豆瓣电影数据可视化，分别用matplotlib和pyecharts画图

import matplotlib.pylab as plt
import pandas as pd
from matplotlib.font_manager import FontProperties
from pyecharts.charts import Bar,Pie,Grid
from pyecharts import options
from pyecharts import options as opts
import re

font_set = FontProperties(fname=r"c:\windows\fonts\simsun.ttc", size=12)
df = pd.read_csv(r"E:\movie_info(1.3).csv",encoding='gb18030')
plt.rcParams['font.family'] = ['sans-serif']
plt.rcParams['font.sans-serif'] = ['SimHei']

#电影发行量分析：折线图
def FaXingLiang():
    dfyear = df['年份'].dropna().astype(int) #dropna:去空值
    # year = df['年份'][0][:4]  #取前四位
    dff = pd.Series(dfyear).value_counts()
    dff.sort_index(inplace=True,ascending=True)  #对索引列排序，inplace:覆盖源数据；ascending：true：升序。false：降序
    # dff.sort_values(inplace=False) #对dateframe的多列同时进行排序
    # print(dff)
    plt.plot(dff.index,dff.values)         #线
    plt.ylabel('数量', fontproperties=font_set) #Y轴
    plt.xlabel('年份', fontproperties=font_set) #X轴
    plt.title('年份发行量分析', fontproperties=font_set) #标题
    plt.xlabel('数据分析：1888年开始数据一致处于上升趋势，且2000年到2016年上升趋势最大，2016年之后呈下降趋势', color='red'
                        '', fontsize=15, fontproperties=font_set)
    plt.xticks(dff.index) #将x轴所有数据都显示
    # plt.leg end()  #图例
    # plt.show() #输出图
    return plt

#电影类型分析:饼图
def LeiXing():
    df = pd.read_csv(r"E:\movie_info(1.3).csv", encoding='gb18030')
    LX = df["类型"]
    list1 = []
    for x in LX:
        if "/" in str(x):
            x = x.split("/")
            for y in x:
                list1.append(y)
        else:
            list1.append(x)
    dff = pd.Series(list1).value_counts()
    # print(dff)
    # print(list1)
    # 画饼图
    # explode：设置各部分突出
    # label:设置各部分标签
    # labeldistance:设置标签文本距圆心位置，1.1表示1.1倍半径
    # autopct：设置圆里面文本
    # shadow：设置是否有阴影
    # startangle：起始角度，默认从0开始逆时针转
    # pctdistance：设置圆内文本距圆心距离
    # 返回值
    # l_text：圆内部文本，matplotlib.text.Text object
    # p_text：圆外部文本
    plt.pie(dff, autopct='%.2f%%')
    plt.legend(labels=dff.index, ncol=2)
    plt.axis("equal")  # 设置横轴和纵轴大小相等，这样饼才是圆的
    plt.title("各个类型电影分析")
    plt.xlabel("数据分析：剧情和喜剧依然是最爱出的电影", color='red', fontsize=15)
    # plt.legend()
    return plt

#评分分析:echarts柱状图
def PingFen():
    # 导入输出图片工具
    from pyecharts.render import make_snapshot
    # 使用snapshot-selenium 渲染图片
    from snapshot_selenium import snapshot
    dff = df["评分"].dropna().value_counts()  # 去空值  统计
    dff.sort_index(inplace=True, ascending=True)  # 对索引列排序，inplace:覆盖源数据；ascending：true：升序。false：降序
    # dff.plot(kind="bar")
    # plt.xlabel("数据分析：（1）从均分的分布情况来看出来，评分分布最多的区间大概是6.5～7.5分之间，和我们计算的评分均值--6.8分也是不冲突的；"
    #            "（2）整体来看，大部分电影都是超过5分的，所以说5分以下的电影是烂片一点也不过分。",color='red',fontsize=12)
    # plt.show()
    # print(dff)
    bar = (Bar()
    .add_xaxis([float(x) for x in dff.index])
    .add_yaxis('评分', [int(x) for x in dff])
    .set_global_opts(title_opts=options.TitleOpts('评分分析'))  # 添加标题
    .set_series_opts(label_opts=options.LabelOpts(is_show=False))  #不显示具体数据
    )
    # 输出保存为图片
    make_snapshot(snapshot, bar.render(), "评分分析.png")
    return bar

#分析电影的时长：echarts
def ShiChang():
    dff = df['长度'].dropna()#去空值并统计
    list1 = []
    for x in dff:
        if " (" in str(x):
            x = x.split(' (')[0]
            list1.append(x)
        elif ": " in str(x):
            x = x.split(': ')[1]
            list1.append(x)
        elif "(" in str(x):
            x = x.split('(')[0]
            list1.append(x)
        elif '（' in str(x):
            x = x.split('（')[0]
        else:
            list1.append(x)

    # list1.sort_index(inplace=True,ascending=True) #排序
    list2 = []
    for x in list1:
        i = re.sub('\s','',x)
        y = re.sub('[a-zA-Z]+','',i)
        z = re.sub('[^\w\s]+','',y)
        zz = re.sub('[\u4e00-\u9fa5]','',z)
        list2.append(zz)
    df1 = pd.Series(list2)
    df1.values.astype(int)
    count = df1.value_counts()
    count.sort_values(ascending=True,inplace=True)
    # bar = (Bar()
    #        .add_xaxis([x for x in count.index])
    #        .add_yaxis("时长",[x for x in count.values])
    #        .set_global_opts(title_opts=opts.TitleOpts(title="时长分析"))
    #        )

    h = list(count.items())
    pie = Pie()
    pie.add('总数',data_pair=h)
    pie.render("地区总数饼图.html")

    return pie

#不同国家或地区发行电影数量:饼图
def GuoJia():
    dfcountry = df['国家']
    list1 = []
    list2 = []
    for x in dfcountry:
        if " / " in str(x) or "/" in str(x):
            x1 = x.split(" / " and "/")
            for xx in x1:
                list1.append(xx)
        else:
            list1.append(x)
    for i in list1:
        if " " in str(i):
            ii = i.replace(' ', '')
            list2.append(ii)
    dff = pd.Series(list2).value_counts()
    df1 = pd.DataFrame({"地区": dff.index, "总数": dff.values})
    # dff.plot(kind="bar")
    list2 = []
    for i in df1['总数']:
        if i == 1 or i == 2 or i == 3 or i == 4 or i == 5 or i == 6 or i == 7 or i == 8 or i == 10 or i == 11:
            list2.append(i)
    dff["少数国家"] = len(list2)
    dff.sort_values(inplace=True, ascending=False)
    df1.to_csv('地区.csv', index=False)
    df2 = pd.read_csv('地区.csv')
    # plt.pie(dff.values, autopct='%.2f%%', center=(10, 0))
    plt.pie(df2['总数'], autopct="%.2f%%")
    plt.title('地区饼图')
    plt.legend(labels=dff.index, ncol=5, loc=10, bbox_to_anchor=(-0.09, 0.5))
    # plt.legend(labels=df2['地区'], ncol=2, loc=10, bbox_to_anchor=(-0.3, 0.5))
    return plt

#用echarts画不同国家发行电影总量
def GuoJiaE():
    dff = pd.read_csv(r'E:\地区.csv',encoding='gb18030')
    # 1.x版本支持链式调用
    # bar = (Bar()
    #        .add_xaxis([x for x in dff['地区']])
    #        .add_yaxis('总数', [x for x in dff['总数']])
    #        .set_global_opts(title_opts=opts.TitleOpts(title="不同国家或地区发行电影数量"))
    #        .set_series_opts(label_opts=options.LabelOpts(is_show=False))  # 不显示具体数据
    #        )

    pie = (Pie()
           .add('', [list(z) for z in zip([x for x in dff['地区']], [x for x in dff['总数']])],
                radius=["30%", "70%"],center=["50%", "50%"],
                rosetype="radius")
           .set_global_opts(title_opts=opts.TitleOpts(title="不同国家或地区发行电影数量"))
           .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {d}%"))

           # .set_series_opts(label_opts=opts.LabelOpts(is_show=False))  # 不显示具体数据  ????????????????
           )

    return pie

#语言分析
def YuYan():
    dff = df['语言'].dropna()
    # print(dff)
    list1 = []
    list2 = []
    for x in dff:
        if " / " in str(x) or "/" in str(x):
            x1 = x.split(" / " and "/")
            for x2 in x1:
                list1.append(x2)
        else:
            list1.append(x)
    # print(list1)
    for x in list1:
        if " " in str(x):
            x1 = x.replace(" ","")
            list2.append(x1)
        else:
            list2.append(x)
    # print(list2)
    df1 = pd.Series(list2).value_counts()
    one = []
    two = []
    for x in df1.index:
        one.append(x)
    for x in df1.values:
        two.append(int(x))
    Fang = 0
    Shou = 0
    for i in df1.index:
        if i !="汉语普通话":
            if ("方言" or "话" or "手语") in i:
                Fang = Fang + df1[i]
                df1.drop(i,inplace=True,axis = 0)
        if ("手语" or "话") in i:
            Shou = Shou + df1[i]
            df1.drop(i, inplace=True, axis=0)
    df1["方言"] = Fang
    # df1["手语"] = Shou
    print(df1)
    # bar = (
    #     Bar()
    #     .add_xaxis(one)
    #     .add_yaxis('111',two)
    # )
    # bar.render('111.html')
    # df2 = pd.DataFrame({'语言':df1.index,'总数':df1.values})
    # print(df2.values)
    # bar = (Bar()
    #        .add_xaxis(df2.index)
    #        .add_yaxis("总数",df2.values)
    #        .set_global_opts(title_opts=options.TitleOpts("语言分析"),toolbox_opts=options.ToolboxOpts(is_show=True))
    #        )
    # return bar
if __name__ == "__main__":
    # FaXingLiang().show()
    # LeiXing().show()
    # PingFen().render('评分分析.html')
    # ShiChang().render("电影时长.html")
    # GuoJia().show()
    GuoJiaE().render("不同国家或地区发行电影数量扇形图.html")
    # YuYan().render("语言分析.html")
    # YuYan()