機械学習ランダムフォレストアルゴリズムの実践的解析

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df['target'], test_size=0.2, random_state=0)

# 训练随机森林算法并计算得分
simple_rf_model = RandomForestClassifier(n_estimators=100, random_state=0)
simple_rf_model.fit(X_train, y_train)
print(f"accuracy: {simple_rf_model.score(X_test, y_test)}")

# accuracy: 0.93

simple_rf_model = RandomForestClassifier(n_estimators=100, random_state=0)

#创建决策树
tree1 = DecisionTreeClassifier().fit(X_train, y_train)
tree2 = DecisionTreeClassifier().fit(X_train, y_train)
tree3 = DecisionTreeClassifier().fit(X_train, y_train)

# 预测X_test上的每一棵决策树
predictions_1 = tree1.predict(X_test)
predictions_2 = tree2.predict(X_test)
predictions_3 = tree3.predict(X_test)
print(predictions_1, predictions_2, predictions_3)

# 采取优先级策略
final_prediction = np.array([np.round((predictions_1[i] + predictions_2[i] + predictions_3[i])/3) for i in range(len(predictions_1))])
print(final_prediction)

blue, blue, red, green, red

blue, red

red, red

import numpy as np
import pandas as pd
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split

# 对于每一棵树从X_train中采用3次放回抽样
df_sample1 = df.sample(frac=.67, replace=True)
df_sample2 = df.sample(frac=.67, replace=True)
df_sample3 = df.sample(frac=.67, replace=True)

X_train_sample1, X_test_sample1, y_train_sample1, y_test_sample1 = train_test_split(df_sample1.drop('target', axis=1), df_sample1['target'], test_size=0.2)
X_train_sample2, X_test_sample2, y_train_sample2, y_test_sample2 = train_test_split(df_sample2.drop('target', axis=1), df_sample2['target'], test_size=0.2)
X_train_sample3, X_test_sample3, y_train_sample3, y_test_sample3 = train_test_split(df_sample3.drop('target', axis=1), df_sample3['target'], test_size=0.2)

#生成决策树
tree1 = DecisionTreeClassifier().fit(X_train_sample1, y_train_sample1)
tree2 = DecisionTreeClassifier().fit(X_train_sample2, y_train_sample2)
tree3 = DecisionTreeClassifier().fit(X_train_sample3, y_train_sample3)

# 在X_test上预测每一棵决策树
predictions_1 = tree1.predict(X_test)
predictions_2 = tree2.predict(X_test)
predictions_3 = tree3.predict(X_test)
df = pd.DataFrame([predictions_1, predictions_2, predictions_3]).T
df.columns = ["tree1", "tree2", "tree3"]

# 采取优先级策略 
final_prediction = np.array([np.round((predictions_1[i] + predictions_2[i] + predictions_3[i])/3) for i in range(len(predictions_1))])
preds = pd.DataFrame([predictions_1, predictions_2, predictions_3, final_prediction, y_test]).T.head(20)
preds.columns = ["tree1", "tree2", "tree3", "final", "label"]
preds

import numpy as np
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import BaggingClassifier

# 集合中所使用的树的数量
n_estimators = 3

# 初始化装袋分类器
bag_clf = BaggingClassifier(
DecisionTreeClassifier(), n_estimators=n_estimators, bootstrap=True)

# 根据训练数据拟合装袋分类器
bag_clf.fit(X_train, y_train)

# 对测试数据进行预测
y_pred = bag_clf.predict(X_test)
pd.DataFrame([y_pred, y_test]).T

import numpy as np
import pandas as pd
import math
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
#对于每一棵树从X_train中取3个样本
df_sample1 = df.sample(frac=.67, replace=True)
df_sample2 = df.sample(frac=.67, replace=True)
df_sample3 = df.sample(frac=.67, replace=True)

# 分割训练集
X_train_sample1, y_train_sample1 = df_sample1.drop('target', axis=1), df_sample1['target']
X_train_sample2, y_train_sample2 = df_sample2.drop('target', axis=1), df_sample2['target']
X_train_sample3, y_train_sample3 = df_sample3.drop('target', axis=1), df_sample3['target']

# 使用sqrt获取训练和测试的采样特征，现在注意replace如何等于False的
num_features = len(X_train.columns)
X_train_sample1 = X_train_sample1.sample(n=int(math.sqrt(num_features)), replace=False, axis = 1)
X_train_sample2 = X_train_sample2.sample(n=int(math.sqrt(num_features)), replace=False, axis = 1)
X_train_sample3 = X_train_sample3.sample(n=int(math.sqrt(num_features)), replace=False, axis = 1)

# 创建决策树，这次我们对列进行采样
tree1 = DecisionTreeClassifier().fit(X_train_sample1, y_train_sample1)
tree2 = DecisionTreeClassifier().fit(X_train_sample2, y_train_sample2)
tree3 = DecisionTreeClassifier().fit(X_train_sample3, y_train_sample3)

# 预测X_test上的每个决策树
predictions_1 = tree1.predict(X_test[X_train_sample1.columns])
predictions_2 = tree2.predict(X_test[X_train_sample2.columns])
predictions_3 = tree3.predict(X_test[X_train_sample3.columns])
preds = pd.DataFrame([predictions_1, predictions_2, predictions_3]).T
preds.columns = ["tree1", "tree2", "tree3"]

# 使用优先级规则 
final_prediction = np.array([np.round((predictions_1[i] + predictions_2[i] + predictions_3[i])/3) for i in range(len(predictions_1))])
preds = pd.DataFrame([predictions_1, predictions_2, predictions_3, final_prediction, y_test]).T.head(20)
preds.columns = ["tree1", "tree2", "tree3", "final", "label"]

from collections import Counter
from math import log2

#我的预测分类为：0或者1。其中，0代表蓝色弹珠，1代表是绿色弹珠。
data = [0, 0, 0, 1, 1, 1, 1, 0, 1, 0]
# 获取标签的长度
len_labels = len(data)
def calculate_entropy(data, len_labels):
# 对每一种分类进行计数
counts = Counter(labels)
# 我们计算分数，这个例子的输出应该是[.5，.5]
probs = [count / num_labels for count in counts.values()]
# 实际熵计算
return - sum(p * log2(p) for p in probs)

calculate_entropy(labels, num_labels)

entropy(parent) — [weighted_average_of_entropy(children)]

def information_gain(left_labels, right_labels, parent_entropy):
"""计算拆分的信息增益"""
#计算左侧节点的权重
proportion_left_node = float(len(left_labels)) / (len(left_labels) + len(right_labels))
#计算右节点的权重
proportion_right_node = 1 - proportion_left_node
# 计算子节点的加权平均值
weighted_average_of_child_nodes = ((proportion_left_node * entropy(left_labels)) + (proportion_right_node * entropy(right_labels)))
#返回父节点熵——子节点的加权熵
return parent_entropy - weighted_average_of_child_nodes

import pandas as pd
import numpy as np
from math import log2

def entropy(data, target_col):
# calculate the entropy of the entire dataset
values, counts = np.unique(data[target_col], return_counts=True)
entropy = np.sum([-count/len(data) * log2(count/len(data)) for count in counts])
return entropy

def compute_information_gain(data, feature, target_col):
parent_entropy = entropy(data, target_col)
# 计算在给定特征上拆分的信息增益
split_values = np.unique(data[feature])
# initialize at 0
weighted_child_entropy = 0
# 计算加权熵，记住这与新节点中的点数有关
for value in split_values:
sub_data = data[data[feature] == value]
node_weight = len(sub_data)/len(data)
weighted_child_entropy += node_weight * entropy(sub_data, target_col)
#与之前相同的计算，我们只是从父节点熵中减去加权熵 
return parent_entropy - weighted_child_entropy

def grow_tree(data, features, target_col, depth=0, max_depth=3):
# 我们将最大深度设置为3以“预修剪”或限制树的复杂性
if depth >= max_depth or len(np.unique(data[target_col])) == 1:
# 如果达到最大深度或所有标签都相同，则停止生长树。所有标签相同意味着熵为0
return np.unique(data[target_col])[0]
# 我们根据信息增益计算最佳特征（或最佳问题）
node = {}
gains = [compute_information_gain(data, feature, target_col) for feature in features]
best_feature = features[np.argmax(gains)]

for value in np.unique(data[best_feature]):
sub_data = data[data[best_feature] == value]
node[value] = grow_tree(sub_data, features, target_col, depth+1, max_depth)

return node


# 模拟一些数据并制作一个数据帧，注意我们是如何建立一个目标的
data = {
'A': [1, 2, 1, 2, 1, 2, 1, 2],
'B': [3, 3, 4, 4, 3, 3, 4, 4],
'C': [5, 5, 5, 5, 6, 6, 6, 6],
'target': [0, 0, 0, 1, 1, 1, 1, 0]
}
df = pd.DataFrame(data)

# 定义我们的特征和标签
features = ["A", "B", "C"]
target_col = "target"

# 成长树
tree = grow_tree(df, features, target_col, max_depth=3)
print(tree)

from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(df.drop('target', axis=1), df['target'], test_size=0.2, random_state=0)

# 训练和评分随机森林
simple_rf_model = RandomForestClassifier(n_estimators=100, random_state=0)
simple_rf_model.fit(X_train, y_train)
print(f"accuracy: {simple_rf_model.score(X_test, y_test)}")

# accuracy: 0.93