🚧 change import in all notebook (scripts)

RasmussenLab · Jul 2, 2024 · 563655e · 563655e
1 parent 9d6858b
commit 563655e
Show file tree

Hide file tree

Showing 71 changed files with 957 additions and 1,023 deletions.
diff --git a/project/00_5_training_data_exploration.py b/project/00_5_training_data_exploration.py
@@ -5,7 +5,7 @@
 #       extension: .py
 #       format_name: percent
 #       format_version: '1.3'
-#       jupytext_version: 1.15.0
+#       jupytext_version: 1.16.2
 #   kernelspec:
 #     display_name: vaep
 #     language: python
@@ -37,14 +37,14 @@
 import pandas as pd
 import seaborn as sns
 
-import vaep
-import vaep.data_handling
-from vaep import plotting
-from vaep.analyzers import analyzers
-from vaep.pandas import missing_data
-from vaep.utils import create_random_df
+import pimmslearn
+import pimmslearn.data_handling
+from pimmslearn import plotting
+from pimmslearn.analyzers import analyzers
+from pimmslearn.pandas import missing_data
+from pimmslearn.utils import create_random_df
 
-logger = vaep.logging.setup_nb_logger()
+logger = pimmslearn.logging.setup_nb_logger()
 logging.getLogger('fontTools').setLevel(logging.WARNING)
 
 matplotlib.rcParams.update({'font.size': 6,
@@ -58,7 +58,7 @@ def get_clustermap(data,
                    **kwargs):
     from sklearn.impute import SimpleImputer
 
-    from vaep.pandas import _add_indices
+    from pimmslearn.pandas import _add_indices
     X = SimpleImputer().fit_transform(data)
     X = _add_indices(X, data)
     cg = sns.clustermap(X,
@@ -226,27 +226,27 @@ def get_dynamic_range(min_max):
                                               min_samples_per_feat=min_samples_per_feat)
 fname = FIGUREFOLDER / 'dist_all_lineplot_w_cutoffs.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 # %%
 fig = plotting.data.plot_missing_dist_highdim(data)
 fname = FIGUREFOLDER / 'dist_all_lineplot_wo_cutoffs.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 # %%
 fig = plotting.data.plot_missing_pattern_histogram(data,
                                                    min_feat_per_sample=min_feat_per_sample,
                                                    min_samples_per_feat=min_samples_per_feat)
 fname = FIGUREFOLDER / 'dist_all_histogram_w_cutoffs.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 # %%
 fig = plotting.data.plot_missing_pattern_histogram(data)
 fname = FIGUREFOLDER / 'dist_all_histogram_wo_cutoffs.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 # %% [markdown]
 # ### Boxplots
@@ -255,7 +255,7 @@ def get_dynamic_range(min_max):
 fig = plotting.data.plot_missing_dist_boxplots(data)
 fname = FIGUREFOLDER / 'dist_all_boxplots.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 # %% [markdown]
 # ### Violinplots
@@ -265,7 +265,7 @@ def get_dynamic_range(min_max):
     data, min_feat_per_sample, min_samples_per_feat)
 fname = FIGUREFOLDER / 'dist_all_violin_plot.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 # %% [markdown]
 # ## Feature medians over prop. of missing of feature
@@ -274,14 +274,14 @@ def get_dynamic_range(min_max):
     data=data, type='scatter', s=1)
 fname = FIGUREFOLDER / 'intensity_median_vs_prop_missing_scatter'
 files_out[fname.stem] = fname
-vaep.savefig(ax.get_figure(), fname)
+pimmslearn.savefig(ax.get_figure(), fname)
 
 # %%
 ax = plotting.data.plot_feat_median_over_prop_missing(
     data=data, type='boxplot', s=.8)
 fname = FIGUREFOLDER / 'intensity_median_vs_prop_missing_boxplot'
 files_out[fname.stem] = fname
-vaep.savefig(ax.get_figure(), fname)
+pimmslearn.savefig(ax.get_figure(), fname)
 
 
 # %% [markdown]
@@ -305,7 +305,7 @@ def get_dynamic_range(min_max):
 fig.suptitle(f'Histogram of correlations based on {FEATURES_CUTOFF_TEXT}')
 fname = FIGUREFOLDER / 'corr_histogram_feat.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname)
+pimmslearn.savefig(fig, name=fname)
 
 
 # %% [markdown]
@@ -318,7 +318,7 @@ def get_dynamic_range(min_max):
 ax.set_title(f'Histogram of coefficient of variation (CV) of {FEATURES_CUTOFF_TEXT}')
 fname = FIGUREFOLDER / 'CV_histogram_features.pdf'
 files_out[fname.name] = fname
-vaep.savefig(ax.get_figure(), name=fname)
+pimmslearn.savefig(ax.get_figure(), name=fname)
 
 # %% [markdown]
 # ## Clustermap and heatmaps of missing values
@@ -327,7 +327,7 @@ def get_dynamic_range(min_max):
 # needs to deal with duplicates
 # notna = data.notna().T.drop_duplicates().T
 # get index and column names
-vaep.plotting.make_large_descriptors(5)
+pimmslearn.plotting.make_large_descriptors(5)
 
 cg = sns.clustermap(selected.notna(),
                     cbar_pos=None,
@@ -345,10 +345,10 @@ def get_dynamic_range(min_max):
 cg.figure.tight_layout()
 fname = FIGUREFOLDER / 'clustermap_present_absent_pattern.png'
 files_out[fname.name] = fname
-vaep.savefig(cg.figure,
-             name=fname,
-             pdf=False,
-             dpi=600)
+pimmslearn.savefig(cg.figure,
+                   name=fname,
+                   pdf=False,
+                   dpi=600)
 
 # %% [markdown]
 # based on cluster, plot heatmaps of features and samples
@@ -358,7 +358,7 @@ def get_dynamic_range(min_max):
     cg.dendrogram_col.reordered_ind)) == selected.shape
 
 # %%
-vaep.plotting.make_large_descriptors(5)
+pimmslearn.plotting.make_large_descriptors(5)
 fig, ax = plt.subplots(figsize=(7.5, 3.5))
 ax = sns.heatmap(
     selected.iloc[cg.dendrogram_row.reordered_ind,
@@ -370,8 +370,8 @@ def get_dynamic_range(min_max):
 )
 ax.set_title(f'Heatmap of intensities clustered by missing pattern of {FEATURES_CUTOFF_TEXT}',
              fontsize=8)
-vaep.plotting.only_every_x_ticks(ax, x=2)
-vaep.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
+pimmslearn.plotting.only_every_x_ticks(ax, x=2)
+pimmslearn.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
 if PG_SEPARATOR is not None:
     _new_labels = [_l.get_text().split(PG_SEPARATOR)[0]
                    for _l in ax.get_xticklabels()]
@@ -381,7 +381,7 @@ def get_dynamic_range(min_max):
     ax.set_yticks([])
 fname = FIGUREFOLDER / 'heatmap_intensities_ordered_by_missing_pattern.png'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname, pdf=False, dpi=600)
+pimmslearn.savefig(fig, name=fname, pdf=False, dpi=600)
 # ax.get_figure().savefig(fname, dpi=300)
 
 # %% [markdown]
@@ -400,8 +400,8 @@ def get_dynamic_range(min_max):
 )
 ax.set_title(f'Heatmap of feature correlation of {FEATURES_CUTOFF_TEXT}',
              fontsize=8)
-_ = vaep.plotting.only_every_x_ticks(ax, x=2)
-_ = vaep.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
+_ = pimmslearn.plotting.only_every_x_ticks(ax, x=2)
+_ = pimmslearn.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
 if PG_SEPARATOR is not None:
     _new_labels = [_l.get_text().split(PG_SEPARATOR)[0]
                    for _l in ax.get_xticklabels()]
@@ -411,7 +411,7 @@ def get_dynamic_range(min_max):
     ax.set_yticks([])
 fname = FIGUREFOLDER / 'heatmap_feature_correlation.png'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname, pdf=False, dpi=600)
+pimmslearn.savefig(fig, name=fname, pdf=False, dpi=600)
 
 # %%
 lower_corr = analyzers.corr_lower_triangle(
@@ -427,18 +427,18 @@ def get_dynamic_range(min_max):
     cbar_kws={'shrink': 0.75},
     square=True,
 )
-_ = vaep.plotting.only_every_x_ticks(ax, x=2)
-_ = vaep.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
+_ = pimmslearn.plotting.only_every_x_ticks(ax, x=2)
+_ = pimmslearn.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
 if NO_TICK_LABELS_ON_HEATMAP:
     ax.set_xticks([])
     ax.set_yticks([])
 ax.set_title(f'Heatmap of sample correlation based on {FEATURES_CUTOFF_TEXT}', fontsize=7)
 fname = FIGUREFOLDER / 'heatmap_sample_correlation.png'
 files_out[fname.name] = fname
-vaep.savefig(fig, name=fname, pdf=False, dpi=600)
+pimmslearn.savefig(fig, name=fname, pdf=False, dpi=600)
 
 # %%
-vaep.plotting.make_large_descriptors(6)
+pimmslearn.plotting.make_large_descriptors(6)
 kwargs = dict()
 if NO_TICK_LABELS_ON_HEATMAP:
     kwargs['xticklabels'] = False
@@ -449,15 +449,15 @@ def get_dynamic_range(min_max):
     _new_labels = [_l.get_text().split(PG_SEPARATOR)[0]
                    for _l in ax.get_xticklabels()]
     _ = ax.set_xticklabels(_new_labels)
-_ = vaep.plotting.only_every_x_ticks(ax, x=2, axis=0)
-_ = vaep.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
+_ = pimmslearn.plotting.only_every_x_ticks(ax, x=2, axis=0)
+_ = pimmslearn.plotting.use_first_n_chars_in_labels(ax, x=SAMPLE_FIRST_N_CHARS)
 # ax.set_title(f'Clustermap of intensities based on {FEATURES_CUTOFF_TEXT}', fontsize=7)
 # cg.fig.tight_layout()  # tight_layout makes the cbar a bit ugly
 cg.fig.suptitle(f'Clustermap of intensities based on {FEATURES_CUTOFF_TEXT}', fontsize=7)
 fname = FIGUREFOLDER / 'clustermap_intensities_normalized.png'
 files_out[fname.name] = fname
 cg.fig.savefig(fname, dpi=300)  # avoid tight_layout
-# vaep.savefig(cg.fig,
+# pimmslearn.savefig(cg.fig,
 #              name=fname,
 #              pdf=False)
 
@@ -469,17 +469,17 @@ def get_dynamic_range(min_max):
 COL_NO_MISSING, COL_NO_IDENTIFIED = f'no_missing_{TYPE}', f'no_identified_{TYPE}'
 COL_PROP_SAMPLES = 'prop_samples'
 
-sample_stats = vaep.data_handling.compute_stats_missing(
+sample_stats = pimmslearn.data_handling.compute_stats_missing(
     data.notna(), COL_NO_MISSING, COL_NO_IDENTIFIED)
 sample_stats
 
 # %%
-vaep.plotting.make_large_descriptors(8)
+pimmslearn.plotting.make_large_descriptors(8)
 fig_ident = sns.relplot(
     x='SampleID_int', y=COL_NO_IDENTIFIED, data=sample_stats)
 fig_ident.set_axis_labels('Sample ID', f'Frequency of identified {TYPE}')
 fig_ident.fig.suptitle(f'Frequency of identified {TYPE} by sample id', y=1.03)
-vaep.savefig(fig_ident, f'identified_{TYPE}_by_sample', folder=FIGUREFOLDER)
+pimmslearn.savefig(fig_ident, f'identified_{TYPE}_by_sample', folder=FIGUREFOLDER)
 
 fig_ident_dist = sns.relplot(
     x=COL_PROP_SAMPLES, y=COL_NO_IDENTIFIED, data=sample_stats)
@@ -489,7 +489,7 @@ def get_dynamic_range(min_max):
     f'Frequency of identified {TYPE} groups by sample id', y=1.03)
 fname = FIGUREFOLDER / f'identified_{TYPE}_ordered.pdf'
 files_out[fname.name] = fname
-vaep.savefig(fig_ident_dist, fname)
+pimmslearn.savefig(fig_ident_dist, fname)
 
 # %%
 COL_NO_MISSING_PROP = COL_NO_MISSING + '_PROP'
@@ -505,7 +505,7 @@ def get_dynamic_range(min_max):
 
 fname = FIGUREFOLDER / 'proportion_feat_missing.pdf'
 files_out[fname.name] = fname
-vaep.savefig(g, fname)
+pimmslearn.savefig(g, fname)
 
 # %% [markdown]
 # ### Reference table intensities (log2)

diff --git a/project/00_6_0_permute_data.ipynb b/project/00_6_0_permute_data.ipynb
@@ -21,11 +21,11 @@
     "from typing import Union, List\n",
     "\n",
     "import numpy as np\n",
-    "import vaep\n",
-    "import vaep.analyzers.analyzers\n",
-    "from vaep.utils import create_random_df\n",
+    "import pimmslearn\n",
+    "import pimmslearn.analyzers.analyzers\n",
+    "from pimmslearn.utils import create_random_df\n",
     "\n",
-    "logger = vaep.logging.setup_nb_logger()\n",
+    "logger = pimmslearn.logging.setup_nb_logger()\n",
     "logger.info(\"Split data and make diagnostic plots\")"
    ]
   },
@@ -92,7 +92,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "args = vaep.nb.get_params(args, globals=globals())\n",
+    "args = pimmslearn.nb.get_params(args, globals=globals())\n",
     "args"
    ]
   },
@@ -105,7 +105,7 @@
    },
    "outputs": [],
    "source": [
-    "args = vaep.nb.Config().from_dict(args)\n",
+    "args = pimmslearn.nb.Config().from_dict(args)\n",
     "args"
    ]
   },
@@ -166,7 +166,7 @@
    "outputs": [],
    "source": [
     "constructor = getattr(\n",
-    "    vaep.analyzers.analyzers.AnalyzePeptides,\n",
+    "    pimmslearn.analyzers.analyzers.AnalyzePeptides,\n",
     "    FILE_FORMAT_TO_CONSTRUCTOR_IN[FILE_EXT])  # AnalyzePeptides.from_csv\n",
     "analysis = constructor(fname=args.FN_INTENSITIES,\n",
     "                       index_col=args.index_col,\n",
@@ -214,7 +214,7 @@
     "\n",
     "method = getattr(df, FILE_FORMAT_TO_CONSTRUCTOR.get(FILE_EXT))\n",
     "\n",
-    "fname = vaep.utils.append_to_filepath(args.FN_INTENSITIES, 'permuted')\n",
+    "fname = pimmslearn.utils.append_to_filepath(args.FN_INTENSITIES, 'permuted')\n",
     "method(fname)"
    ]
   },
@@ -226,7 +226,7 @@
    "outputs": [],
    "source": [
     "constructor = getattr(\n",
-    "    vaep.analyzers.analyzers.AnalyzePeptides,\n",
+    "    pimmslearn.analyzers.analyzers.AnalyzePeptides,\n",
     "    FILE_FORMAT_TO_CONSTRUCTOR_IN[FILE_EXT])  # AnalyzePeptides.from_csv\n",
     "analysis = constructor(fname=args.FN_INTENSITIES,\n",
     "                       index_col=args.index_col,\n",

diff --git a/project/00_6_0_permute_data.py b/project/00_6_0_permute_data.py
@@ -7,11 +7,11 @@
 from typing import Union, List
 
 import numpy as np
-import vaep
-import vaep.analyzers.analyzers
-from vaep.utils import create_random_df
+import pimmslearn
+import pimmslearn.analyzers.analyzers
+from pimmslearn.utils import create_random_df
 
-logger = vaep.logging.setup_nb_logger()
+logger = pimmslearn.logging.setup_nb_logger()
 logger.info("Split data and make diagnostic plots")
 
 # %%
@@ -38,11 +38,11 @@
 file_format: str = 'pkl'
 
 # %%
-args = vaep.nb.get_params(args, globals=globals())
+args = pimmslearn.nb.get_params(args, globals=globals())
 args
 
 # %%
-args = vaep.nb.Config().from_dict(args)
+args = pimmslearn.nb.Config().from_dict(args)
 args
 
 
@@ -71,7 +71,7 @@
 
 # %%
 constructor = getattr(
-    vaep.analyzers.analyzers.AnalyzePeptides,
+    pimmslearn.analyzers.analyzers.AnalyzePeptides,
     FILE_FORMAT_TO_CONSTRUCTOR_IN[FILE_EXT])  # AnalyzePeptides.from_csv
 analysis = constructor(fname=args.FN_INTENSITIES,
                        index_col=args.index_col,
@@ -94,11 +94,11 @@
 
 method = getattr(df, FILE_FORMAT_TO_CONSTRUCTOR.get(FILE_EXT))
 
-fname = vaep.utils.append_to_filepath(args.FN_INTENSITIES, 'permuted')
+fname = pimmslearn.utils.append_to_filepath(args.FN_INTENSITIES, 'permuted')
 method(fname)
 # %%
 constructor = getattr(
-    vaep.analyzers.analyzers.AnalyzePeptides,
+    pimmslearn.analyzers.analyzers.AnalyzePeptides,
     FILE_FORMAT_TO_CONSTRUCTOR_IN[FILE_EXT])  # AnalyzePeptides.from_csv
 analysis = constructor(fname=args.FN_INTENSITIES,
                        index_col=args.index_col,