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)
#calculate the average for each value
v_precision = sum(v_precisions)/k
v_recall = sum(v_recalls)/k
v_accuracy = sum(v_accuracys)/k
result_dict["test_precision"] = v_precision
result_dict["test_recall"] = v_recall
result_dict["test_accuracy"] = v_accuracy
t_precision = sum(t_precisions)/k
t_recall = sum(t_recalls)/k
t_accuracy = sum(t_accuracys)/k
result_dict["train_precision"] = t_precision
result_dict["train_recall"] = t_recall
result_dict["train_accuracy"] = t_accuracy
return result_dict
if __name__ == '__main__':
#data = joblib.load("tgmc_stripReal_subset.pkl")
data = mlUtil.extract_data("nursery.csv")
data = mlUtil.enhance_data(data)
print k_fold_eval(data, 5)
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'])
def testSelAttRest(self):
dt = decisionTree.DecisionTree()
rest = mu.extract_data('restaurant.csv')
attrib = dt.selectAttribute(rest['data'], rest['target'])
self.assertEquals(attrib, 4)
def testSelAttTenn(self):
dt = decisionTree.DecisionTree()
tennis = mu.extract_data('tennis.csv')
attrib = dt.selectAttribute(tennis['data'], tennis['target'])
self.assertEquals(attrib, 0)
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'])
def printTree(root, val='Tree', indentNum=0):
""" For printing the decision tree in a nice format
Usage: printTree(rootNode)
"""
indent = "\t" * indentNum
if root.is_leaf():
print indent + "+-" + str(val) + '-- ' + root.value
else:
print indent + "+-" + str(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
data = mlUtil.extract_data("lymphography.csv")
data = mlUtil.enhance_data(data)
tree = DecisionTree(attrib_d=data['feature_dict'],
attribs=data['feature_names'],
default_v="default")
tree.fit(data['data'], data['target'])
printTree(tree.clf)
#test on training data
print data['target']
print tree.predict(data['data'])