K近鄰(knn)算法預測電影類型案例1案例2 Facebook入住地點

K近鄰思想: 根據你的"鄰居們"來确定你的類别

你一覺醒來,不知道自己身在何方裡,你能通過計算機定位到周圍5個"最近的"鄰居,其中有4個身處火星,1個身處月球,你認為應該自己距火星更近,自己應該在火星...(K近鄰算法又稱為Knn算法,屬于分類算法)

案例1

from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
import pandas as pd

def knncls():

    """
    預測電影分類
    :return:
    """
    data = pd.read_csv("./data/movies.csv")
    # 提取特征值, 目标值
    x = data.drop(["type", "movie_name"], axis=1)
    y = data["type"]
    # 分割資料集
    x_train, x_test, y_train, y_test =train_test_split(x, y, test_size=0.25)

    # 通過knn進行預測
    knn = KNeighborsClassifier()

    knn.fit(x_train, y_train)

    y_predict = knn.predict(x_test)
    print(x_test, "的預測結果為:", y_predict)

    print("預測準确率為:", knn.score(x_test, y_test))

if __name__ == '__main__':
    knncls()
           

準确率

movie_name,fight,kiss,type
California Man,3,104,1
He's not Really into dues,2,100,1
Beautiful Woman,1,81,1
Kevin Longblade,101,10,2
Robo Slayer 3000,99,5,2
Amped II,98,2,2
unname,18,90,1
vampire,90,15,2
           

案例2 Facebook入住地點

facebook預測入住地點

train_data

from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
import pandas as pd

def knncls():
    """
    facebook題目:k近鄰算法預測入住位置
    :return:
    """
    # 使用pandas讀取100000資料
    train_data = pd.read_csv("./data/fb/train.csv", nrows = 100000)

    # 特征工程
    # 1.縮小x,y的範圍
    train_data = train_data.query("x>1.0 & x<1.5 & y>1.0 & y<2.5")

    # 2.解析時間戳
    time_value = pd.to_datetime(train_data["time"], unit="s")
    time_value = pd.DatetimeIndex(time_value)

    # 3.添加特征(時間)
    train_data["weekday"] = time_value.weekday
    train_data["year"] = time_value.day
    train_data["hour"] = time_value.hour
    train_data["minute"] = time_value.minute

    # 4.删除特征(時間戳)
    train_data = train_data.drop(["time"], axis=1)

    # 5.隻保留入住人數大于5的place,生成新的train_data
    place_count = train_data.groupby("place_id").count()
    place_count_r = place_count[place_count.row_id > 3].reset_index()
    train_data = train_data[train_data["place_id"].isin(place_count_r["place_id"])]

    # 提取特征值和目标值
    x = train_data.drop(["place_id", "row_id"], axis=1)

    y = train_data["place_id"]

    # 分割資料集
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)

    # 進行标準化
    std = StandardScaler()

    x_train = std.fit_transform(x_train)
    x_test = std.transform(x_test)

    # 執行個體化knn估計器
    knn = KNeighborsClassifier()

    knn.fit(x_train, y_train)

    # 預測結果
    y_predict = knn.predict(x_test)

    # 列印準确率
    print("準确率為:",knn.score(x_test, y_test))

    return None

if __name__ == '__main__':
    knncls()