基于数据集Airbnb的数据分析

基于数据集Airbnb的数据分析

链接：https://pan.baidu.com/s/1Tz0e9WowqGQ6gam4LhWC3g

提取码：nqtq

开发环境：PyCharm

写在前面：数据的分析形式多种多样，本篇文章仅供参考。在python中可以不用打分号，纯属个人习惯

Airbnb数据集分析---基于calendar数据集的价格因素分析

1）将需要的包导入并读取calendar文件

import pandas as pd;
import numpy as np;
import matplotlib.pyplot as plt;
import seaborn as sns;

calendar = pd.read_csv('madrid-airbnb-data/calendar.csv');
print(calendar.head())

2）显示数据：（因为使用PyCharm所有列没有显示完整，可以自行查看）

3）修改气质price和date的数据类型

calendar['price'] = calendar['price'].str.replace(r'[$,]', "", regex = True).astype(np.float32);
calendar['adjusted_price'] = calendar['adjusted_price'].str.replace(r'[$,]', "", regex = True).astype(np.float32);

calendar['date'] = pd.to_datetime(calendar['date']);
print(calendar['date'].head())

4）添加星期和月份属性，注意星期从0开始

calendar['weekday'] = calendar['date'].dt.weekday;
calendar['month'] = calendar['date'].dt.month;
print(calendar['month'].head())

 5）使用柱状图表示月份和价格的关系，将每个月的价格分为一组，求改月价格的平均值

month_price = calendar.groupby('month')['price'].mean();
sns.barplot(x = month_price.index, y = month_price.values);
plt.show()

 6）使用柱状图来表示星期几和价格的关系

weekday_price = calendar.groupby('weekday')['price'].mean();
sns.barplot(x = weekday_price.index, y = weekday_price.values);
plt.show();

7）查看价格小于300的直方图

sns.displot(calendar[calendar['price'] < 300]['price'], kde = True);
plt.show();

 Airbnb数据集分析---基于listings_detailed房屋数据预处理

说明：本数据集的里面有一处数据有一点问题，会显示以下内容，不会影响我们的操作

1）观察数据集的列

listings_detailed = pd.read_csv('madrid-airbnb-data/listings_detailed.csv');     
print(listings_detailed.columns.values.tolist());  
#列数很多，先不展示，可以自行查看即可

 2）修改其中price的类型并添加最低消费字段

listings_detailed['price'] = listings_detailed['price'].str.replace(r'[$,]', "", regex = True).astype(np.float32);                  
listings_detailed['cleaning_fee'] = listings_detailed['cleaning_fee'].str.replace(r'[$,]', "", regex = True).astype(np.float32);    
listings_detailed['cleaning_fee'].fillna(0, inplace=True);       

#最低消费计算方法
listings_detailed['minimum_cost'] = (listings_detailed['price'] + listings_detailed['cleaning_fee']) * listings_detailed['minimum_nights'];  

3）添加设施数量字段，再增添一个新的列，在代码注释中说明

listings_detailed['n_amenities'] = listings_detailed['amenities'].str[1:-1].str.split(",").apply(len);                                                         
# 根据房间容纳人数，添加一个新的列，用来表示类型：Signal(1)、Couple(2)、Family(5)、Group(100)                                               
listings_detailed['accommodates_type'] = pd.cut(listings_detailed['accommodates'], bins = [1,2,3,5,100], right=False, include_lowest=True, 
labels=['Signal', 'Couple', 'Family', 'Group']); 

4）查看房屋属于哪一个社区，以及房间评分

listings_detailed['neighbourhood_group_cleansed']; 
listings_detailed['review_scores_rating']

5）将接下来需要的字段进行整理，主要为与房间价格有关的字段

listings_detailed_df = listings_detailed[['id','host_id', 'listing_url', 'room_type', 'neighbourhood_group_cleansed','price',
 'cleaning_fee', 'n_amenities', 'amenities','accommodates_type', 'minimum_cost', 'minimum_nights']]

 Airbnb数据集分析---房间类型和社区分析

1）房间类型

# 房间类型对比
room_type_counts = listings_detailed_df['room_type'].value_counts();
fig, axes = plt.subplots(1,2, figsize= (10,5));
# 饼图
axes[0].pie(room_type_counts.values, autopct = '%.2f%%', labels = room_type_counts.index);
# 柱状图
sns.barplot(x = room_type_counts.index, y = room_type_counts.values);
# 让两个图别有重叠处，进行调整
plt.tight_layout();
plt.show();

 2）社区分析

neighbourhood_counts = listings_detailed_df['neighbourhood_group_cleansed'].value_counts();
sns.barplot(y = neighbourhood_counts.index, x = neighbourhood_counts.values, orient = 'h');
plt.show();

  Airbnb数据集分析---房间类型和社区对比分析

1）在某一个社区，各种房屋类型占比，先查看数据，后绘图

# 在某一个社区，各种房屋类型占比
# 按照neighbourhood_group_cleansed和room_type进行分组
# unstack 按照room_type不进行堆叠
# fillna(0) 使用0进行替换Nan
# 计算比例，row是series类型，series的/是每个value单独计算的
# 按照Entire home/apt进行排序
neighbour_room_type = listings_detailed_df.groupby(['neighbourhood_group_cleansed', 'room_type']) \
    .size() \
    .unstack('room_type') \
    .fillna(0) \
    .apply(lambda row: row / row.sum(), axis=1) \
    .sort_values('Entire home/apt', ascending=True);

print(neighbour_room_type.head())

  2）绘图

# left进行起始位置确定
columns = neighbour_room_type.columns;
index = neighbour_room_type.index;
plt.figure(figsize=(10,5))
plt.barh(index, neighbour_room_type[columns[0]]);
left = neighbour_room_type[columns[0]];
plt.barh(index, neighbour_room_type[columns[1]], left = left);
left += neighbour_room_type[columns[1]];
plt.barh(index, neighbour_room_type[columns[2]], left = left);
left += neighbour_room_type[columns[2]];
plt.barh(index, neighbour_room_type[columns[3]], left = left);
plt.legend(columns);
plt.show();

   Airbnb数据集分析---房东房源数量分析

1）房东房源数量分析

host_number = listings_detailed_df.groupby('host_id').size();
sns.displot(data = host_number[host_number < 10], kde = True);
plt.show();

 

2）按照房东拥有房间数量 查看比例 1,2,3,5+   [1,2),[2,3),[3,4),5+

host_number_bins = pd.cut(host_number,bins=[1,2,3,5,100],right=False, include_lowest=True, labels=['1', '2', '3-4', '5+']).value_counts();
plt.pie(host_number_bins,autopct='%.2f%%', labels=host_number_bins.index);
plt.show();

    Airbnb数据集分析---评论数与时间分析

# 获取数据集，将date转换为日期类型
reviews = pd.read_csv('madrid-airbnb-data/reviews_detailed.csv', parse_dates=['date']);
# 添加年月
reviews['year'] = reviews['date'].dt.year;
reviews['month'] = reviews['date'].dt.month;
# 按照年月对数据进行分组，查看哪一年/月的数据有多少
n_reviews_year = reviews.groupby('year').size();
sns.barplot(x = n_reviews_year.index, y = n_reviews_year.values);
plt.show();

 

 

n_reviews_month = reviews.groupby('month').size();
sns.barplot(x = n_reviews_month.index, y = n_reviews_month.values);
plt.show();

 

 Airbnb数据集分析---评论数与时间综合分析

year_month_reviews = reviews.groupby(['year', 'month']).size().unstack('month').fillna(0);
# 根据月份绘制（月份-评论）折线图
fig, ax = plt.subplots(figsize=(20,10));
for index in year_month_reviews.index:
    series = year_month_reviews.loc[index];
    sns.lineplot(x = series.index, y = series.values, ax = ax);
ax.legend(labels = year_month_reviews.index);
ax.grid();
# 显示横轴所有月份
_ = ax.set_xticks(list(range(1,13)))
plt.show();

 Airbnb数据集分析---房间价格分析

1）找出与价格相关的因素，保存并相应格式修改

# 使用listing数据集对房屋价格进行预测
# 提取价格有关的字段
from sklearn.preprocessing import StandardScaler;
ml_listings = listings_detailed[listings_detailed['price'] < 300][[
    'host_is_superhost',
    'host_identity_verified',
    'neighbourhood_group_cleansed',
    'latitude',
    'longitude',
    'property_type',
    'room_type',
    'accommodates',
    'bathrooms',
    'bedrooms',
    'cleaning_fee',
    'minimum_nights',
    'maximum_nights',
    'availability_90',
    'number_of_reviews',
    # 'review_scores_rating',
    'is_business_travel_ready',
    'n_amenities',
    'price'
]]

# 删除异常值
ml_listings.dropna(axis=0, inplace=True);

# 提取特征值和目标值
features = ml_listings.drop(columns=['price']);
targets = ml_listings['price'];

# 对于离散值进行one-hot编码, 统一特征值数据类型,进行目标值预测
disperse_columns = [
    'host_is_superhost',
    'host_identity_verified',
    'neighbourhood_group_cleansed',
    'property_type',
    'room_type',
    'is_business_travel_ready'
]
disperse_features = features[disperse_columns];
disperse_features = pd.get_dummies(disperse_features);
# 对连续值进行标准化,因为数值相差不大,对于结果影响不大
continuouse_features = features.drop(columns = disperse_columns);
scaler = StandardScaler();
continuouse_features = scaler.fit_transform(continuouse_features);

# 对特征值进行组合
feature_array = np.hstack([disperse_features, continuouse_features]);

2）使用随机森林查看平均误差和r2误差

from sklearn.model_selection import train_test_split;
# from sklearn.linear_model import LinearRegression;
from sklearn.metrics import mean_absolute_error, r2_score;
# r2评分：r2的值越接近1越好，提升r2评分,让他拟合的更好,使用随机森林的回归
from sklearn.ensemble import RandomForestRegressor;

# 分割训练集和测试集
X_train, X_test,y_train,y_test = train_test_split(feature_array, targets,test_size=0.25);
regression = RandomForestRegressor();
# 预测
regression.fit(X_train, y_train);
y_predict = regression.predict(X_test);

# 查看平均误差和r2评分
print("平均误差:",mean_absolute_error(y_test, y_predict));
print("r2评分:" , r2_score(y_test, y_predict));

 如果使用线性回归平均误差和r2评分都没有使用随机森林好,使用线性回归结果如下

  Airbnb数据集分析---评论数量可视化及可视化

# 评论数量预测
ym_reviews = reviews.groupby(['year', 'month']).size().reset_index().rename(columns={0:'count'});
# 获取特征和目标值
features = ym_reviews[['year', 'month']];
targets = ym_reviews['count'];

# 分割训练集和测试集, 查看模型训练的泛化性
# X_train, X_test,y_train,y_test = train_test_split(features, targets,test_size=0.3);
# regression = RandomForestRegressor(n_estimators=100);
# regression.fit(X_train, y_train);
# y_predict = regression.predict(X_test);
# print("平均误差:",mean_absolute_error(y_test, y_predict));
# print("r2评分:" , r2_score(y_test, y_predict));

regression = RandomForestRegressor(n_estimators=100);
regression.fit(features,targets);

# 预测后结果
y_predict = regression.predict([
    [2019,10],
    [2019,11],
    [2019,12],
])

# 预测可视化
predict_reviews = pd.DataFrame([[2019, 10 + index, x] for index, x in enumerate(y_predict)], columns=['year', 'month', 'count']);
final_reviews = pd.concat([ym_reviews, predict_reviews]).reset_index();
years = final_reviews['year'].unique();
fig, ax = plt.subplots(figsize=(10,5));
for year in years:
    df = final_reviews[final_reviews['year'] == year];
    sns.lineplot(x = 'month', y = 'count', data = df);

ax.legend(labels = year_month_reviews.index);
ax.grid();
_ = ax.set_xticks(list(range(1,13)))
plt.show();