1、導包

import pandas as pd
from pyecharts.charts import Bar, Pie, Map, Line, Scatter
from pyecharts import options as opts
from pyecharts.render import make_snapshot
from snapshot_selenium import snapshot
from pyecharts.globals import CurrentConfig

2、讀取資料

# 
df = pd.read_excel("./xlsx/二手房資料.xlsx")

3、資料清洗

# 檢視資料前5列
print(df.head())
# 檢視資料表結構
print(df.describe())
# 檢視資料為空值的總數
print(df.isnull().sum())
# 將電梯這一列有空值的資料填充為未知，inplace=True在原資料進行修改
print(df["電梯"].fillna("未知", inplace=True))
# 在次檢視是否有空值
print(df.isnull().sum())

4、資料視覺化

視覺化展示-北京各城區二手房數量地圖分佈

# 根據市區進行分組後計算小區的數量
nums = df.groupby("市區")["小區"].agg("count")
# 將這市區轉換為list的列表
citys = nums.index.tolist()
# 每個值加上區
city = [i + "區" for i in citys]
# 小區的數量轉換為tolist()
xqnum = nums.values.tolist()


map = (
    Map(init_opts=opts.InitOpts(bg_color="white"))
        .add("", [list(z) for z in zip(city, xqnum)], "北京")
        .set_global_opts(title_opts=opts.TitleOpts(title="北京市二手房區分佈"),
                         visualmap_opts=opts.VisualMapOpts(is_show=True, max_=3000))
)
# 如果只需要HTML5程式碼不要圖片選第一個，要圖片選第二個
# map.render("beiJingMap.html")
make_snapshot(snapshot, map.render("beiJingMap.html"), "./beiJingMap.png")
 

視覺化展示-北京各城區二手房數量-平均價格柱狀圖

prices = df.groupby("市區")["價格(萬元)"].agg("mean")
prices = prices.round(2) #只要兩位小數
price = prices.values.tolist()

bar = (
    Bar(init_opts=opts.InitOpts(bg_color="white"))
        .add_xaxis(citys)
        .add_yaxis("數量", xqnum)
        .extend_axis(yaxis=opts.AxisOpts(is_show=True, max_=900, min_=200, name="價格(萬元)"))
        .set_global_opts(yaxis_opts=opts.AxisOpts(name="數量"),
                         title_opts=opts.TitleOpts(title="各城區二手房數量-平均價格柱狀圖"),
                         tooltip_opts=opts.TooltipOpts(is_show=True, trigger="axis", axis_pointer_type="cross"),
                         xaxis_opts=opts.AxisOpts(axispointer_opts=opts.AxisPointerOpts(is_show=True, type_="shadow")))
)

line = (
    Line()
        .add_xaxis(citys)
        .add_yaxis("價格", price, z=10, yaxis_index=1)
)
bar.overlap(line)

make_snapshot(snapshot, bar.render("./Mean房價數量.html"), "./Mean房價數量.png")
 

視覺化展示-二手房價格最高的TOP15

df.sort_values(by="價格(萬元)", ascending=False, inplace=True)
top_price = df["價格(萬元)"].apply("{0:.0f}".format).head(15).tolist()
xiaoqu = df["小區"].head(15).tolist()

top_bar = (
    Bar(init_opts=opts.InitOpts(bg_color="white"))
        .add_xaxis(xiaoqu)
        .add_yaxis("數量", top_price)
        .set_global_opts(xaxis_opts=opts.AxisOpts(name="數量"),
                         yaxis_opts=opts.AxisOpts(name="價格(萬元)"))
)

make_snapshot(snapshot,top_bar.render("./TOP15房價最高.html"),"./TOP15房價最高.png")

裝修情況-有無電梯（玫瑰圖）

# 計算Bar資料
zhuangxiu = df.groupby("裝修情況")["裝修情況"].agg("count")
x_zx = zhuangxiu.index.tolist()
y_num = zhuangxiu.values.tolist()

# 計算圓資料
dianti = df.groupby("電梯")["電梯"].agg("count")
youdt = dianti.index.tolist()
dt_num = dianti.values.tolist()
youdt.pop()
dt_num.pop()
zx_bar = (
    Bar(init_opts=opts.InitOpts(bg_color="white"))
        .add_xaxis(x_zx)
        .add_yaxis("", y_num, category_gap="50%")
        .set_global_opts(legend_opts=opts.LegendOpts(pos_left='85%', pos_top="63%", orient="scroll"),
                         yaxis_opts=opts.AxisOpts(name="裝修情況"),
                         xaxis_opts=opts.AxisOpts(name="數量"))
        .set_series_opts(label_opts=opts.LabelOpts(position="right"))

        .reversal_axis()
)
zx_pie = (
    Pie()
        .add("", [list(z) for z in zip(youdt, dt_num)], radius=["8%", "25%"], rosetype="radius", center=["75%", "65%"])
        .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}:{c}\n({d}%)"))
)
zx_bar.overlap(zx_pie)

make_snapshot(snapshot, zx_bar.render("./裝修情況.html"), "./裝修情況.png")

二手房總價與面積（散點圖）

jg = df["價格(萬元)"].tolist()
mj = df["面積(㎡)"].tolist()

scatter = (
    Scatter(init_opts=opts.InitOpts(bg_color="white"))
        .add_xaxis(mj)
        .add_yaxis("", jg)
        .set_global_opts(xaxis_opts=opts.AxisOpts(type_="value", name="面積(㎡)"),
                         yaxis_opts=opts.AxisOpts(name="價格(萬元)"))

)

make_snapshot(snapshot,scatter.render("./散點圖.html"),"./散點圖.png")