91 lines
2.9 KiB
Plaintext
91 lines
2.9 KiB
Plaintext
# 随机森林Random Forests
|
|
<p align="center">
|
|
<img src="https://github.com/MachineLearning100/100-Days-Of-ML-Code/blob/master/Info-graphs/Day%2033.png">
|
|
</p>
|
|
|
|
### 导入库
|
|
```python
|
|
import numpy as np
|
|
import matplotlib.pyplot as plt
|
|
import pandas as pd
|
|
```
|
|
|
|
### 导入数据集
|
|
```python
|
|
dataset = pd.read_csv('Social_Network_Ads.csv')
|
|
X = dataset.iloc[:, [2, 3]].values
|
|
y = dataset.iloc[:, 4].values
|
|
```
|
|
|
|
### 将数据集拆分成训练集和测试集
|
|
```python
|
|
from sklearn.cross_validation import train_test_split
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = 0.25, random_state = 0)
|
|
```
|
|
|
|
### 特征缩放
|
|
```python
|
|
from sklearn.preprocessing import StandardScaler
|
|
sc = StandardScaler()
|
|
X_train = sc.fit_transform(X_train)
|
|
X_test = sc.transform(X_test)
|
|
```
|
|
|
|
### 调试训练集的随机森林
|
|
```python
|
|
from sklearn.ensemble import RandomForestClassifier
|
|
classifier = RandomForestClassifier(n_estimators = 10, criterion = 'entropy', random_state = 0)
|
|
classifier.fit(X_train, y_train)
|
|
```
|
|
|
|
### 预测测试集结果
|
|
```python
|
|
y_pred = classifier.predict(X_test)
|
|
```
|
|
|
|
### 生成混淆矩阵，也称作误差矩阵
|
|
```python
|
|
from sklearn.metrics import confusion_matrix
|
|
cm = confusion_matrix(y_test, y_pred)
|
|
```
|
|
|
|
### 将训练集结果可视化
|
|
```python
|
|
from matplotlib.colors import ListedColormap
|
|
X_set, y_set = X_train, y_train
|
|
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
|
|
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
|
|
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
|
|
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
|
|
plt.xlim(X1.min(), X1.max())
|
|
plt.ylim(X2.min(), X2.max())
|
|
for i, j in enumerate(np.unique(y_set)):
|
|
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
|
|
c = ListedColormap(('red', 'green'))(i), label = j)
|
|
plt.title('Random Forest Classification (Training set)')
|
|
plt.xlabel('Age')
|
|
plt.ylabel('Estimated Salary')
|
|
plt.legend()
|
|
plt.show()
|
|
```
|
|
|
|
### 将数据集结果可视化
|
|
```python
|
|
from matplotlib.colors import ListedColormap
|
|
X_set, y_set = X_test, y_test
|
|
X1, X2 = np.meshgrid(np.arange(start = X_set[:, 0].min() - 1, stop = X_set[:, 0].max() + 1, step = 0.01),
|
|
np.arange(start = X_set[:, 1].min() - 1, stop = X_set[:, 1].max() + 1, step = 0.01))
|
|
plt.contourf(X1, X2, classifier.predict(np.array([X1.ravel(), X2.ravel()]).T).reshape(X1.shape),
|
|
alpha = 0.75, cmap = ListedColormap(('red', 'green')))
|
|
plt.xlim(X1.min(), X1.max())
|
|
plt.ylim(X2.min(), X2.max())
|
|
for i, j in enumerate(np.unique(y_set)):
|
|
plt.scatter(X_set[y_set == j, 0], X_set[y_set == j, 1],
|
|
c = ListedColormap(('red', 'green'))(i), label = j)
|
|
plt.title('Random Forest Classification (Test set)')
|
|
plt.xlabel('Age')
|
|
plt.ylabel('Estimated Salary')
|
|
plt.legend()
|
|
plt.show()
|
|
```
|