Skip to content

Commit

Permalink
Update template files to comply with linter jobs. (#249)
Browse files Browse the repository at this point in the history
* Lint?

Signed-off-by: Laura Couto <[email protected]>

* Revert "Lint again"

This reverts commit 088365d.

Signed-off-by: Laura Couto <[email protected]>

* Replace all Set, Tuple and Dict uses by python builtin type hints

Signed-off-by: Laura Couto <[email protected]>

---------

Signed-off-by: Laura Couto <[email protected]>
  • Loading branch information
lrcouto authored Nov 4, 2024
1 parent 91a46e3 commit 7a263e9
Show file tree
Hide file tree
Showing 31 changed files with 35 additions and 53 deletions.
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-


# {{ cookiecutter.python_package }} documentation build
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
dynamic = ["dependencies", "version"]

[project.scripts]
{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
"{{ cookiecutter.repo_name }}" = "{{ cookiecutter.python_package }}.__main__:main"

[project.entry-points."kedro.hooks"]

Expand Down
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
"""Project pipelines."""
from typing import Dict

from kedro.framework.project import find_pipelines
from kedro.pipeline import Pipeline


def register_pipelines() -> Dict[str, Pipeline]:
def register_pipelines() -> dict[str, Pipeline]:
"""Register the project's pipelines.
Returns:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -4,12 +4,12 @@
PLEASE DELETE THIS FILE ONCE YOU START WORKING ON YOUR OWN PROJECT!
"""

from typing import Any, Dict
from typing import Any

import pandas as pd


def split_data(data: pd.DataFrame, example_test_data_ratio: float) -> Dict[str, Any]:
def split_data(data: pd.DataFrame, example_test_data_ratio: float) -> dict[str, Any]:
"""Node for splitting the classical Iris data set into training and test
sets, each split into features and labels.
The split ratio parameter is taken from conf/project/parameters.yml.
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,14 @@
Delete this when you start working on your own Kedro project.
"""
import logging
from typing import Any, Dict
from typing import Any

import numpy as np
import pandas as pd


def train_model(
train_x: pd.DataFrame, train_y: pd.DataFrame, parameters: Dict[str, Any]
train_x: pd.DataFrame, train_y: pd.DataFrame, parameters: dict[str, Any]
) -> np.ndarray:
"""Node for training a simple multi-class logistic regression model. The
number of training iterations as well as the learning rate are taken from
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
dynamic = ["dependencies", "version"]

[project.scripts]
{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
"{{ cookiecutter.repo_name }}" = "{{ cookiecutter.python_package }}.__main__:main"

[project.entry-points."kedro.hooks"]

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,13 @@
"""

import logging
from typing import Dict, Tuple

import numpy as np
import pandas as pd
from pyspark.sql import DataFrame


def split_data(data: DataFrame, parameters: Dict) -> Tuple:
def split_data(data: DataFrame, parameters: dict) -> tuple:
"""Splits data into features and targets training and test sets.
Args:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
"""Project pipelines."""
from typing import Dict

from kedro.framework.project import find_pipelines
from kedro.pipeline import Pipeline


def register_pipelines() -> Dict[str, Pipeline]:
def register_pipelines() -> dict[str, Pipeline]:
"""Register the project's pipelines.
Returns:
Expand Down
4 changes: 2 additions & 2 deletions features/environment.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,9 +8,9 @@
import tempfile
import venv
from pathlib import Path
from typing import Any, Set
from typing import Any

_PATHS_TO_REMOVE: Set[Path] = set()
_PATHS_TO_REMOVE: set[Path] = set()



Expand Down
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-


# {{ cookiecutter.python_package }} documentation build
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
dynamic = ["dependencies", "version"]

[project.scripts]
{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
"{{ cookiecutter.repo_name }}" = "{{ cookiecutter.python_package }}.__main__:main"

[project.entry-points."kedro.hooks"]

Expand Down Expand Up @@ -43,7 +43,7 @@ namespaces = false
package_name = "{{ cookiecutter.python_package }}"
project_name = "{{ cookiecutter.project_name }}"
kedro_init_version = "{{ cookiecutter.kedro_version }}"
tools = {{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}
tools = "{{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}"
example_pipeline = "{{ cookiecutter.example_pipeline }}"
source_dir = "src"

Expand Down
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
"""Project pipelines."""
from typing import Dict

from kedro.framework.project import find_pipelines
from kedro.pipeline import Pipeline


def register_pipelines() -> Dict[str, Pipeline]:
def register_pipelines() -> dict[str, Pipeline]:
"""Register the project's pipelines.
Returns:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
from typing import Dict, Tuple

import pandas as pd

Expand All @@ -19,7 +18,7 @@ def _parse_money(x: pd.Series) -> pd.Series:
return x


def preprocess_companies(companies: pd.DataFrame) -> Tuple[pd.DataFrame, Dict]:
def preprocess_companies(companies: pd.DataFrame) -> tuple[pd.DataFrame, dict]:
"""Preprocesses the data for companies.
Args:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,12 @@
import logging
from typing import Dict, Tuple

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import max_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split


def split_data(data: pd.DataFrame, parameters: Dict) -> Tuple:
def split_data(data: pd.DataFrame, parameters: dict) -> tuple:
"""Splits data into features and targets training and test sets.
Args:
Expand Down Expand Up @@ -41,7 +40,7 @@ def train_model(X_train: pd.DataFrame, y_train: pd.Series) -> LinearRegression:

def evaluate_model(
regressor: LinearRegression, X_test: pd.DataFrame, y_test: pd.Series
) -> Dict[str, float]:
) -> dict[str, float]:
"""Calculates and logs the coefficient of determination.
Args:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -64,4 +64,4 @@ def test_data_science_pipeline(caplog, dummy_data, dummy_parameters):

SequentialRunner().run(pipeline, catalog)

assert successful_run_msg in caplog.text
assert successful_run_msg in caplog.text
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-


# {{ cookiecutter.python_package }} documentation build
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
dynamic = ["dependencies", "version"]

[project.scripts]
{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
"{{ cookiecutter.repo_name }}" = "{{ cookiecutter.python_package }}.__main__:main"

[project.entry-points."kedro.hooks"]

Expand Down Expand Up @@ -43,7 +43,7 @@ namespaces = false
package_name = "{{ cookiecutter.python_package }}"
project_name = "{{ cookiecutter.project_name }}"
kedro_init_version = "{{ cookiecutter.kedro_version }}"
tools = {{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}
tools = "{{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}"
example_pipeline = "{{ cookiecutter.example_pipeline }}"
source_dir = "src"

Expand Down
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
"""Project pipelines."""
from typing import Dict

from kedro.framework.project import find_pipelines
from kedro.pipeline import Pipeline


def register_pipelines() -> Dict[str, Pipeline]:
def register_pipelines() -> dict[str, Pipeline]:
"""Register the project's pipelines.
Returns:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,12 @@
import logging
from typing import Dict, Tuple

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split


def split_data(data: pd.DataFrame, parameters: Dict) -> Tuple:
def split_data(data: pd.DataFrame, parameters: dict) -> tuple:
"""Splits data into features and targets training and test sets.
Args:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -64,4 +64,4 @@ def test_data_science_pipeline(caplog, dummy_data, dummy_parameters):

SequentialRunner().run(pipeline, catalog)

assert successful_run_msg in caplog.text
assert successful_run_msg in caplog.text
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-


# {{ cookiecutter.python_package }} documentation build
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
dynamic = ["dependencies", "version"]

[project.scripts]
{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
"{{ cookiecutter.repo_name }}" = "{{ cookiecutter.python_package }}.__main__:main"

[project.entry-points."kedro.hooks"]

Expand Down Expand Up @@ -43,7 +43,7 @@ namespaces = false
package_name = "{{ cookiecutter.python_package }}"
project_name = "{{ cookiecutter.project_name }}"
kedro_init_version = "{{ cookiecutter.kedro_version }}"
tools = {{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}
tools = "{{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}"
example_pipeline = "{{ cookiecutter.example_pipeline }}"
source_dir = "src"

Expand Down
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
"""Project pipelines."""
from typing import Dict

from kedro.framework.project import find_pipelines
from kedro.pipeline import Pipeline


def register_pipelines() -> Dict[str, Pipeline]:
def register_pipelines() -> dict[str, Pipeline]:
"""Register the project's pipelines.
Returns:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,4 +1,3 @@
from typing import Dict, Tuple

import pandas as pd
from pyspark.sql import Column
Expand All @@ -24,7 +23,7 @@ def _parse_money(x: Column) -> Column:
return x


def preprocess_companies(companies: SparkDataFrame) -> Tuple[SparkDataFrame, Dict]:
def preprocess_companies(companies: SparkDataFrame) -> tuple[SparkDataFrame, dict]:
"""Preprocesses the data for companies.
Args:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,12 @@
import logging
from typing import Dict, Tuple

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import max_error, mean_absolute_error, r2_score
from sklearn.model_selection import train_test_split


def split_data(data: pd.DataFrame, parameters: Dict) -> Tuple:
def split_data(data: pd.DataFrame, parameters: dict) -> tuple:
"""Splits data into features and targets training and test sets.
Args:
Expand Down Expand Up @@ -41,7 +40,7 @@ def train_model(X_train: pd.DataFrame, y_train: pd.Series) -> LinearRegression:

def evaluate_model(
regressor: LinearRegression, X_test: pd.DataFrame, y_test: pd.Series
) -> Dict[str, float]:
) -> dict[str, float]:
"""Calculates and logs the coefficient of determination.
Args:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -64,4 +64,4 @@ def test_data_science_pipeline(caplog, dummy_data, dummy_parameters):

SequentialRunner().run(pipeline, catalog)

assert successful_run_msg in caplog.text
assert successful_run_msg in caplog.text
Original file line number Diff line number Diff line change
@@ -1,5 +1,4 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-


# {{ cookiecutter.python_package }} documentation build
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,7 @@ readme = "README.md"
dynamic = ["dependencies", "version"]

[project.scripts]
{{ cookiecutter.repo_name }} = "{{ cookiecutter.python_package }}.__main__:main"
"{{ cookiecutter.repo_name }}" = "{{ cookiecutter.python_package }}.__main__:main"

[project.entry-points."kedro.hooks"]

Expand Down Expand Up @@ -43,7 +43,7 @@ namespaces = false
package_name = "{{ cookiecutter.python_package }}"
project_name = "{{ cookiecutter.project_name }}"
kedro_init_version = "{{ cookiecutter.kedro_version }}"
tools = {{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}
tools = "{{ cookiecutter.tools | default('') | string | replace('\"', '\\\"') }}"
example_pipeline = "{{ cookiecutter.example_pipeline }}"
source_dir = "src"

Expand Down
Original file line number Diff line number Diff line change
@@ -1,11 +1,10 @@
"""Project pipelines."""
from typing import Dict

from kedro.framework.project import find_pipelines
from kedro.pipeline import Pipeline


def register_pipelines() -> Dict[str, Pipeline]:
def register_pipelines() -> dict[str, Pipeline]:
"""Register the project's pipelines.
Returns:
Expand Down
Original file line number Diff line number Diff line change
@@ -1,13 +1,12 @@
import logging
from typing import Dict, Tuple

import pandas as pd
from sklearn.linear_model import LinearRegression
from sklearn.metrics import r2_score
from sklearn.model_selection import train_test_split


def split_data(data: pd.DataFrame, parameters: Dict) -> Tuple:
def split_data(data: pd.DataFrame, parameters: dict) -> tuple:
"""Splits data into features and targets training and test sets.
Args:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -64,4 +64,4 @@ def test_data_science_pipeline(caplog, dummy_data, dummy_parameters):

SequentialRunner().run(pipeline, catalog)

assert successful_run_msg in caplog.text
assert successful_run_msg in caplog.text

0 comments on commit 7a263e9

Please sign in to comment.