随机森林相关API:
import sklearn.ensemble as se
# 随机森林回归模型 (属于集合算法的一种)
# max_depth:决策树最大深度10
# n_estimators:构建1000棵决策树,训练模型
# min_samples_split: 子表中最小样本数 若小于这个数字,则不再继续向下拆分
model = se.RandomForestRegressor(max_depth=10, n_estimators=1000, min_samples_split=2)
案例:分析共享单车的需求,从而判断如何进行共享单车的投放。
共享单车部分数据如下
倒数第二和第三列分别是游客和注册用户的使用量,最后一列是游客+注册用户的使用量,我直接预测的是最后一列的数据
import numpy as np
import sklearn.utils as su
import sklearn.ensemble as se
import sklearn.metrics as sm
import matplotlib.pyplot as mp
data = np.loadtxt('../data/bike_day.csv', unpack=False, dtype='U20', delimiter=',')
day_headers = data[0, 2:13]
x = np.array(data[1:, 2:13], dtype=float)
y = np.array(data[1:, -1], dtype=float)
x, y = su.shuffle(x, y, random_state=7)
print(x.shape, y.shape)
#(731, 11) (731,)
train_size = int(len(x) * 0.9)
train_x, test_x, train_y, test_y = \
x[:train_size], x[train_size:], y[:train_size], y[train_size:]
# 随机森林回归器
model = se.RandomForestRegressor( max_depth=10, n_estimators=1000, min_samples_split=2)
model.fit(train_x, train_y)
# 基于“天”数据集的特征重要性
fi_dy = model.feature_importances_
pred_test_y = model.predict(test_x)
print(sm.r2_score(test_y, pred_test_y))
##0.892898964206058
data = np.loadtxt('../data/bike_hour.csv', unpack=False, dtype='U20', delimiter=',')
hour_headers = data[0, 2:13]
x = np.array(data[1:, 2:13], dtype=float)
y = np.array(data[1:, -1], dtype=float)
x, y = su.shuffle(x, y, random_state=7)
train_size = int(len(x) * 0.9)
train_x, test_x, train_y, test_y = \
x[:train_size], x[train_size:], \
y[:train_size], y[train_size:]
# 随机森林回归器
model = se.RandomForestRegressor(
max_depth=10, n_estimators=1000,
min_samples_split=2)
model.fit(train_x, train_y)
# 基于“小时”数据集的特征重要性
fi_hr = model.feature_importances_
pred_test_y = model.predict(test_x)
print(sm.r2_score(test_y, pred_test_y))
#0.91879221816765
画图显示两组样本数据的特征重要性:
mp.figure('Bike', facecolor='lightgray')
mp.subplot(211)
mp.title('Day', fontsize=16)
mp.ylabel('Importance', fontsize=12)
mp.tick_params(labelsize=10)
mp.grid(axis='y', linestyle=':')
sorted_indices = fi_dy.argsort()[::-1]
pos = np.arange(sorted_indices.size)
mp.bar(pos, fi_dy[sorted_indices], facecolor='deepskyblue', edgecolor='steelblue')
mp.xticks(pos, day_headers[sorted_indices], rotation=30)
mp.subplot(212)
mp.title('Hour', fontsize=16)
mp.ylabel('Importance', fontsize=12)
mp.tick_params(labelsize=10)
mp.grid(axis='y', linestyle=':')
sorted_indices = fi_hr.argsort()[::-1]
pos = np.arange(sorted_indices.size)
mp.bar(pos, fi_hr[sorted_indices], facecolor='lightcoral', edgecolor='indianred')
mp.xticks(pos, hour_headers[sorted_indices], rotation=30)
mp.tight_layout()
mp.show()