Based on example from http://blog.yhathq.com/posts/random-forests-in-python.html, with modifications from https://gist.github.com/glamp/5717321



In [ ]:

    
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
import numpy as np



In [ ]:

    
iris = load_iris()
df = pd.DataFrame(iris.data, columns=iris.feature_names)



In [ ]:

    
df['is_train'] = np.random.uniform(0, 1, len(df)) <= .75



In [ ]:

    
df['species'] = pd.Categorical.from_codes(iris.target, iris.target_names)



In [ ]:

    
df.head()



In [ ]:

    
train, test = df[df['is_train']==True], df[df['is_train']==False]



In [ ]:

    
features = df.columns[:4]
clf = RandomForestClassifier(n_jobs=2)
y, _ = pd.factorize(train['species'])
clf.fit(train[features], y)



In [ ]:

    
preds = iris.target_names[clf.predict(test[features])]
pd.crosstab(test['species'], preds, rownames=['actual'], colnames=['preds'])



In [ ]: