樸素貝葉斯演算法及應用

作業資訊

實驗目的

1.理解決策樹演算法原理，掌握決策樹演算法框架；
2.理解決策樹學習演算法的特徵選擇、樹的生成和樹的剪枝；
3.能根據不同的資料型別，選擇不同的決策樹演算法；
4.針對特定應用場景及資料，能應用決策樹演算法解決實際問題。

實驗內容

1.設計演算法實現熵、經驗條件熵、資訊增益等方法。
2.實現ID3演算法。
3.熟悉sklearn庫中的決策樹演算法；
4.針對iris資料集，應用sklearn的決策樹演算法進行類別預測。
5.針對iris資料集，利用自編決策樹演算法進行類別預測。

實驗報告要求

1.對照實驗內容，撰寫實驗過程、演算法及測試結果；
2.程式碼規範化：命名規則、註釋；
3.分析核心演算法的複雜度；
4.查閱文獻，討論ID3、5演算法的應用場景；
查詢文獻，分析決策樹剪枝策略。

實驗程式碼

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline
from sklearn.datasets import load_iris
from sklearn.model_selection import train_test_split
from collections import Counter
import math
from math import log
import pprint
 

def create_data():
    datasets = [['青年', '否', '否', '一般', '否'],
                ['青年', '否', '否', '好', '否'],
                ['青年', '是', '否', '好', '是'],
                ['青年', '是', '是', '一般', '是'],
                ['青年', '否', '否', '一般', '否'],
                ['中年', '否', '否', '一般', '否'],
                ['中年', '否', '否', '好', '否'],
                ['中年', '是', '是', '好', '是'],
                ['中年', '否', '是', '非常好', '是'],
                ['中年', '否', '是', '非常好', '是'],
                ['老年', '否', '是', '非常好', '是'],
                ['老年', '否', '是', '好', '是'],
                ['老年', '是', '否', '好', '是'],
                ['老年', '是', '否', '非常好', '是'],
                ['老年', '否', '否', '一般', '否'],
                ]
    labels = [u'年齡', u'有工作', u'有自己的房子', u'信貸情況', u'類別']
    # 返回資料集和每個維度的名稱
    return datasets, labels
 

datasets, labels = create_data()

train_data = pd.DataFrame(datasets, columns=labels)

train_data

# 熵
def calc_ent(datasets):
    data_length = len(datasets)
    label_count = {}
    for i in range(data_length):
        label = datasets[i][-1]
        if label not in label_count:
            label_count[label] = 0
        label_count[label] += 1
    ent = -sum([(p / data_length) * log(p / data_length, 2)
            for p in label_count.values()])
    return ent
# def entropy(y):
# """
# Entropy of a label sequence
# """
# hist = np.bincount(y)
# ps = hist / np.sum(hist)
# return -np.sum([p * np.log2(p) for p in ps if p > 0])
# 經驗條件熵
def cond_ent(datasets, axis=0):
    data_length = len(datasets)
    feature_sets = {}
    for i in range(data_length):
        feature = datasets[i][axis]
        if feature not in feature_sets:
            feature_sets[feature] = []
        feature_sets[feature].append(datasets[i])
    cond_ent = sum(
        [(len(p) / data_length) * calc_ent(p) for p in feature_sets.values()])
    return cond_ent
# 資訊增益
def info_gain(ent, cond_ent):
    return ent - cond_ent
def info_gain_train(datasets):
    count = len(datasets[0]) - 1
    ent = calc_ent(datasets)
# ent = entropy(datasets)
    best_feature = []
    for c in range(count):
        c_info_gain = info_gain(ent, cond_ent(datasets, axis=c))
        best_feature.append((c, c_info_gain))
        print('特徵({}) - info_gain - {:.3f}'.format(labels[c], c_info_gain))
# 比較大小
    best_ = max(best_feature, key=lambda x: x[-1])
    return '特徵({})的資訊增益最大，選擇為根節點特徵'.format(labels[best_[0]])

info_gain_train(np.array(datasets))

# 定義節點類 二叉樹
class Node:
    def __init__(self, root=True, label=None, feature_name=None, feature=None):
        self.root = root
        self.label = label
        self.feature_name = feature_name
        self.feature = feature
        self.tree = {}
        self.result = {
            'label:': self.label,
            'feature': self.feature,
            'tree': self.tree
        }
    def __repr__(self):
        return '{}'.format(self.result)
    def add_node(self, val, node):
        self.tree[val] = node
    def predict(self, features):
        if self.root is True:
            return self.label
        return self.tree[features[self.feature]].predict(features)
class DTree:
    def __init__(self, epsilon=0.1):
        self.epsilon = epsilon
        self._tree = {}
    # 熵
    @staticmethod
    def calc_ent(datasets):
        data_length = len(datasets)
        label_count = {}
        for i in range(data_length):
            label = datasets[i][-1]
            if label not in label_count:
                label_count[label] = 0
            label_count[label] += 1
        ent = -sum([(p / data_length) * log(p / data_length, 2)
                    for p in label_count.values()])
        return ent
    # 經驗條件熵
    def cond_ent(self, datasets, axis=0):
        data_length = len(datasets)
        feature_sets = {}
        for i in range(data_length):
            feature = datasets[i][axis]
            if feature not in feature_sets:
                feature_sets[feature] = []
            feature_sets[feature].append(datasets[i])
        cond_ent = sum([(len(p) / data_length) * self.calc_ent(p)
                        for p in feature_sets.values()])
        return cond_ent
    # 資訊增益
    @staticmethod
    def info_gain(ent, cond_ent):
        return ent - cond_ent
    def info_gain_train(self, datasets):
        count = len(datasets[0]) - 1
        ent = self.calc_ent(datasets)
        best_feature = []
        for c in range(count):
            c_info_gain = self.info_gain(ent, self.cond_ent(datasets, axis=c))
            best_feature.append((c, c_info_gain))
        # 比較大小
        best_ = max(best_feature, key=lambda x: x[-1])
        return best_
    def train(self, train_data):
        """
        input:資料集D(DataFrame格式)，特徵集A，閾值eta
        output:決策樹T
        """
        _, y_train, features = train_data.iloc[:, :
                                                -1], train_data.iloc[:,
                                                                    -1], train_data.columns[:
                                                                                            -1]
        # 1,若D中例項屬於同一類Ck，則T為單節點樹，並將類Ck作為結點的類標記，返回T
        if len(y_train.value_counts()) == 1:
            return Node(root=True, label=y_train.iloc[0])
        # 2, 若A為空，則T為單節點樹，將D中例項樹最大的類Ck作為該節點的類標記，返回T
        if len(features) == 0:
            return Node(
                root=True,
                label=y_train.value_counts().sort_values(
                    ascending=False).index[0])
        # 3,計算最大資訊增益 同5.1,Ag為資訊增益最大的特徵
        max_feature, max_info_gain = self.info_gain_train(np.array(train_data))
        max_feature_name = features[max_feature]
        # 4,Ag的資訊增益小於閾值eta,則置T為單節點樹，並將D中是例項數最大的類Ck作為該節點的類標記，返
        if max_info_gain < self.epsilon:
            return Node(
                root=True,
                label=y_train.value_counts().sort_values(
                    ascending=False).index[0])
        # 5,構建Ag子集
        node_tree = Node(
            root=False, feature_name=max_feature_name, feature=max_feature)
        feature_list = train_data[max_feature_name].value_counts().index
        for f in feature_list:
            sub_train_df = train_data.loc[train_data[max_feature_name] ==
                                            f].drop([max_feature_name], axis=1)
            # 6, 遞迴生成樹
            sub_tree = self.train(sub_train_df)
            node_tree.add_node(f, sub_tree)
        # pprint.pprint(node_tree.tree)
        return node_tree
    def fit(self, train_data):
        self._tree = self.train(train_data)
        return self._tree
    def predict(self, X_test):
        return self._tree.predict(X_test)

datasets, labels = create_data()
data_df = pd.DataFrame(datasets, columns=labels)
dt = DTree()
tree = dt.fit(data_df)

tree

dt.predict(['老年', '否', '否', '一般'])

# data
def create_data():
    iris = load_iris()
    df = pd.DataFrame(iris.data, columns=iris.feature_names)
    df['label'] = iris.target
    df.columns = [
        'sepal length', 'sepal width', 'petal length', 'petal width', 'label'
    ]
    data = np.array(df.iloc[:100, [0, 1, -1]])
    # print(data)
    return data[:, :2], data[:, -1]
X, y = create_data()
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)

from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import export_graphviz
import graphviz

clf = DecisionTreeClassifier()
clf.fit(X_train, y_train,)

clf.score(X_test, y_test)

tree_pic = export_graphviz(clf, out_file="mytree.pdf")
with open('mytree.pdf') as f:
    dot_graph = f.read()

graphviz.Source(dot_graph)

from sklearn.tree import DecisionTreeClassifier
from sklearn import preprocessing
import numpy as np
import pandas as pd
from sklearn import tree
import graphviz
features = ["年齡", "有工作", "有自己的房子", "信貸情況"]
X_train = pd.DataFrame([
    ["青年", "否", "否", "一般"],
    ["青年", "否", "否", "好"],
    ["青年", "是", "否", "好"],
    ["青年", "是", "是", "一般"],
    ["青年", "否", "否", "一般"],
    ["中年", "否", "否", "一般"],
    ["中年", "否", "否", "好"],
    ["中年", "是", "是", "好"],
    ["中年", "否", "是", "非常好"],
    ["中年", "否", "是", "非常好"],
    ["老年", "否", "是", "非常好"],
    ["老年", "否", "是", "好"],
    ["老年", "是", "否", "好"],
    ["老年", "是", "否", "非常好"],
    ["老年", "否", "否", "一般"]
])
y_train = pd.DataFrame(["否", "否", "是", "是", "否",
                        "否", "否", "是", "是", "是",
                        "是", "是", "是", "是", "否"])
# 資料預處理
le_x = preprocessing.LabelEncoder()
le_x.fit(np.unique(X_train))
X_train = X_train.apply(le_x.transform)
le_y = preprocessing.LabelEncoder()
le_y.fit(np.unique(y_train))
y_train = y_train.apply(le_y.transform)
# 呼叫sklearn.DT建立訓練模型
model_tree = DecisionTreeClassifier()
model_tree.fit(X_train, y_train)
# 視覺化
dot_data = tree.export_graphviz(model_tree, out_file=None,
                                    feature_names=features,
                                    class_names=[str(k) for k in np.unique(y_train)],
                                    filled=True, rounded=True,
                                    special_characters=True)
graph = graphviz.Source(dot_data)
graph

import numpy as np
class LeastSqRTree:
    def __init__(self, train_X, y, epsilon):
        # 訓練集特徵值
        self.x = train_X
        # 類別
        self.y = y
        # 特徵總數
        self.feature_count = train_X.shape[1]
        # 損失閾值
        self.epsilon = epsilon
        # 迴歸樹
        self.tree = None
    def _fit(self, x, y, feature_count, epsilon):
        # 選擇最優切分點變數j與切分點s
        (j, s, minval, c1, c2) = self._divide(x, y, feature_count)
        # 初始化樹
        tree = {"feature": j, "value": x[s, j], "left": None, "right": None}
        if minval < self.epsilon or len(y[np.where(x[:, j] <= x[s, j])]) <= 1:
            tree["left"] = c1
        else:
            tree["left"] = self._fit(x[np.where(x[:, j] <= x[s, j])],
                                     y[np.where(x[:, j] <= x[s, j])],
                                     self.feature_count, self.epsilon)
        if minval < self.epsilon or len(y[np.where(x[:, j] > s)]) <= 1:
            tree["right"] = c2
        else:
            tree["right"] = self._fit(x[np.where(x[:, j] > x[s, j])],
                                      y[np.where(x[:, j] > x[s, j])],
                                      self.feature_count, self.epsilon)
        return tree
    def fit(self):
        self.tree = self._fit(self.x, self.y, self.feature_count, self.epsilon)
    @staticmethod
    def _divide(x, y, feature_count):
        # 初始化損失誤差
        cost = np.zeros((feature_count, len(x)))
        # 公式5.21
        for i in range(feature_count):
            for k in range(len(x)):
                # k行i列的特徵值
                value = x[k, i]
                y1 = y[np.where(x[:, i] <= value)]
                c1 = np.mean(y1)
                y2 = y[np.where(x[:, i] > value)]
                c2 = np.mean(y2)
                y1[:] = y1[:] - c1
                y2[:] = y2[:] - c2
                cost[i, k] = np.sum(y1 * y1) + np.sum(y2 * y2)
        # 選取最優損失誤差點
        cost_index = np.where(cost == np.min(cost))
        # 選取第幾個特徵值
        j = cost_index[0][0]
        # 選取特徵值的切分點
        s = cost_index[1][0]
        # 求兩個區域的均值c1,c2
        c1 = np.mean(y[np.where(x[:, j] <= x[s, j])])
        c2 = np.mean(y[np.where(x[:, j] > x[s, j])])
        return j, s, cost[cost_index], c1, c2

train_X = np.array([[1, 2, 3, 4, 5, 6, 7, 8, 9, 10]]).T
y = np.array([4.50, 4.75, 4.91, 5.34, 5.80, 7.05, 7.90, 8.23, 8.70, 9.00])
model_tree = LeastSqRTree(train_X, y, .2)
model_tree.fit()
model_tree.tree

執行截圖