用户画像（七）：基于用户搜索数据，建立预测模型

绘图函数，以性别为例，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')

测试集的构造方法和训练集一样

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

检查一下数据有木有问题

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()

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()

堆叠模型

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))