jevans96_2.py

"""
John Evans
PHYS476
Homework 2
Problem 2
3/10/2018
"""
import sys
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier
from sklearn.naive_bayes import GaussianNB
import pandas as pd
import numpy as np

#fix random seed
seed = 7
np.random.seed(seed)

#import data
header_names = ['age', 'sex', 'cp', 'trestbps', 'chol', 'fbs', 'restecg', 'thalach', 'exang', 'oldpeak', 'slope', 'ca', 'thal', 'num']
data = pd.read_csv(sys.argv[1], header = None, names = header_names)

#munge data
del data['slope']
del data['ca']
del data['thal']
data = data.replace('?', float('NaN'))
data = data.dropna()

#build training and testing sets
train = data.sample(frac = 9/10, axis = 0)
test  = data.drop(train.index)

#split sets into inputs and outputs
output_cols = ['num']
del data

def split_sample(sample, cols):
    outputs = sample[cols].values
    for x in cols:
        del sample[x]
    inputs = sample.values
    return inputs, outputs.T[0], len(sample.columns), len(cols)

train_in, train_out, *_  = split_sample(train, output_cols)
test_in, test_out, *dims = split_sample(test, output_cols)
del train
del test

#build models
classifiers = [DecisionTreeClassifier(criterion='gini', splitter='best', max_depth=20,
                                      min_samples_split=2, min_samples_leaf=1,
                                      min_weight_fraction_leaf=0.0, max_features=4,
                                      random_state=None, max_leaf_nodes=None,
                                      class_weight=None, presort=False),
               RandomForestClassifier(n_estimators=10, criterion='gini', max_depth=50,
                                      min_samples_split=2, min_samples_leaf=1,
                                      min_weight_fraction_leaf=0.0, max_features=1,
                                      max_leaf_nodes=None, bootstrap=True, oob_score=False,
                                      n_jobs=1, random_state=None, verbose=0, warm_start=False,
                                      class_weight=None),
               GaussianNB(priors=None)]

#train and test models, print results
for x in classifiers:
    x.fit(train_in, train_out)
    print(x.score(test_in, test_out))