python-随机森林后筛选最重要变量，模型准确率、随机森林混淆矩阵结果、基尼系数排序图

演示数据是花粉数据：列是花粉种类 行是花粉特征

导入必要的库

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
import matplotlib.pyplot as plt

1、模型准确率

# <------------随机森林模型运行结果-------------->
# 读取数据
df = pd.read_csv('C:\\Users\\31425\\Desktop\\新建文件夹\\序列\\蒿属1.csv')

# 分离特征和目标变量
X = df.iloc[:, 1:-1]
y = df.iloc[:, -1]

# 将数据集分为训练集和测试集
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# 创建随机森林模型
rf = RandomForestClassifier(n_estimators=100, random_state=42)

# 在训练集上拟合模型
rf.fit(X_train, y_train)

# 在测试集上进行预测
y_pred = rf.predict(X_test)

# 计算模型准确率
accuracy = accuracy_score(y_test, y_pred)
print("模型准确率:", accuracy)

1.1、对应输出

2.随机森林混淆矩阵结果

# <------------------随机森林混淆矩阵结果----------------------->
# # 读取数据
data = pd.read_csv('C:\\Users\\31425\\Desktop\\新建文件夹\\序列\\蒿属1.csv')
labels = data['species']
data = data.drop('species', axis=1)
# 拆分数据集
train_data, test_data, train_labels, test_labels = train_test_split(data, labels, test_size=0.2, random_state=42)

# 创建随机森林分类器
rfc = RandomForestClassifier(n_estimators=100, random_state=42)

# 训练模型
rfc.fit(train_data, train_labels)

# 进行预测
predictions = rfc.predict(test_data)

# 计算混淆矩阵
cm = confusion_matrix(test_labels, predictions)
print(cm)

2.1矩阵结果

3、随机森林对影响蒺藜科花粉判别的自变量重要性基尼系数排序图

# 《--------------随机森林对影响蒺藜科花粉判别的自变量重要性基尼系数排序图-------------------》

# 读取数据
data = pd.read_csv('C:\\Users\\31425\\Desktop\\新建文件夹\\序列\\蒿属1.csv')
# 将数据集分为自变量和因变量
X = data.drop('species', axis=1)
y = data['species']

# 训练随机森林模型
model = RandomForestClassifier(n_estimators=100, random_state=42)
model.fit(X, y)

# 绘制特征重要性排序图
feature_importances = model.feature_importances_
feature_names = X.columns.values
indices = np.argsort(feature_importances)[::-1]

plt.bar(range(X.shape[1]), feature_importances[indices])
# 在每个柱子上添加文本标签
ontainer = plt.bar(range(X.shape[1]), feature_importances[indices]) 
padding = 0.01 
for rect in  plt.bar(range(X.shape[1]), feature_importances[indices]):
    height = rect.get_height() 
    plt.text(rect.get_x() + rect.get_width() / 2, height + padding, f"{height:.3f}", ha="center", va="bottom") 


plt.xticks(range(X.shape[1]), feature_names[indices], rotation=90)
plt.rcParams['font.family'] = 'sans-serif'
plt.rcParams['font.sans-serif'] = ['SimHei'] # 设置中文字体为黑体
plt.title("随机森林对影响蒺藜科花粉判别的自变量重要性基尼系数排序图")
plt.show()

自变量重要性基尼系数排序图