def testTennis(self):
"""
Test entire program on the tennis data set
"""
tennis = mu.extract_data('tennis.csv')
tennis = mu.enhance_data(tennis)
dt = decisionTree.DecisionTree(tennis['feature_dict'], tennis['feature_names'])
dt.fit(tennis['data'],tennis['target'])
for x,y in zip(tennis['data'],tennis['target']):
self.assertEquals(dt.predict([x]), [y])
self.assertEquals(dt.predict(tennis['data']), tennis['target'])
if __name__ == '__main__':
#parse the command line arguments
parser = argparse.ArgumentParser()
parser.add_argument("train_file",
help="Name of file with training data",
type=str)
parser.add_argument("-k", help="number of folds", type=int, default=5)
parser.add_argument(
"--ibm",
help="Flag to indicate that input is IBM data, else plain CSV",
action="store_true")
parser.add_argument("--y_col",
help="name of column containing target",
type=str)
args = parser.parse_args()
#for you to add is logic for handling the --y_col flag if given (for tennis, for example)
if args.ibm:
data = joblib.load(args.train_file)
else:
if not args.y_col:
data = mlUtil.extract_data(args.train_file)
else:
data = mlUtil.extract_data(fileName=args.train_file,
targetInfo=args.y_col)
data = mlUtil.enhance_data(data)
print k_fold_eval(data, args.k)
print indent+"+-"+val+'-- <'+root.attribute+'>'
print indent+"{"
for k in root.children.keys():
printTree(root.children[k],k,indentNum+1)
print indent+"}"
if __name__ == '__main__':
#parse the command line arguments
parser = argparse.ArgumentParser()
parser.add_argument("train_file", help="Name of file with training data", type=str)
parser.add_argument("--y_col", help="name of column containing target", type=str)
parser.add_argument("--ibm", help="Flag to indicate that input is IBM data, else plain CSV", action="store_true")
args = parser.parse_args()
#for you to add is logic for handling the --y_col flag if given (for tennis, for example)
if args.ibm:
data = joblib.load(args.train_file)
else:
data = mlUtil.extract_data(args.train_file)
data = mlUtil.enhance_data(data)
#will need some args in constructor
tree = DecisionTree('***YOU ADD ARGUMENTS HERE***')
tree.fit(data['data'], data['target'])
#pritnTree(tree.clf)
#test on training data
tree.predict(data['data'])