Machine Learning 简明教程

Machine Learning - Random Forest

随机森林是一种机器学习算法，它使用决策树的集成来进行预测。该算法最初由 Leo Breiman 在 2001 年提出。该算法背后的关键思想是创建大量的决策树，其中每个决策树都在不同的数据子集上进行训练。然后将这些单个树的预测结果结合起来，生成最终预测。

Random Forest is a machine learning algorithm that uses an ensemble of decision trees to make predictions. The algorithm was first introduced by Leo Breiman in 2001. The key idea behind the algorithm is to create a large number of decision trees, each of which is trained on a different subset of the data. The predictions of these individual trees are then combined to produce a final prediction.

Working of Random Forest Algorithm

借助以下步骤，我们可以了解随机森林算法的工作原理：

We can understand the working of Random Forest algorithm with the help of following steps −

  1. Step 1 − First, start with the selection of random samples from a given dataset.

  2. Step 2 − Next, this algorithm will construct a decision tree for every sample. Then it will get the prediction result from every decision tree.

  3. Step 3 − In this step, voting will be performed for every predicted result.

  4. Step 4 − At last, select the most voted prediction result as the final prediction result.

下一张图展示了随机森林算法是怎么工作的 −

The following diagram illustrates how the Random Forest Algorithm works −

random forest algorithm

随机森林是一种灵活性很高的算法，可以同时用于分类和回归任务。在分类任务中，算法使用各个树的预测众数来做出最后的预测。在回归任务中，算法使用各个树的预测均值。

Random Forest is a flexible algorithm that can be used for both classification and regression tasks. In classification tasks, the algorithm uses the mode of the predictions of the individual trees to make the final prediction. In regression tasks, the algorithm uses the mean of the predictions of the individual trees.

Advantages of Random Forest Algorithm

随机森林算法比其他机器学习算法有很多优势。一些主要优势如下 −

Random Forest algorithm has several advantages over other machine learning algorithms. Some of the key advantages are −

  1. Robustness to Overfitting − Random Forest algorithm is known for its robustness to overfitting. This is because the algorithm uses an ensemble of decision trees, which helps to reduce the impact of outliers and noise in the data.

  2. High Accuracy − Random Forest algorithm is known for its high accuracy. This is because the algorithm combines the predictions of multiple decision trees, which helps to reduce the impact of individual decision trees that may be biased or inaccurate.

  3. Handles Missing Data − Random Forest algorithm can handle missing data without the need for imputation. This is because the algorithm only considers the features that are available for each data point and does not require all features to be present for all data points.

  4. Non-Linear Relationships − Random Forest algorithm can handle non-linear relationships between the features and the target variable. This is because the algorithm uses decision trees, which can model non-linear relationships.

  5. Feature Importance − Random Forest algorithm can provide information about the importance of each feature in the model. This information can be used to identify the most important features in the data and can be used for feature selection and feature engineering.

Implementation of Random Forest Algorithm in Python

让我们看一下 Python 中随机森林算法的实现。我们将使用 scikit-learn 库实现该算法。scikit-learn 库是一个流行的机器学习库，它提供各种机器学习算法和工具。

Let’s take a look at the implementation of Random Forest Algorithm in Python. We will be using the scikit-learn library to implement the algorithm. The scikit-learn library is a popular machine learning library that provides a wide range of algorithms and tools for machine learning.

Step 1 − Importing the Libraries

我们将从导入必要的库开始。我们将使用 pandas 库进行数据处理，并使用 scikit-learn 库实现随机森林算法。

We will begin by importing the necessary libraries. We will be using the pandas library for data manipulation, and the scikit-learn library for implementing the Random Forest algorithm.

import pandas as pd
from sklearn.ensemble import RandomForestClassifier

Step 2 − Loading the Data

接下来，我们将数据加载到 pandas 数据框中。对于本教程，我们将使用著名的 Iris 数据集，这是一个用于分类任务的经典数据集。

Next, we will load the data into a pandas dataframe. For this tutorial, we will be using the famous Iris dataset, which is a classic dataset for classification tasks.

# Loading the iris dataset

iris = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learningdatabases/iris/iris.data', header=None)

iris.columns = ['sepal_length', 'sepal_width', 'petal_length','petal_width', 'species']

Step 3 − Data Preprocessing

在我们使用数据训练模型之前，我们需要对其进行预处理。这涉及分离特征和目标变量，然后将数据拆分为训练集和测试集。

Before we can use the data to train our model, we need to preprocess it. This involves separating the features and the target variable and splitting the data into training and testing sets.

# Separating the features and target variable
X = iris.iloc[:, :-1]
y = iris.iloc[:, -1]

# Splitting the data into training and testing sets
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.35, random_state=42)

Step 4 − Training the Model

接下来，我们将根据训练数据训练我们的随机森林分类器。

Next, we will train our Random Forest classifier on the training data.

# Creating the Random Forest classifier object
rfc = RandomForestClassifier(n_estimators=100)

# Training the model on the training data
rfc.fit(X_train, y_train)

Step 5 − Making Predictions

一旦我们训练好模型，就可以使用它对测试数据进行预测。

Once we have trained our model, we can use it to make predictions on the test data.

# Making predictions on the test data
y_pred = rfc.predict(X_test)

Step 6 − Evaluating the Model

最后，我们将使用各种指标（例如准确度、精确率、召回率和 F1 值）对模型的性能进行评估。

Finally, we will evaluate the performance of our model using various metrics such as accuracy, precision, recall, and F1-score.

# Importing the metrics library
from sklearn.metrics import accuracy_score, precision_score,
recall_score, f1_score

# Calculating the accuracy, precision, recall, and F1-score
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')

print("Accuracy:", accuracy)
print("Precision:", precision)
print("Recall:", recall)
print("F1-score:", f1)

Complete Implementation Example

以下是在 python 中使用 iris 数据集的随机森林算法的完整实现示例 −

Below is the complete implementation example of Random Forest Algorithm in python using the iris dataset −

import pandas as pd
from sklearn.ensemble import RandomForestClassifier

# Loading the iris dataset
iris = pd.read_csv('https://archive.ics.uci.edu/ml/machine-learningdatabases/iris/iris.data', header=None)

iris.columns = ['sepal_length', 'sepal_width', 'petal_length', 'petal_width', 'species']

# Separating the features and target variable
X = iris.iloc[:, :-1]
y = iris.iloc[:, -1]

# Splitting the data into training and testing sets
from sklearn.model_selection import train_test_split

X_train, X_test, y_train, y_test = train_test_split(X, y,
test_size=0.35, random_state=42)

# Creating the Random Forest classifier object
rfc = RandomForestClassifier(n_estimators=100)

# Training the model on the training data
rfc.fit(X_train, y_train)
# Making predictions on the test data
y_pred = rfc.predict(X_test)
# Importing the metrics library
from sklearn.metrics import accuracy_score, precision_score,
recall_score, f1_score

# Calculating the accuracy, precision, recall, and F1-score
accuracy = accuracy_score(y_test, y_pred)
precision = precision_score(y_test, y_pred, average='weighted')
recall = recall_score(y_test, y_pred, average='weighted')
f1 = f1_score(y_test, y_pred, average='weighted')

print("Accuracy:", accuracy)
print("Precision:", precision)
print("Recall:", recall)
print("F1-score:", f1)

这将为我们提供随机森林分类器的以下性能指标 −

This will give us the performance metrics of our Random Forest classifier as follows −

Accuracy: 0.9811320754716981
Precision: 0.9821802935010483
Recall: 0.9811320754716981
F1-score: 0.9811157396063056