21_交叉验证与网络搜索

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


def knncls():
    """
    K-近邻算法预测用户签到位置
    """

    # 读取数据
    data = pd.read_csv("./predict/train.csv")
    # print(data)
        # 处理数据
            # 1.缩小数据,查询数据筛选
    data = data.query("x > 1.0 & x < 1.25 & y > 2.5 & y < 2.75")
            # 2.处理日期数据
    time_value = pd.to_datetime(data["time"], unit=‘s‘)
    # print(time_value)

    # 把日期格式转换成字典格式
    time_value = pd.DatetimeIndex(time_value)

    # 构造一些特征
    data[‘day‘] = time_value.day
    data[‘hour‘] = time_value.hour
    data[‘weekday‘] = time_value.weekday

    # 把时间特征戳删除
    data = data.drop([‘time‘], axis=1)
    # print(data)
    # 在sklearn中列axis=1（记住）

    # 把签到数量少于n个目标位置删除
    place_count = data.groupby(‘place_id‘).count()
    tf = place_count[place_count.row_id > 3].reset_index()
    data = data[data[‘place_id‘].isin(tf.place_id)]
    # print(data)

    # 取出数据当中的特征值和目标值
    y = data[‘place_id‘]
    x = data.drop([‘place_id‘], axis=1)
    print(x)

    # x = data.drop([‘row_id‘], axis=1)
    # 进行数据的分割训练集合测试集
    x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.25)
    # 特征工程（标准化）
    std = StandardScaler()
    # 对测试集和训练集的特征值进行标准化
    x_train = std.fit_transform(x_train)
    x_test = std.transform(x_test)

    # 进行算法流程
    knn = KNeighborsClassifier()

    # 进行网格搜索
    # 构造一些参数的值进行搜索
    param = {"n_neighbors":[1,3,5]}
    gc = GridSearchCV(knn,param_grid=param,cv=2)
    # cv一般为10，这里是便于计算
    gc.fit(x_train,y_train)

    
    knn.fit(x_train, y_train)
    # 得出预测结果
    y_predict = knn.predict(x_test)

    print("预测目标的签到位置：", y_predict)

    # 得出准确率
    print("预测的准确率：", knn.score(x_test, y_test))

if __name__ == ‘__main__‘:
    knncls()