Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

if column.model not provided in visual app then set default model name #235

Open
wants to merge 3 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,11 @@ All notable changes to this project will be documented in this file.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [Unreleased]

### Added
- If `Column.Model` is not provided in `VisualApp`, then default model name added to dataframe ([#235](https://github.com/MobileTeleSystems/RecTools/pull/235))
- Changed tests for `VisualApp` missing columns

## [0.9.0] - 11.12.2024

Expand Down
6 changes: 4 additions & 2 deletions rectools/visuals/visual_app.py
Original file line number Diff line number Diff line change
Expand Up @@ -29,6 +29,7 @@
MIN_WIDTH_LIMIT = 10
REQUEST_NAMES_COL = "request_name"
REQUEST_IDS_COL = "request_id"
DEFAULT_MODEL_NAME = "model1"

VisualAppT = tp.TypeVar("VisualAppT", bound="VisualAppBase")

Expand Down Expand Up @@ -71,7 +72,8 @@ def from_raw(
----------
reco : tp.Union[pd.DataFrame, TablesDict]
Recommendations from different models in a form of a pd.DataFrame or a dict.
In DataFrame form model names must be specified in `Columns.Model` column. In dict form
In DataFrame form model names must be specified in `Columns.Model` column.
If not, `Columns.Model` column will be created with default value ``model1``. In dict form
model names are supposed to be dict keys.
item_data : pd.DataFrame
Data for items that is used for visualisation in both interactions and recommendations
Expand Down Expand Up @@ -100,7 +102,7 @@ def from_raw(

if isinstance(reco, pd.DataFrame):
if Columns.Model not in reco.columns:
raise KeyError("Missing `{Columns.Model}` column in `reco` DataFrame")
reco[Columns.Model] = DEFAULT_MODEL_NAME
reco = cls._df_to_tables_dict(reco, Columns.Model)
cls._check_columns_present_in_reco(reco=reco, id_col=id_col)

Expand Down
24 changes: 12 additions & 12 deletions tests/visuals/test_visual_app.py
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,7 @@
INTERACTIONS = pd.DataFrame({Columns.User: [1, 1, 2], Columns.Item: [3, 7, 8]})
SELECTED_REQUESTS_U2I: tp.Dict[tp.Hashable, tp.Hashable] = {"user_one": 1, "user_three": 3}
SELECTED_REQUESTS_I2I: tp.Dict[tp.Hashable, tp.Hashable] = {"item_three": 3}

DEFAULT_MODEL_NAME = "model1"

def check_data_storages_equal(one: AppDataStorage, two: AppDataStorage) -> None:
assert one.id_col == two.id_col
Expand Down Expand Up @@ -229,17 +229,17 @@ def test_missing_columns_validation(self) -> None:
)

# Missing `Columns.Model` in reco pd.DataFrame
with pytest.raises(KeyError):
incorrect_reco = pd.DataFrame(
{Columns.User: [1, 2, 3, 4], Columns.Item: [3, 4, 3, 4], Columns.Score: [0.99, 0.9, 0.5, 0.5]}
)
AppDataStorage.from_raw(
reco=incorrect_reco,
item_data=ITEM_DATA,
interactions=INTERACTIONS,
is_u2i=True,
selected_requests=SELECTED_REQUESTS_U2I,
)
incorrect_reco = pd.DataFrame(
{Columns.User: [1, 2, 3, 4], Columns.Item: [3, 4, 3, 4], Columns.Score: [0.99, 0.9, 0.5, 0.5]}
)
ads = AppDataStorage.from_raw(
reco=incorrect_reco,
item_data=ITEM_DATA,
interactions=INTERACTIONS,
is_u2i=True,
selected_requests=SELECTED_REQUESTS_U2I,
)
assert "model1" in ads.model_names

def test_incorrect_interactions_for_reco_case(self) -> None:

Expand Down