def train(self, data, labels):
self.data = data
self.labels = labels
for i in range(self.num_trees):
sample_index = np.random.choice(self.data.shape[0],
self.num_sample,
replace=True)
train_data = self.data[sample_index, :]
train_labels = self.labels[sample_index]
tree = DecisionTree(self.max_depth, self.num_feature)
tree.train(train_data, train_labels)
self.trees.append(tree)
def test_all_file(self):
options = {
'df': pd.read_csv("benchmark.csv", sep=';'),
'label_column': "Joga"
}
tr = DecisionTree()
model = tr.train(options)
for _, row in options['df'].iterrows():
target_label = row["Joga"]
predicted = model.predict(row.drop("Joga"))
self.assertEqual(target_label, predicted)
def test_benchmark(self):
options = {
'df': pd.read_csv("benchmark.csv", sep=';'),
'label_column': "Joga"
}
tr = DecisionTree()
model = tr.train(options)
inf_data = pd.Series(
["Ensolarado", "Quente", "Normal", "Verdadeiro"],
index=["Tempo", "Temperatura", "Umidade", "Ventoso"],
name="InferenceData")
self.assertEqual(model.predict(inf_data), 'Sim')
def train(self, options):
"""
train a random forest, using n_trees decision trees
options['df']: pandas dataframe
options['n_trees']: number of trees
options['label_column']: label column to be predicted
options['bootstrap_size']: the size of the bootstrap, entries not used in the bootstrap will be ignored
"""
num_trees = options['n_trees']
df = options['df']
bootstrap_size = options['bootstrap_size']
tree_options = {
'label_column': options['label_column']
}
for i in range(num_trees):
tree_options['df'] = get_bootstrap(df, bootstrap_size)
new_tree = DecisionTree()
self.ensemble.append(new_tree.train(tree_options))
return self
cat_data_test = np.array(cat_data_test, dtype='float')
# zip categorical and non-categorical data together
train_data = np.concatenate((cat_data, non_cat_data), axis=1)
train_label = data[:, -1].astype(int)
validation_data = train_data[:200, :]
validation_label = train_label[:200]
train_data = train_data[:, :]
train_label = train_label[:]
test_data = np.concatenate((cat_data_test, non_cat_data_test), axis=1)
# decision tree
tree = DecisionTree(5, train_data.shape[0])
tree.train(train_data, train_label)
res = tree.predict(validation_data)
score = 0
for i in range(len(res)):
if res[i] == validation_label[i]:
score += 1
score /= len(res)
print(score)
# random forest
forest = RandomForest(100,5,train_data.shape[0],6)
forest.train(train_data, train_label)
res = forest.predict(validation_data)