From 54fe1424789071e3777ff41225de8456f38a4eef Mon Sep 17 00:00:00 2001 From: Henry Date: Tue, 4 Jun 2024 14:28:21 +0200 Subject: [PATCH] :bug: make all imports explicit w.r.t. to pkg --- vaep/__init__.py | 3 --- vaep/analyzers/__init__.py | 2 +- vaep/data_handling.py | 2 -- vaep/filter.py | 2 -- vaep/models/__init__.py | 3 +-- vaep/models/ae.py | 2 +- vaep/models/collab.py | 3 +-- vaep/pandas/__init__.py | 34 ++++++++++++++++++++++++++++------ vaep/plotting/__init__.py | 7 ++----- 9 files changed, 34 insertions(+), 24 deletions(-) diff --git a/vaep/__init__.py b/vaep/__init__.py index 98460455a..059ccf970 100644 --- a/vaep/__init__.py +++ b/vaep/__init__.py @@ -9,10 +9,7 @@ from importlib import metadata import njab -import pandas as pd -import pandas.io.formats.format as pf -# from . import logging, nb, pandas, plotting import vaep.logging import vaep.nb import vaep.pandas diff --git a/vaep/analyzers/__init__.py b/vaep/analyzers/__init__.py index 9856dafb9..6d16805a6 100644 --- a/vaep/analyzers/__init__.py +++ b/vaep/analyzers/__init__.py @@ -2,7 +2,7 @@ """ from types import SimpleNamespace -from . import compare_predictions, diff_analysis +from vaep.analyzers import compare_predictions, diff_analysis __all__ = ['diff_analysis', 'compare_predictions', 'Analysis'] diff --git a/vaep/data_handling.py b/vaep/data_handling.py index 1f0bc5404..41be078ac 100644 --- a/vaep/data_handling.py +++ b/vaep/data_handling.py @@ -4,8 +4,6 @@ import numpy as np import pandas as pd -# coverage - def coverage(X: pd.DataFrame, coverage_col: float, coverage_row: float): """Select proteins by column depending on their coverage. diff --git a/vaep/filter.py b/vaep/filter.py index 2c85999a9..2d26c4806 100644 --- a/vaep/filter.py +++ b/vaep/filter.py @@ -4,8 +4,6 @@ logger = logging.getLogger(__name__) -# ! use in data selection and tutorial - def select_features(df: pd.DataFrame, feat_prevalence: float = .2, diff --git a/vaep/models/__init__.py b/vaep/models/__init__.py index 3be35408b..2ae111d44 100644 --- a/vaep/models/__init__.py +++ b/vaep/models/__init__.py @@ -16,8 +16,7 @@ from fastcore.foundation import L import vaep - -from . import ae, analysis, collab, vae +from vaep.models import ae, analysis, collab, vae logger = logging.getLogger(__name__) diff --git a/vaep/models/ae.py b/vaep/models/ae.py index fd5d081a1..8295c8560 100644 --- a/vaep/models/ae.py +++ b/vaep/models/ae.py @@ -21,7 +21,7 @@ import vaep.models import vaep.transform -from . import analysis +from vaep.models import analysis logger = logging.getLogger(__name__) diff --git a/vaep/models/collab.py b/vaep/models/collab.py index 6e1403213..f54ab6df2 100644 --- a/vaep/models/collab.py +++ b/vaep/models/collab.py @@ -11,8 +11,7 @@ import vaep.io.dataloaders import vaep.io.datasplits - -from . import analysis +from vaep.models import analysis logger = logging.getLogger(__name__) diff --git a/vaep/pandas/__init__.py b/vaep/pandas/__init__.py index 97520bb02..5f82204b1 100644 --- a/vaep/pandas/__init__.py +++ b/vaep/pandas/__init__.py @@ -7,7 +7,30 @@ import omegaconf import pandas as pd -from .calc_errors import calc_errors_per_feat, get_absolute_error +from vaep.pandas.calc_errors import calc_errors_per_feat, get_absolute_error + +__all__ = [ + 'calc_errors_per_feat', + 'get_absolute_error', + 'unique_cols', + 'get_unique_non_unique_columns', + 'prop_unique_index', + 'replace_with', + 'index_to_dict', + 'get_columns_accessor', + 'get_columns_accessor_from_iterable', + 'select_max_by', + 'get_columns_namedtuple', + 'highlight_min', + '_add_indices', + 'interpolate', + 'flatten_dict_of_dicts', + 'key_map', + 'parse_query_expression', + 'length', + 'get_last_index_matching_proportion', + 'get_lower_whiskers', + 'get_counts_per_bin'] def unique_cols(s: pd.Series) -> bool: @@ -285,16 +308,15 @@ def get_lower_whiskers(df: pd.DataFrame, factor: float = 1.5) -> pd.Series: return ret -def get_counts_per_bin(df: pd.DataFrame, bins: range, columns: Optional[List[str]] = None) -> pd.DataFrame: +def get_counts_per_bin(df: pd.DataFrame, + bins: range, + columns: Optional[List[str]] = None) -> pd.DataFrame: """Return counts per bin for selected columns in DataFrame.""" counts_per_bin = dict() if columns is None: columns = df.columns.to_list() for col in columns: - _series = (pd.cut(df[col], bins=bins) - .to_frame() - .groupby(col) - .size()) + _series = (pd.cut(df[col], bins=bins).to_frame().groupby(col).size()) _series.index.name = 'bin' counts_per_bin[col] = _series counts_per_bin = pd.DataFrame(counts_per_bin) diff --git a/vaep/plotting/__init__.py b/vaep/plotting/__init__.py index 17cc86ced..105c183f8 100644 --- a/vaep/plotting/__init__.py +++ b/vaep/plotting/__init__.py @@ -11,11 +11,8 @@ import seaborn import vaep.pandas - -from . import data, defaults, errors, plotly -from .errors import plot_rolling_error - -# from . defaults import order_categories, labels_dict, IDX_ORDER +from vaep.plotting import data, defaults, errors, plotly +from vaep.plotting.errors import plot_rolling_error seaborn.set_style("whitegrid") # seaborn.set_theme()