def test_most_common_int(self):
data = pd.Series([1, 1, 2, 4, 2, 5])
data = pd.DataFrame(data, columns=['col1'])
df = Data(data, test_split_percentage=0.5)
df.most_common('col1', plot=True, use_test=True)
self.assertTrue(True)
def test_most_common_list(self):
data = pd.Series([['hi', 'aethos'], ['hi', 'py-automl'], [], ['hi']])
data = pd.DataFrame(data, columns=['col1'])
df = Data(data, split=False)
df.most_common('col1', plot=True)
self.assertTrue(True)
def test_compare_dist_predict(self):
data = np.random.randint(0, 2, size=(1000, 3))
data = pd.DataFrame(data=data, columns=["col1", "col2", "col3"])
df = Data(data, target_field="col3", report_name="test")
df.predict_data_sample()
self.assertTrue(True)
def test_plot_clusters_pca(self):
data, label = make_blobs(100, 4, centers=3)
df = pd.DataFrame(data)
df['label'] = label
df = Data(df, split=False)
df.plot_dim_reduction('label', algo='pca', dim=2)
self.assertTrue(True)
def test_compare_dist_ks(self):
data = np.random.randint(0, 2, size=(1000, 3))
data = pd.DataFrame(data=data, columns=["col1", "col2", "col3"])
df = Data(data, target_field="col3", report_name="test")
df["col4"] = np.random.normal(1, 2, size=(1, 800))[0]
df["col4"] = np.random.normal(10, 20, size=(1, 200))[0]
df.ks_feature_distribution()
self.assertTrue(True)
def test_most_common_str(self):
data = pd.Series([
'hi aethos', 'aethos is awesome', 'hi',
'py-automl is the old name', 'hi everyone'
])
data = pd.DataFrame(data, columns=['col1'])
df = Data(data, split=False)
df.most_common('col1')
self.assertTrue(True)
def test_lineplot(self):
np.random.seed(42)
df = pd.DataFrame(
{
"Google": np.random.randn(1000) + 0.2,
"Apple": np.random.randn(1000) + 0.17,
"date": pd.date_range("1/1/2000", periods=1000),
}
)
clean = Data(x_train=df, split=False)
clean.lineplot(x="date", y=["Google", "Apple"], show_figure=False)
self.assertTrue(True)
def test_jointplot(self):
data = sns.load_dataset("iris")
base = Data(
x_train=data,
x_test=None,
split=True,
target_field="species",
report_name="test",
test_split_percentage=0.5,
)
base.jointplot(x="sepal_width", y="sepal_length")
self.assertTrue(True)
def test_pairplot_custom(self):
data = sns.load_dataset("iris")
base = Data(
x_train=data,
x_test=None,
split=True,
target_field="species",
report_name="test",
test_split_percentage=0.5,
)
base.pairplot(diag_kind='hist', upper_kind='scatter', lower_kind='kde')
self.assertTrue(True)
def test_pairplot(self):
data = sns.load_dataset("iris")
base = Data(
x_train=data,
x_test=None,
split=True,
target_field="species",
report_name="test",
test_split_percentage=0.5,
)
base.pairplot()
self.assertTrue(True)
def test_histogram_1(self):
data = sns.load_dataset("iris")
base = Data(
x_train=data,
x_test=None,
split=True,
target_field="species",
report_name="test",
test_split_percentage=0.5,
)
base.histogram("sepal_length")
self.assertTrue(True)
def test_correlation_plot(self):
data = pd.DataFrame(np.random.rand(100, 10))
base = Data(
x_train=data,
x_test=None,
split=True,
target_field="col3",
report_name="test",
test_split_percentage=0.5,
)
base.correlation_matrix(data_labels=True, hide_mirror=True)
self.assertTrue(True)
def test_barplot(self):
data = sns.load_dataset("iris")
base = Data(
x_train=data,
x_test=None,
split=True,
target_field="species",
report_name="test",
test_split_percentage=0.5,
)
base.barplot(
x="species", y=["sepal_length", "sepal_width"], method="mean", orient="h", barmode="group",
)
base.barplot(
x="species", y=["sepal_length", "sepal_width"], method="mean", orient="v", barmode="group",
)
self.assertTrue(True)