机器学习简要教程1

开发机器学习应用程序的步骤

1. 收集数据
2. 准备输入数据（格式化、归一化）
3. 分析输入数据
4. 训练算法
5. 测试算法
6. 使用算法

k近邻算法

优点：精度高、对异常值不敏感、无数据输入假定
缺点：计算复杂度高、空间复杂度高
使用数据范围：数值型和标称型

from numpy import *import operatordef create_data_set():    group = array([[1.0,1.1],[1.0,1.0],[0,0.1],[0.1,0.1]])    labels = ['a','a','b','b']    return group,labelsdef classify(pre_data,data_set,labels,k):    data_set_size = data_set.shape[0]    diff_mat = tile(pre_data,(data_set_size,1)) - data_set    sq_diff_mat = diff_mat**2    sq_distances = sq_diff_mat.sum(axis=1)    distances = sq_distances**0.5    sorted_dist_indicies = distances.argsort()    class_count = {}    for i in range(k):        vote_label = labels[sorted_dist_indicies[i]]        class_count[vote_label] = class_count.get(vote_label,0) + 1    sorted_class_count = sorted(class_count.iteritems(),key=operator.itemgetter(1),reverse=True)    return sorted_class_count[0][0]def main():    group,labels = create_data_set()    print classify([0,0],group,labels,2)    print classify([1,0],group,labels,2)if __name__=="__main__":    main()

决策树

优点：计算复杂度不高，结果易于理解，对缺失值不敏感，可以处理不相关特征数据
缺点：可能产生过度匹配问题
适用数据类型：数值型和标称型

from numpy import *import operatordef create_data_set():    group = array([[1.0,1.1,'no'],[1.0,1.0,'no'],[0,0.1,'yes'],[0.1,0.1,'yes']])    labels = ['a','a','b','b']    return group,labelsdef classify(pre_data,data_set,labels,k):    data_set_size = data_set.shape[0]    diff_mat = tile(pre_data,(data_set_size,1)) - data_set    sq_diff_mat = diff_mat**2    sq_distances = sq_diff_mat.sum(axis=1)    distances = sq_distances**0.5    sorted_dist_indicies = distances.argsort()    class_count = {}    for i in range(k):        vote_label = labels[sorted_dist_indicies[i]]        class_count[vote_label] = class_count.get(vote_label,0) + 1    sorted_class_count = sorted(class_count.iteritems(),key=operator.itemgetter(1),reverse=True)    return sorted_class_count[0][0]def calc_shannon_ent(data_set):    num_entries = len(data_set)    label_counts = {}    for v in data_set:        current_label = v[-1]        if current_label not in label_counts:            label_counts[current_label] = 0        label_counts[current_label] += 1    shannon_ent = 0    for key in label_counts:        prob = float(label_counts[key])/num_entries        shannon_ent -= prob * log(prob,2)    return shannon_entdef split_data_set(data_set,axis,value):    ret_data_set = []    for v in data_set:        if v[axis] == value:            reduce_feat_vec = v[:axis]            reduce_feat_vec.extend(v[:axis+1])            ret_data_set.append(reduce_feat_vec)    return ret_data_setdef choose_best_feature_to_split(data_set):    num_features = len(data_set[0]) - 1    base_Entropy = calc_shannon_ent(data_set)    best_info_gain = 0    best_featurn = -1    for i in range(num_features):        feat_list = set([e[i] for e in data_set])        new_entropy = 0.0        for value in feat_list:            sub_data_set = split_data_set(data_set,i,value)            prob = len(sub_data_set)/float(len(data_set)            new_entropy += prob * calc_shannon_ent(sub_data_set)        info_gain = base_Entropy - new_entropy        if(info_gain > best_info_gain):            best_info_gain = info_gain            best_featurn = i    return best_featurndef majority_cnt(class_list):    class_count = {}    for v in class_list:        if v not in class_count:            class_count[v] = 0        class_count[v] += 1    sorted_dist_count = sorted(class_count.iteritems(),key=operator.itemgetter(1),reverse=True)    return sorted_class_count[0][0]def create_tree(data_set,labels):    class_list = [i[-1] for i in data_set]    if class_list.count(class_list[0]) == len(class_list):        return class_list[0]    if len(data_set[0]) == 1:        return majority_cnt(class_list)    best_feat = choose_best_feature_to_split(data_set)    best_feat_label = labels[best_feat]    my_tree = {best_feat_label:{}}    del(labels[best_feat])    uniq_feat_values = set([i[best_feat] for i in data_set])    for value in uniq_feat_values:        sub_labels = labels[:]        my_tree[best_feat_label][value] = create_tree(split_data_set(data_set,best_feat,value),sub_labels)    return my_treedef main():    group,labels = create_data_set()    my_tree = create_tree(group,labels)if __name__=="__main__":    main()