Pandas — 数据处理
Pyecharts — 数据可视化
可视化部分：
import reimport jiebaimport stylecloudimport numpy as npimport pandas as pdfrom collections import Counterfrom pyecharts.charts import Barfrom pyecharts.charts import Map from pyecharts.charts import Piefrom pyecharts.charts import Gridfrom pyecharts.charts import Pagefrom pyecharts.components import Imagefrom pyecharts.charts import WordCloudfrom pyecharts import options as opts from pyecharts.globals import SymbolTypefrom pyecharts.commons.utils import JsCode
df = pd.read_excel("月饼.xlsx")df.head(10)
结果：
print(df.shape)df.drop_duplicates(inplace=True)print(df.shape)
(4520, 5)(1885, 5)
处理购买人数为空的记录：df['付款情况'] = df['付款情况'].replace(np.nan,'0人付款')
2.4 处理付款情况字段
df[df['付款情况'].str.contains("万")]
付款人数超过10000后会直接用"万"替代，这里我们需要将其恢复：
# 提取数值df['num'] = [re.findall(r'(\d+\.{0,1}\d*)', i)[0] for i in df['付款情况']] df['num'] = df['num'].astype('float')# 提取单位（万）df['unit'] = [''.join(re.findall(r'(万)', i)) for i in df['付款情况']] df['unit'] = df['unit'].apply(lambda x:10000 if x=='万' else 1)# 计算销量df['销量'] = df['num'] * df['unit']df = df[df['地址'].notna()]df['省份'] = df['地址'].str.split(' ').apply(lambda x:x[0])# 删除多余的列df.drop(['付款情况', 'num', 'unit'], axis=1, inplace=True)# 重置索引df = df.reset_index(drop=True)
结果：
代码： 效果：
商品名称太长显示不全，我们调整一下边距： 还可以来些其他（比如：形状）设置：
3.2 月饼销量排名TOP10店铺 代码：
稻香村的月饼销量遥遥领先。 3.3 全国各地区月饼销量 结果：
shop_top10 = df.groupby('商品名称')['销量'].sum().sort_values(ascending=False).head(10)bar0 = ( Bar() .add_xaxis(shop_top10.index.tolist()[::-1]) .add_yaxis('sales_num', shop_top10.values.tolist()[::-1]) .reversal_axis() .set_global_opts(title_opts=opts.TitleOpts(title='月饼商品销量Top10'), xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-30))) .set_series_opts(label_opts=opts.LabelOpts(position='right')))
bar1 = ( Bar() .add_xaxis(shop_top10.index.tolist()[::-1]) .add_yaxis('sales_num', shop_top10.values.tolist()[::-1],itemstyle_opts=opts.ItemStyleOpts(color=JsCode(color_js))) .reversal_axis() .set_global_opts(title_opts=opts.TitleOpts(title='月饼商品销量Top10'), xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-30)), ) .set_series_opts(label_opts=opts.LabelOpts(position='right')))# 将图形整体右移grid = ( Grid() .add(bar1, grid_opts=opts.GridOpts(pos_left='45%', pos_right='10%')) )
shop_top10 = df.groupby('店铺名称')['销量'].sum().sort_values(ascending=False).head(10)bar3 = ( Bar(init_opts=opts.InitOpts( width='800px', height='600px',)) .add_xaxis(shop_top10.index.tolist()) .add_yaxis('', shop_top10.values.tolist(), category_gap='30%', ) .set_global_opts( xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-30)), title_opts=opts.TitleOpts( title='月饼销量排名TOP10店铺', pos_left='center', pos_top='4%', title_textstyle_opts=opts.TextStyleOpts( color='#ed1941', font_size=16) ), visualmap_opts=opts.VisualMapOpts( is_show=False, max_=600000, range_color=["#CCD3D9", "#E6B6C2", "#D4587A","#FF69B4", "#DC364C"] ), ))bar3.render_notebook()
province_num = df.groupby('省份')['销量'].sum().sort_values(ascending=False) map_chart = Map(init_opts=opts.InitOpts(theme='light', width='800px', height='600px'))map_chart.add('', [list(z) for z in zip(province_num.index.tolist(), province_num.values.tolist())], maptype='china', is_map_symbol_show=False, itemstyle_opts={ 'normal': { 'shadowColor': 'rgba(0, 0, 0, .5)', # 阴影颜色 'shadowBlur': 5, # 阴影大小 'shadowOffsetY': 0, # Y轴方向阴影偏移 'shadowOffsetX': 0, # x轴方向阴影偏移 'borderColor': '#fff' } } )map_chart.set_global_opts( visualmap_opts=opts.VisualMapOpts( is_show=True, is_piecewise=True, min_ = 0, max_ = 1, split_number = 5, series_index=0, pos_top='70%', pos_left='10%', range_text=['销量(份)：', ''], pieces=[ {'max':2000000, 'min':200000, 'label':'> 200000', 'color': '#990000'}, {'max':200000, 'min':100000, 'label':'100000-200000', 'color': '#CD5C5C'}, {'max':100000, 'min':50000, 'label':'50000-100000', 'color': '#F08080'}, {'max':50000, 'min':10000, 'label':'10000-50000', 'color': '#FFCC99'}, {'max':10000, 'min':0, 'label':'0-10000', 'color': '#FFE4E1'}, ], ), legend_opts=opts.LegendOpts(is_show=False), tooltip_opts=opts.TooltipOpts( is_show=True, trigger='item', formatter='{b}:{c}' ), title_opts=dict( text='全国各地区月饼销量', left='center', top='5%', textStyle=dict( color='#DC143C')))map_chart.render_notebook()
每一天都是一个阶梯，是向既定目标迈进的新的一步。
