ML accuracy quiz.

gistfile1.txt

import sys
from class_vis import prettyPicture
from prep_terrain_data import makeTerrainData

import matplotlib.pyplot as plt
import numpy as np
import pylab as pl

features_train, labels_train, features_test, labels_test = makeTerrainData()



########################## DECISION TREE #################################


### your code goes here--now create 2 decision tree classifiers,
### one with min_samples_split=2 and one with min_samples_split=50
### compute the accuracies on the testing data and store
### the accuracy numbers to acc_min_samples_split_2 and
### acc_min_samples_split_50, respectively

def classify1(features_train, labels_train):
    from sklearn import tree
    X = features_train
    Y = labels_train
    clf1 = tree.DecisionTreeClassifier(min_samples_leaf=2)
    clf1 = clf1.fit(X, Y)
    return clf1
clf1 = classify1(features_train, labels_train)
preds1= clf1.predict(features_test)

from sklearn.metrics import accuracy_score
acc_min_samples_split_2 = accuracy_score(labels_test, preds1)

def classify2(features_train, labels_train):
    from sklearn import tree
    X = features_train
    Y = labels_train
    clf2 = tree.DecisionTreeClassifier(min_samples_split=50)
    clf2 = clf2.fit(X, Y)
    return clf2
clf2 = classify2(features_train, labels_train)
preds2= clf2.predict(features_test)

from sklearn.metrics import accuracy_score
acc_min_samples_split_50 = accuracy_score(labels_test, preds2)





def submitAccuracies():
  return {"acc_min_samples_split_2":round(acc_min_samples_split_2,3),
          "acc_min_samples_split_50":round(acc_min_samples_split_50,3)}