机器学习入门-Knn算法

knn算法不需要进行训练， 耗时，适用于多标签分类情况

1. 将输入的单个测试数据与每一个训练数据依据特征做一个欧式距离、

2. 将求得的欧式距离进行降序排序，取前n_个

3. 计算这前n_个的y值的平均或者(类别)，获得测试数据的预测值

4.根据测试数据的实际值和测试数据的预测值计算当前的rmse，判断该方法的好坏

使用AIRbob的房子的特征与房价做演示：

演示1.首先使用accommodates属性对一个数据做演示，采用的距离是绝对值距离

import pandas as pd
import numpy as np

df_listings = pd.read_csv('listings.csv')
# 选取部分特征
features = ['accommodates', 'bedrooms', 'bathrooms', 'beds', 'price', 'minimum_nights', 'maximum_nights', 'number_of_reviews']
# 选取部分特征重新组合
df_listings = df_listings[features]
# 先只对accommodates进行操作
new_accomodates = 3  # 有一个房子的可容纳住房为3
df_listings['distance'] = np.abs(df_listings['accommodates'] - new_accomodates)
# 接下来对df_listings按照'distance'进行排序操作.value_counts()统计个数， sort_index() 进行排序
df_listings.distance.value_counts().sort_index()
# 使用洗牌操作,重新赋值
df_listings = df_listings.sample(frac=1, random_state=0)
# 重新继续排序
df_listings = df_listings.sort_values('distance')
print(df_listings.price.head())
# 由于价格是$150 ，我们需要将其转换为float类型
df_listings['price'] = df_listings['price'].str.replace('\$|,', "").astype(float)
# 取前5个数据，求价格的平均值
price_mean_5 = df_listings['price'].iloc[:5].mean()
print(price_mean_5)

演示2 将住房数据分为训练集和测试集， 使用单个特征进行测试

df_listings = df_listings.drop('distance', axis=1)
# 将数据进行拆分
train_df = df_listings[:2792]
test_df = df_listings[2792:]
# 定义预测函数
def predict_price(test_content, feature_name):
    temp_df = train_df
    temp_df['distance'] = np.abs(test_content - temp_df[feature_name])
    # 根据distance进行排序
    temp_df = temp_df.sort_values('distance')
    price_mean_5 = temp_df.price.iloc[:5].mean()
    return price_mean_5
cols = ['accommodates']
# 这个.apply相当于将每一个数据输入，参数为函数， feature_name为第二个参数
test_df['predict_price'] = test_df[cols[0]].apply(predict_price, feature_name = 'accommodates')
print(test_df['predict_price'])
# 计算rmse
mse = ((test_df['predict_price'] - test_df['price']) ** 2).mean()
rmse = mse ** (1 / 2)
print(rmse)

# 分别比较其他属性单个的区别
for feature in ['accommodates', 'bedrooms', 'bathrooms', 'number_of_reviews']:
    test_df['predict_price'] = test_df[feature].apply(predict_price, feature_name=feature)
    print(test_df['predict_price'])
    # 计算rmse
    mse = ((test_df['predict_price'] - test_df['price']) ** 2).mean()
    rmse = mse ** (1 / 2)
    print('where{}:{}'.format(feature, rmse))

演示3：在上面的基础上，添加数据标准化（zeros）操作，标准化的意思是先减去均值，然后再除于标准差。同时引入多变量操作

使用的包有： from sklearn.mean_squred_error  用于求平均值
                      from scipy.spatial import distance 用于求欧式距离

from sklearn.processing import  StandardScaler  用于进行标准化操作

from sklearn.preprocessing import StandardScaler
df_listings = pd.read_csv('listings.csv')
# 选取部分特征
features = ['accommodates', 'bedrooms', 'bathrooms', 'beds', 'price', 'minimum_nights', 'maximum_nights', 'number_of_reviews']
# 选取部分特征重新组合
df_listings = df_listings[features]
# 对价格进行处理
df_listings['price'] = df_listings['price'].str.replace('\$|,', "").astype(float)
# 去除有缺失值的行
df_listings = df_listings.dropna()

# 对数据进行标准化的操作
df_listings[features] = StandardScaler().fit_transform(df_listings[features])

# 进行数据拆分
train_df = df_listings[:2792]
test_df = df_listings[2792:]

# 使用欧式距离构成距离
from scipy.spatial import distance
from sklearn.metrics import mean_squared_error
# 构造多变量函数
def predict_price(new_content, feature_name):
    temp_df = train_df.copy()
    temp_df['distance'] = distance.cdist(temp_df[feature_name], [new_content[feature_name]])
    temp_df = temp_df.sort_values('distance')
    price_mean_5 = temp_df.price.iloc[:5].mean()
    return price_mean_5
# 选取其中的两个变量
cols = ['accommodates', 'bathrooms']
test_df['predict_price'] = test_df.apply(predict_price, feature_name=cols, axis=1)
mse = mean_squared_error(test_df['predict_price'], test_df['price'])
rmse = mse ** (1 / 2)
print(rmse)

演示4 使用sklearn附带的knn进行运算

from sklearn.neighbors import KNeighborsRegressor
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import mean_squared_error

df_listings = pd.read_csv('listings.csv')
# 选取部分特征
features = ['accommodates', 'bedrooms', 'bathrooms', 'beds', 'price', 'minimum_nights', 'maximum_nights', 'number_of_reviews']
# 选取部分特征重新组合
df_listings = df_listings[features]
# 对价格进行处理
df_listings['price'] = df_listings['price'].str.replace('\$|,', "").astype(float)
# 去除有缺失值的行
df_listings = df_listings.dropna()
# 拆分数据
df_listings[features] = StandardScaler().fit_transform(df_listings[features])
train_df = df_listings[:2792]
test_df = df_listings[2792:]
print(test_df.head())
cols = ['accommodates', 'bathrooms']
# 实例化一个knn, n_neighbors用来调整k值
knn = KNeighborsRegressor(n_neighbors=10)
# 进行模型的训练
knn.fit(train_df[cols], train_df['price'])
# 进行模型的预测
test_df['predict_price'] = knn.predict(test_df[cols])
# 计算mse
mse = mean_squared_error(test_df['predict_price'], test_df['price'])
rmse = mse ** (1 / 2)
print(rmse)

# 使用全部特征做一个比较
cols = ['accommodates', 'bedrooms', 'bathrooms', 'beds', 'minimum_nights', 'maximum_nights', 'number_of_reviews']
knn = KNeighborsRegressor(n_neighbors=10)
knn.fit(train_df[cols], train_df['price'])
test_df['predict_price'] = knn.predict(test_df[cols])
mse = mean_squared_error(test_df['predict_price'], test_df['price'])
rmse = mse ** (1 / 2)
print(rmse)