导入库

import numpy as np
import pandas as pd

import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns
import geopandas as gpd
plt.style.use("fivethirtyeight")
%matplotlib inline

import plotly as plotly
import plotly.express as px
import plotly.graph_objects as go
from plotly.offline import init_notebook_mode,iplot,plot
init_notebook_mode(connected=True)

import folium
import folium.plugins

import wordcloud
from wordcloud import WordCloud,STOPWORDS,ImageColorGenerator

import sklearn
from sklearn import preprocessing
from sklearn.metrics import r2_score,mean_absolute_error
from sklearn.preprocessing import LabelEncoder,OneHotEncoder
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression,LogisticRegression
from sklearn.ensemble import RandomForestRegressor,GradientBoostingRegressor

import warnings
warnings.filterwarnings("ignore")

数据基本信息

df = pd.read_csv("listings.csv")
df.head()

image.png

df.shape

image.png

columns = df.columns
columns

image.png

df.dtypes

image.png

df.info()

image.png

df.isnull().sum()

image.png

缺失值处理

# 1.先查看字段缺失值分布情况
sns.set(rc={"figure.figsize":(19.7,8.27)})
sns.heatmap(df.isnull(),yticklabels=False,cbar=False,cmap="viridis")

plt.show()

image.png

# 2.缺失值的字段(上面的两个)和name字段的两行记录直接删除
df.drop(["last_review","reviews_per_month"],inplace=True,axis=1)
df.dropna(inplace=True)
df.shape

image.png

数据EDA

# 价格price
sns.distplot(df["price"])

plt.show()

image.png

sns.scatterplot(x="price",y="minimum_nights",data=df)

plt.show()

image.png

# 区域
sns.countplot(x="neighbourhood_group", data=df)

plt.show()

image.png

df1 = df[df.price<250]

plt.figure(figsize=(10,6))

sns.boxplot(x="neighbourhood_group",y="price",data=df1)
plt.title("neighbourhood_group < 250")

plt.show()

image.png

plt.figure(figsize=(12,8))

sns.scatterplot(x="longitude",y="latitude",hue="neighbourhood_group",data=df)

plt.show()

image.png

房源分布热力图

import folium
from folium.plugins import HeatMap

m = folium.Map([1.44255,103.79580],zoom_start=11)

HeatMap(df[['latitude','longitude']].dropna(),
        radius=10,
        gradient={0.2:'blue',
                  0.4:'purple',
                  0.6:'orange',
                  1.0:'red'}).add_to(m)
display(m)

image.png

房间类型room_type

# 不同房间类型的占比
df["room_type"].value_counts()

image.png

import plotly.offline as pyo
import plotly.graph_objs as go

room_df = df.groupby("room_type").size() / df["room_type"].count()*100

room_df

image.png

labels = room_df.index
values = room_df.values

fig = go.Figure(data=[go.Pie(labels=labels,values=values,hole=0.5)])

fig.show()

image.png

# 不同区域的房间类型
plt.figure(figsize=(12,6))

sns.countplot(data=df,x="room_type",hue="neighbourhood_group")
plt.title("room types occupied by the neighbourhood_group")

plt.show()

image.png

type_group = df.groupby(["room_type","neighbourhood_group"]).size().reset_index().rename(columns={0:"number"})

type_group.head()

image.png

px.bar(type_group,x="room_type",y="number",color="neighbourhood_group",barmode="group")

image.png

# 房间类型和价格关系
plt.figure(figsize=(12,6))

sns.catplot(data=df,x="room_type",y="price")

plt.show()

image.png

px.scatter(df,x="room_type",y="price",color="room_type")

image.png

房间名称

# 整体词云图
from wordcloud import WordCloud,ImageColorGenerator

text = " ".join(str(each) for each in df.name)
wordcloud = WordCloud(max_words=200,background_color="white").generate(text)
plt.figure(figsize=(10,6))
plt.figure(figsize=(15,10))
plt.imshow(wordcloud,interpolation="Bilinear")
plt.axis("off")

plt.show()

image.png

# 名字中的关键
names = []
for name in df.name:
    names.append(name)
    
def split_name(name):
    spl = str(name).split()
    return spl

names_count = []
for each in names:
    for word in split_name(each):
        word = word.lower()
        names_count.append(word)

        
from collections import Counter

result = Counter(names_count).most_common()
result[:5]

image.png

top_20 = result[0:20]

top_20_words = pd.DataFrame(top_20,columns=["words","count"])
top_20_words

image.png

plt.figure(figsize=(10,6))

fig = sns.barplot(data=top_20_words,x="words",y="count")
fig.set_title("Counts of the top 20 used words for listing names")
fig.set_ylabel("Count of words")
fig.set_xlabel("Words")
fig.set_xticklabels(fig.get_xticklabels(),rotation=80)

plt.show()

image.png

回访量统计

df1 = df.sort_values(by="number_of_reviews",ascending=False).head(1000)

df1.head()

image.png

import folium
from folium.plugins import MarkerCluster
from folium import plugins

print("Rooms with the most number of reviews")

Long=103.91492
Lat=1.32122

mapdf1 = folium.Map([Lat, Long], zoom_start=10)

mapdf1_rooms_map = plugins.MarkerCluster().add_to(mapdf1)

for lat, lon, label in zip(df1.latitude,df1.longitude,df1.name):
    folium.Marker(location=[lat, lon],icon=folium.Icon(icon="home"),popup=label).add_to(mapdf1_rooms_map)

mapdf1.add_child(mapdf1_rooms_map)

image.png

可租天数

plt.figure(figsize=(10,6))

plt.scatter(df.longitude,df.latitude,c=df.availability_365,cmap="spring",edgecolors="black",linewidths=1,alpha=1)
cbar = plt.colorbar()
cbar.set_label("availability_365")

image.png

px.scatter(df,x="longitude",y="latitude",color="availability_365")

image.png

plt.figure(figsize=(10,6))
low_500 = df[df.price<500]

viz1 = low_500.plot(kind="scatter",x="longitude",y="latitude",label="availability_365",c="price",cmap=plt.get_cmap("jet"),colorbar=True,alpha=0.4)
viz1.legend()

plt.show()

image.png

px.scatter(low_500,x="longitude",y="latitude",color="price")

image.png

线性回归建模

# 预处理
df.drop(["name","id","host_name"],inplace=True,axis=1)

# 编码类型的转化
cols = ["neighbourhood_group","neighbourhood","room_type"]

for col in cols:
    le = preprocessing.LabelEncoder()
    le.fit(df[col])
    df[col] = le.transform(df[col])
    
df.head()

image.png

# 建模
lm = LinearRegression()

X = df.drop("price",axis=1)
y = df["price"]

X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2,random_state=101)
lm.fit(X_train,y_train)

image.png

predicts = lm.predict(X_test)
predicts

image.png

error_airbnb = pd.DataFrame({"Actual":np.array(y_test).tolist(),"Predict":predicts.tolist()})
error_airbnb.head()

image.png

title=['Pred vs Actual']

fig = go.Figure(data=[
    go.Bar(name='Predicted',x=error_airbnb.index,y=error_airbnb['Predict']),
    go.Bar(name='Actual',x=error_airbnb.index,y=error_airbnb['Actual'])
])
fig.update_layout(barmode='group')

fig.show()

image.png

error_airbnb["diff"] = error_airbnb["Predict"] - error_airbnb["Actual"]
px.box(error_airbnb,y="diff")

image.png

error_airbnb.describe()

image.png