十三朝古都西安

import pandas as pd
import re
import csv
import json
import requests
import random

# 显示所有列
# pd.set_option('display.max_columns', None)

# 显示所有行
# pd.set_option('display.max_rows', None)

# 设置value的显示长度为100，默认为50
# pd.set_option('max_colwidth',100)

# 绘图相关
import jieba
import matplotlib.pyplot as plt
from pyecharts.globals import CurrentConfig, OnlineHostType   
from pyecharts import options as opts  # 配置项
from pyecharts.charts import Bar, Scatter, Pie, Line, HeatMap, Funnel, WordCloud, Grid, Page  
from pyecharts.commons.utils import JsCode   
from pyecharts.globals import ThemeType,SymbolType

import plotly.express as px
import plotly.graph_objects as go
from plotly.subplots import make_subplots  # 子图

location = df["location"].value_counts().reset_index().rename(columns={"index":"location","location":"number"})

c = (
    Pie(init_opts=opts.InitOpts(theme=ThemeType.MACARONS))
    .add("西安景点个数",[list(z) for z in zip(location["location"].tolist(),location["number"].tolist())])
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)

c.render_notebook()

df = pd.read_csv("西安景点.csv")
comment_top10 = df.sort_values("comment",ascending=False)[:10]

# 作图
fig = px.bar(comment_top10,x="cn_title",y="comment",color="comment",text="comment")
fig.update_traces(textposition="outside")
fig.show()

# pyecharts实现

x_data = strategy_top10["cn_title"].tolist()
y_data = strategy_top10["strategy"].tolist()

c = (
    Bar(init_opts=opts.InitOpts(theme=ThemeType.DARK))
    .add_xaxis(x_data)
    .add_yaxis("西安景点攻略数前10名",y_data)
    .set_global_opts(
        xaxis_opts=opts.AxisOpts(axislabel_opts=opts.LabelOpts(rotate=-20)),  # 设置旋转角度
    )
)

c.render_notebook()

comment_strategy = df[(df["comment"] >= 1000) & (df["strategy"] >= 100)]

fig = px.scatter(comment_strategy,
           x="comment",
           y="strategy",
           color="comment",
           size="strategy",
           text="cn_title"
          )

# ['top left', 'top center', 'top right', 'middle left',
# 'middle center', 'middle right', 'bottom left', 'bottom center', 'bottom right']

fig.update_traces(textposition="top center")

fig.show()

# 西安市区景点排名

ranking_xian = df[(df["location"] == "西安") & (df["ranking"] != 0)].sort_values("ranking",ascending=True)[1:][:20]
ranking_xian

qinshihuang = df[df["cn_title"].str.contains("秦始皇")].reset_index(drop=True)
qinshihuang

park = df[df["cn_title"].str.contains("公园")].reset_index(drop=True)
print("公园个数：{}".format(len(park)))
# 结果
公园个数：133

lvyou = df.sort_values("lvyou_number",ascending=False)[:10].reset_index(drop=True)

fig = px.bar(lvyou,x="cn_title",y="lvyou_number",text="lvyou_number")

fig.update_traces(textposition="outside")

fig.show()

df1 = pd.read_csv("西安美食.csv")
noodles = df1[df1["中文名"].str.contains("面")].reset_index(drop=True)
noodles
print("面馆总数：",len(noodles))

# 结果
面馆总数： 115

liangpi = df1[df1["中文名"].str.contains("凉皮")].sort_values("得分",ascending=False).reset_index(drop=True)
liangpi.head(10)

# 取出前10家店
fig = px.scatter(liangpi[:10],x="得分",y="均价",color="均价",size="均价",text="中文名")
fig.update_traces(textposition="top center")

fig.show()

mo = df1[df1["中文名"].str.contains("馍")].sort_values("得分",ascending=False).reset_index(drop=True)

# 取出前10家店

fig = px.scatter(mo[:10],
                 x="得分",
                 y="均价",
                 color="均价",
                 size="均价",
                 text="中文名",
                 width=900, 
                 height=700)

fig.update_traces(textposition="top center")

fig.show()

roujiamo = df1[df1["中文名"].str.contains("肉夹馍")].sort_values("得分",ascending=False).reset_index(drop=True)
roujiamo.head(5)

paomo = df1[df1["中文名"].str.contains("泡馍")].sort_values("得分",ascending=False).reset_index(drop=True)
paomo

kaochuan = df1[df1["中文名"].str.contains("串")].sort_values("得分",ascending=False).reset_index(drop=True)
kaochuan

kaorou = df1[df1["中文名"].str.contains("烤肉")].sort_values("得分",ascending=False).reset_index(drop=True)

# 取出前10家店
fig = px.scatter(kaorou[:10],x="得分",y="均价",color="均价",size="均价",text="中文名")
fig.update_traces(textposition="top center")
fig.show()

shops = pd.DataFrame({
    "name":["面馆","biangbiang面","裤带面","馍","肉夹馍","泡馍","串串","烤肉","凉皮","清真"],
    "number":[116,11,10,87,36,38,32,57,19,42]
})

shops

c = (
    Pie()
    .add("", [list(z) for z in zip(shops["name"].tolist(), shops["number"].tolist())])
    .set_global_opts(title_opts=opts.TitleOpts(title="西安店铺"))
    .set_series_opts(label_opts=opts.LabelOpts(formatter="{b}: {c}"))
)

c.render_notebook()

name_list = df1["中文名"].tolist()
recommand_list = df1[df1["推荐菜"] != "无"]["推荐菜"].tolist()
lst = name_list + recommand_list

# 分词过程
rec_jieba_list = []
for i in range(len(lst)):
  	# jieba分词
    seg_list = jieba.cut(str(lst[i]).strip(), cut_all=False)
    for each in list(seg_list):
        rec_jieba_list.append(each)

# 词频统计
rec_result = pd.value_counts(rec_jieba_list)[5::].to_frame().reset_index().rename(columns={"index":"词语",0:"次数"})

# 词云图
rec_words = [tuple(z) for z in zip(rec_result["词语"].tolist(), rec_result["次数"].tolist())]

c = (
    WordCloud()
    .add("", rec_words, word_size_range=[20, 80], shape=SymbolType.DIAMOND)
    .set_global_opts(title_opts=opts.TitleOpts(title="西安美食推荐菜词云"))
)

c.render_notebook()

# 取出前100个词语

rec_words = [tuple(z) for z in zip(rec_result["词语"].tolist(), rec_result["次数"].tolist())]

c = (
    WordCloud()
    .add("", rec_words[:50], word_size_range=[20, 80], shape=SymbolType.DIAMOND)
    .set_global_opts(title_opts=opts.TitleOpts(title="西安美食推荐菜词云图"))
)

c.render_notebook()