前言
關於亞馬遜訂單數據的探索！
次項目大家就僅當作學習使用好了
import pandas as pd from pyecharts.charts import * from pyecharts import options as opts from pyecharts.commons.utils import JsCode
- 對時間字段進行處理，轉為datetime；
- 對配送州字段進行處理，原始數據中既有州縮寫也有全稱，統一為全稱呼；
df_c = pd.read_excel('C:/Users/Administrator/Desktop/市場占有率.xls') df = pd.read_excel('C:/Users/Administrator/Desktop/亞馬遜入駐商訂單報表.xls', header=1) df['支付時間'] = pd.to_datetime(df['支付時間'], utc=False)# .dt.strftime('%Y-%m-%d %H:%M:%S') df['下單時間'] = pd.to_datetime(df['下單時間'], utc=False)# .dt.strftime('%Y-%m-%d %H:%M:%S') df['最早配送時間'] = pd.to_datetime(df['最早配送時間'], utc=False) df['最晚配送時間'] = pd.to_datetime(df['最晚配送時間'], utc=False) df['最早送達時間'] = pd.to_datetime(df['最早送達時間'], utc=False) df['最晚送達時間'] = pd.to_datetime(df['最晚送達時間'], utc=False) c_map = dict() for idx, row in df_c.iterrows(): c_map[row['州名簡寫']] = row['美國州名英文'].replace(u'\xa0', u' ') c_map['SD'] = 'South Dakota' c_map['NM'] = 'New Mexico' c_map['SC'] = 'South Carolina' c_map['NH'] = 'New Hampshire' c_map['NJ'] = 'New Jersey' def format_state(state): try: c = state.upper().replace('.', '') if c in c_map.keys(): return c_map[c] elif c in [x.upper() for x in c_map.values()]: return list(c_map.values())[[x.upper() for x in c_map.values()].index(c)] else: return None except AttributeError: return None df['配送州'] = df['配送州'].map(format_state) df.head()
早上的訂單最多，好像和國內用戶習慣不太一樣呢～
data = df.groupby([df['下單時間'].dt.hour])['訂單ID'].count().reset_index() data_x = ['{}點'.format(int(i)) for i in data['下單時間']] data_y = data['訂單ID'].tolist() area_color_js = """ new echarts.graphic.LinearGradient( 0, 0, 0, 1, [{offset: 0, color: 'rgba(128, 255, 165)'}, {offset: 1, color: 'rgba(1, 191, 236)'}], false) """ bg_color_js = """ new echarts.graphic.LinearGradient( 0, 0, 0, 1, [{offset: 0, color: 'rgba(128, 255, 165, 0.2)'}, {offset: 1, color: 'rgba(1, 191, 236, 0.2)'}], false) """ line = Line(init_opts=opts.InitOpts(theme='white', width='1000px', height='500px', bg_color=JsCode(bg_color_js))) line.add_xaxis(data_x) line.add_yaxis( '', data_y, is_smooth=True, symbol="circle", is_symbol_show=False, linestyle_opts=opts.LineStyleOpts(color="#fff"), areastyle_opts=opts.AreaStyleOpts(color=JsCode(area_color_js), opacity=1), ) line.set_series_opts(opts.LabelOpts(is_show=False)) line.set_global_opts(xaxis_opts=opts.AxisOpts(boundary_gap=False), yaxis_opts=opts.AxisOpts(axisline_opts=opts.AxisLineOpts(is_show=False), axistick_opts=opts.AxisTickOpts( is_show=False), splitline_opts=opts.SplitLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(color='#E0E6F1')) ), tooltip_opts=opts.TooltipOpts( is_show=True, trigger='axis', axis_pointer_type='cross'), title_opts=opts.TitleOpts(title="全天各時間段訂單數", pos_left='center') ) line.render_notebook()
data = df.groupby([df['下單時間'].dt.weekday_name])['訂單ID'].count().reset_index() cat_day_of_week = pd.api.types.CategoricalDtype( ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday'], ordered=True ) data['下單時間'] = data['下單時間'].astype(cat_day_of_week) data = data.sort_values(['下單時間']) data_x = data['下單時間'].tolist() data_y = data['訂單ID'].tolist() area_color_js = """ new echarts.graphic.LinearGradient( 0, 0, 0, 1, [{offset: 0, color: 'rgba(128, 255, 165)'}, {offset: 1, color: 'rgba(1, 191, 236)'}], false) """ bg_color_js = """ new echarts.graphic.LinearGradient( 0, 0, 0, 1, [{offset: 0, color: 'rgba(128, 255, 165, 0.2)'}, {offset: 1, color: 'rgba(1, 191, 236, 0.2)'}], false) """ line = Line( init_opts=opts.InitOpts( theme='white', width='1000px', height='500px', bg_color=JsCode(bg_color_js))) line.add_xaxis(data_x) line.add_yaxis( '', data_y, is_smooth=True, symbol="circle", is_symbol_show=False, linestyle_opts=opts.LineStyleOpts(color="#fff"), areastyle_opts=opts.AreaStyleOpts(color=JsCode(area_color_js), opacity=1), ) line.set_series_opts(opts.LabelOpts(is_show=False)) line.set_global_opts(xaxis_opts=opts.AxisOpts(boundary_gap=False), yaxis_opts=opts.AxisOpts( is_scale=True, axisline_opts=opts.AxisLineOpts(is_show=False), axistick_opts=opts.AxisTickOpts( is_show=False), splitline_opts=opts.SplitLineOpts(is_show=True, linestyle_opts=opts.LineStyleOpts(color='#E0E6F1')) ), tooltip_opts=opts.TooltipOpts( is_show=True, trigger='axis', axis_pointer_type='cross'), title_opts=opts.TitleOpts(title="一周內各天訂單數", pos_left='center') ) line.render_notebook()
import requests GEO_data = requests.get(url="https://echarts.apache.org/examples/data/asset/geo/USA.json").json() area_move = """{ Alaska: { // 把阿拉斯加移到美國主大陸左下方 left: -128, top: 25, width: 15 }, Hawaii: { left: -110, // 夏威夷 top: 25, width: 5 }, 'Puerto Rico': { // 波多黎各 left: -76, top: 26, width: 2 } }""" data = df.groupby(['配送州'])['訂單ID'].count().reset_index() data_pair = [] for idx, row in data.iterrows(): data_pair.append((row['配送州'], row['訂單ID'])) map_chart = Map(init_opts=opts.InitOpts(width='1000px', height='600px')) map_chart.add_js_funcs( """echarts.registerMap('USA', {}, {});""".format( GEO_data, area_move)) map_chart.add('訂單數', data_pair=data_pair, maptype='USA', is_roam=False, # 關閉symbol的顯示 is_map_symbol_show=False, zoom=1.1, label_opts=opts.LabelOpts(is_show=False), ) map_chart.set_global_opts( legend_opts=opts.LegendOpts(is_show=False), title_opts=opts.TitleOpts(title="美國各州訂單數分布", pos_left='center'), visualmap_opts=opts.VisualMapOpts(is_show=True, is_piecewise=True, orient='vertical', pos_left='2%', pos_top='65%', range_text=['訂單數', ''], pieces=[{'min': 100}, {'min': 60, 'max': 100}, {'min': 30, 'max': 60}, {'min': 10, 'max': 30}, {'min': 1, 'max': 10} ], range_color=["#CCD3D9", "#E6B6C2", "#D4587A", "#DC364C"] ) ) map_chart.render_notebook()
根據商品名稱關鍵詞來判斷，93%的商品都是女款
f, m = 0, 0 for i in df['產品名稱']: try: if i.upper().__contains__('WOMEN') or i.upper().__contains__('GIRL'): f+=1 elif i.upper().__contains__('MEN'): m+=1 else: pass except AttributeError: pass f_p = round(f/(f+m)*100) m_p = round(m/(f+m)*100) symbols = [ 'path://M18.2629891,11.7131596 L6.8091608,11.7131596 C1.6685112,11.7131596 0,13.032145 0,18.6237673 L0,34.9928467 C0,38.1719847 4.28388932,38.1719847 4.28388932,34.9928467 L4.65591984,20.0216948 L5.74941883,20.0216948 L5.74941883,61.000787 C5.74941883,65.2508314 11.5891201,65.1268798 11.5891201,61.000787 L11.9611506,37.2137775 L13.1110872,37.2137775 L13.4831177,61.000787 C13.4831177,65.1268798 19.3114787,65.2508314 19.3114787,61.000787 L19.3114787,20.0216948 L20.4162301,20.0216948 L20.7882606,34.9928467 C20.7882606,38.1719847 25.0721499,38.1719847 25.0721499,34.9928467 L25.0721499,18.6237673 C25.0721499,13.032145 23.4038145,11.7131596 18.2629891,11.7131596 M12.5361629,1.11022302e-13 C15.4784742,1.11022302e-13 17.8684539,2.38997966 17.8684539,5.33237894 C17.8684539,8.27469031 15.4784742,10.66467 12.5361629,10.66467 C9.59376358,10.66467 7.20378392,8.27469031 7.20378392,5.33237894 C7.20378392,2.38997966 9.59376358,1.11022302e-13 12.5361629,1.11022302e-13', 'path://M28.9624207,31.5315864 L24.4142575,16.4793596 C23.5227152,13.8063773 20.8817445,11.7111088 17.0107398,11.7111088 L12.112691,11.7111088 C8.24168636,11.7111088 5.60080331,13.8064652 4.70917331,16.4793596 L0.149791395,31.5315864 C-0.786976655,34.7595013 2.9373074,35.9147532 3.9192135,32.890727 L8.72689855,19.1296485 L9.2799493,19.1296485 C9.2799493,19.1296485 2.95992025,43.7750224 2.70031069,44.6924335 C2.56498417,45.1567684 2.74553639,45.4852068 3.24205501,45.4852068 L8.704461,45.4852068 L8.704461,61.6700801 C8.704461,64.9659872 13.625035,64.9659872 13.625035,61.6700801 L13.625035,45.360657 L15.5097899,45.360657 L15.4984835,61.6700801 C15.4984835,64.9659872 20.4191451,64.9659872 20.4191451,61.6700801 L20.4191451,45.4852068 L25.8814635,45.4852068 C26.3667633,45.4852068 26.5586219,45.1567684 26.4345142,44.6924335 C26.1636859,43.7750224 19.8436568,19.1296485 19.8436568,19.1296485 L20.3966199,19.1296485 L25.2043926,32.890727 C26.1862111,35.9147532 29.9105828,34.7595013 28.9625083,31.5315864 L28.9624207,31.5315864 Z M14.5617154,0 C17.4960397,0 19.8773132,2.3898427 19.8773132,5.33453001 C19.8773132,8.27930527 17.4960397,10.66906 14.5617154,10.66906 C11.6274788,10.66906 9.24611767,8.27930527 9.24611767,5.33453001 C9.24611767,2.3898427 11.6274788,0 14.5617154,0 L14.5617154,0 Z', ] area_color_js = """ new echarts.graphic.LinearGradient( 0, 1, 0, 1, [{offset: 0, color: 'rgba(128, 255, 165)'}, {offset: 1, color: 'rgba(1, 191, 236)'}], false) """ p = PictorialBar( init_opts=opts.InitOpts( theme='white', width='1000px', height='800px', bg_color=JsCode(bg_color_js))) p.add_xaxis([0, 1]) # 此部分數據為要顯示的數值 p.add_yaxis( "", [{ "value": m_p, "symbol": symbols[0], 'symbolBoundingData': 100, "itemStyle": { "normal": { "color": 'rgba(105,204,230)' # 單獨控制顏色 } }, }, { "value": f_p, "symbol": symbols[1], 'symbolBoundingData': 100, "itemStyle": { "normal": { "color": 'rgba(255,130,130)' # 單獨控制顏色 } }, } ], label_opts=opts.LabelOpts( is_show=True, position='inside', font_family='Arial', font_weight='bolder', font_size=40, formatter='{c}%'), symbol_repeat=False, is_symbol_clip=True ) # 此部分數據用於背景，設置為100 p.add_yaxis( "", [{ "value": 100, "symbol": symbols[0], 'symbolBoundingData': 100, "itemStyle": { "normal": { "color": 'rgba(105,204,230,0.40)' # 單獨控制顏色 } }, }, { "value": 100, "symbol": symbols[1], 'symbolBoundingData': 100, "itemStyle": { "normal": { "color": 'rgba(255,130,130,0.40)' # 單獨控制顏色 } }, } ], category_gap='30%', label_opts=opts.LabelOpts(is_show=False), is_symbol_clip=True, symbol_repeat=False ) p.set_global_opts( title_opts=opts.TitleOpts( title="男款商品 VS 女款商品", subtitle='依據訂單商品名稱中的關鍵詞判斷, 如“women”，“girl”等。', pos_left='center'), tooltip_opts=opts.TooltipOpts(is_show=False), legend_opts=opts.LegendOpts(is_show=False), xaxis_opts=opts.AxisOpts(is_show=False), yaxis_opts=opts.AxisOpts(is_show=False, max_=100), ) p.render_notebook()
- 哪個尺碼的衣服買的更多？
- 那個顏色更受歡迎？
pie = Pie( init_opts=opts.InitOpts( theme='white', width='1000px', height='500px', bg_color='#F5F5F5', ) ) pie.add( "", c.most_common(10), radius=["30%", "50%"], center=["25%", "50%"], # rosetype="area", label_opts=opts.LabelOpts(is_show=True, formatter='{b}:{d}%'), itemstyle_opts={ 'normal': { 'shadowColor': 'rgba(0, 0, 0, .5)', # 陰影顏色 'shadowBlur': 5, # 陰影大小 'shadowOffsetY': 5, # Y軸方向陰影偏移 'shadowOffsetX': 5, # x軸方向陰影偏移 'opacity': '0.7', } } ) pie.add( "", cl.most_common(10), radius=["30%", "50%"], center=["75%", "50%"], # rosetype="area", label_opts=opts.LabelOpts(is_show=True, formatter='{b}:{d}%'), itemstyle_opts={ 'normal': { 'shadowColor': 'rgba(0, 0, 0, .5)', # 陰影顏色 'shadowBlur': 5, # 陰影大小 'shadowOffsetY': 5, # Y軸方向陰影偏移 'shadowOffsetX': 5, # x軸方向陰影偏移 # 'opacity': '0.7', } } ) pie.set_global_opts( title_opts=[ dict( text='商品屬性', left='center', top='5%', textStyle=dict( color='#282828', fontSize=20)), dict( text='SIZE', left='23%', top='48%', textStyle=dict( color='#282828', fontSize=17)), dict( text='COLOR', left='72%', top='48%', textStyle=dict( color='#282828', fontSize=17)) ], tooltip_opts=opts.TooltipOpts(is_show=False), legend_opts=opts.LegendOpts(is_show=False), visualmap_opts=opts.VisualMapOpts( is_show=False, max_=300, range_color=['rgb(1, 191, 236)', 'rgb(128, 255, 165)'] ) ) pie.render_notebook()
from stylecloud import gen_stylecloud from IPython.display import Image gen_stylecloud(' '.join(word_list), size=1000, max_words=1000, # palette='palettable.tableau.TableauMedium_10', icon_name='fab fa-amazon', output_name='comment.png', ) Image(filename='comment.png')
