数据分析步骤及分析报告

最新推荐文章于 2024-08-27 17:01:01 发布

wpzhuo

最新推荐文章于 2024-08-27 17:01:01 发布

阅读量893

点赞数

文章标签： python 数据分析

本文链接：https://blog.csdn.net/wpzhuo/article/details/106114733

版权

数据分析步骤及分析报告练习

这是第一次在博客上发东西，练习练习.是关于一个电商平台的部分数据分析，只是练习，再无他用。

数据分析需要用到库

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import datetime
from matplotlib import font_manager

读入数据

df=pd.read_excel(r'C:\Users\huawei\Desktop\.ipynb_checkpoints\data.xlsx',index_col= 'id')

数据清理

将dataframe时间数据转化成datetime格式的数据类型

df['orderTime'] = pd.to_datetime(df.orderTime)
df['payTime'] = pd.to_datetime(df.payTime)

删除不合理数据

df['pay_gap'] = (df.payTime-df.orderTime).dt.total_seconds() ###换成秒数
df.drop(index = df[df.pay_gap > 1800].index,inplace = True)  ##删除支付时间过长的
df.drop(index = df[df.pay_gap < 0].index,inplace = True)   ###删除支付时间早于下单时间
df[df.orderAmount < 0]
df[df.payment < 0]
df.drop(index = df[df.payment < 0].index,inplace = True)  #删除支付金额为负
df.drop(index = df[df.payment > df.orderAmount].index,inplace = True)
df.orderID.unique().size  
df.orderID.duplicated()
df.drop(index = df[df.orderID.duplicated()].index,inplace = True)  #删除orderID重复值 
df.userID.unique().size
df.userID.duplicated()
df.goodsID.unique().size
df[df.goodsID == 'PR000000'].size
df.drop(index = df[df.goodsID == "PR000000"].index,inplace = True) 
df[df.chanelID.isnull()]
df['chanelID'].fillna(value = df.chanelID.mode()[0],inplace = True)
df.platfromType.unique() 
df['platfromType'] = df.platfromType.str.replace(" ","")  #
###可能还会遇到大小写问题，需要转换使用upper()和loewr()函数

数据分析

1.基本销售情况

plt.rcParams['font.sans-serif']='SimHei'   #设置中文字体显示
df['month'] = df['orderTime'].dt.month  ##提取月份
plt.figure("销售情况",figsize = (10,8))
plt.grid(alpha = 0.5)
df_new = df.groupby('month')['orderAmount','payment','chargeback'].agg('sum')
x = df_new.index
y1,y2 = [df_new.orderAmount/10000,df_new.payment/10000]
y3 = df[df['chargeback'] == "否"].groupby('month')['payment'].sum().values/10000

plt.plot(x,y1,label = '总销售额',color = 'r',marker = '*')
plt.plot(x,y2,label = '成交额',color = 'g',marker = '_')
plt.plot(x,y3,label = '实际成交额',color = 'orange',marker = 'o')
x_ticks_label = ['{}月份'.format(i) for i in x]
plt.xticks(x,x_ticks_label)
plt.xlabel('月份')
plt.ylabel('销售额')
plt.title("销售情况分析",color = "r",size = 20)
##添加数据标签
for a,b,c,d in zip(x,y1,y2,y3):
    plt.annotate('(%.2f)'%(b),xy=(a,b),xytext=(-10,10),textcoords='offset points')
    plt.annotate('(%.2f)'%(c),xy=(a,c),xytext=(-10,10),textcoords='offset points')
    plt.annotate('(%.2f)'%(d),xy=(a,d),xytext=(-10,10),textcoords='offset points')
plt.legend(prop = my_font,loc = 'upper left')
ax = plt.gca()
ax.spines['right'].set_color('none')  ##去掉右边和上边的边框
ax.spines['top'].set_color('none')
plt.show()

2.销售渠道分析

df.chanelID.unique().size
plt.figure(figsize = (15,9))
cus = df.groupby('chanelID')['userID'].count()
label = cus.index
plt.pie(cus,labels = label,autopct='%1.1f%%',rotatelabels=True,shadow=True)
plt.title("各渠道用户占比",size = 20)
plt.show()

平台来源分析

df.platfromType.unique()
plat_cus = df.pivot_table(index = 'platfromType',
                          values = ['userID','orderAmount'],
                          aggfunc = {'userID':'count','orderAmount':'mean'})
data1 =  plat_cus.userID
data2 =  plat_cus.orderAmount
data3 = [1]
labels = plat_cus.index
def pie_fun(x,y,z):
    fig,ax = plt.subplots()
    ax.pie(x,radius = 1,autopct = '%1.1f%%',pctdistance=0.75)
    ax.pie(y,radius = 0.6,colors = 'white')
    ax.set(aspect = "equal",title = "不同平台的{}占比环形图".format(x.name))
    plt.legend(z,bbox_to_anchor = (1,1),loc = 'best')
    plt.show()

3.客户分析
订单分析

df['weekday'] = df.orderTime.dt.dayofweek
df.weekday.unique()
df_w = df.groupby('weekday')['orderID'].count()
df_w

plt.figure('figure3')
df_wX = ['周一','周二','周三','周四','周五','周六','周日']
df_wY = df_w.values

df_bar= plt.bar(df_wX,height = df_wY,color=['r','g','b','r','g','b'],width = 0.3)
for b in df_bar:
    height = b.get_height()
    plt.text(b.get_x()+b.get_width()/2,height+0.6,str(height),ha = 'center')
plt.show()

RFM模型

df1 = df.copy()
df1.drop(index = df1[df1['chargeback'] == '是'].index,inplace = True)
df1['orderTime'] = pd.to_datetime(df1.orderTime,format = '%Y-%m-%d')
df1.set_index('userid',drop = True,inplace = True)
df1['orders'] = 1
RFMdf = df1.pivot_table(index = ['userid'],
                        values = ['orderAmount','orderTime','orders'],
                        aggfunc = {'orderAmount':'sum',
                                   'orderTime':'max',
                                   'orders':'sum'})
RFMdf['R'] = (RFMdf.orderTime.max()-RFMdf.orderTime).dt.days
RFMdf.rename(columns = {"orderAmount":'M',"orders":'F'},inplace = True)
RFMdf[['R','F','M']].apply(lambda x: x-x.mean())
def rfm_fun(x):
    level = x.apply(lambda x: '1' if x > 1 else '0')
    label = level.R + level.F+ level.M
    d = {'111':'重要价值客户',
        '011':'重要保持客户',
        '101':'重要发展客户',
        '001':'重要挽留客户',
        '110':'一般价值客户',
        '010':'一般保持客户',
        '100':'一般发展客户',
        '000':'一般挽留客户'
        }
    result = d[label]
    return result
RFMdf['label'] = RFMdf[['R','F','M']].apply(lambda x: x-x.mean()).apply(rfm_fun,axis = 1)
# tabel = RFMdf.groupby('label').count()
plt.figure('figure4',figsize = (10,8))
RFMdf.label.value_counts().plot.bar()
plt.xticks(rotation = 0)