文章目录
大家好，我是 👉 【Python当打之年(点击跳转)】
本期我们利用Python分析 30000+条电影影评数据，分析一下由沈腾、马丽主演的《独行月球》这部电影观影情况，看看大家对这部国产灾难电影都有哪些看法，希望对小伙伴们有所帮助，如有疑问或者需要改进的地方可以私信小编。
涉及到的库：
- Pandas — 数据处理
- Pyecharts — 数据可视化
- Matplotlib — 数据可视化
可视化部分：
- 折线图 — Line
- 散点图 — Scatter
- 楔形图 — Wedge
- 多边形 — Polygon
- 词云图 — WordCloud
- 地图 — Geo
🏳️🌈 1. 导入模块
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
🏳️🌈 2. Pandas数据处理
2.1 读取数据
df = pd.read_excel('独行月球.xlsx')
df.head(10)
2.2 数据大小
df.shape()
(34436, 6)
一共有34436条影评数据，数据时间分布2022-8-01至2021-08-07。
2.3 查看索引、数据类型和内存信息
df.info()
🏳️🌈 3. Pyecharts数据可视化
3.1 《独行月球》评分分布-1
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)
semicircle=Wedge((0,0),1.05,0,180, edgecolor = 'grey', facecolor = 'None', linestyle='--')
ax.add_artist(semicircle)
plt.axis('equal')
semicircle=Wedge((0,0),0.55,0,180, edgecolor = 'grey', facecolor = 'None', linestyle='-')
ax.add_artist(semicircle)
plt.axis('equal')
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.legend(patches, label[::-1], loc=0, ncol = 6, fontsize = 11,
bbox_to_anchor=(0.92, 0.15),handlelength=1, handleheight=1)
- 5.0的评分占比达到了74.77%，多半数观众打出了五星好评，三星以上好评更是达到了93%之多，大家对这部电影的整体评价还是很高的。
3.2 《独行月球》评分分布-2
复古版海报：
3.3 每日评论量
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),
)
)
3.4 每小时评论量
3.5 一周每天每时评论量
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,
)
- 从小时分布来看，高峰时间段为21:00-24:00，中午12:00也偶尔出现一波小高峰。
3.6 地理位置分布
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"),
),
)
)
3.7 评论词云
stylecloud.gen_stylecloud(
text=’ ‘.join(content_list),
font_path=r’STXINWEI.TTF’,
palette=‘cartocolors.diverging.TealRose_2’,
icon_name=‘fas fa-moon’, # 设置蒙版方案
output_name=‘独行月球.png’,
background_color=‘#FFEFD5’,
)
🏳️🌈 4. 可视化项目源码+数据：
网盘： https://pan.baidu.com/doc/share/Olj4d~aKuXT7AF0cq01MrQ-437060019167360
提取码： pyra
以上就是本期为大家整理的全部内容了，赶快练习起来吧，原创不易，喜欢的朋友可以点赞、收藏也可以分享（注明出处）让更多人知道。
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
