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')