diff --git a/docs/source/examples/classification_example.rst b/docs/source/examples/classification_example.rst index 2723c7e91f..1d420ecf60 100644 --- a/docs/source/examples/classification_example.rst +++ b/docs/source/examples/classification_example.rst @@ -15,11 +15,10 @@ Fedot uses it's own data object notation (InputData). It contains index, features and target for each sample. You can create it from file using ``InputData.from_dataframe()`` method. You need to provide ``Task`` object with type of task you want to solve. You also can find another ways of data passing in `this example `. -.. code-block:: python +.. code-block:: python from fedot.core.data.data import InputData - data_path = 'path_to_data' data = InputData.from_dataframe(features_df, target_df, @@ -32,6 +31,7 @@ You also can find another ways of data passing in `this example `. * TaskTypesEnum.classification * TaskTypesEnum.regression * TaskTypesEnum.ts_forecasting + Initialize the FEDOT object and define the type of modeling problem. In this case, problem is ``classification``. You also can define metric parameter (ROC-AUC in this example), timeout in minutes (in this example we limit fedot for 5 minutes). diff --git a/docs/source/examples/regression_example.rst b/docs/source/examples/regression_example.rst index 3afb7a1548..afd5e212cb 100644 --- a/docs/source/examples/regression_example.rst +++ b/docs/source/examples/regression_example.rst @@ -10,16 +10,16 @@ to import certain object: .. code-block:: python from fedot import Fedot + Then we have to load data and split it on train and test set. Fedot uses it's own data object notation (InputData). It contains index, features and target for each sample. You can create it from file using ``InputData.from_dataframe()`` method. You need to provide ``Task`` object with type of task you want to solve. You also can find another ways of data passing in `this example `. -.. code-block:: python +.. code-block:: python from fedot.core.data.data import InputData - data_path = 'path_to_data' data = InputData.from_dataframe(features_df, target_df,