【sklearn学习】随机森林RandomForest

集成算法会考虑多个评估器的建模结果，汇总之后得到一个综合结果，以此来获取比单个模型更好的回归或分类表现。

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error, mean_squared_error
from sklearn.dataset import load_breast_cancer, load_wine
from sklearn.datasets import load_boston
import warnings
warnings.simplefilter("ignore")

 随机森林分类树

class sklearn.ensemble.RandomForestClassifier(n_estimators=100, *, criterion='gini', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, class_weight=None, ccp_alpha=0.0, max_samples=None)2 randomForestClassifier

• n_estimators

随机森林中树木的数量，即基评估器的数量，n_estimators的值越大，模型效果往往越好，当该值达到一定程度后，模型的精确性往往不再上升或开始波动

cancer = load_breast_cancer()
df_data = pd.DataFrame(cancer.data)
df_data.columns = cancer.feature_names
df_target = pd.DataFrame(cancer.target)
df_target.columns = ['LABEL']
df = pd.concat([df_data, df_target], axis=1)
X_train, X_test, y_train, y_test = train_test_split(df_data, df_target, test_size=0.2, random_state=0)

from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
train_score = rfc.score(X_train, y_train['LABEL'])
test_score = rfc.score(X_test, y_test['LABEL'])
print('train_score',train_score)
print('test_score',test_score)
y_pred = rfc.predict(X_test)
acc_score = accuracy_score(y_pred, y_test)
print('acc_score',acc_score)

 

 随机森林回归树

class sklearn.ensemble.RandomForestRegressor(n_estimators=100, *, criterion='squared_error', max_depth=None, min_samples_split=2, min_samples_leaf=1, min_weight_fraction_leaf=0.0, max_features='auto', max_leaf_nodes=None, min_impurity_decrease=0.0, bootstrap=True, oob_score=False, n_jobs=None, random_state=None, verbose=0, warm_start=False, ccp_alpha=0.0, max_samples=None)

通常使用均方误差MSE、绝对平均误差MAE作为评价指标

不纯度指标参数criterion不一致

boston = load_boston()
df_data = pd.DataFrame(boston.data)
df_data.columns = boston.feature_names
df_target = pd.DataFrame(boston.target)
df_target.columns = ['LABEL']
df = pd.concat([df_data, df_target], axis=1)
X_train, X_test, y_train, y_test = train_test_split(df_data, df_target, test_size=0.2, random_state=0)

rfr = RandomForestRegressor()
rfr.fit(X_train, y_train)
train_score = rfr.score(X_train, y_train['LABEL'])
test_score = rfr.score(X_test, y_test['LABEL'])
print('train_score',train_score)
print('test_score',test_score)
y_pred = rfr.predict(X_test)
mae = mean_absolute_error(y_pred, y_test)
mse = mean_squared_error(y_pred, y_test)
print('mae_score',mae)
print('mse_score',mse)

 

 

plt.figure(figsize=(20,5),dpi=80)

x = np.arange(0,50,1)
y = y_test[0:50]
z = y_pred[0:50]
plt.scatter(x, y, s=20, color='blue', label='y_test')
plt.scatter(x, z, s=20, color='red', label='y_pred')

# 添加描述信息
plt.xlabel('index')
plt.ylabel('value')
plt.title('y_test and y_pred')
plt.legend(loc='upper left')
plt.show()