def test_ratio(self):
df_iris = load_iris()
res = split_data(table=df_iris,
train_ratio=1.0,
test_ratio=1.0,
random_state=12345,
shuffle=True,
stratify=None)
df_train = res['train_table']
df_test = res['test_table']
self.assertEqual(75, len(df_train), 'wrong size of train table')
self.assertEqual(75, len(df_test), 'wrong size of test table')
self.assertListEqual([5.0, 3.4, 1.6, 0.4, 'setosa'],
df_train.loc[0].tolist(),
'incorrect train data in the 1st row')
self.assertListEqual([7.1, 3.0, 5.9, 2.1, 'virginica'],
df_train.loc[1].tolist(),
'incorrect train data in the 2nd row')
self.assertListEqual([6.7, 3.1, 4.7, 1.5, 'versicolor'],
df_train.loc[2].tolist(),
'incorrect train data in the 3rd row')
self.assertListEqual([5.6, 2.5, 3.9, 1.1, 'versicolor'],
df_test.loc[0].tolist(),
'incorrect train data in the 1st row')
self.assertListEqual([4.4, 3.2, 1.3, 0.2, 'setosa'],
df_test.loc[1].tolist(),
'incorrect train data in the 2nd row')
self.assertListEqual([6.3, 3.3, 4.7, 1.6, 'versicolor'],
df_test.loc[2].tolist(),
'incorrect train data in the 3rd row')
def test_predict_thresholds(self):
iris = load_iris()
df_splitted = split_data(table=iris, train_ratio=0.7, test_ratio=0.3)
train_df = df_splitted['train_table']
test_df = df_splitted['test_table']
train_out = svm_classification_train(table=train_df, feature_cols=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'], label_col='species')
predict_out = svm_classification_predict(table=test_df, model=train_out['model'], thresholds=[0.1, 0.2, 0.3])
def test1(self):
iris = load_iris()
df_splitted = split_data(table=iris, train_ratio=0.7, test_ratio=0.3)
train_df = df_splitted['train_table']
test_df = df_splitted['test_table']
train_out = svm_classification_train(table=train_df, feature_cols=['sepal_length', 'sepal_width', 'petal_length', 'petal_width'], label_col='species')
# print(train_out['model']['svc_model'])
predict_out = svm_classification_predict(table=test_df, model=train_out['model'])
print(predict_out['out_table'][['species', 'prediction']])
def predict_thresholds(self):
iris = get_iris()
df_splitted = split_data(iris, 0.7, 0.3)
train_df = df_splitted['train_table']
test_df = df_splitted['test_table']
train_out = svm_classification_train(train_df,
feature_cols=[
'sepal_length', 'sepal_width',
'petal_length', 'petal_width'
],
label_col='species')
# print(train_out['model']['svc_model'])
predict_out = svm_classification_predict(test_df,
train_out['model'],
thresholds=[0.1, 0.2, 0.3])
print(predict_out['out_table'][['species', 'prediction']])