def test_generate_fig_univariate_3(self, mock_plot_cat, mock_plot_cont):
df = pd.DataFrame({
"int_cat_data": [10, 10, 20, 20, 20, 10],
"data_train_test":
['train', 'train', 'train', 'train', 'test', 'test']
})
generate_fig_univariate(df,
'int_cat_data',
'data_train_test',
type=VarType.TYPE_CAT)
mock_plot_cat.assert_called_once()
self.assertEqual(mock_plot_cont.call_count, 0)
def test_generate_fig_univariate_1(self, mock_plot_cat, mock_plot_cont):
df = pd.DataFrame({
"string_data": ["a", "b", "c", "d", "e", np.nan],
"data_train_test":
['train', 'train', 'train', 'train', 'test', 'test']
})
generate_fig_univariate(df,
'string_data',
'data_train_test',
type=VarType.TYPE_CAT)
mock_plot_cat.assert_called_once()
self.assertEqual(mock_plot_cont.call_count, 0)
def test_generate_fig_univariate_2(self, mock_plot_cat, mock_plot_cont):
df = pd.DataFrame({
"int_data":
list(range(50)),
"data_train_test":
['train', 'train', 'train', 'train', 'test'] * 10
})
generate_fig_univariate(df,
'int_data',
'data_train_test',
type=VarType.TYPE_NUM)
mock_plot_cont.assert_called_once()
self.assertEqual(mock_plot_cat.call_count, 0)
def _perform_and_display_analysis_univariate(self, df: pd.DataFrame,
col_splitter: str,
split_values: list,
names: list, group_id: str):
col_types = compute_col_types(df)
n_splits = df[col_splitter].nunique()
test_stats_univariate = perform_univariate_dataframe_analysis(
df.loc[df[col_splitter] == split_values[0]], col_types=col_types)
if n_splits > 1:
train_stats_univariate = perform_univariate_dataframe_analysis(
df.loc[df[col_splitter] == split_values[1]],
col_types=col_types)
univariate_template = template_env.get_template("univariate.html")
univariate_features_desc = list()
list_cols_labels = [
self.explainer.features_dict.get(col, col)
for col in df.drop(col_splitter, axis=1).columns.to_list()
]
for col_label in sorted(list_cols_labels):
col = self.explainer.inv_features_dict.get(col_label, col_label)
fig = generate_fig_univariate(df_all=df,
col=col,
hue=col_splitter,
type=col_types[col])
df_col_stats = self._stats_to_table(
test_stats=test_stats_univariate[col],
train_stats=train_stats_univariate[col]
if n_splits > 1 else None,
names=names)
univariate_features_desc.append({
'feature_index':
int(self.explainer.inv_columns_dict.get(col, 0)),
'name':
col,
'type':
str(series_dtype(df[col])),
'description':
col_label,
'table':
df_col_stats.to_html(classes="greyGridTable"),
'image':
convert_fig_to_html(fig)
})
print_html(
univariate_template.render(features=univariate_features_desc,
groupId=group_id))