sklearn之三分类应用

偏执的太偏执、 2022-03-01 00:20 222阅读 0赞

### 用到的代码目录： ###

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70][]

### 1.入门demo：（先不关心具体数据是什么） ###

python代码：lr\_iris.py

import numpy as np
    
    from sklearn import datasets
    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import LogisticRegression
    
    def load_data():
        inputdata = datasets.load_iris()
    
        x_train, x_test, y_train, y_test = \
            train_test_split(inputdata.data, inputdata.target, test_size = 0.2, random_state=0)
        return x_train, x_test, y_train, y_test
    
    def main():
        x_train, x_test, y_train, y_test = load_data()
        model = LogisticRegression(penalty='l1')
        model.fit(x_train, y_train)
    
        print "w: ", model.coef_
        print "b: ", model.intercept_
        print "precision: ", model.score(x_test, y_test)
        print "MSE: ", np.mean((model.predict(x_test) - y_test) ** 2)
    
    if __name__ == '__main__':
        main()

1.将数据切分为20%的测试集，80%的训练集

2.调用逻辑回归的方法得到一个模型

3.将训练集数据放入模型进行学习训练

4.训练后得到结果

5.LogisticRegression(penalty='l2')中的l1是做稀疏化，通常是l2

模型：w，b

准确率：precision

执行结果：

![20190321114256370.png][]

第二步，单独得到w和b

代码 lr\_out\_model.py：

import numpy as np
    
    from sklearn import datasets
    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import LogisticRegression
    
    def load_data():
        inputdata = datasets.load_iris()
    
        x_train, x_test, y_train, y_test = \
            train_test_split(inputdata.data, inputdata.target, test_size = 0.2, random_state=0)
        return x_train, x_test, y_train, y_test
    
    def main():
        x_train, x_test, y_train, y_test = load_data()
        model = LogisticRegression(penalty='l2')
        model.fit(x_train, y_train)
    
        ff_w = open('model.w', 'w')
        ff_b = open('model.b', 'w')
    
        for w_list in model.coef_:
            for w in w_list:
                print >> ff_w, "w: ", w
    
        for b in model.intercept_:
            print >> ff_b, "b: ", b
    
        # print "w: ", model.coef_
        # print "b: ", model.intercept_
        print "precision: ", model.score(x_test, y_test)
        print "MSE: ", np.mean((model.predict(x_test) - y_test) ** 2)
    
    if __name__ == '__main__':
        main()

w:每四个为一组，共12组

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 1][]

### 2.用我们自己找的数据得到一个model ###

验证模型的数据：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 2][]

第一列：label（做2分类）

第二列：冒号左边：每一个数字代表一个特征

第二列：冒号右边：权重

目标：来了一些样本，找出样本背后的label是什么

代码lr.py：

import sys
    import numpy as np
    from scipy.sparse import csr_matrix
    
    from sklearn import datasets
    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import LogisticRegression
    
    data_in = sys.argv[1]
    
    def load_data():
        target_list = []
        fea_row_list = []
        fea_col_list = []
        data_list = []
    
        row_idx = 0
        max_col = 0
    
        with open(data_in, 'r') as fd:
            for line in fd:
                ss = line.strip().split(' ')
                label = ss[0]
                fea = ss[1:]
    
                target_list.append(int(label))
    
                for fea_score in fea:
                    sss = fea_score.strip().split(':')
                    if len(sss) != 2:
                        continue
                    feature, score = sss
    
                    fea_row_list.append(row_idx)
                    fea_col_list.append(int(feature))
                    data_list.append(float(score))
                    if int(feature) > max_col:
                        max_col = int(feature)
    
                row_idx += 1
    
        row = np.array(fea_row_list)
        col = np.array(fea_col_list)
        data = np.array(data_list)
    
        fea_datasets = csr_matrix((data, (row, col)), shape=(row_idx, max_col + 1))
    
        x_train, x_test, y_train, y_test = train_test_split(fea_datasets, target_list, test_size=0.2, random_state=0)
        return x_train, x_test, y_train, y_test
    
    # def load_data():
    #     inputdata = datasets.load_iris()
    #
    #     x_train, x_test, y_train, y_test = \
    #         train_test_split(inputdata.data, inputdata.target, test_size = 0.2, random_state=0)
    #     return x_train, x_test, y_train, y_test
    
    def main():
        x_train, x_test, y_train, y_test = load_data()
        model = LogisticRegression(penalty='l1')
        model.fit(x_train, y_train)
    
        ff_w = open('model.w', 'w')
        ff_b = open('model.b', 'w')
    
        for w_list in model.coef_:
            for w in w_list:
                print >> ff_w, "w: ", w
    
        for b in model.intercept_:
            print >> ff_b, "b: ", b
    
        # print "w: ", model.coef_
        # print "b: ", model.intercept_
        print "precision: ", model.score(x_test, y_test)
        print "MSE: ", np.mean((model.predict(x_test) - y_test) ** 2)
    
    if __name__ == '__main__':
        main()

执行代码：

![20190321115738298.png][]

结果：

w：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 3][]

![20190321115925542.png][]

### 3.从实际工作中得到训练数据 ###

数据整理代码gen\_samples.py：

#coding=utf-8
    import sys
    sys.path.append('../')
    reload(sys)
    sys.setdefaultencoding('utf-8')
    
    import jieba
    import jieba.analyse
    import jieba.posseg
    
    merge_base_infile = '../data/merge_base.data'
    output_file = '../data/samples.data'
    
    output_user_feature_file = '../data/user_feature.data'
    output_item_feature_file = '../data/item_feature.data'
    
    output_itemid_to_name_file = '../data/name_id.dict'
    
    def get_base_samples(infile):
        ret_samples_list = []
        user_info_set = set()
        item_info_set = set()
        item_name2id = {}
        item_id2name = {}
    
        with open(infile, 'r') as fd:
            for line in fd:
                ss = line.strip().split('\001')
                if len(ss) != 13:
                    continue
                userid = ss[0].strip()
                itemid = ss[1].strip()
                watch_time = ss[2].strip()
                total_time = ss[10].strip()
    
                # user info
                gender = ss[4].strip()
                age = ss[5].strip()
                user_feature = '\001'.join([userid, gender, age])
    
                # item info
                name = ss[8].strip()
                item_feature = '\001'.join([itemid, name])
    
                # label info
                label = float(watch_time) / float(total_time)
                final_label = '0'
    
                if label >= 0.82:
                    final_label = '1'
                elif label <= 0.3:
                    final_label = '0'
                else:
                    continue
    
                # gen name2id dict for item feature
                item_name2id[name] = itemid
    
                # gen id2name dict
                item_id2name[itemid] = name
    
                # gen all samples list
                ret_samples_list.append([final_label, user_feature, item_feature])
    
                # gen uniq userinfo
                user_info_set.add(user_feature)
                item_info_set.add(name)
    
        return ret_samples_list, user_info_set, item_info_set, item_name2id, item_id2name
    
    
    # step1. generate base samples(label, user feature, item feature)
    base_sample_list, user_info_set, item_info_set, item_name2id, item_id2name = \
        get_base_samples(merge_base_infile)
    
    
    # step2. extract user feature
    user_fea_dict = {}
    for info in user_info_set:
        userid, gender, age = info.strip().split('\001')
        #gender
        idx = 0 # default 女
        if gender == '男':
            idx = 1
    
        gender_fea = ':'.join([str(idx), '1'])
    
        # age
        idx = 0
        if age == '0-18':
            idx = 0
        elif age == '19-25':
            idx = 1
        elif age == '26-35':
            idx = 2
        elif age == '36-45':
            idx = 3
        else:
            idx = 4
    
        idx += 2
    
        age_fea = ':'.join([str(idx), '1'])
    
        user_fea_dict[userid] = ' '.join([gender_fea, age_fea])
    
    # step3. extract item feature
    
    token_set = set()
    
    item_fs_dict = {}
    for name in item_info_set:
        token_score_list = []
        for x, w in jieba.analyse.extract_tags(name, withWeight=True):
            token_score_list.append((x, w))
            token_set.add(x)
        item_fs_dict[name] = token_score_list
    
    user_feature_offset = 10
    # gen item id feature
    token_id_dict = {}
    for tu in enumerate(list(token_set)):
        # token -> token id
        token_id_dict[tu[1]] = tu[0]
    
    item_fea_dict = {}
    for name, fea in item_fs_dict.items():
        tokenid_score_list = []
        for (token, score) in fea:
            if token not in token_id_dict:
                continue
            token_id = token_id_dict[token] + user_feature_offset
            tokenid_score_list.append(':'.join([str(token_id), str(score)]))
    
        item_fea_dict[name] = ' '.join(tokenid_score_list)
    
    
    # step 4.generate final samples
    ofile = open(output_file, 'w')
    for (label, user_feature, item_feature) in base_sample_list:
        userid = user_feature.strip().split('\001')[0]
        item_name = item_feature.strip().split('\001')[1]
        if userid not in user_fea_dict:
            continue
        if item_name not in item_fea_dict:
            continue
    
        ofile.write(' '.join([label, user_fea_dict[userid], item_fea_dict[item_name]]))
        ofile.write('\n')
    ofile.close()
    # step 5. generate user feature mapping file
    o_u_file = open(output_user_feature_file, 'w')
    for userid, feature in user_fea_dict.items():
        o_u_file.write('\t'.join([userid, feature]))
        o_u_file.write('\n')
    o_u_file.close()
    
    # step 6. generate item feature mapping file
    o_i_file = open(output_item_feature_file, 'w')
    for item_name, feature in item_fea_dict.items():
        if item_name not in item_name2id:
            continue
        itemid = item_name2id[item_name]
        o_i_file.write('\t'.join([itemid, feature]))
        o_i_file.write('\n')
    o_i_file.close()
    
    # step 7. generate item id to name mapping file
    o_file = open(output_itemid_to_name_file, 'w')
    for itemid, item_name in item_id2name.items():
        o_file.write('\t'.join([itemid, item_name]))
        o_file.write('\n')
    o_file.close()

执行代码：

![20190321133231778.png][]

结果：

![20190321133301127.png][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 4][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 5][]

样本（第一列是正负例）：

![20190321133518843.png][]

### 利用我们自己的数据进行训练： ###

![20190321134019829.png][]

准确率81%

模型：

![20190321134103683.png][]

MSE（误差平方和）：0.18

### 用测试数据对模型进行测试（打印真实label和预测label） ###

测试代码lr\_auc.py：

#coding=utf8
    import sys
    import numpy as np
    from scipy.sparse import csr_matrix
    
    from sklearn import datasets
    from sklearn.model_selection import train_test_split
    from sklearn.linear_model import LogisticRegression
    
    data_in = sys.argv[1]
    
    def load_data():
        target_list = []
        fea_row_list = []
        fea_col_list = []
        data_list = []
    
        row_idx = 0
        max_col = 0
    
        with open(data_in, 'r') as fd:
            for line in fd:
                ss = line.strip().split(' ')
                label = ss[0]
                fea = ss[1:]
    
                target_list.append(int(label))
    
                for fea_score in fea:
                    sss = fea_score.strip().split(':')
                    if len(sss) != 2:
                        continue
                    feature, score = sss
    
                    fea_row_list.append(row_idx)
                    fea_col_list.append(int(feature))
                    data_list.append(float(score))
                    if int(feature) > max_col:
                        max_col = int(feature)
    
                row_idx += 1
    
        row = np.array(fea_row_list)
        col = np.array(fea_col_list)
        data = np.array(data_list)
    
        fea_datasets = csr_matrix((data, (row, col)), shape=(row_idx, max_col + 1))
    
        x_train, x_test, y_train, y_test = train_test_split(fea_datasets, target_list, test_size=0.2, random_state=0)
        return x_train, x_test, y_train, y_test
    
    # def load_data():
    #     inputdata = datasets.load_iris()
    #
    #     x_train, x_test, y_train, y_test = \
    #         train_test_split(inputdata.data, inputdata.target, test_size = 0.2, random_state=0)
    #     return x_train, x_test, y_train, y_test
    
    def main():
        x_train, x_test, y_train, y_test = load_data()
        model = LogisticRegression(penalty='l1')
        model.fit(x_train, y_train)
    
        ff_t = open('T.txt', 'w')
        ff_p = open('P.txt', 'w')
    
        #for b in model.intercept_:
            #print >> ff_b, "b: ", b
    
        # print "w: ", model.coef_
        # print "b: ", model.intercept_
        #print "precision: ", model.score(x_test, y_test)
        #print "MSE: ", np.mean((model.predict(x_test) - y_test) ** 2)
    
        #print y_test, model.predict(x_test)
    
        # 输出真实label和预测label，到两个不同的文件中
        for y in y_test:
            print >> ff_t, y
    
        for y in model.predict_proba(x_test):
            print >> ff_p, y
    
    
    if __name__ == '__main__':
        main()

执行代码及结果：

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 6][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 7][]

![watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 8][]

[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70]: /images/20220301/997c1e3f392241a29419bb643f0db8b3.png
[20190321114256370.png]: /images/20220301/73adea37fb154cbabae780817588cb04.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 1]: /images/20220301/cf9691fd658f414bad1059490bbb6609.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 2]: /images/20220301/f89fa9b376f74726ba20fb5165a54b1a.png
[20190321115738298.png]: /images/20220301/286d4f26961146a3875ccaaac8815627.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 3]: /images/20220301/e387e15e716e4b01b6670b9342651ea3.png
[20190321115925542.png]: /images/20220301/ce804ce8ddc440c9844ac5790ba08f61.png
[20190321133231778.png]: /images/20220301/12d8156b8f1944ffbc0b76accfed3dd8.png
[20190321133301127.png]: /images/20220301/6421a38b1d274937a51bbe85b1b1dda2.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 4]: /images/20220301/46162446c52f4169823d80d3c4ca4a22.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 5]: /images/20220301/0723cdc58c0b42ea81ed1e2685f3c18c.png
[20190321133518843.png]: /images/20220301/348fcd1bba1047e19f27c5793f0cf4b5.png
[20190321134019829.png]: /images/20220301/7d07f570ebd74d1c965cac809d657a20.png
[20190321134103683.png]: /images/20220301/0d0f0b97803c4d6387cd9ce7e912d0d0.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 6]: /images/20220301/e1cae2cf712e490887e7d1464f4896e6.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 7]: /images/20220301/a4d5a3752bb9475dbaec76708de53e6c.png
[watermark_type_ZmFuZ3poZW5naGVpdGk_shadow_10_text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzI4Mjg2MDI3_size_16_color_FFFFFF_t_70 8]: /images/20220301/1718fa0fd98d48a38b0b02be1c0e462f.png