sklearn random forest template

sklearn_randomforest_snip.py

%matplotlib inline

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.cross_validation import train_test_split
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.metrics import recall_score
from sklearn.metrics import precision_score

##  set train and target here

X_train, X_test, y_train, y_test = train_test_split(train, target, test_size=0.33, random_state=83)
rf = RandomForestClassifier(n_estimators=100,n_jobs=3)
rf.fit(X_train, y_train)

imp = zip(col_names[1:],rf.feature_importances_)
sorted(imp, key=lambda x: -x[1])

y_pred = rf.predict(X_test)
accuracy_score(y_test, y_pred)

test_pred_proba = rf.predict_proba(X_test)