﻿ 使用Python的随机森林特征重要性图表 - 代码日志

#### 使用Python的随机森林特征重要性图表

``````from sklearn.ensemble import RandomForestRegressor

df = MT.reset_index(drop = False)

columns2 = df.columns.tolist()

# Filter the columns to remove ones we don't want.
columns2 = [c for c in columns2 if c not in["Violent_crime_rate","Change_Property_crime_rate","State","Year"]]

# Store the variable we'll be predicting on.
target = "Property_crime_rate"

# Let’s randomly split our data with 80% as the train set and 20% as the test set:

# Generate the training set.  Set random_state to be able to replicate results.
train2 = df.sample(frac=0.8, random_state=1)

#exclude all obs with matching index
test2 = df.loc[~df.index.isin(train2.index)]

print(train2.shape) #need to have same number of features only difference should be obs
print(test2.shape)

# Initialize the model with some parameters.

model = RandomForestRegressor(n_estimators=100, min_samples_leaf=8, random_state=1)

#n_estimators= number of trees in forrest
#min_samples_leaf= min number of samples at each leaf

# Fit the model to the data.
model.fit(train2[columns2], train2[target])
# Make predictions.
predictions_rf = model.predict(test2[columns2])
# Compute the error.
mean_squared_error(predictions_rf, test2[target])#650.4928
``````

``````features=df.columns[[3,4,6,8,9,10]]
importances = model.feature_importances_
indices = np.argsort(importances)

plt.figure(1)
plt.title('Feature Importances')
plt.barh(range(len(indices)), importances[indices], color='b', align='center')
plt.yticks(range(len(indices)), features[indices])
plt.xlabel('Relative Importance')
``````

``````  IndexError: index 6 is out of bounds for axis 1 with size 6
``````

``````>>> from sklearn.datasets import load_iris
>>> rnd_clf = RandomForestClassifier(n_estimators=500, n_jobs=-1, random_state=42)
>>> rnd_clf.fit(iris["data"], iris["target"])
>>> for name, importance in zip(iris["feature_names"], rnd_clf.feature_importances_):
...     print(name, "=", importance)

sepal length (cm) = 0.112492250999
sepal width (cm) = 0.0231192882825
petal length (cm) = 0.441030464364
petal width (cm) = 0.423357996355
``````

``````>>> features = iris['feature_names']
>>> importances = rnd_clf.feature_importances_
>>> indices = np.argsort(importances)

>>> plt.title('Feature Importances')
>>> plt.barh(range(len(indices)), importances[indices], color='b', align='center')
>>> plt.yticks(range(len(indices)), [features[i] for i in indices])
>>> plt.xlabel('Relative Importance')
>>> plt.show()
``````