【机器学习】用户画像

用户画像-案例

基于用户搜索关键词数据为用户打上标签(年龄,性别,学历)

整体流程

(一)数据预处理

  • 编码方式转换
  • 对数据搜索内容进行分词
  • 词性过滤
  • 数据检查

(二)特征选择

  • 建立word2vec词向量模型
  • 对所有搜索数据求平均向量

(三)建模预测

  • 不同机器学习模型对比
  • 堆叠模型

将原始数据转换成utf-8编码,防止后续出现各种编码问题

由于原始数据比较大,在分词与过滤阶段会比较慢,这里我们选择了原始数据中的1W个

import csv

#原始数据存储路径
data_path = './data/user_tag_query.10W.TRAIN' 
#生成数据路径
csvfile = open(data_path + '-1w.csv', 'w')
writer = csv.writer(csvfile)
writer.writerow(['ID', 'age', 'Gender', 'Education', 'QueryList'])
#转换成utf-8编码的格式
with open(data_path, 'r',encoding='gb18030',errors='ignore') as f:
    lines = f.readlines()
    for line in lines[0:10000]:
        try:
            line.strip()          
            data = line.split("\t")
            writedata = [data[0], data[1], data[2], data[3]]
            querystr = ''
            data[-1]=data[-1][:-1]
            for d in data[4:]:
                try:
                    cur_str = d.encode('utf8')
                    cur_str = cur_str.decode('utf8')
                    querystr += cur_str + '\t'
                except:
                    continue
                    #print (data[0][0:10])
            querystr = querystr[:-1]
            writedata.append(querystr)
            writer.writerow(writedata)
        except:
            #print (data[0][0:20])
            continue
data_path = './data/user_tag_query.10W.TEST'

csvfile = open(data_path + '-1w.csv', 'w')
writer = csv.writer(csvfile)
writer.writerow(['ID', 'QueryList'])
with open(data_path, 'r',encoding='gb18030',errors='ignore') as f:
    lines = f.readlines()
    for line in lines[0:10000]:
        try:
            data = line.split("\t")
            writedata = [data[0]]
            querystr = ''
            data[-1]=data[-1][:-1]
            for d in data[1:]:
                try:                  
                    cur_str = d.encode('utf8')
                    cur_str = cur_str.decode('utf8')
                    querystr += cur_str + '\t'               
                except:
                    #print (data[0][0:10])
                    continue
            querystr = querystr[:-1]
            writedata.append(querystr)
            writer.writerow(writedata)
        except:
            #print (data[0][0:20])
            continue

生成对应的数据表

import pandas as pd

#编码转换完成的数据,取的是1W的子集
trainname = './data/user_tag_query.10W.TRAIN-1w.csv'
testname = './data/user_tag_query.10W.TEST-1w.csv'

data = pd.read_csv(trainname,encoding='gbk')
print (data.info())

#分别生成三种标签数据(性别,年龄,学历)
data.age.to_csv("./data/train_age.csv", index=False)
data.Gender.to_csv("./data/train_gender.csv", index=False)
data.Education.to_csv("./data/train_education.csv", index=False)
#将搜索数据单独拿出来
data.QueryList.to_csv("./data/train_querylist.csv", index=False)

data = pd.read_csv(testname,encoding='gbk')
print (data.info())

data.QueryList.to_csv("./data/test_querylist.csv", index=False)

对用户的搜索数据进行分词与词性过滤

import pandas as pd
import jieba.analyse
import time
import jieba
import jieba.posseg
import os, sys


def input(trainname):
    traindata = []
    with open(trainname, 'rb') as f:
        line = f.readline()
        count = 0
        while line:
            try:
                traindata.append(line)
                count += 1
            except:
                print ("error:", line, count)
            line=f.readline()
    return traindata
start = time.clock()

filepath = './data/test_querylist.csv'
QueryList = input(filepath)

writepath = './data/test_querylist_writefile-1w.csv'
csvfile = open(writepath, 'w')

POS = {}
for i in range(len(QueryList)):
    #print (i)
    if i%2000 == 0 and i >=1000:
        print (i,'finished') 
    s = []
    str = ""
    words = jieba.posseg.cut(QueryList[i])# 带有词性的精确分词模式
    allowPOS = ['n','v','j']
    for word, flag in words:
        POS[flag]=POS.get(flag,0)+1
        if (flag[0] in allowPOS) and len(word)>=2:
            str += word + " "
            
    cur_str = str.encode('utf8')
    cur_str = cur_str.decode('utf8')
    s.append(cur_str)
    
    csvfile.write(" ".join(s)+'\n')
csvfile.close()

end = time.clock()
print ("total time: %f s" % (end - start))

使用Gensim库建立word2vec词向量模型

参数定义:

  • sentences:可以是一个list

  • sg: 用于设置训练算法,默认为0,对应CBOW算法;sg=1则采用skip-gram算法。

  • size:是指特征向量的维度,默认为100。大的size需要更多的训练数据,但是效果会更好. 推荐值为几十到几百。

  • window:表示当前词与预测词在一个句子中的最大距离是多少

  • alpha: 是学习速率

  • seed:用于随机数发生器。与初始化词向量有关。

  • min_count: 可以对字典做截断. 词频少于min_count次数的单词会被丢弃掉, 默认值为5

  • max_vocab_size: 设置词向量构建期间的RAM限制。如果所有独立单词个数超过这个,则就消除掉其中最不频繁的一个。每一千万个单词需要大约1GB的RAM。设置成None则没有限制。

  • workers参数控制训练的并行数。

  • hs: 如果为1则会采用hierarchica·softmax技巧。如果设置为0(defau·t),则negative sampling会被使用。

  • negative: 如果>0,则会采用negativesamp·ing,用于设置多少个noise words

  • iter: 迭代次数,默认为5

from gensim.models import word2vec
#将数据变换成list of list格式
train_path = './data/train_querylist_writefile-1w.csv'
with open(train_path, 'r') as f:
    My_list = []
    lines = f.readlines()
    for line in lines:
        cur_list = []
        line = line.strip()
        data = line.split(" ")
        for d in data:
            cur_list.append(d)
        My_list.append(cur_list)
    
    model = word2vec.Word2Vec(My_list, size=300, window=10,workers=4)  
    savepath = '1w_word2vec_' + '300'+'.model' # 保存model的路径

    model.save(savepath)

加载训练好的word2vec模型,求用户搜索结果的平均向量

import numpy as np
file_name = './data/train_querylist_writefile-1w.csv'
cur_model = gensim.models.Word2Vec.load('1w_word2vec_300.model')
with open(file_name, 'r') as f:
    cur_index = 0
    lines = f.readlines()
    doc_cev = np.zeros((len(lines),300))
    for line in lines:
        word_vec = np.zeros((1,300))
        words = line.strip().split(' ')
        wrod_num = 0
        #求模型的平均向量
        for word in words:
            if word in cur_model:
                wrod_num += 1
                word_vec += np.array([cur_model[word]])
        doc_cev[cur_index] = word_vec / float(wrod_num)
        cur_index += 1
import numpy as np
file_name = './data/test_querylist_writefile-1w.csv'
cur_model = gensim.models.Word2Vec.load('1w_word2vec_300.model')
with open(file_name, 'r') as f:
    cur_index = 0
    lines = f.readlines()
    doc_cev = np.zeros((len(lines),300))
    for line in lines:
        word_vec = np.zeros((1,300))
        words = line.strip().split(' ')
        wrod_num = 0
        #求模型的平均向量
        for word in words:
            if word in cur_model:
                wrod_num += 1
                word_vec += np.array([cur_model[word]])
        doc_cev[cur_index] = word_vec / float(wrod_num)
        cur_index += 1
genderlabel = np.loadtxt(open('./data/train_gender.csv', 'r')).astype(int)


educationlabel = np.loadtxt(open('./data/train_education.csv', 'r')).astype(int)


agelabel = np.loadtxt(open('./data/train_age.csv', 'r')).astype(int)

处理一些为0的数据

def removezero(x, y):
        nozero = np.nonzero(y)
        y = y[nozero]
        x = np.array(x)
        x = x[nozero]
        return x, y
gender_train, genderlabel = removezero(doc_cev, genderlabel)
age_train, agelabel = removezero(doc_cev, agelabel)
education_train, educationlabel = removezero(doc_cev, educationlabel)

绘图函数,绘制混淆矩阵

import matplotlib.pyplot as plt
import itertools
def plot_confusion_matrix(cm, classes,
                          title='Confusion matrix',
                          cmap=plt.cm.Blues):
    """
    This function prints and plots the confusion matrix.
    """
    plt.imshow(cm, interpolation='nearest', cmap=cmap)
    plt.title(title)
    plt.colorbar()
    tick_marks = np.arange(len(classes))
    plt.xticks(tick_marks, classes, rotation=0)
    plt.yticks(tick_marks, classes)

    thresh = cm.max() / 2.
    for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
        plt.text(j, i, cm[i, j],
                 horizontalalignment="center",
                 color="white" if cm[i, j] > thresh else "black")

    plt.tight_layout()
    plt.ylabel('True label')
    plt.xlabel('Predicted label')

建立一个基础预测模型

from sklearn.linear_model import LogisticRegression
from sklearn.metrics import confusion_matrix
from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(gender_train,genderlabel,test_size = 0.2, random_state = 0)

LR_model = LogisticRegression()

LR_model.fit(X_train,y_train)
y_pred = LR_model.predict(X_test)
print (LR_model.score(X_test,y_test))

cnf_matrix = confusion_matrix(y_test,y_pred)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

print("accuracy metric in the testing dataset: ", (cnf_matrix[1,1]+cnf_matrix[0,0])/(cnf_matrix[0,0]+cnf_matrix[1,1]+cnf_matrix[1,0]+cnf_matrix[0,1]))

# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Gender-Confusion matrix')
plt.show()

0.798155737705
Recall metric in the testing dataset: 0.735074626866
accuracy metric in the testing dataset: 0.798155737705
【机器学习】用户画像_第1张图片

from sklearn.ensemble import RandomForestClassifier
from sklearn.metrics import confusion_matrix
from sklearn.cross_validation import train_test_split

X_train, X_test, y_train, y_test = train_test_split(gender_train,genderlabel,test_size = 0.2, random_state = 0)

RF_model = RandomForestClassifier(n_estimators=100,min_samples_split=5,max_depth=10)

RF_model.fit(X_train,y_train)
y_pred = RF_model.predict(X_test)
print (RF_model.score(X_test,y_test))

cnf_matrix = confusion_matrix(y_test,y_pred)

print("Recall metric in the testing dataset: ", cnf_matrix[1,1]/(cnf_matrix[1,0]+cnf_matrix[1,1]))

print("accuracy metric in the testing dataset: ", (cnf_matrix[1,1]+cnf_matrix[0,0])/(cnf_matrix[0,0]+cnf_matrix[1,1]+cnf_matrix[1,0]+cnf_matrix[0,1]))

# Plot non-normalized confusion matrix
class_names = [0,1]
plt.figure()
plot_confusion_matrix(cnf_matrix
                      , classes=class_names
                      , title='Gender-Confusion matrix')
plt.show()

0.795081967213
Recall metric in the testing dataset: 0.730099502488
accuracy metric in the testing dataset: 0.795081967213
【机器学习】用户画像_第2张图片

堆叠模型

【机器学习】用户画像_第3张图片

from sklearn.svm import SVC
from sklearn.naive_bayes import MultinomialNB
clf1 = RandomForestClassifier(n_estimators=100,min_samples_split=5,max_depth=10)
clf2 = SVC()
clf3 = LogisticRegression()
basemodes = [
            ['rf', clf1],
            ['svm', clf2],
            ['lr', clf3]
            ]
from sklearn.cross_validation import KFold, StratifiedKFold
models = basemodes

#X_train, X_test, y_train, y_test

folds = list(KFold(len(y_train), n_folds=5, random_state=0))
print (len(folds))
S_train = np.zeros((X_train.shape[0], len(models)))
S_test = np.zeros((X_test.shape[0], len(models)))

for i, bm in enumerate(models):
    clf = bm[1]

    #S_test_i = np.zeros((y_test.shape[0], len(folds)))
    for j, (train_idx, test_idx) in enumerate(folds):
        X_train_cv = X_train[train_idx]
        y_train_cv = y_train[train_idx]
        X_val = X_train[test_idx]
        clf.fit(X_train_cv, y_train_cv)
        y_val = clf.predict(X_val)[:]
          
        S_train[test_idx, i] = y_val
    S_test[:,i] = clf.predict(X_test)

final_clf = RandomForestClassifier(n_estimators=100)
final_clf.fit(S_train,y_train)

print (final_clf.score(S_test,y_test))

5
0.796106557377

结果不是很好,可以继续调参

你可能感兴趣的:(python,机器学习)