乐高天猫旗舰店数据分析

乐高天猫旗舰店数据分析

01 导入模块

# 导入模块
import pandas as pd
import numpy as np
import jieba 
import time
import stylecloud
from IPython.display import Image
from pyecharts.charts import Bar,Line,Map,Page,Pie
from pyecharts import options as opts
from pyecharts.globals import SymbolType

02 读取数据

df_tm=pd.read_csv('F:Python数据分析课程python数据处理Pandas练习数据分析项目练习legao3225天猫乐高旗舰店数据.csv')
df_tm.head()

#查看信息
df_tm.info()

1. 重复值处理
2. age_range:暂不处理
3. price:价格处理/类型转换
4. sales_num:类型转换
5. color_cat:暂不处理

df_tm.drop_duplicates(inplace=True)
# 价格处理
def transform_price(x):
    if '-' in x:
        return (float(x.split('-')[1])-float(x.split('-')[0]))/2
    else:
        return x
# 价格转换
df_tm['price']=df_tm.price.apply(lambda x:transform_price(x)).astype('float')
# 使用平均值填充缺失值
df_tm['sales_num']=df_tm.sales_num.replace('无',200)
# 转换类型
df_tm['sales_num']=df_tm.sales_num.astype('int')
df_tm.head()

df_tm['title']=df_tm.title.str.replace('乐高旗舰店|官网|2020年','')
# 销售额
df_tm['sales_volumn']=df_tm['sales_num']*df_tm['price']
df_tm.head()

df_tm.info()

df_tm['title']=df_tm.title.str.replace('乐高旗舰店|官网|2020年','')
# 销售额
df_tm['sales_volumn']=df_tm['sales_num']*df_tm['price']

df_tm.head()

rank_top10=df_tm.groupby('title')['sales_num'].sum().sort_values(ascending=False).head(10)
rank_top10

rank_top10=df_tm.sort_values('sales_num',ascending=False).head(10)[['title','sales_num']]
rank_top10=rank_top10.sort_values('sales_num')
rank_top10

x_data=rank_top10.title.values.tolist()
y_data=rank_top10.sales_num.values.tolist()

bar1=Bar()
bar1.add_xaxis(x_data)
bar1.add_yaxis('',y_data)
bar1.set_global_opts(title_opts=opts.TitleOpts(title='乐高旗舰店月销量排名Top10商品'),
                     # visualmap_opts=opts.VisualMapOpts(max_=5000)
                     )
bar1.set_series_opts(label_opts=opts.LabelOpts(position='right'))
bar1.reversal_axis()
bar1.render_notebook()

cut_bins=[0,200,400,600,800,1000,2000,9469]
cut_labels=['0~50元','50~100元','100~200元','200~300元','300~500元','500~1000元','1000元以上']

price_cut=pd.cut(df_tm['price'],bins=cut_bins,labels=cut_labels)
price_num=price_cut.value_counts()
price_num

bar2=Bar()
bar2.add_xaxis(['0~50元','50~100元','100~200元','200~300元','300~500元','500~1000元','1000元以上'])
bar2.add_yaxis('',[52,71,86,39,35,61,25])
bar2.set_global_opts(title_opts=opts.TitleOpts(title='乐高旗舰店不同价格区间商品数量'),
                    visualmap_opts=opts.VisualMapOpts(max_=90)
)
bar2.render_notebook()

# 添加到
df_tm['price_cut']=price_cut
cut_purchase=df_tm.groupby('price_cut')['sales_volumn'].sum()
cut_purchase

data_pair=[list(z) for z in zip(cut_purchase.index.tolist(),cut_purchase.values.tolist())]
# 绘制饼图
piel=Pie()
piel.add('',data_pair,radius=['35%','60%'])
piel.set_global_opts(title_opts=opts.TitleOpts(title='不同价格区间的销售额整体表现'),
                    legend_opts=opts.LegendOpts(orient='vertical',pos_top='15%',pos_left='2%'))
piel.set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{d}%"))
piel.set_colors(['#EF9050','#3B7BA9','#6FB27C','#FFAF34','#D7BFD7','#00BFFE','#7FFFAA'])
piel.render_notebook()

def get_cut_words(content_series):
    # 读入停用图表析
    stop_words=[]
    with open("F:\Python数据分析课程\python数据处理\Pandas练习\数据分析项目练习\legao3225\cn_stopwords.txt",'r',encoding='utf-8')as f:
        lines=f.readlines()
        for line in lines:
            stop_words.append(line.strip())
    # 添加关键词
    my_words=['乐高','悟空小侠','大颗粒','小颗粒']
    for i in my_words:
        jieba.add_word(i)
    # 自定义停用词
    # my_stop_words=[]
    # stop_words.extend(my_stop_words)

    # 分词
    word_num=jieba.lcut(content_series.str.cat(sep='。'),cut_all=False)
    # 条件筛选
    word_num_selected=[i for i in word_num if i not in stop_words and len(i)>=2]
    return  word_num_selected

text=get_cut_words(content_series=df_tm['title'])
text[:6]

text=get_cut_words(content_series=df_tm['title'])
text[:6]

stylecloud.gen_stylecloud(
    text=' '.join(text),
    collocations=False,
    font_path=r'F:Python数据分析课程python数据处理Pandas练习数据分析项目练习legao3225simhei.ttf',
    icon_name='fas fa-gamepad',
    size=768,
    output_name='乐高旗舰店商品标题词云图.png'
)
Image(filename='乐高旗舰店商品标题词云图.png')