Pyecharts | 用Python分析了3W+《独行月球》影评数据，看看观众们怎么说~

import jieba
import stylecloud
import pandas as pd
from PIL import Image
from collections import Counter
from pyecharts.charts import Geo
from pyecharts.charts import Scatter
from pyecharts.charts import Line
from pyecharts import options as opts
from pyecharts.commons.utils import JsCode
from pyecharts.globals import ChartType
import math
import matplotlib
import matplotlib.pyplot as plt
from matplotlib.patches import Wedge, Polygon
from matplotlib.offsetbox import TextArea, AnnotationBbox
plt.rcParams['font.sans-serif']=['Microsoft YaHei']
plt.rcParams['axes.unicode_minus']=False

df = pd.read_excel('独行月球.xlsx')
df.head(10)

df.shape()
(34436, 6)

df.info()

def pic():
    df_star = df.groupby('评分')['评论'].count()
    count_sco = list(df_star.values)
    sum_count = sum(count_sco)
    data = [count_sco[0]/sum_count/2]
 for i in range(1,len(count_sco),2):
        rate = (count_sco[i] + count_sco[i+1])/sum_count
        data.append(rate/2)
    series = pd.Series(data)
    label = ['5分力荐', '4分推荐','3分还行','2分较差','1分很差','0分极差']
    colors = ['#009688','#26A69A','#4DB6AC','#80CBC4','#B2DFDB','#E0F2F1'][::-1]
    rate_lable = [f'{i*2:.2%}' for i in data]
    fig = plt.figure(figsize=(10,7),dpi = 100,facecolor='#FFEFD5')
    ax=plt.subplot(111,facecolor='#FFEFD5', alpha=.01)
    patches,l_text = ax.pie(
        series,
        colors = colors,
        wedgeprops = dict(width = 0.4),
        startangle = 0,
        textprops = dict(fontsize = 15),
        normalize = False
 # 数据标签
    ax.text(-0.45, 0.6, rate_lable[5], fontsize = 18,rotation = 298)
    ax.text(0.53, 0.36, rate_lable[4], fontsize = 17,rotation = 35)
    ax.text(0.64, 0.20, rate_lable[3], fontsize = 16,rotation = 21)
    ax.text(0.7, 0.048, rate_lable[1], fontsize = 14,rotation = 5) 
    x = [-1.05,1.05]
    y = [0,0]
    plt.plot(x, y,color="#FFEFD5",alpha=1)
    plt.plot(x, y,color="#FFEFD5",alpha=1)
    plt.text(-0.43, 0.25, '《独行月球》评分分布', fontsize = 20, color = "r"),
    plt.text(-0.32, 0.4, '（制作@公众号：Python当打之年）', color = "#283593", fontsize = 10,alpha = 0.8),
    plt.text(-0.49, 0.13, '数据来源：猫眼电影 采集时间：2022/8/8', color = "r", fontsize = 13,alpha = 0.8),
    plt.legend(patches, label[::-1], loc=0, ncol = 6, fontsize = 11,
               bbox_to_anchor=(0.92, 0.15),handlelength=1, handleheight=1)
    plt.show()

line1 = (
    Line(init_opts=opts.InitOpts(bg_color=JsCode(color_js)))
    .add_xaxis(xaxis_data=day_x_data)
    .add_yaxis(
        series_name="",
        y_axis=day_y_data,
        is_smooth=True,
        is_symbol_show=True,
        symbol="circle",
        symbol_size=6,
        linestyle_opts=opts.LineStyleOpts(color="#fff"),
        label_opts=opts.LabelOpts(is_show=True, position="top", color="white"),
        itemstyle_opts=opts.ItemStyleOpts(
            color="red", border_color="#fff", border_width=3
        tooltip_opts=opts.TooltipOpts(is_show=False),
    .set_global_opts(
        title_opts=opts.TitleOpts(
            title="每日评论量",
            pos_top="5%",
            pos_left="center",
            title_textstyle_opts=opts.TextStyleOpts(color="#fff", font_family='FZYaoTi', font_size=16),
        xaxis_opts=opts.AxisOpts(
            type_="category",
            boundary_gap=True,
            axislabel_opts=opts.LabelOpts(margin=30, color="#ffffff63"),
            axisline_opts=opts.AxisLineOpts(is_show=False),
        yaxis_opts=opts.AxisOpts(
            type_="value",
            position="left",
            axislabel_opts=opts.LabelOpts(margin=20, color="#ffffff63"),
            axisline_opts=opts.AxisLineOpts(
                linestyle_opts=opts.LineStyleOpts(width=2, color="#fff")
        legend_opts=opts.LegendOpts(is_show=False),

single_axis, titles = [], []
scatter = Scatter(init_opts=opts.InitOpts(width='1000px', height='800px', theme='light',bg_color='#0d0735'))
for idx, day in enumerate(weeks[::-1]):
    scatter.add_xaxis(xaxis_data=hours)
    single_axis.append({'left': 100,
 'nameGap': 20,
 'nameLocation': 'start',
 'type': 'category',
 'boundaryGap': False,
 'data': hours,
 'top': '{}%'.format(idx * 100 / 7 + 5),
 'height': '{}%'.format(100 / 7 - 10),
 'gridIndex': idx,
 'axisLabel': {'interval': 2,'color':'#9FC131'},
    titles.append(dict(text=day,top='{}%'.format(idx * 100 / 7 + 6), left='2%',
                       textStyle=dict(color='#fff200', font_family='FZYaoTi')))
    scatter.add_yaxis('',
                    y_axis=[int(item[2]) for item in allinfo if item[0] == 7-idx],
                    symbol_size=JsCode('function(p) { return p[1] * 0.15;}'),
                    label_opts=opts.LabelOpts(is_show=False),
scatter.set_global_opts(
    xaxis_opts=opts.AxisOpts(is_show=False),
    yaxis_opts=opts.AxisOpts(is_show=False),
    title_opts=titles,
scatter.render_notebook()

geo = (
    Geo(init_opts=opts.InitOpts(width="1000px", height="600px", bg_color="#0d0735"))
    .add_schema(maptype="china")
    .add("评论数量", data,type_=ChartType.HEATMAP,)
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(
       title_opts=opts.TitleOpts(title="地理位置分布",pos_top="2%", pos_left="center",
                                 title_textstyle_opts=opts.TextStyleOpts(color="#fff", font_family='FZYaoTi',font_size=16)),
       legend_opts=opts.LegendOpts(is_show=False),
       visualmap_opts=opts.VisualMapOpts(
            is_show=True,
            is_piecewise=True,
            min_ = 0,
            max_ = 50,
            split_number = 5,
            series_index=0,
            pos_bottom='5%',
            pos_left='5%',
            textstyle_opts=opts.TextStyleOpts(color="#fff"),
)

stylecloud.gen_stylecloud(
    text=' '.join(content_list),
    font_path=r'STXINWEI.TTF',
    palette='cartocolors.diverging.TealRose_2',