.fillna(False,inplace=True) #雙十一當天參與活動的商品個數與比例 m=len(d1) m_11=len(id_11) m_pre=m_11/m print("雙十一當天參與活動的商品個數是%i個，比例是%.2f%%"%(m_11,m_pre*100))
結論：雙十一當天參與活動的商品個數是405個，比例是74.18%
#------------------------------------------------------------------------ #商品銷售分類 id_data["type"]="待分類" id_data["type"][(id_data["min"]<11)&(id_data["max"]>11)]="A" id_data["type"][(id_data["min"]<11)&(id_data["max"]==11)]="B" id_data["type"][(id_data["min"]==11)&(id_data["max"]>11)]="C" id_data["type"][(id_data["min"]==11)&(id_data["max"]==11)]="D" id_data["type"][(id_data["雙十一是否售賣"]==False)]="F" id_data["type"][(id_data["max"]<11)]="E" id_data["type"][(id_data["min"]>11)]="G" result1=id_data["type"].value_counts() result1=result1.loc[["A","B","C","D","E","F","G"]] #不同類別商品比例 from bokeh.palettes import brewer colori=brewer["YlGn"][7] plt.axis("equal") plt.pie(result1,labels=result1.index,autopct="%.2f%%",colors=colori, startangle=90,radius=1.5,counterclock=True) #------------------------------------------------------------------------ #未參與雙十一活動的商品去向如何 id_not11=id_data[id_data["雙十一是否售賣"]==False]#暫時下架商品----id_con2 df_not11=id_not11[["id","type"]] data_not11=pd.merge(df_not11,df,on="id",how="left")#分組欄位不夠用需要從原始總資料裡借，所以要合併 #不合並就沒法分組，沒法分組，就沒法統計 id_con1=id_data["id"][id_data["type"]=="F"].values data_con2=data_not11[["id","title","date"]].groupby(by=["id","title"]).count() title_count=data_con2.reset_index()["id"].value_counts() id_con2=title_count[title_count>1].index data_con3=data_not11[data_not11["title"].str.contains("預售")] id_con3=data_con3["id"].value_counts().index print("未參與雙十一當天活動的商品裡，%i個為暫時下架商品，%i個為重新上架商品，%i個為預售商品"% (len(id_con1),len(id_con2),len(id_con3)) )
結論：未參與雙十一當天活動的商品裡，95個為暫時下架商品，155個為重新上架商品，69個為預售商品
#------------------------------------------------------------------------ #商品銷售分類 id_data["type"]="待分類" id_data["type"][(id_data["min"]<11)&(id_data["max"]>11)]="A" id_data["type"][(id_data["min"]<11)&(id_data["max"]==11)]="B" id_data["type"][(id_data["min"]==11)&(id_data["max"]>11)]="C" id_data["type"][(id_data["min"]==11)&(id_data["max"]==11)]="D" id_data["type"][(id_data["雙十一是否售賣"]==False)]="F" id_data["type"][(id_data["max"]<11)]="E" id_data["type"][(id_data["min"]>11)]="G" result1=id_data["type"].value_counts() result1=result1.loc[["A","B","C","D","E","F","G"]]
#不同類別商品比例
from bokeh.palettes import brewer
colori=brewer["YlGn"][7]
plt.axis("equal")
plt.pie(result1,labels=result1.index,autopct="%.2f%%",colors=colori,
startangle=90,radius=1.5,counterclock=True)
#------------------------------------------------------------------------
#未參與雙十一活動的商品去向如何
id_not11=id_data[id_data["雙十一是否售賣"]==False]#暫時下架商品----id_con2
df_not11=id_not11[["id","type"]]
data_not11=pd.merge(df_not11,df,on="id",how="left")#分組欄位不夠用需要從原始總資料裡借，所以要合併
#不合並就沒法分組，沒法分組，就沒法統計
id_con1=id_data["id"][id_data["type"]=="F"].values
data_con2=data_not11[["id","title","date"]].groupby(by=["id","title"]).count()
title_count=data_con2.reset_index()["id"].value_counts()
id_con2=title_count[title_count>1].index
data_con3=data_not11[data_not11["title"].str.contains("預售")]
id_con3=data_con3["id"].value_counts().index
print("未參與雙十一當天活動的商品裡，%i個為暫時下架商品，%i個為重新上架商品，%i個為預售商品"%
(len(id_con1),len(id_con2),len(id_con3))
)
#------------------------------------------------------------------------
data_11sale=id_11
data_11sale_final=np.hstack((data_11sale,id_con3))
result2_i=pd.DataFrame({"id":data_11sale_final})
x1=pd.DataFrame({"id":id_11})
x1_df=pd.merge(x1,df,on="id",how="left")
brand_11sale=x1_df.groupby(by="店名")["id"].count()
x2=pd.DataFrame({"id":id_con3})
x2_df=pd.merge(x2,df,on="id",how="left")
brand_ys=x2_df.groupby(by="店名")["id"].count()
result2_data=pd.DataFrame({"當天參與活動的商品數量":brand_11sale,
"預售商品數量":brand_ys})
result2_data["總量"]=result2_data["當天參與活動的商品數量"]+result2_data["預售商品數量"]
result2_data.sort_values(by="總量",ascending=False)
from bokeh.models import HoverTool
from bokeh.core.properties import value
lst_brand=result2_data.index.tolist()
lst_type=result2_data.columns.tolist()[:2]#result2_data的列名columns.取前2個
color=["red","green"]
result2_data.index.name="brand"
result2_data.columns=["sale_on_11","presell","sum"]
source1=ColumnDataSource(result2_data)
hover=HoverTool(
tooltips=[
("品牌","@brand"),
("雙十一當天參與活動商品數量","@sale_on_11"),
("預售商品數量","@presell"),
("商品總數","@sum")
])
output_file("project08.html")
p=figure(x_range=lst_brand,plot_width=900,plot_height=350,
title="各個品牌參與雙十一活動的情況",
tools=[hover,"box_select,pan,reset,wheel_zoom,crosshair"]
)
p.vbar(top="sum",x="brand",source=source1,width=0.9,
#color=color,alpha=0.7,
#legend=[value(x) for x in lst_type],
muted_color="black", muted_alpha=0.2
)
show(p)
#不同品牌銷售數量情況
#------------------------------------------------------------------------
