#In the next recipe, we'll look at how to tune the random forest classifier.

#Let's start by importing datasets:

from sklearn import datasets

X, y = datasets.make_classification(1000)

# X(1000,20)

#y(1000) 取值范围【0,1】

from sklearn.ensemble import RandomForestClassifier

rf = RandomForestClassifier()

rf.n_jobs=-1

rf.fit(X, y)

print ("Accuracy:\t", (y == rf.predict(X)).mean())

print ("Total Correct:\t", (y == rf.predict(X)).sum())

#每个例子属于哪个类的概率

probs = rf.predict_proba(X)

import pandas as pd

probs_df = pd.DataFrame(probs, columns=['', ''])

probs_df['was_correct'] = rf.predict(X) == y

import matplotlib.pyplot as plt

f, ax = plt.subplots(figsize=(7, 5))

probs_df.groupby('').was_correct.mean().plot(kind='bar', ax=ax)

ax.set_title("Accuracy at 0 class probability")

ax.set_ylabel("% Correct")

ax.set_xlabel("% trees for 0")

f.show()

#检测重要特征

rf = RandomForestClassifier()

rf.fit(X, y)

f, ax = plt.subplots(figsize=(7, 5))

ax.bar(range(len(rf.feature_importances_)),rf.feature_importances_)

ax.set_title("Feature Importances")

f.show()